Non-convex hull based anomaly detection in CPPS

Abstract Along with the constantly increasing complexity of industrial automation systems, machine learning methods have been widely applied to detecting abnormal states in such systems. Anomaly detection tasks can be treated as one-class classification problems in machine learning. Geometric methods can give an intuitive solution to such problems. In this paper, we propose a new geometric structure, oriented non-convex hulls, to represent decision boundaries used for one-class classification. Based on this geometric structure, a novel boundary based one-class classification algorithm is developed to solve the anomaly detection problem. Compared with traditional boundary-based approaches such as convex hulls based methods and one-class support vector machines, the proposed approach can better reflect the true geometry of target data and needs little effort for parameter tuning. The effectiveness of this approach is evaluated with artificial and real world data sets to solve the anomaly detection problem in Cyber–Physical-Production-Systems (CPPS). The evaluation results also show that the proposed approach has higher generality than the used baseline algorithms.

[1]  Abdelwahab Hamou-Lhadj,et al.  An anomaly detection system based on variable N-gram features and one-class SVM , 2017, Inf. Softw. Technol..

[2]  Steven X. Ding,et al.  A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches , 2015, IEEE Transactions on Industrial Electronics.

[3]  Florentin Wörgötter,et al.  Object Partitioning Using Local Convexity , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Bernhard Schölkopf,et al.  One-Class Support Measure Machines for Group Anomaly Detection , 2013, UAI.

[5]  Junyi Xu,et al.  A Concave Hull algorithm for scattered data and its applications , 2010, 2010 3rd International Congress on Image and Signal Processing.

[6]  J. E. Lewis,et al.  Geometry of Convex Sets , 2015 .

[7]  José R. Dorronsoro,et al.  Clipping algorithms for solving the nearest point problem over reduced convex hulls , 2011, Pattern Recognit..

[8]  Min Wang,et al.  Online Support Vector Machine Based on Convex Hull Vertices Selection , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Se-Jong Oh,et al.  A New Concave Hull Algorithm and Concaveness Measure for n-dimensional Datasets , 2012, J. Inf. Sci. Eng..

[10]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[11]  Geert Gins,et al.  Industrial Process Monitoring in the Big Data/Industry 4.0 Era: from Detection, to Diagnosis, to Prognosis , 2017 .

[12]  Michael Galetzka,et al.  A Simple and Correct Even-Odd Algorithm for the Point-in-Polygon Problem for Complex Polygons , 2017, VISIGRAPP.

[13]  Junsheng Cheng,et al.  One-class classification based on the convex hull for bearing fault detection , 2016 .

[14]  Yu Yang,et al.  Linear maximum margin tensor classification based on flexible convex hulls for fault diagnosis of rolling bearings , 2019, Knowl. Based Syst..

[15]  Kristin P. Bennett,et al.  Duality and Geometry in SVM Classifiers , 2000, ICML.

[16]  Jun Miao,et al.  One-Class Classification with Extreme Learning Machine , 2015 .

[17]  Oliver Niggemann,et al.  Symptomes Classifier Hypotheses Phenomenological Approach to Diagnosis Causality Analysis Causality Model Hypotheses Model-Based Approach to Diagnosis Symptomes Similarity Search Case Database Hypotheses , 2014 .

[18]  Seong-Dae Kim,et al.  Visual Hull-Based Geometric Data Compression of a 3-D Object , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Shehroz S. Khan,et al.  One-class classification: taxonomy of study and review of techniques , 2013, The Knowledge Engineering Review.

[20]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[21]  Zhiwei Gao,et al.  From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and Diagnosis , 2013, IEEE Transactions on Industrial Informatics.

[22]  Huangang Wang,et al.  Ramp Loss based robust one-class SVM , 2017, Pattern Recognit. Lett..

[23]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[24]  Petia Radeva,et al.  Approximate polytope ensemble for one-class classification , 2014, Pattern Recognit..

[25]  Aiman H. El-Maleh,et al.  Test data compression based on geometric shapes , 2011, Comput. Electr. Eng..

[26]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[27]  D. M. Y. Sommerville,et al.  An Introduction to The Geometry of N Dimensions , 2022 .

[28]  Pasi Fränti,et al.  K-means properties on six clustering benchmark datasets , 2018, Applied Intelligence.

[29]  Zhijian QU,et al.  Big data compression processing and verification based on Hive for smart substation , 2015 .

[30]  George Chryssolouris,et al.  Manufacturing Systems Complexity Review: Challenges and Outlook , 2012 .

[31]  Zhenbing Liu,et al.  Maximal-Margin Approach for Cost-Sensitive Learning Based on Scaled Convex Hull , 2011, ISNN.

[32]  Nico Görnitz,et al.  One-class classification in the presence of point, collective, and contextual anomalies , 2019 .

[33]  Peng Li,et al.  Data Driven Modeling for System-Level Condition Monitoring on Wind Power Plants , 2015, DX.

[34]  Peng Li,et al.  A Geometric Approach to Clustering Based Anomaly Detection for Industrial Applications , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[35]  John Shawe-Taylor,et al.  Novelty Detection with One-Class Support Vector Machines , 2015 .

[36]  Jürgen Beyerer,et al.  Gaussian Mixture Trees for One Class Classification in Automated Visual Inspection , 2017, ICIAR.