Kesheng Wang

A hybrid intelligent method for modelling the EDM process

This paper discusses the development and application of a hybrid artificial neural network and genetic algorism methodology to modelling and optimisation of electro-discharge machining. The hybridisation approach is aimed not only at exploiting the strong capabilities of the two tools, but also at solving manufacturing problems that are not amenable for modelling using traditional methods. Based on an experimental data, the model was tested with satisfactory results. The developed methodology with the model is highly beneficial to manufacturing industries, such as aerospace, automobile and tool making industries.

Applying data mining to manufacturing: the nature and implications

Recent advances in computers and manufacturing techniques have made it easy to collect and store all kinds of data in manufacturing enterprises. The problem of how to enable engineers and managers to understand large amount of data remains. Traditional data analysis methods are no longer the best alternative to be used. Data Mining (DM) approaches have created new intelligent tools for extracting useful information and knowledge automatically. All these will have a profound impact on current practices in manufacturing. In this paper the nature and implications of DM techniques in manufacturing and their implementations on product design and manufacturing are discussed.

Particle Swarm Optimization (PSO) for the constrained portfolio optimization problem

One of the most studied problems in the financial investment expert system is the intractability of portfolios. The non-linear constrained portfolio optimization problem with multi-objective functions cannot be efficiently solved using traditionally approaches. This paper presents a meta-heuristic approach to portfolio optimization problem using Particle Swarm Optimization (PSO) technique. The model is tested on various restricted and unrestricted risky investment portfolios and a comparative study with Genetic Algorithms is implemented. The PSO model demonstrates high computational efficiency in constructing optimal risky portfolios. Preliminary results show that the approach is very promising and achieves results comparable or superior with the state of the art solvers.

Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network

This paper proposes a method for classification of fault and prediction of degradation of components and machines in manufacturing system. The analysis is focused on the vibration signals collected from the sensors mounted on the machines for critical components monitoring. The pre-processed signals were decomposed into several signals containing one approximation and some details using Wavelet Packet Decomposition and, then these signals are transformed to frequency domain using Fast Fourier Transform. The features extracted from frequency domain could be used to train Artificial Neural Network (ANN). Trained ANN could predict the degradation (Remaining Useful Life) and identify the fault of the components and machines. A case study is used to illustrate the proposed method and the result indicates its higher efficiency and effectiveness comparing to traditional methods.

An expert system for engine fault diagnosis: development and application

The mass production and wider use of automobiles and the incorporation of complex electronic technologies all indicate that the control of faults should be given an integral part of engine design and usage. Today, artificial intelligence (AI) technology is widely suggested for systematic diagnosis of faults where the amount of well-defined diagnosis knowledge is vast and the sequence of steps required to identify the fault is very long. This article describes on an expert system application for automotive engines. A new prototype named EXEDS (expert engine diagnosis system) has been developed using KnowledgePro, an expert system development tool, and run on a PC. The purpose of the prototype is to assist auto mechanics in fault diagnosis of engines by providing systematic and step-by-step analysis of failure symptoms and offering maintenance or service advice. The result of this development is expected to introduce a systematic and intelligent method in engine diagnosis and mai ntenance environments.

Adaptive spherical Gaussian kernel in sparse Bayesian learning framework for nonlinear regression

Kernel based machine learning techniques have been widely used to tackle problems of function approximation and regression estimation. Relevance vector machine (RVM) has state of the art performance in sparse regression. As a popular and competent kernel function in machine learning, conventional Gaussian kernel has unified kernel width with each of basis functions, which make impliedly a basic assumption: the response is represented below certain frequency and the noise is represented above such certain frequency. However, in many case, this assumption does not hold. To overcome this limitation, a novel adaptive spherical Gaussian kernel is utilized for nonlinear regression, and the stagewise optimization algorithm for maximizing Bayesian evidence in sparse Bayesian learning framework is proposed for model selection. Extensive empirical study, on two artificial datasets and two real-world benchmark datasets, shows its effectiveness and flexibility of model on representing regression problem with higher levels of sparsity and better performance than classical RVM. The attractive ability of this approach is to automatically choose the right kernel widths locally fitting RVs from the training dataset, which could keep right level smoothing at each scale of signal.

Knowledge based manufacturing system (KBMS)

Production management, in batch type manufacturing environment, is regarded by the current research community as a very complex task. This paper claims that the complexity is a result of the system approach where management performance relies on decisions made at a too early stage in the manufacturing process. Decisions are made and stored in company databases by engineers who are neither economists nor production planner’s experts. This paper presents a new method where engineer’s task is not to make decisions but rather to prepare a knowledge-based “road map”. The road map method does introduce flexibility and dynamics in the manufacturing process and thus simplifies the decision making process in production planning. Each user will generate a routine that meets his/her needs at the time of needs by using KBMS CAPP. Thereby this method increases dramatically manufacturing efficiency.

Using B-spline neural network to extract fuzzy rules for a centrifugal pump monitoring

In mechanical equipment monitoring tasks, fuzzy logic theory has been applied to situations where accurate mathematical models are unavailable or too complex to be established, but there may exist some obscure, subjective and empirical knowledge about the problem under investigation. Such kind of knowledge is usually formalized as a set of fuzzy relationships (rules) on which the entire fuzzy system is based upon. Sometimes, the fuzzy rules provided by human experts are only partial and rarely complete, while a set of system input/output data are available. Under such situations, it is desirable to extract fuzzy relationships from system data and combine human knowledge and experience to form a complete and relevant set of fuzzy rules. This paper describes application of B-spline neural network to monitor centrifugal pumps. A neuro-fuzzy approach has been established for extracting a set of fuzzy relationships from observation data, where B-spline neural network is employed to learn the internal mapping relations from a set of features/conditions of the pump. A general procedure has been setup using the basic structure and learning mechanism of the network and finally, the network performance and results have been discussed.

Incorporating prior model into Gaussian processes regression for WEDM process modeling

Sufficient sampling is usually time-consuming and expensive but also is indispensable for supporting high precise data-driven modeling of wire-cut electrical discharge machining (WEDM) process. Considering the natural way to describe the behavior of a WEDM process by IF-THEN rules drawn from the field experts, engineering knowledge and experimental work, in this paper, the fuzzy logic model is chosen as prior knowledge to leverage the predictive performance. Focusing on the fusion between rough fuzzy system and very scarce noisy samples, a simple but effective re-sampling algorithm based on piecewise relational transfer interpolation is presented and it is integrated with Gaussian processes regression (GPR) for WEDM process modeling. First, by using re-sampling algorithm encoded derivative regularization, the prior model is translated into a pseudo training dataset, and then the dataset is trained by the Gaussian processes. An empirical study on two benchmark datasets intuitively demonstrates the feasibility and effectiveness of this approach. Experiments on high-speed WEDM (DK7725B) are conducted for validation of nonlinear relationship between the design variables (i.e., workpiece thickness, peak current, on-time and off-time) and the responses (i.e., material removal rate and surface roughness). The experimental result shows that combining very rough fuzzy prior model with training examples still significantly improves the predictive performance of WEDM process modeling, even with very limited training dataset. That is, given the generalized prior model, the samples needed by GPR model could be reduced greatly meanwhile keeping precise.

An integrated intelligent process planning system (IIPPS) for machining

A key component of computer integrated manufacturing (CIM) is computer aided process planning (CAPP). Process planning in machining involves the determination of the cutting operations and sequences, the selection of machine tools and cutting tools, the calculation of machining parameters, and the generation of CNC part programs. Industrial structures in Norway are defined as small and medium-sized companies. The important fact is how well these companies use high technologies and resources in order to improve their production efficiency, product quality, and company competition in international markets. The concept of an integrated intelligent system (IIS) is created for this purpose. A prototype system, the integrated intelligent process planning system (IIPPS), is described for machining; it was developed on the basis of an IIS and constructed using three levels of effort: (1) AutoCAD, (2) dBASE III and (3) KnowledgePro. The system may be utilized not only by a process plann ing engineer in a company, but also by students of mechanical or industrial engineering.