Junhong Zhou

Intelligent Diagnosis and Prognosis of Tool Wear Using Dominant Feature Identification

Identification and prediction of a lifetime of industrial cutting tools using minimal sensors is crucial to reduce production costs and downtime in engineering systems. In this paper, we provide a formal decision software tool to extract the dominant features enabling tool wear prediction. This decision tool is based on a formal mathematical approach that selects dominant features using the singular value decomposition of real-time measurements from the sensors of an industrial cutting tool. Selection of dominant features is important, as retaining only essential features allows reduced signal processing or even reduction in the number of required sensors, which cuts costs. It is shown that the proposed method of dominant feature selection is optimal in the sense that it minimizes the least-squares estimation error. The identified dominant features are used with the recursive least squares (RLS) algorithm to identify parameters in forecasting the time series of cutting tool wear. Experimental results on an industrial high-speed milling machine show the effectiveness in predicting the tool wear using only the dominant features.

Tool Wear Monitoring Using Acoustic Emissions by Dominant-Feature Identification

Identification and online prediction of lifetime of cutting tools using cheap sensors is crucial to reduce production costs and downtime in industrial machines. In this paper, we use the acoustic emission from an embedded sensor for computation of features and prediction of tool wear. Acoustic sensors are cheap and nonintrusive, coupled with fast dynamic responses as compared with conventional force measurements using dynamometers. A reduced feature subset, which is optimal in both estimation and clustering least squares errors, is then selected using a new dominant-feature identification algorithm to reduce the signal processing and number of sensors required. Tool wear is then predicted using an Auto-Regressive Moving Average with eXogenous inputs model based on the reduced features. Our experimental results on a ball nose cutter in a high-speed milling machine show the effectiveness in predicting the tool wear using only the dominant features. A reduction in 16.83% of mean relative error is observed when compared to the other methods proposed in the literature.

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.

A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics

In this paper, a temporal probabilistic approach based on the hidden Markov model (HMM), named physically segmented HMM with continuous output, is introduced for continuous tool condition monitoring in machinery systems. The proposed approach has the advantage of providing an explicit relationship between the actual health states and the hidden state values. The provided relationship is further exploited for formulation and parameter estimation in the proposed approach. The introduced approach is tested for continuous tool wear prediction in a computer numerical control milling machine and compared with two well-established neural network (NN) approaches, namely, multilayer perceptron and Elman network. In the experimental study, the prediction results are provided and compared after adopting appropriate hyper-parameter values for all the approaches by cross-validation. Based on the experimental results, physically segmented HMM approach outperforms the NN approaches. Moreover, the prognosis ability of the proposed approach is studied.

Intelligent prediction monitoring system for predictive maintenance in manufacturing

This paper presents an intelligent prediction and monitoring system for equipment failure prediction to support equipment maintenance, diagnostics and prognostics in manufacturing environment. The system architecture and implementation techniques, such as agent framework, real-time data acquisition and federated communication are briefly described. Details are given on the intelligent prediction engine which is the key component of the system. A case study for machining tool useful lifetime prediction is presented to demonstrate the usability of the system.

Multimodal Hidden Markov Model-Based Approach for Tool Wear Monitoring

In this paper, a novel multimodal hidden Markov model (HMM)-based approach is proposed for tool wear monitoring (TWM). The proposed approach improves the performance of a pre-existing HMM-based approach named physically segmented HMM with continuous output (PSHMCO) by using multiple PSHMCOs in parallel. In this multimodal approach, each PSHMCO captures and emphasizes on a different tool wear regiment. In this paper, three weighting schemes, namely, bounded hindsight, discounted hindsight, and semi-nonparametric hindsight, are proposed, and two switching strategies named soft and hard switching are introduced to combine the outputs from multiple modes into one. As an illustrative example, the proposed approach is applied to TWM in a computer numerically controlled milling machine. The performance of the multimodal approach with various weighting schemes and switching strategies is reported and compared with PSHMCO.

Mode Tracking of Hybrid Systems in FDI Framework

A hybrid system combines continuous and discrete dynamics and runs with a set of modes. In we proposed an efficient health monitoring method for hybrid systems. This method utilizes unified constraint relations, named the global analytical redundancy relations (GARRs). Using GARRs for hybrid system health monitoring requires knowledge of the systems mode which is provided by a mode tracker. GARRs represent global information (i.e. information relevant to all modes), and the hybrid system properties can be analyzed across systems modes. In this paper, we utilize this unique feature to develop a GARRs based mode tracking approach. The most significant contribution of this development is the mode-change signature matrix, its derivation from the GARRs and its use for mode tracking.

Data-driven approaches in health condition monitoring — A comparative study

In this paper, four data-driven classification approaches, that is, K-nearest neighbors (K-NN), self-organizing map (SOM), multi-layer perceptron (MLP), and Bayesian Network classifier (BNC), are applied to a health condition monitoring problem for the wearing cutter. The dataset is produced from a cutting machine using force sensing. A genetic algorithm (GA) based search is performed to select 3 dominant features from a 16-dimensional feature space, which is computed directly from the real dataset. Subsequently K-NN, SOM, MLP, and BNC algorithms are trained to predict the wearing status of the cutter, respectively. The suitability of the four data-driven approaches for the health condition monitoring are investigated and compared.

Vibration-based fault diagnostic platform for rotary machines

This paper provides a vibration-based diagnostic platform to systematically monitor and diagnose of rotary machine faults. Commonly rotary machine faults described in this paper are misalignment fault, bearing cage defect, ball bearing defect, bearing outer race fault and inner race fault. The use of structural resonance frequency, ISO 10816 for vibration level assessment, spectrum assessment for misalignment and bearing faults have been detailed. Beside fault diagnosis, repair action has been included to recommend different maintenance plans according to the faulty conditions. These methods form the basis of a knowledge-based system for diagnosis. The results have been successfully tested on a Hitachi Seiki high speed milling machine. The developed diagnosis platform minimized the need for human intervention in rotary machine performance monitoring and degradation detection.

PDF and Breakdown Time Prediction for Unobservable Wear Using Enhanced Particle Filters in Precognitive Maintenance

Machine health prognosis is crucial to reduce unexpected downtime, maintenance costs, and safety hazards in industrial systems. In this paper, a novel methodology to predict probability density function (pdf) and breakdown time of unobservable degradation processes is proposed. A transition-based autoregressive moving average model and an enhanced particle filter (EPF) are developed at the prognosis stage for the pdf prediction of industrial wear. The strictly monotonic increasing behavior of degradation is ensured by executing a monotonic resampling scheme in EPF, and the number of particles is chosen to be time-varying to reduce computation costs. The effectiveness of our proposed framework is tested on the tool wear in an industrial milling machine, and achieves the predicted bounds with accuracies of at least 90.3% as well as saves more than 50% calculation time without loss of accuracy.