Oon Peen Gan

FUZZY REGRESSION MODELING FOR TOOL PERFORMANCE PREDICTION AND DEGRADATION DETECTION

In this paper, the viability of using Fuzzy-Rule-Based Regression Modeling (FRM) algorithm for tool performance and degradation detection is investigated. The FRM is developed based on a multi-layered fuzzy-rule-based hybrid system with Multiple Regression Models (MRM) embedded into a fuzzy logic inference engine that employs Self Organizing Maps (SOM) for clustering. The FRM converts a complex nonlinear problem to a simplified linear format in order to further increase the accuracy in prediction and rate of convergence. The efficacy of the proposed FRM is tested through a case study - namely to predict the remaining useful life of a ball nose milling cutter during a dry machining process of hardened tool steel with a hardness of 52-54 HRc. A comparative study is further made between four predictive models using the same set of experimental data. It is shown that the FRM is superior as compared with conventional MRM, Back Propagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in terms of prediction accuracy and learning speed.

Classification of energy consumption patterns for energy audit and machine scheduling in industrial manufacturing systems

To reduce energy consumption for sustainable and energy-efficient manufacturing, continuous energy monitoring and process tracking of industrial machines are essential. In this paper, we introduce a novel approach to reduce the number of required sensors in process tracking by identifying the operational states based on real-time energy data. Finite-state machines are used to model the engineering processes, and a two-stage framework for online classification of real-time energy measurement data in terms of machine operational states is proposed for energy audit and machine scheduling. The first stage uses advanced signal processing techniques to reduce noise while preserving important features, and the second stage uses intelligent pattern recognition algorithms to cluster energy consumption patterns. Our proposed two-stage framework is evaluated on an industrial injection moulding system using a Savizky–Golay filter and a neural network, and our experimental results show a 95.85% accuracy in identification of machine operational states.

Discrete-Event Shop-Floor Monitoring System in RFID-Enabled Manufacturing

In this paper, a real-time discrete-event (DE)-based monitoring system is developed for radio-frequency identification (RFID)-enabled shop-floor monitoring in manufacturing industries. The monitoring system uses rigorous mathematical techniques for event construction, state prediction, and disturbance detection that are suitable for big-data environments of modern complex manufacturing systems. The biggest challenge is to design an efficient scheme for computers to process the event data fast and for engineers to modify the monitoring rules conveniently. First, a DE observer is designed to construct complex events from the simple events extracted from the raw RFID data. The DE observer is based on matrices with binary entries, and thus is easy for multiple users to interpret and modify to define new events or delete event definitions. Temporal relations between time-related events are also included. Second, a hidden Markov model, which considers the impact of user actions and disturbance events, is developed to predict the belief state of manufacturing systems and detect disturbances. Finally, an application case study of the developed system in the shop-floor monitoring of a precision machining parts manufacturing process is provided to show how it can help engineers/managers monitor the events and states efficiently.

Intelligent energy audit and machine management for energy-efficient manufacturing

To reduce energy consumption for sustainable and energy-efficient manufacturing, a good understanding of the dynamic energy consumption patterns on the manufacturing shop floor is essential. In this paper, we introduce a novel approach to address the challenge of missing operation context information during in-situ energy data measurement. Finite-State Machines (FSMs) are used to model the engineering processes, and a two-stage framework for online classification of real time energy measurement data in terms of machine operation states is proposed for energy audit and machine management. The first stage uses advanced signal processing techniques to reduce noise while preserving important features, and the second stage uses intelligent pattern recognition algorithms to cluster energy consumption patterns. Our proposed two-stage framework is evaluated on an industrial injection moulding system using a Savizky-Golay (SG) filter and a Neural Network (NN), and our experimental results show a 95.85% accuracy in identification of machine operation states.

Multi-commodity flow dynamic resource assignment and matrix-based job dispatching for multi-relay transfer in complex material handling systems (MHS)

Mass management and production of customized products requires material handling systems (MHS) which are flexible and responsive enough to accommodate dynamic and real-time changes in material handling tasks. Towards this goal, we develop a novel control framework to improve the flexibility and responsiveness of material handling systems. Flexibility is achieved by using multi-commodity flow network optimization to find the most optimized job sequence in terms of minimum transfer steps. Responsiveness is achieved by the use of a matrix-based discrete event (DE) supervisory controller to dispatch equipment control commands in real-time based on real-time sensor information, according to the optimized sequence. By modeling the MHS network as multi-commodity flow network to define job routes, and using the matrix-based DE controller to implement the job routes in real-time, the users achieve a seamlessly integrated solution to control the execution of transfer jobs that covers the supervisory planning stage through the real-time actual dispatching decisions. The proposed control framework is evaluated on an industrial case study of airfreight terminal material handling and simulation results show its effectiveness.

An exTS based neuro-fuzzy algorithm for prognostics and tool condition monitoring

The growing interest in predictive maintenance makes industrials and researchers turning themselves to artificial intelligence methods for fulfilling the tasks of condition monitoring and prognostics. Within this frame, the general purpose of this paper is to investigate the capabilities of an Evolving extended Takagi Sugeno (exTS) based neuro-fuzzy algorithm to predict the tool condition in high-speed machining conditions. The performance of evolving Neuro-Fuzzy model is compared with an Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Multiple Regression Model (MRM) in term of accuracy and reliability through a case study of tool condition monitoring. The reliability of exTS also investigated.

Genetic Algorithms for Feature Subset Selection in Equipment Fault Diagnosis

This paper presents a method to determine optimum feature subset selection with a modified wrapper-based multi-criteria approach using genetic algorithms. We present details of the algorithm, design and implementation of feature subset selection using genetic algorithms. The best compound features found by genetic algorithms are verified by multiple regression models and are used to construct fault prediction models. A case study of machinery tool wear-out prediction is presented. The fairly good agreement between the prediction result and real tool wear-out data demonstrates the viability of the feature subset selection method for diagnosis applications.

Adaptive Network Fuzzy Inference System and support vector machine learning for tool wear estimation in high speed milling processes

In metal cutting processes, tool condition monitoring (TCM) plays an important role in maintaining the quality of surface finishing. Monitoring of tool wear in order to prevent surface damage is one of the difficult tasks in the context of TCM. Through early detection, high quality surface finishing and near-zero loss for potential failures can be ensured. Real-time/online tool degradation detection by using machine learning is highly desired. The ability to predict the tool wear, which is related to the remaining useful life of a tool, will improve efficiency and optimize tool usage while ensuring the quality of the work piece produced. In this paper, examine two popular methods of machine learning, namely the Adaptive Network Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM) are used to estimate the tool wear and correlation models for tool wear estimation using ANFIS and SVM are estimated. A case study for six sets of ball nose cutters in a high speed milling machining process of Inconel 718 is carried out. Comparative studies of the two methods are carried out and experimental results analysed and discussed. In turns out that the accuracy of the ANFIS is generally better than the SVM whereas SVM is much faster than ANFIS in terms of speed.

RFID for MRO Work In Progress Tracking

The aerospace maintenance, repair and overhaul (MRO) operation is a dynamic business. The job scope is unpredictable and there are also other challenges such as urgent orders that upset the production plan. As a result, the planner needs to make prompt decision to adjust production plan from time to time. To do this efficiently, the availability of timely and accurate work-in-progress (WIP) information at the shop floor is critically important. The traditional practices of paper based WIP tracking are tedious and inefficient. This paper discusses a novel approach of using the rewritable RFID tag as a means for electronic job order that overcomes the shortcomings of the paper based tracking

Passive UHF far-field RFID based localization in smart rack

Many companies face issues today in locating their assets and inventories in storage racks. In this study, we explored the use of passive UHF RFID for locating relative positions of items on storage racks. The storage rack with UHF RFID localization function is named as smart rack in this study. This paper addresses the technical issue of how to make use of the reference RFID tag signals to improve the accuracy of the position estimation of the target RFID tag. A passive UHF RFID smart rack test bed was built to quantify the UHF RFID signals variance in the test bed. The signals are analyzed for the development of next generation RFID system for smart rack applications.