🍩 Database of Original & Non-Theoretical Uses of Topology
(found 32 matches in 0.012159s)
-
-
Induction Motor Eccentricity Fault Detection and Quantification Using Topological Data Analysis (2024)
Bingnan Wang, Chungwei Lin, Hiroshi Inoue, Makoto KanemaruAbstract
In this paper, we propose a topological data analysis (TDA) method for the processing of induction motor stator current data, and apply it to the detection and quantification of eccentricity faults. Traditionally, physics-based models and involved signal processing techniques are required to identify and extract the subtle frequency components in current data related to a particular fault. We show that TDA offers an alternative way to extract fault related features, and effectively distinguish data from different fault conditions. We will introduce TDA method and the procedure of extracting topological features from time-domain data, and apply it to induction motor current data measured under different eccentricity fault conditions. We show that while the raw time-domain data are very challenging to distinguish, the extracted topological features from these data are distinct and highly associated with eccentricity fault level. With TDA processed data, we can effectively train machine learning models to predict fault levels with good accuracy, even for new data from eccentricity levels that are not seen in the training data. The proposed method is model-free, and only requires a small segment of time-domain data to make prediction. These advantages make it attractive for a wide range of data-driven fault detection applications. -
A Functional Data-Driven Approach to Monitor and Analyze Equipment Degradation in Multiproduct Batch Processes (2023)
Joel Sansana, Ricardo Rendall, Mark N. Joswiak, Ivan Castillo, Gloria Miller, Leo H. Chiang, Marco S. ReisAbstract
Equipment degradation is ubiquitous in the Chemical Process Industry (CPI), causing significant losses in efficiency, controllability, and plant economy, as well as an increased environmental fingerprint and additional operational safety risks. The case of fouling in heat exchangers, in particular, is well-known and pervasive but still hard to cope with, given the complexity of the underlying mechanisms and the difficulty of assessing its extension in real-time. This problem becomes even more complex in batch processes producing different products, where multiple recipes are used, bringing additional variability and new challenges to the analysis. In this work, we propose a functional data-driven approach for streamlining the analysis and monitoring of the progression of fouling taking place in heat exchangers in multiproduct batch processes. With the approach developed and presented in this paper, process analysis can be efficiently conducted by integrating historical data with engineering knowledge. Furthermore, a surrogate measure of fouling extension in heat exchangers is proposed, that can be readily implemented as an equipment health indicator (EHI) leading to a safer operation of the heat exchanger. -
A Data-Driven Workflow for Evaporation Performance Degradation Analysis: A Full-Scale Case Study in the Herbal Medicine Manufacturing Industry (2023)
Sheng Zhang, Xinyuan Xie, Haibin QuAbstract
The evaporation process is a common step in herbal medicine manufacturing and often lasts for a long time. The degradation of evaporation performance is inevitable, leading to more consumption of steam and electricity, and it may also have an impact on the content of thermosensitive components. Recently, a vast amount of evaporation process data is collected with the aid of industrial information systems, and process knowledge is hidden behind the data. But currently, these data are seldom deeply analyzed. In this work, an exploratory data analysis workflow is proposed to evaluate the evaporation performance and to identify the root causes of the performance degradation. The workflow consists of 6 steps: data collecting, preprocessing, characteristic stage identification, feature extraction, model development and interpretation, and decision making. In the model development and interpretation step, the workflow employs the HDBSCAN clustering algorithm for data annotation and then uses the ccPCA method to compare the differences between clusters for root cause analysis. A full-scale case is presented to verify the effectiveness of the workflow. The evaporation process data of 192 batches in 2018 were collected in the case. Through the steps of the workflow, the features of each batch were extracted, and the batches were clustered into 6 groups. The root causes of the performance degradation were determined as the high Pv,II and high LI by ccPCA. Recommended suggestions for future manufacturing were given according to the results. The proposed workflow can determine the root causes of the evaporation performance degradation. -
A Novel Approach for Wafer Defect Pattern Classification Based on Topological Data Analysis (2023)
Seungchan Ko, Dowan KooAbstract
In semiconductor manufacturing, wafer map defect pattern provides critical information for facility maintenance and yield management, so the classification of defect patterns is one of the most important tasks in the manufacturing process. In this paper, we propose a novel way to represent the shape of the defect pattern as a finite-dimensional vector, which will be used as an input for a neural network algorithm for classification. The main idea is to extract the topological features of each pattern by using the theory of persistent homology from topological data analysis (TDA). Through some experiments with a simulated dataset, we show that the proposed method is faster and much more efficient in training with higher accuracy, compared with the method using convolutional neural networks (CNN) which is the most common approach for wafer map defect pattern classification. Moreover, it was shown that our method outperforms the CNN-based method when the number of training data is not enough and is imbalanced. -
Manifold Learning for Coherent Design Interpolation Based on Geometrical and Topological Descriptors (2023)
D. Muñoz, O. Allix, F. Chinesta, J. J. Ródenas, E. NadalAbstract
In the context of intellectual property in the manufacturing industry, know-how is referred to practical knowledge on how to accomplish a specific task. This know-how is often difficult to be synthesised in a set of rules or steps as it remains in the intuition and expertise of engineers, designers, and other professionals. Today, a new research line in this concern spot-up thanks to the explosion of Artificial Intelligence and Machine Learning algorithms and its alliance with Computational Mechanics and Optimisation tools. However, a key aspect with industrial design is the scarcity of available data, making it problematic to rely on deep-learning approaches. Assuming that the existing designs live in a manifold, in this paper, we propose a synergistic use of existing Machine Learning tools to infer a reduced manifold from the existing limited set of designs and, then, to use it to interpolate between the individuals, working as a generator basis, to create new and coherent designs. For this, a key aspect is to be able to properly interpolate in the reduced manifold, which requires a proper clustering of the individuals. From our experience, due to the scarcity of data, adding topological descriptors to geometrical ones considerably improves the quality of the clustering. Thus, a distance, mixing topology and geometry is proposed. This distance is used both, for the clustering and for the interpolation. For the interpolation, relying on optimal transport appear to be mandatory. Examples of growing complexity are proposed to illustrate the goodness of the method. -
Practical Joint Human-Machine Exploration of Industrial Time Series Using the Matrix Profile (2023)
Felix Nilsson, Mohamed-Rafik Bouguelia, Thorsteinn RögnvaldssonAbstract
Technological advancements and widespread adaptation of new technology in industry have made industrial time series data more available than ever before. With this development grows the need for versatile methods for mining industrial time series data. This paper introduces a practical approach for joint human-machine exploration of industrial time series data using the Matrix Profile, and presents some challenges involved. The approach is demonstrated on three real-life industrial data sets to show how it enables the user to quickly extract semantic information, detect cycles, find deviating patterns, and gain a deeper understanding of the time series. A benchmark test is also presented on ECG (electrocardiogram) data, showing that the approach works well in comparison to previously suggested methods for extracting relevant time series motifs. -
Motor Eccentricity Fault Detection: Physics-Based and Data-Driven Approaches (2023)
Bingnan Wang, Hiroshi Inoue, Makoto KanemaruAbstract
Fault detection using motor current signature analysis (MCSA) is attractive for industrial applications due to its simplicity with no additional sensor installation required. However current components associated with faults are often very subtle and much smaller than the supply frequency component, making it challenging to detect and quantify fault levels. In this paper, we present our work on quantitative eccentricity fault diagnosis technologies for electric motors, including physical-model approach using improved winding function theory, which can simulate motor dynamics under faulty conditions and agrees well with experiment data, and data-driven approach using topological data analysis (TDA), which can effectively differentiate signals measured at different eccentricity levels. The advantages and limitations of each approach is discussed. Both methods can be extended to the detection and quantification of other types of electric motor faults. -
Efficient Planning of Multi-Robot Collective Transport Using Graph Reinforcement Learning With Higher Order Topological Abstraction (2023)
Steve Paul, Wenyuan Li, Brian Smyth, Yuzhou Chen, Yulia Gel, Souma ChowdhuryAbstract
Efficient multi-robot task allocation (MRTA) is fundamental to various time-sensitive applications such as disaster response, warehouse operations, and construction. This paper tackles a particular class of these problems that we call MRTA-collective transport or MRTA-CT - here tasks present varying workloads and deadlines, and robots are subject to flight range, communication range, and payload constraints. For large instances of these problems involving 100s-1000's of tasks and 10s-100s of robots, traditional non-learning solvers are often time-inefficient, and emerging learning-based policies do not scale well to larger-sized problems without costly retraining. To address this gap, we use a recently proposed encoder-decoder graph neural network involving Capsule networks and multi-head attention mechanism, and innovatively add topological descriptors (TD) as new features to improve transferability to unseen problems of similar and larger size. Persistent homology is used to derive the TD, and proximal policy optimization is used to train our TD-augmented graph neural network. The resulting policy model compares favorably to state-of-the-art non-learning baselines while being much faster. The benefit of using TD is readily evident when scaling to test problems of size larger than those used in training. -
Optimizing Porosity Detection in Wire Laser Metal Deposition Processes Through Data-Driven AI Classification Techniques (2023)
Meritxell Gomez-Omella, Jon Flores, Basilio Sierra, Susana Ferreiro, Nicolas Hascoët, Francisco ChinestaAbstract
Additive manufacturing (AM) is an attractive solution for many companies that produce geometrically complex parts. This process consists of depositing material layer by layer following a sliced CAD geometry. It brings several benefits to manufacturing capabilities, such as design freedom, reduced material waste, and short-run customization. However, one of the current challenges faced by users of the process, mainly in wire laser metal deposition (wLMD), is to avoid defects in the manufactured part, especially the porosity. This defect is caused by extreme conditions and metallurgical transformations of the process. And not only does it directly affect the mechanical performance of the parts, especially the fatigue properties, but it also means an increase in costs due to the inspection tasks to which the manufactured parts must be subjected. This work compares three operational solution approaches, product-centric, based on signal-based feature extraction and Topological Data Analysis together with statistical and Machine Learning (ML) techniques, for the early detection and prediction of porosity failure in a wLMD process. The different forecasting and validation strategies demonstrate the variety of conclusions that can be drawn with different objectives in the analysis of the monitored data in AM problems. -
Novel Production Prediction Model of Gasoline Production Processes for Energy Saving and Economic Increasing Based on AM-GRU Integrating the UMAP Algorithm (2023)
Jintao Liu, Liangchao Chen, Wei Xu, Mingfei Feng, Yongming Han, Tao Xia, Zhiqiang GengAbstract
Gasoline, as an extremely important petroleum product, is of great significance to ensure people's living standards and maintain national energy security. In the actual gasoline industrial production environment, the point information collected by industrial devices usually has the characteristics of high dimension, high noise and time series because of the instability of manual operation and equipment operation. Therefore, it is difficult to use the traditional method to predict and optimize gasoline production. In this paper, a novel production prediction model using an attention mechanism (AM) based gated recurrent unit (GRU) (AM-GRU) integrating the uniform manifold approximation and projection (UMAP) is proposed. The data collected in the industrial plant are processed by the box plot to remove the data outside the quartile. Then, the UMAP is used to remove the strong correlation between the data, which can improve the running speed and the performance of the AM-GRU. Compared with the existing time series data prediction method, the superiority of the AM-GRU is verified based on University of California Irvine (UCI) benchmark datasets. Finally, the production prediction model of actual complex gasoline production processes for energy saving and economic increasing based on the proposed method is built. The experiment results show that compared with other time series data prediction models, the proposed model has better stability and higher accuracy with reaching 0.4171, 0.9969, 0.2538 and 0.5038 in terms of the mean squared error, the average absolute accuracy, the mean squared error and the root mean square error. Moreover, according to the optimal scheme of the raw material, the inefficiency production points can be expected to increase about 0.69 tons of the gasoline yield and between about \$645.1 and \$925.6 of economic benefits of industrial production. -
Mapping Geometric and Electromagnetic Feature Spaces With Machine Learning for Additively Manufactured RF Devices (2022)
Deanna Sessions, Venkatesh Meenakshisundaram, Andrew Gillman, Alexander Cook, Kazuko Fuchi, Philip R. Buskohl, Gregory H. HuffAbstract
Multi-material additive manufacturing enables transformative capabilities in customized, low-cost, and multi-functional electromagnetic devices. However, process-specific fabrication anomalies can result in non-intuitive effects on performance; we propose a framework for identifying defect mechanisms and their performance impact by mapping geometric variances to electromagnetic performance metrics. This method can accelerate additive fabrication feedback while avoiding the high computational cost of in-line electromagnetic simulation. We first used dimension reduction to explore the population of geometric manufacturing anomalies and electromagnetic performance. Convolutional neural networks are then trained to predict the electromagnetic performance of the printed geometries. In generating the networks, we explored two inputs: one image-derived geometric description and one using the same description with additional simulated electromagnetic information. Network latent space analysis shows the networks learned both geometric and electromagnetic values even without electromagnetic input. This result demonstrates it is possible to create accelerated additive feedback systems predicting electromagnetic performance without in-line simulation. -
Rule Generation for Classifying SLT Failed Parts (2022)
Ho-Chieh Hsu, Cheng-Che Lu, Shih-Wei Wang, Kelly Jones, Kai-Chiang Wu, Mango C.-T. ChaoAbstract
System-level test (SLT) has recently gained visibility when integrated circuits become harder and harder to be fully tested due to increasing transistor density and circuit design complexity. Albeit SLT is effective for reducing test escapes, little diagnostic information can be obtained for product improvement. In this paper, we propose an unsupervised learning (UL) method to resolve the aforementioned issue by discovering correlative, potentially systematic defects during the SLT phase. Toward this end, HDBSCAN [1] is used for clustering SLT failed devices in a low-dimensional space created by UMAP [2]. Decision trees are subsequently applied to explain the HDBSCAN results based on generating explainable quantitative rules, e.g., inequality constraints, providing domain experts additional information for advanced diagnosis. Experiments on industrial data demonstrate that the proposed methodology can effectively cluster SLT failed devices and then explain the clustering results with a promising accuracy of above 90%. Our methodology is also scalable and fast, requiring two to five orders of magnitude lower runtime than the method presented in [3]. -
Cybersecurity Challenges in Downstream Steel Production Processes (2022)
Joaquín Ordieres-Meré, Andreas Wolff, Antonia Pacios-Álvarez, Antonio Bello-GarcíaAbstract
The goal of this paper is to explore proposals coming from different EU-RFCS research funded projects, in such a way that cybersecurity inside the steel industry can be increased from the Operational Technology area, with the current level of adopted Information Technology solutions. The dissemination project Control In Steel has reviewed different projects with different strategies, including ideas to be developed inside the Auto Surveillance project. An advanced control process strategy is considered and cloud based solutions are the main analysed alternatives. The different steps in the model lifecycle are considered where different cloud configurations provide different solutions. Advanced techniques such as UMAP projection are proposed to be used as detectors for anomalous behaviour in the continuous development / continuous implementation strategy, suitable for integration in processing workflows -
Identifying Repeating Patterns in IEC 61499 Systems Using Feature-Based Embeddings (2022)
Markus Unterdechler, Antonio M. Gutiérrez, Lisa Sonnleithner, Rick Rabiser, Alois ZoitlAbstract
Cyber-Physical Production Systems (CPPSs) are highly variable systems of systems comprised of software and hardware interacting with each other and the environment. The increasing integration of technologies and devices has brought an unprecedented level of automation and customization. At the same time, it has also increased the efforts to maintain highly complex and heterogeneous systems. Although engineering practices support the reuse of common components to ease the development and maintenance of the systems in different projects, the identification of common components is still manually performed, which is a time-consuming, error-prone task. In this paper, a novel approach identifying repeating patterns in CPPSs based on artificial intelligence techniques is presented. This approach allows finding exact and similar components to support the CPPS design. Furthermore, it enables the maintenance of common components by reusing predefined types thereby reducing development effort. We implemented and evaluated our approach in an industry case study on developing CPPS control software with IEC 61499. -
A Novel Quality Clustering Methodology on Fab-Wide Wafer Map Images in Semiconductor Manufacturing (2022)
Yuan-Ming Hsu, Xiaodong Jia, Wenzhe Li, Jay LeeAbstract
Abstract. In semiconductor manufacturing, clustering the fab-wide wafer map images is of critical importance for practitioners to understand the subclusters of wafer defects, recognize novel clusters or anomalies, and develop fast reactions to quality issues. However, due to the high-mix manufacturing of diversified wafer products of different sizes and technologies, it is difficult to cluster the wafer map images across the fab. This paper addresses this challenge by proposing a novel methodology for fab-wide wafer map data clustering. In the proposed methodology, a well-known deep learning technique, vision transformer with multi-head attention is first trained to convert binary wafer images of different sizes into condensed feature vectors for efficient clustering. Then, the Topological Data Analysis (TDA), which is widely used in biomedical applications, is employed to visualize the data clusters and identify the anomalies. The TDA yields a topological representation of high-dimensional big data as well as its local clusters by creating a graph that shows nodes corresponding to the clusters within the data. The effectiveness of the proposed methodology is demonstrated by clustering the public wafer map dataset WM-811k from the real application which has a total of 811,457 wafer map images. We further demonstrate the potential applicability of topology data analytics in the semiconductor area by visualization. -
Transfer Learning for Autonomous Chatter Detection in Machining (2022)
Melih C. Yesilli, Firas A. Khasawneh, Brian P. MannAbstract
Large-amplitude chatter vibrations are one of the most important phenomena in machining processes. It is often detrimental in cutting operations causing a poor surface finish and decreased tool life. Therefore, chatter detection using machine learning has been an active research area over the last decade. Three challenges can be identified in applying machine learning for chatter detection at large in industry: an insufficient understanding of the universality of chatter features across different processes, the need for automating feature extraction, and the existence of limited data for each specific workpiece-machine tool combination, e.g., when machining one-off products. These three challenges can be grouped under the umbrella of transfer learning, which is concerned with studying how knowledge gained from one setting can be leveraged to obtain information in new settings. This paper studies automating chatter detection by evaluating transfer learning of prominent as well as novel chatter detection methods. We investigate chatter classification accuracy using a variety of features extracted from turning and milling experiments with different cutting configurations. The studied methods include Fast Fourier Transform (FFT), Power Spectral Density (PSD), the Auto-correlation Function (ACF), and decomposition based tools such as Wavelet Packet Transform (WPT) and Ensemble Empirical Mode Decomposition (EEMD). We also examine more recent approaches based on Topological Data Analysis (TDA) and similarity measures of time series based on Discrete Time Warping (DTW). We evaluate transfer learning potential of each approach by training and testing both within and across the turning and milling data sets. Four supervised classification algorithms are explored: support vector machine (SVM), logistic regression, random forest classification, and gradient boosting. In addition to accuracy, we also comment on the automation potential of feature extraction for each approach which is integral to creating autonomous manufacturing centers. Our results show that carefully chosen time-frequency features can lead to high classification accuracies albeit at the cost of requiring manual pre-processing and the tagging of an expert user. On the other hand, we found that the TDA and DTW approaches can provide accuracies and F1-scores on par with the time-frequency methods without the need for manual preprocessing via completely automatic pipelines. Further, we discovered that the DTW approach outperforms all other methods when trained using the milling data and tested on the turning data. Therefore, TDA and DTW approaches may be preferred over the time-frequency-based approaches for fully automated chatter detection schemes. DTW and TDA also can be more advantageous when pooling data from either limited workpiece-machine tool combinations, or from small data sets of one-off processes. -
Topological Data Analysis for Electric Motor Eccentricity Fault Detection (2022)
Bingnan Wang, Chungwei Lin, Hiroshi Inoue, Makoto KanemaruAbstract
In this paper, we develop topological data analysis (TDA) method for motor current signature analysis (MCSA), and apply it to induction motor eccentricity fault detection. We introduce TDA and present the procedure of extracting topological features from time-domain data that will be represented using persistence diagrams and vectorized Betti sequences. The procedure is applied to induction machine phase current signal analysis, and shown to be highly effective in differentiating signals from different eccentricity levels. With TDA, we are able to use a simple regression model that can predict the fault levels with reasonable accuracy, even for the data of eccentricity levels that are not seen in the training data. The proposed method is model-free, and only requires a small segment of time-domain data to make prediction. These advantages make it attractive for a wide range of fault detection applications. -
Wear Monitoring in Fine Blanking Processes Using Feature Based Analysis of Acoustic Emission Signals (2021)
Martin Unterberg, Herman Voigts, Ingo Felix Weiser, Andreas Feuerhack, Daniel Trauth, Thomas BergsAbstract
Tool wear during fine blanking impairs the quality of the sheared part, which is assessed in regular samples in an industrial environment. This leads to scrap production and low planning reliability due to low wear predictability. A tool condition monitoring based on acoustic emission (AE) data for the prediction of the remaining useful life of the tool would mitigate those effects. In a production series, AE signals were recorded, and the tool wear observed. The AE signals were then preprocessed using feature engineering and visualized using linear and nonlinear dimensionality reduction techniques. These visualizations preserve information about the data structure even in two dimensions and resemble the temporal dependent observed tool wear during fine blanking. -
A Visual Analytics Approach for the Diagnosis of Heterogeneous and Multidimensional Machine Maintenance Data (2021)
Xiaoyu Zhang, Takanori Fujiwara, Senthil Chandrasegaran, Michael P. Brundage, Thurston Sexton, Alden Dima, Kwan-Liu MaAbstract
Analysis of large, high-dimensional, and heterogeneous datasets is challenging as no one technique is suitable for visualizing and clustering such data in order to make sense of the underlying information. For instance, heterogeneous logs detailing machine repair and maintenance in an organization often need to be analyzed to diagnose errors and identify abnormal patterns, formalize root-cause analyses, and plan preventive maintenance. Such real-world datasets are also beset by issues such as inconsistent and/or missing entries. To conduct an effective diagnosis, it is important to extract and understand patterns from the data with support from analytic algorithms (e.g., finding that certain kinds of machine complaints occur more in the summer) while involving the human-in-the-loop. To address these challenges, we adopt existing techniques for dimensionality reduction (DR) and clustering of numerical, categorical, and text data dimensions, and introduce a visual analytics approach that uses multiple coordinated views to connect DR + clustering results across each kind of the data dimension stated. To help analysts label the clusters, each clustering view is supplemented with techniques and visualizations that contrast a cluster of interest with the rest of the dataset. Our approach assists analysts to make sense of machine maintenance logs and their errors. Then the gained insights help them carry out preventive maintenance. We illustrate and evaluate our approach through use cases and expert studies respectively, and discuss generalization of the approach to other heterogeneous data. -
Persistent Homology Based Graph Convolution Network for Fine-Grained 3D Shape Segmentation (2021)
Chi-Chong Wong, Chi-Man VongAbstract
Fine-grained 3D segmentation is an important task in 3D object understanding, especially in applications such as intelligent manufacturing or parts analysis for 3D objects. However, many challenges involved in such problem are yet to be solved, such as i) interpreting the complex structures located in different regions for 3D objects; ii) capturing fine-grained structures with sufficient topology correctness. Current deep learning and graph machine learning methods fail to tackle such challenges and thus provide inferior performance in fine-grained 3D analysis. In this work, methods in topological data analysis are incorporated with geometric deep learning model for the task of fine-grained segmentation for 3D objects. We propose a novel neural network model called Persistent Homology based Graph Convolution Network (PHGCN), which i) integrates persistent homology into graph convolution network to capture multi-scale structural information that can accurately represent complex structures for 3D objects; ii) applies a novel Persistence Diagram Loss (ℒPD) that provides sufficient topology correctness for segmentation over the fine-grained structures. Extensive experiments on fine-grained 3D segmentation validate the effectiveness of the proposed PHGCN model and show significant improvements over current state-of-the-art methods. -
Dynamic State Analysis of a Driven Magnetic Pendulum Using Ordinal Partition Networks and Topological Data Analysis (2020)
Audun Myers, Firas A. KhasawnehAbstract
Abstract. The use of complex networks for time series analysis has recently shown to be useful as a tool for detecting dynamic state changes for a wide variety of applications. In this work, we implement the commonly used ordinal partition network to transform a time series into a network for detecting these state changes for the simple magnetic pendulum. The time series that we used are obtained experimentally from a base-excited magnetic pendulum apparatus, and numerically from the corresponding governing equations. The magnetic pendulum provides a relatively simple, non-linear example demonstrating transitions from periodic to chaotic motion with the variation of system parameters. For our method, we implement persistent homology, a shape measuring tool from Topological Data Analysis (TDA), to summarize the shape of the resulting ordinal partition networks as a tool for detecting state changes. We show that this network analysis tool provides a clear distinction between periodic and chaotic time series. Another contribution of this work is the successful application of the networks-TDA pipeline, for the first time, to signals from non-autonomous nonlinear systems. This opens the door for our approach to be used as an automatic design tool for studying the effect of design parameters on the resulting system response. Other uses of this approach include fault detection from sensor signals in a wide variety of engineering operations. -
An Industry Case of Large-Scale Demand Forecasting of Hierarchical Components (2019)
Rodrigo Rivera-Castro, Ivan Nazarov, Yuke Xiang, Ivan Maksimov, Aleksandr Pletnev, Evgeny BurnaevAbstract
Demand forecasting of hierarchical components is essential in manufacturing. However, its discussion in the machine-learning literature has been limited, and judgemental forecasts remain pervasive in the industry. Demand planners require easy-to-understand tools capable of delivering state-of-the-art results. This work presents an industry case of demand forecasting at one of the largest manufacturers of electronics in the world. It seeks to support practitioners with five contributions: (1) A benchmark of fourteen demand forecast methods applied to a relevant data set, (2) A data transformation technique yielding comparable results with state of the art, (3) An alternative to ARIMA based on matrix factorization, (4) A model selection technique based on topological data analysis for time series and (5) A novel data set. Organizations seeking to up-skill existing personnel and increase forecast accuracy will find value in this work. -
Chatter Diagnosis in Milling Using Supervised Learning and Topological Features Vector (2019)
Melih C. Yesilli, Sarah Tymochko, Firas A. Khasawneh, Elizabeth MunchAbstract
Chatter detection has become a prominent subject of interest due to its effect on cutting tool life, surface finish and spindle of machine tool. Most of the existing methods in chatter detection literature are based on signal processing and signal decomposition. In this study, we use topological features of data simulating cutting tool vibrations, combined with four supervised machine learning algorithms to diagnose chatter in the milling process. Persistence diagrams, a method of representing topological features, are not easily used in the context of machine learning, so they must be transformed into a form that is more amenable. Specifically, we will focus on two different methods for featurizing persistence diagrams, Carlsson coordinates and template functions. In this paper, we provide classification results for simulated data from various cutting configurations, including upmilling and downmilling, in addition to the same data with some added noise. Our results show that Carlsson Coordinates and Template Functions yield accuracies as high as 96% and 95%, respectively. We also provide evidence that these topological methods are noise robust descriptors for chatter detection. -
A Classification of Topological Discrepancies in Additive Manufacturing (2019)
Morad Behandish, Amir M. Mirzendehdel, Saigopal NelaturiAbstract
Additive manufacturing (AM) enables enormous freedom for design of complex structures. However, the process-dependent limitations that result in discrepancies between as-designed and as-manufactured shapes are not fully understood. The tradeoffs between infinitely many different ways to approximate a design by a manufacturable replica are even harder to characterize. To support design for AM (DfAM), one has to quantify local discrepancies introduced by AM processes, identify the detrimental deviations (if any) to the original design intent, and prescribe modifications to the design and/or process parameters to countervail their effects. Our focus in this work will be on topological analysis. There is ample evidence in many applications that preserving local topology (e.g., connectivity of beams in a lattice) is important even when slight geometric deviations can be tolerated. We first present a generic method to characterize local topological discrepancies due to material under-and over-deposition in AM, and show how it captures various types of defects in the as-manufactured structures. We use this information to systematically modify the as-manufactured outcomes within the limitations of available 3D printer resolution(s), which often comes at the expense of introducing more geometric deviations (e.g., thickening a beam to avoid disconnection). We validate the effectiveness of the method on 3D examples with nontrivial topologies such as lattice structures and foams. -
Topological Data Analysis for True Step Detection in Periodic Piecewise Constant Signals (2018)
Firas A. Khasawneh, Elizabeth MunchAbstract
This paper introduces a simple yet powerful approach based on topological data analysis for detecting true steps in a periodic, piecewise constant (PWC) signal. The signal is a two-state square wave with randomly varying in-between-pulse spacing, subject to spurious steps at the rising or falling edges which we call digital ringing. We use persistent homology to derive mathematical guarantees for the resulting change detection which enables accurate identification and counting of the true pulses. The approach is tested using both synthetic and experimental data obtained using an engine lathe instrumented with a laser tachometer. The described algorithm enables accurate and automatic calculations of the spindle speed without any choice of parameters. The results are compared with the frequency and sequency methods of the Fourier and Walsh–Hadamard transforms, respectively. Both our approach and the Fourier analysis yield comparable results for pulses with regular spacing and digital ringing while the latter causes large errors using the Walsh–Hadamard method. Further, the described approach significantly outperforms the frequency/sequency analyses when the spacing between the peaks is varied. We discuss generalizing the approach to higher dimensional PWC signals, although using this extension remains an interesting question for future research. -
Chatter Classification in Turning Using Machine Learning and Topological Data Analysis (2018)
Firas A. Khasawneh, Elizabeth Munch, Jose A. PereaAbstract
Chatter identification and detection in machining processes has been an active area of research in the past two decades. Part of the challenge in studying chatter is that machining equations that describe its occurrence are often nonlinear delay differential equations. The majority of the available tools for chatter identification rely on defining a metric that captures the characteristics of chatter, and a threshold that signals its occurrence. The difficulty in choosing these parameters can be somewhat alleviated by utilizing machine learning techniques. However, even with a successful classification algorithm, the transferability of typical machine learning methods from one data set to another remains very limited. In this paper we combine supervised machine learning with Topological Data Analysis (TDA) to obtain a descriptor of the process which can detect chatter. The features we use are derived from the persistence diagram of an attractor reconstructed from the time series via Takens embedding. We test the approach using deterministic and stochastic turning models, where the stochasticity is introduced via the cutting coefficient term. Our results show a 97% successful classification rate on the deterministic model labeled by the stability diagram obtained using the spectral element method. The features gleaned from the deterministic model are then utilized for characterization of chatter in a stochastic turning model where there are very limited analysis methods. -
Shape Terra: Mechanical Feature Recognition Based on a Persistent Heat Signature (2017)
Ramy Harik, Yang Shi, Stephen BaekAbstract
This paper presents a novel approach to recognizing mechanical features through a multiscale persistent heat signature similarity identification technique. First, heat signature is computed using a modified Laplacian in the application of the heat kernel. Regularly, matrices tend to include an indicator to the manifold curvature (the cotangent in our case), but we add a mesh uniformity factor to overcome mesh proportionality and skewness. Second, once heat retention values are computed, we apply persistent homology to extract significant subsets of the global mesh at different time intervals. Subsets are computed based on similarity of heat retention levels and/or retention values. Third, we present a multiscale persistence identification approach where we scan the part at different persistence levels to detect the presence of a feature. Once features are recognized and their geometrical descriptors identified, the next stage in future work will be feature matching. -
Raw Material Flow Optimization as a Capacitated Vehicle Routing Problem: A Visual Benchmarking Approach for Sustainable Manufacturing (2017)
Michele Dassisti, Yasamin Eslami, Matin MohagheghAbstract
Optimisation problem concerning material flows, to increase the efficiency while reducing relative resource consumption is one of the most pressing problems today. The focus point of this study is to propose a new visual benchmarking approach to select the best material-flow path from the depot to the production lines, referring to the well-known Capacitated Vehicle Routing Problem (CVRP). An example industrial case study is considered to this aim. Two different solution techniques were adopted (namely Mixed Integer Linear Programming and the Ant Colony Optimization) in searching optimal solutions to the CVRP. The visual benchmarking proposed, based on the persistent homology approach, allowed to support the comparison of the optimal solutions based on the entropy of the output in different scenarios. Finally, based on the non-standard measurements of Crossing Length Percentage (CLP), the visual benchmarking procedure makes it possible to find the most practical and applicable solution to CVRP by considering the visual attractiveness and the quality of the routes. -
Identification of Key Features Using Topological Data Analysis for Accurate Prediction of Manufacturing System Outputs (2017)
Wei Guo, Ashis G. BanerjeeAbstract
Topological data analysis (TDA) has emerged as one of the most promising approaches to extract insights from high-dimensional data of varying types such as images, point clouds, and meshes, in an unsupervised manner. To the best of our knowledge, here, we provide the first successful application of TDA in the manufacturing systems domain. We apply a widely used TDA method, known as the Mapper algorithm, on two benchmark data sets for chemical process yield prediction and semiconductor wafer fault detection, respectively. The algorithm yields topological networks that capture the intrinsic clusters and connections among the clusters present in the data sets, which are difficult to detect using traditional methods. We select key process variables or features that impact the system outcomes by analyzing the network shapes. We then use predictive models to evaluate the impact of the selected features. Results show that the models achieve at least the same level of high prediction accuracy as with all the process variables, thereby, providing a way to carry out process monitoring and control in a more cost-effective manner. -
Chatter Detection in Turning Using Persistent Homology (2016)
Firas A. Khasawneh, Elizabeth MunchAbstract
This paper describes a new approach for ascertaining the stability of stochastic dynamical systems in their parameter space by examining their time series using topological data analysis (TDA). We illustrate the approach using a nonlinear delayed model that describes the tool oscillations due to self-excited vibrations in turning. Each time series is generated using the Euler-Maruyama method and a corresponding point cloud is obtained using the Takens embedding. The point cloud can then be analyzed using a tool from TDA known as persistent homology. The results of this study show that the described approach can be used for analyzing datasets of delay dynamical systems generated both from numerical simulation and experimental data. The contributions of this paper include presenting for the first time a topological approach for investigating the stability of a class of nonlinear stochastic delay equations, and introducing a new application of TDA to machining processes. -
Toward Automated Prediction of Manufacturing Productivity Based on Feature Selection Using Topological Data Analysis (2016)
Wei Guo, Ashis G. BanerjeeAbstract
In this paper, we extend the application of topological data analysis (TDA) to the field of manufacturing for the first time to the best of our knowledge. We apply a particular TDA method, known as the Mapper algorithm, on a benchmark chemical processing data set. The algorithm yields a topological network that captures the intrinsic clusters and connections among the clusters present in the high-dimensional data set, which are difficult to detect using traditional methods. We select key process variables or features that impact the final product yield by analyzing the shape of this network. We then use three prediction models to evaluate the impact of the selected features. Results show that the models achieve the same level of high prediction accuracy as with all the process variables, thereby, providing a way to carry out process monitoring and control in a more cost-effective manner.