Decision-Level Data Fusion in Quality Control and Predictive Maintenance

Data fusion integrates data from multiple sources to improve prediction performance. While significant research has been conducted to develop data-level and feature-level fusion methods, very few studies are performed to develop more effective decision-level data fusion methods. This research aims at developing a decision-level data fusion approach that transforms low-dimensional decisions (i.e., predictions) made based on individual sensor data such as temperature and vibration to high-dimensional decisions. Integration of these high-dimensional decisions is formulated as a convex optimization problem rather than a traditional multivariate linear regression problem. The proposed decision-level data fusion approach is demonstrated in two cases: 1) quality control in additive manufacturing and 2) predictive maintenance in aircraft engines. Experimental results have shown that the proposed decision-level fusion method can reduce prediction variance by at least 30% as well as increase prediction accuracy by 45%. Note to Practitioners—This article was motivated by a need to make more accurate predictions with multiple sensors. Traditional data-level and feature-level fusion methods integrate raw sensor data from individual sensors and statistical features extracted from individual sensors, respectively. This article suggests a novel decision-level fusion approach as opposed to the traditional data- and feature-level fusion methods. In the first case study, temperature and vibration sensor data are integrated to predict the surface roughness of additively manufactured components. In the second case study, multiple sensor data are fused to estimate the remaining useful life (RUL) of aircraft engines. To implement the decision-level fusion technique, it is critical to determine optimal weights by solving the convex optimization problem. In future research, we will demonstrate the proposed decision-level fusion approach in real-time prognostics and health-monitoring applications.

[1]  Xi Zhang,et al.  Integration of Data-Level Fusion Model and Kernel Methods for Degradation Modeling and Prognostic Analysis , 2018, IEEE Transactions on Reliability.

[2]  Pramod K. Varshney,et al.  Multisensor Data Fusion , 1997, IEA/AIE.

[3]  Jonathan S. Litt,et al.  User's Guide for the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) , 2007 .

[4]  Allan J. Volponi,et al.  Development of an Information Fusion System for Engine Diagnostics and Health Management , 2013 .

[5]  Byeng D. Youn,et al.  Ensemble of Data-Driven Prognostic Algorithms with Weight Optimization and K-Fold Cross Validation , 2010 .

[6]  K. Goebel,et al.  Prognostic information fusion for constant load systems , 2005, 2005 7th International Conference on Information Fusion.

[7]  D. L. Hall,et al.  Mathematical Techniques in Multisensor Data Fusion , 1992 .

[8]  Jianjun Shi,et al.  A Data-Level Fusion Model for Developing Composite Health Indices for Degradation Modeling and Prognostic Analysis , 2013, IEEE Transactions on Automation Science and Engineering.

[9]  Franklin E White,et al.  Data Fusion Lexicon , 1991 .

[10]  Abhinav Saxena,et al.  Damage propagation modeling for aircraft engine run-to-failure simulation , 2008, 2008 International Conference on Prognostics and Health Management.

[11]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[12]  Shuai Huang,et al.  Integration of Data Fusion Methodology and Degradation Modeling Process to Improve Prognostics , 2016, IEEE Transactions on Automation Science and Engineering.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Pascal Vasseur,et al.  Introduction to Multisensor Data Fusion , 2005, The Industrial Information Technology Handbook.

[15]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[16]  Fakhri Karray,et al.  Multisensor data fusion: A review of the state-of-the-art , 2013, Inf. Fusion.

[17]  Qiao Sun.  Sensor fusion for vehicle health monitoring and degradation detection , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[18]  Connor Jennings,et al.  A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests , 2017 .

[19]  Madhukar Pandit,et al.  Optical wear assessment system for grinding tools , 2004, J. Electronic Imaging.

[20]  Ronald R. Yager,et al.  Generalized probabilities of fuzzy events from fuzzy belief structures , 1982, Inf. Sci..

[21]  John Yen,et al.  Generalizing the Dempster-Schafer theory to fuzzy sets , 1990, IEEE Trans. Syst. Man Cybern..

[22]  Hongwei Zhu,et al.  A novel fuzzy evidential reasoning paradigm for data fusion with applications in image processing , 2006, Soft Comput..

[23]  Fakhri Karray,et al.  Connectionist-based Dempster-Shafer evidential reasoning for data fusion , 2005, IEEE Transactions on Neural Networks.

[24]  Dazhong Wu,et al.  Predictive modelling of surface roughness in fused deposition modelling using data fusion , 2018, Int. J. Prod. Res..

[25]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.