Search

Aircraft structural parts are important and high-value parts used to constitute the frame of the aircraft, and are usually produced by NC machining, where the machining parameters are significant for the machining quality, efficiency, and cost. In the process planning, there are hundreds or even thousands of machining operations that require separate machining parameters, which is a huge task for the existing optimization-based methods that rely on iterative optimizations. Due to the complex structures and high requirements, the existing expert system-based methods require plenty of additional modifications. Recently, with the development of artificial intelligence, data-driven methods are used in machining parameter planning, which mines the knowledge and rules hidden in the historical data. However, the existing data-driven models require a large amount of training data and lack interpretability. To address this issue, this paper proposes an informed machine learning method for machining parameter planning, which introduces multiple prior constraints into the data-driven model. First, the part model is represented as an attribute graph, and the cutting area of each machining operation is correlated to a subgraph, which is used to obtain the vectorized representation of machining operation that covers cutting area and process information. Then, by fitting the mapping between the vectorized machining operation and the machining parameters, the knowledge and rules are learned. Next, to introduce prior constraints into the data-driven model, the constraint loss is designed and incorporated into the original loss function. The proposed method can generate machining parameters for all the machining operations in batch, thereby greatly reducing the human interactions. In the case study, the historical processing files of aircraft structural parts are used to train the proposed model for planning cutting width, cutting depth, spindle speed, and machining feedrate. The results show that the demand for training data is reduced and the prediction accuracy is improved with prior constraints.

As main welded components of the rail vehicle, the railcar frames have specific needs in preparing a suitable welding document for each welded joint to guide the welding process during the manufacturing process. In this paper, the expert system and database technology are introduced into the field of rail vehicle welding process preparation, and a knowledge-based software for railcar frame welding process is developed. This system could maintain the normal operation of the enterprise rail welding system based on knowledge base and database. The numerous paper-based and fragmented electronic documents are stored in a unified format within the system’s database, and a reasoning mechanism based on Rule-Based Reasoning (RBR) and Case-Based Reasoning (CBR) is designed to intelligently match the welding procedure specification (WPS) and welding procedure qualification report (WPQR) online. Furthermore, the system supports multiple departments and personnel by integrating the function of workflow to carry out the WPS prepare and review process. Thousands of welded joints with various structures and complex positions in the same vehicle body can be aggregated into a welding summary table to reduce the repeated welding procedure qualifications (WPQ) of the same or similar welding joint. This method not only saves manpower and resources, but also ensures the accuracy of these process documents. In the end, the future development trend of this kind of application software is prospected.

This paper explores the use of discrete event simulation (DES) for decision making in real time based on the potential for data streamed from production line sensors. Technological innovations for data collection and an increasingly competitive global market have led to an increase in the application of discrete event simulation by manufacturing companies in recent years. Scenario analysis and optimisation methods are often applied to these simulation models to improve objectives such as cost, profit and throughput. The literature review has identified key research gaps as the lack of example cases where multi-objective optimisation methods have been applied to simulation models and the need for a framework to visualise the relationship between inputs and outputs of simulation models. A framework is presented to enable the optimisation DES simulation models and optimise multiple objectives simultaneously using design of experiments and meta-models to create a Pareto front of solutions. The results show that the resource allocation meta-model provides acceptable prediction accuracy whilst the lead time meta-model was not able to provide accurate prediction. Regression trees have been proposed to assist stakeholders with understanding the relationships between input and output variables. The framework uses regression and classification trees with overlaid values for multiple objectives and random forests to improve prediction accuracy for new points. A real-life test case involving a turbine assembly process is presented to illustrate the use and validity of the framework. The generated regression tree expressed a general trend by demonstrating relationships between input variables and two conflicting objectives. Random forests were implemented for creating higher accuracy predictions and they produced a mean square error of ~ 0.066 on the training data and ~ 0.081 on test data.

Injection molding is widely used for mass production of thermoplastic parts with complex geometry and tight dimensional tolerance. However, due to the unavoidable shrinkage and uncontrollable process condition variations, defective parts may occur. Thus, dimensional control and online defect detection are extremely important for quality control, particularly for high precision injection molding. The conventional monitoring and control are based on machine setting parameters, but it may not capture the molding condition variations under the unchanged machine settings. This paper develops an artificial neural network (ANN)-based online defect detection system with the real-time data extracted from in-mold temperature and pressure sensors. Both multilinear linear regression (MLR) and ANN models were developed based on the real-time data, but the ANN model is much better than the MLR model. The ANN model has a high prediction accuracy of 98.34% with the coefficient of determination R2 of 91.37%. When applied to defect detection, the ANN model has a defect detection accuracy of 94.4% in consideration of type I and type II errors. This research demonstrates the feasibility of integrating such an ANN-based expert system to injection molding process, to improve online dimensional monitoring. The ANN model also can be easily adapted for detecting other quality characteristics of injection moldings, which would be helpful for the advances in intelligent injection molding.

Rolling element bearing is a critical component of various rotating machineries. As the demand of reliability of machinery gradually increases, the accurate diagnosis of bearing degradation becomes increasingly important to ensure safe production and reduce operation cost. With more knowledge and data of the bearing degradation accumulated, vibration data of bearings with different fault patterns and indicators are obtained. A diagnosis model with self-learning capability helps the model to understand various features in different degradation stages of bearings. Hence, the model provides more accurate diagnosis information of the current conditions of bearings. In this paper, a tight Gaussian mixture clustering unsupervised learning algorithm is implemented with the assistance of an optimized complementary ensemble empirical mode decomposition (CEEMD) to diagnose the damage severity of rolling element bearings. The obtained information is used for characterizing the severity of damage existed within the machine and facilitating the decision-making of machinery maintenance. The experimental vibrational signals of rolling element bearings are decomposed using the improved CEEMD. After obtaining the critical intrinsic mode function from the CEEMD, the features are calculated, and a tight clustering algorithm is implemented to categorize the bearing degradation stage. The tight clustering algorithm overcomes the incapability of traditional clustering algorithm in distinguish scattered features. A more stable categorization is generated by using the proposed algorithm. Less quantity and more accurate training data are used to improve training efficiency. The proposed model can be implemented in expert systems to distinguish different degradation stages with a self-learning capability.

This paper presents the PullWorks software, an expert system that has been developed for the fast and simple design with the aim of optimizing the multi-stage copper wire drawing process. This software has been implemented applying the analytical method and complemented with the results of a series of experimental tests for the correct characterization of the processed material. The expert software system created has been used to model a real drawing line (Cunext Copper Industries S.L., Cordoba, Spain), with a production capacity of more than 30,000 t/year and an installed capacity of 1700 kW. PullWorks has made it possible to propose two modifications in the industrial process reducing its energy consumption by at least 1260 MWh/year: thanks to a reduction in the number of stages in the process lines (from 8 to 5, in the roughing line; from 19 to 13 in finishing) and by the elimination of the annealing treatment between them. The validity of these results has been verified through of the corresponding simulations made by the software Deform2D by means of which the numerical method of the finite elements analysis has been applied, and the solution was partially checked in the industrial process in operation.

Measurements are the core of quality systems. The calibration of the measurement devices is a form of evaluating it. The variability of these measurement devices is verified to know the variation inherited in the measurement tool. Additionally, the dynamics of the actual production systems cannot be satisfied by the classic approaches of the human visual inspection. This happens because they exceed the human capacities, and this phenomenon causes the loss of reliability at the outputs of the system. This paper presents a hybrid model of adaptive neuro-fuzzy inference system (ANFIS) to evaluate quality features. Also, for this purpose, it offers knowledge-based expert system able to do the quality assurance tasks by learning and adaptation. The obtained results provide an acceptable error rate for this class of systems to run at the speed of the actual manufacturing system.

Fault diagnosis is an important step for software-intensive manufacturing system and process. But because of the increased scale and complexity, as well as the uncertain condition of the running environment, embedded software fault diagnosis is still an open challenge for industry application. In this research, an optimized hybrid model is proposed by integrating a case-based reasoning (CBR) method and a BN-based diagnosis method. Initially, a FMEA-style case-based reasoning (F-CBR) method is proposed by collecting and formalizing the existed fault cases for the low-level similarity searching guided diagnosis. Then, by adopting a new designed algorithm, F-CBR can be further transferred to a deep-level Bayesian diagnosis network for the dynamic multi-fault diagnosis with uncertainty. Based on this framework, we implement a prototype of hybrid expert system for the diagnosis of embedded software by integrating CBR with Bayesian network (BN) through F-CBR by the corresponding failure spectra as the bridge. The feasibility and benefits of this hybrid diagnosis strategy are verified by examples and case studies in real industry applications with great promising results for different kinds of multi-level diagnosis.

An intelligent welding procedure qualification system has been developed in the current study. In this system, the welding procedure of Q345R is intelligently designed based on GBT25343.3-2010 welding standard. By setting the initial welding parameters including welding methods, base metal, and thickness, the welding procedure results will be launched after four steps reasoning of inference engine. To predict the mechanical properties and complete the welding procedure qualification, these initial welding procedure parameters are taken as the input values by artificial neural networks (ANN). Since the hyperbolic tangent function (tanh) is used in ANN, it performs well in dealing with nonlinear problem and controlling the prediction errors accuracy. To reasonably judge the qualification of the Welding Procedure Specifications, the mechanical properties as the output values are compared with the experimental results. Therefore, the ANN are imported to the expert system to control welding procedure design. Furthermore, the mutually beneficial relationship between them has been established. Artificial neural network provides a new approach to resolve the class of experience knowledge for the expert system. In turn, the expert system with a powerful knowledge base and dynamic database provides a lot of training samples for artificial neural networks.

The paper presents an idea of an expert system for determining the quantitative contributions of four principal mechanisms (abrasive wear, thermo-mechanical fatigue, plastic deformation, and mechanical fatigue) to the degradation of forging tools and the geometric die impression loss for a selected industrial hot forging process. The knowledge needed to solve the problem is encoded in a system knowledge base in the form of rules. The knowledge base contains elements of both theoretical knowledge about destructive phenomena and empirical knowledge gained from the experience of the authors and industry experts (forge employees) as well as from a statistical analysis of measurement data for selected forging process parameters. The knowledge is processed through automatic inference based on fuzzy logic rules.

Automating the development of construction schedules has been an interesting topic for researchers around the world for almost three decades. Researchers have approached solving scheduling problems with different tools and techniques. Whenever a new artificial intelligence or op- timization tool has been introduced, researchers in the con- struction field have tried to use it to find the answer to one of their key problems—the "better" construction schedule. Each researcher defines this "better" slightly different. This article reviews the research on automation in construction scheduling from 1985 to 2014. It also covers the topic using different approaches, including case-based reasoning, knowledge-based approaches, model-based approaches, ge- netic algorithms, expert systems, neural networks, and other methods. The synthesis of the results highlights the share of the aforementioned methods in tackling the scheduling chal- lenge, with genetic algorithms shown to be the most dominant approach. Although the synthesis reveals the high applicabil- ity of genetic algorithmstothe different aspects ofmanaginga project, including schedule, cost, and quality, it exposed a more limited project management application for the other methods.

This paper presents a review on soft computing- based expert systems developed to establish input-output re- lationships of various manufacturing processes. To determine these relationships, both fuzzy logic- and neural network- based approaches were tried. Reasonably good results were obtained using the developed approaches. However, there is a chance of further improvement of the results. The scopes for future study have also been discussed.

This paper describes a particle expert system (PES) that was developed to improve particle classification for burrs, casts, and chips in the automotive production process. Image-processing techniques were deployed to extract particle information and remove noise from industrial filters and lighting systems. An advanced model of a particle classification algorithm (PCA) was built with 12 particle classes and a particle-expert-system (PES) algorithm was developed to train the PCA parameters to achieve the target success rate. The particle expert system will help the user locate the source of particles with high reliability and a stable success rate immediately after image processing and training the PCA parameters.

In process planning of wire electrical discharge machining (WEDM), determination of appropriate machining conditions is likely to face problems in many ways. In addition to the construction of the relationship between machining parameters and machining characteristics, optimization search technique, a large number of experiments must be conducted repeatedly to renew parameters for different workpiece materials. The concept of specific discharge energy (SDE) was employed in this paper to represent the WEDM property of workpiece materials as one of the machining parameters. Two kinds of materials with distinctive SDE values, i.e., higher and lower, respectively, were selected for our experiments. The experimental data obtained were used, and a neural network that can accurately predict the relationship between machining parameters and machining characteristics was constructed. It was found that the predicted error was less than 7 %. The optimization technique of genetic algorithms was employed, and the optimal combination of machining parameters that meet the required machining characteristics for different workpiece materials was obtained. The system proposed in this study is both user-friendly and practical. It can save considerable time and cost during the construction of the database for the expert system of process planning.

The present work introduces an expert system that automatically selects and designs rolling sequences for the production of square and round wires. The design strategy is aimed at reducing the overall number of passes assuming a series of process constraints, e.g., available roll cage power and torque, rolls groove filling behaviors, etc. The method is carried out into two steps: first a genetic algorithm is used to select the proper rolling sequence allowing to achieve a desired finished product; then, an optimization roll pass design tool is utilized for proper design of roll passes. Indeed, an artificial neural network (ANN) is utilized to predict the main geometrical characteristics of the rolled semi-finished product and technological requirements. The ANN was trained with a non-linear finite element (FE) model. The proposed methodology was applied to some industrial cases to show the validity of the proposed approach in terms of reduction of number of passes and search robustness.

We propose a cost estimation model based on a fuzzy rule backpropagation network, configuring the rules to estimate the cost under uncertainty. A multiple linear regression analysis is applied to analyze the rules and identify the effective rules for cost estimation. Then, using a dynamic programming approach, we determine the optimal path of the manufacturing network. Finally, an application of this model is illustrated through a numerical example showing the effectiveness of the proposed model for solving the cost estimation problem under uncertainty.

Here, an approach for finding an optimal path in a flexible jobshop manufacturing system considering two criteria of time and cost is proposed. A network is configured in which the nodes are considered to be the shops with arcs representing the paths among the shops. An automated guided vehicle functions as a material handling device through the manufacturing network. To account for uncertainty, time is considered to be a triangular fuzzy number and apply an expert system to infer the cost. The expert system based on fuzzy rule backpropagation network to configure the rules for estimating the cost under uncertainty is proposed. A multiple linear regression model is applied to analyze the rules and find the effective rules for cost estimation. The objective is to find a path minimizing an aggregate weighted unscaled time and cost criteria. A fuzzy dynamic programming approach is presented for computing a shortest path in the network. Then, a comprehensive economic and reliability analysis is worked out on the obtained paths to find the optimal producer’s behavior. Finally, an application of the model is illustrated by a numerical example. The results show the effectiveness of our approach for finding an optimal path in a manufacturing system under uncertainty.

This paper focuses on the design and development of an expert system for on-line detection of various control chart patterns so as to enable the quality control practitioners to initiate prompt corrective actions for an out-of-control manufacturing process. Using this expert system developed in Visual BASIC 6, all the nine most commonly observed control chart patterns, e.g., normal, stratification, systematic, increasing trend, decreasing trend, upward shift, downward shift, cyclic, and mixture can be recognized well, employing an optimal set of seven shape features. Based on an observation window of 32 data points, it can plot the control chart, compute the control limits, identify the control chart pattern, calculate the process capability index, determine the maximum run length, and identify the starting point of the maximum run length. After pattern recognition, it can also inform the users about various root assignable causes associated with a particular pattern along with the necessary pre-emptive actions. It opens up wide opportunities for quality improvement and real-time applications in diverse manufacturing processes. This developed expert system is built for a vertical drilling process and its recognition performance is tested using simulated process data.

Material selection is one of the main phases of product design process that has great impact on the manufacturing of sustainable products. One of the best approaches of material selection for sustainable products is life cycle engineering (LCE). But LCE is a costly and cumbersome task and it is not economic to perform this task for a large number of proposed materials in order to choose the most suitable one for a sustainable product. Instead, it is more reasonable to make a preliminary filtering on the proposed materials and obtain a shorter list of candidate materials and then perform LCE on alternatives which are obtained from preliminary filtering. Since environmental friendliness of materials is a critical sustainability issue, so it is a good criterion for preliminary filtering of alternatives. In this paper, a new methodology is proposed to support preliminary filtering of alternatives from environmental viewpoint. The methodology uses the knowledge of experts in the field of eco-design. The knowledge is translated to decision making rules and a decision tree is developed to guide the choice. In order to use the capabilities of frame-based systems, an object-oriented approach for representation of knowledge is also proposed. Moreover, a prototype hybrid expert system based on the proposed methodology called material selection expert system for sustainable product design is developed to support the task of preliminary filtering. Finally, a case study from tire manufacturing industries is presented to show the validity of the proposed system. The results show that the system can determine the appropriate candidate materials and hence improve the possibility of manufacturing of more sustainable products. Eliminating alternatives that do not have the necessary conditions for sustainable product leads to a large saving in time and cost of the LCE evaluation process

One of the important steps in the process of project planning is the designing of logical precedence network. As the procedure of the logical precedence network planning is case dependent and varies in different projects, it could be considered as an unstructured and complex problem which should be solved by implementing the implicit domain knowledge of the planner. In this paper, we have shown how the artificial neural networks could be implemented to plan the finish-to-start logical precedence network of projects. The implementation results depict that the proposed methodology could result reasonable, accurate, and reliable outcomes, which could be used as a primary solution, which can enrich the acquired knowledge, after the accomplishment of the project and its practical corrections.

In the present paper, neural network-based expert systems have been developed for online predictions of temperature distributions on electron beam-welded plates. Finite element method is a popular tool to carry out this analysis. However, this analysis could be time consuming, and the obtained results might be dependent on a number of mesh parameters, namely shaping ratio, number of element divisions, and others. Thus, an expert system might be necessary for making online predictions of temperature distributions in welding after considering the said uncertainties. Neural network-based expert systems have been developed using the data collected through finite element analysis, and their performances are compared on some test cases. Once trained, the neural network-based expert systems could make the predictions in a fraction of a second.

In the present paper, the problem of increased effectiveness in manufacturing when using diamond abrasive tools is addressed. For this reason, a three-dimensional (3D) methodology is proposed. The aforementioned methodology consists of several parts containing 3D simulation that covers all the basic stages of the life cycle of the tools, from the sintering of diamond composite materials, grinding, and dressing of grinding wheels, to sharpening of single point tools and machining. Furthermore, the creation of expert systems for assignment of rational characteristics of diamond wheels and grinding modes is investigated. The results of these investigations allow reducing the volume of experimental work, offering optimum grinding conditions and allowing the development of new technologies, tools, and equipment.

The presence of a number of available non-traditional machining (NTM) processes has brought out the idea of selecting the most suitable NTM process for generating a desired shape feature on a given work material. This paper presents a digraph-based approach to ease out the appropriate NTM process selection problem. It includes the design and development of an expert system that can automate this decision-making process with the help of graphical user interface and visual aids. The proposed approach employs the use of pair-wise comparison matrices to calculate the relative importance of different attributes affecting the NTM process selection decision. Based on the characteristics and capabilities of the available NTM processes to machine the required shape feature on a given work material, the permanent values of the matrices related to those processes are computed. Finally, if some of the NTM processes satisfy a certain threshold value, those are shortlisted as the acceptable processes for the given shape feature and work material combination. The digraph-based expert system not only segregates the accepted NTM processes from the list of the available processes but also ranks them in decreasing order of preference. It also helps the user as a responsible guide to select the most suitable NTM process by incorporating all the possible error trapping mechanisms. This paper takes into account some new work materials, shape features and NTM processes that have not been considered by the earlier researchers. It is further observed that the developed expert system is quite flexible and versatile as the results of the cited examples totally corroborate with those obtained by the past researchers.

Defects in castings often lead to rejection, which would ultimately result in loss of productivity for a foundry. Expert systems developed by some researchers mostly act as postmortem tools, discussing and analyzing a defect after it has occurred. Though some investigators have attempted to predict a few important defects, a tool that could predict all the possible defects just before the castings are made has not yet been developed. Hence in the present work, an attempt has been made to predict major casting defects like cracks, misruns, scabs, blowholes and air-locks using back-propagation neural networks from the data collected from a steel foundry. The neural network was trained with parameters like green compression strength (GCS), green shear strength (GSS), permeability, moisture percent, composition of the charge and melting conditions as inputs and the presence/absence of defects as outputs. After the training was over, the set of inputs of the casting that is going to be made was fed to the network and the network could predict whether the casting would be sound or defective. If defective, the nature of the defect was also specified by the neural network. The neural network could predict cracks, misruns and air-locks accurately in most of the cases. The neural network could also predict other defects successfully. Investigating the causes followed by altering the moulding parameters and appropriate treatment of the molten metal can prevent the defects that were predicted by the backpropagation neural network.

As flexibility and agility become key success factors of a competitive manufacturing enterprise, the ability to support the short term decision making of manufacturing planning, scheduling, and dispatching becomes a critical issue. This research presents a rule-based knowledge system run on the Java Expert System Shell (JESS) platform to addresses how engineering knowledge can be dynamically represented and efficiently utilized in job dispatching. The knowledge system, called Intelligent Dispatching Decision Support System (IDDSS), is designed and implemented using the rule-based inference and reasoning approach. The distinctive technical contributions of IDDSS focus on three critically integrated elements: (1) a visualized rule editor, (2) a knowledge object data gateway, and (3) an embedded application component. Furthermore, a case study of the thin-film transistor liquid-crystal display (TFT-LCD) panel repair line is applied to demonstrate the rule-based knowledge system for agile TFT-LCD repair job dispatching.

This paper describes the development of an expert system for both process planning and die design of sheet metal cutting and piercing operations. Knowledge for the system is acquired from practical handbooks, theory and empirical knowledge from industrial partners and is expressed as “crude” rules, transformed by the knowledge engineer into production rules. These are then coded into constructs of the CLIPS expert system development environment. This process is explained using a number of examples. The expert system comprises of five modules: initial calculations (including data input), process planning, finishing operation, die and press selection, and tools selection. Each module draws upon one or more among 18 rule pools defined around the important notions characterising the problem studied. The results of the expert system can be used by both the designer deciding on the production feasibility (manufacturability) for a sheet metal component and by the manufacturer receiving advice either on the hardware needed or on the process plan.

The current paper intends to use the typical problems of parameter selection and optimization in machining processes to bring out the design ideas that form the foundation of n-tier management information systems (MIS). These ideas can be used for creating data-driven, scalable enterprise information systems. The current phase (phase I) of the implementation highlights the capabilities of these design ideas in improving three key functional parameters of MIS, i.e. multi-dimensionality, isolation and scalability. The problem area of machining process characteristics of non traditional machining has been chosen with two specific goals in mind: A typical machining process has multiple parameters and various corresponding relationships can be found among such parameters. This will be used to highlight the degree of multi-dimensionality that can be achieved from a simple design pattern. The phase II of this paper can actually shift focus from the design of a generic management information system to a specific problem area of machining. This incorporates the features of an expert system in providing the customer or end user with maximum encapsulation of technical data and much improved decision-making capabilities within the system. Some complex machining processes such as abrasive water jet machining (AWJM), wire electrical discharge machining (WEDM) and electro discharge machining (EDM) are characterized by a large number of parameters which are not available in a structured fashion, thus, all the data associated with AWJM, WEDM and EDM systems has been conglomerated and presented in a normalized fashion. The essential features of the current research include the extraction of the relevant data from a large pool of data, with a distinct architecture of MIS, having three scalable layers. The normalization of the available data has been dealt with management information system and presented in the form of a software named “machining expert”. The code for the software provided is easy to understand, being written in Visual Basic and Access server for implementation. The developed “machining expert” for handling non traditional machining (NTM) data can also be extended with suitable design extensions to handle business logic by interacting with the end user. The current paper is applicable to any research on the structure and design of MIS in manufacturing technology.

Various research studies have concluded that most new design projects are actually re-design activities. This re-design may be for improvement or for reprovision of existing products. Most research efforts for providing computer tools for supporting conceptual or early design mainly concentrated on the design of new products. In practice manufacturing plans generated when an order was placed may quickly become out-dated as the manufacturing environment and constraints often change. It is therefore equally important to regenerate manufacturing plans and re-evaluate design every time a product is changed, re-designed or reordered. This project focuses on manufacturability analysis and provides re-design support for conceptual design of discrete single-piece mechanical parts with emphasis on machined processes. This limitation of implementing the prototype system for re-design activities is not a system design or methodology restriction. The condition has been imposed by the authors as a prelude to validating the system and its results. A novel hybrid approach using a combination of sequential flowchart logic and an expert system has been developed which uses a user-defined feature tree as the input for its analysis. The system allows the designer to estimate manufacturability according to criteria of time and cost, and also to explore different scenarios of parametric variation in the design. A case study has been presented to validate the system’s practicality and usefulness.

The selection of a non-traditional machining (NTM) process is often observed to be a multi-criteria decision-making problem with conflicting and diverse objectives. This paper presents a systematic methodology for selecting the best or optimal non-traditional machining process under constrained material and machining conditions. The paper also includes the design of an analytic-hierarchy-process-based expert system with a graphical user interface to ease the decision-making process. The developed expert system relies on the priority values for different criteria and sub-criteria, as related to a specific non-traditional machining process selection problem. It also depends on the logic table to discover the non-traditional machining processes that lie in the acceptability zone, and then selects the optimal process having the highest acceptability index value. The proposed expert system can automate the selection of a non-traditional machining process and provide artificial intelligence in the multi-criteria decision-making process.

It is widely accepted that stamping process planning for the strip layout is a key task in progressive die design. However, stamping process planning is more of an art rather than a science. This is in spite of recent advances in the field of artificial intelligence, which have achieved a lot of success in incorporating built-in intelligence and applying diverse knowledge to solving this kind of problem. The main difficulty is that existing knowledge-based expert systems for stamping process planning lack a proper architecture for organizing heterogeneous knowledge sources (KSs) in a cooperative decision making environment. This paper presents a knowledge-based blackboard framework for stamping process planning. The proposed approach speeds up the progressive die design process by automating the strip layout design. An example is included to show the effectiveness of the proposed approach.

The paper presents a binary relational analysis and expert system base module for maintenance and fault diagnosis of CNC wire EDM. The module proposes a framework of integrated maintenance and fault diagnosis system. The study explores the binary coded matrix system, which plays an important role in prediction and diagnosis of wire electrical discharge machining (WEDM) faults on the spot by expert guidance. In this study, 15 inputs were considered to observe eight probable causes with the help of the forward and backward propagation algorithms. Inputs and output matrices were considered in the form of a square matrix. To explain the fault diagnosis and to realize the importance of maintenance through advice, the detection of faults is investigated through forward and back propagation of matrix transformation on the spot. It is an integrated backup that can be individually focused when input and output parameter do not match. It is a time saving, knowledge acquisition, easy to maintain, and capable of self-learning system. To verify the developed framework, 120 data sets were generated for proper analyzing of acquired output through graphical representation. The paper also presents some of the important features of maintenance schedule and probable causes of wire breakage with remedial actions in tabular form. The developed system can help the operators, trainees, and manufacturing engineers in achieving trouble free machining through quick detection of faults and proper maintenance of machines in actual practice.

This paper deals with an automated computer-aided process planning and die design system by which the designer can determine operation sequences even if they have little experience in process planning and die design for axisymmetric products. An attempt is made to link programs incorporating a number of expert design rules with the process variables obtained by commercial FEM softwares, DEFORM and ANSYS, to form a useful package. The system is composed of four main modules. The process planning and the die design modules consider several factors, such as the complexities of preform geometry, punch and die profiles, specifications of available multi-former, and the availability of standard parts. They can provide a flexible process based on either the reduction in the number of forming sequences by combining the possible two processes in sequence, or the reduction of deviation of the distribution on the level of the required forming loads by controlling the forming ratios. In the die design module optimal design technique and the horizontal split of the die insert were investigated for determining appropriate dimensions of components of the multi-former die set. It is suggested that the proposed method can be beneficial for improving the tool life of the die set in practice.

The exponential growth of the electronics packaging industry has fueled the availability of a variety of area array packages. The reliability of these packages, as characterized by their capacity to withstand the IPC- (formerly Institute of Interconnecting and Packaging Electronic Circuits) prescribed swings in temperature, differentiates one from the other. With design cycles shrinking and competition surging, the capability to make instant package selection decisions by leveraging prior empirical data could pose as a potential alternative for exhaustive experimentation. By employing expert systems techniques, this research developed suitable models that accurately depict field conditions in order to assist in delineating trends in package reliability data.

This article utilises a scheme to solve both equal and unequal area department problems in facilities layout by using genetic algorithms (GAs) for achieving the minimal total layout cost (TLC). With regards the equal area department problems, the objective function is mainly developed according to the measurement of the material flow factor cost (MFFC). However, the objective function for unequal area department problems in this study is a multiple objective function involving MFFC, shape ratio factor, and area utilisation factor to reach minimal TLC. In addition, a rule-based expert system is implemented to create space-filling curves for connecting each unequal area department to be continuously placed without discontinuity (partition). There is no gap between each unequal area department. The experimental results show that the proposed approach achieves lower TLC compared with existing algorithms. Under the practical limitations, the proposed approach in this study is much more feasible for dealing with the facilities layout problems in the real world.

An efficient expert system for machine fault diagnosis is developed. A new search method is proposed in this system to improve the efficiency of the diagnostic process. First of all, a diagnostic tree (a decision tree) is built by domain experts according to the functions of the devices in the machine. Then, the diagnostic priorities of nodes (devices) in the tree are determined based on a fuzzy group multiple attribute decision making method. A meta knowledge base for fault diagnosis is generated automatically based on the determined priorities to guide the diagnostic process. After that, a domain knowledge base that hypothesises possible faults for each device in the tree is generated by domain experts and/or manuals. At last, the inference process starts based on the meta knowledge base and hypothesises which device is the possible cause of failure. To validate the system performance, an illustrative example (VCR troubleshooting) is presented for demonstration purposes.

An optimisation cycle is a part of the development process for every new product. It has a very important role in today's high-tech technology, where only optimal solutions can succeed in the market. If the structure does not satisfy given criteria, certain optimisation steps, such as redesign, use of other material, etc., have to be taken. A decision about what should be done depends directly on the correct interpretation of the results of the engineering analysis. A lot of knowledge and experience is needed to properly understand the results of the analysis and consequently to chose the appropriate measures, yet, the existing software for computer-aided analyses still does not provide adequate tools for a proper interpretation and evaluation of the results. In the paper, we present our vision of a knowledge-based system for more intelligent post-processing as a part of the optimisation cycle leading to optimal solutions more efficiently.

To remain a competitive force in the world market, manufacturing enterprises must design and produce new products in an effective way. To reduce the product launching time, manufacturing enterprises must be versatile, open to changes, and capable of designing and modifying their own facilities and processes efficiently for the design of new products. In this context, the concept of autonomous, adaptive, cognitive and cooperating entities known as holons is conceived which leads to the evolution of a holonic manufacturing system (HMS) where highly distributed control paradigms are adopted to alleviate the problems related to frequent process disturbances. In order to streamline the functioning of an HMS, it is necessary to form an efficient, flexible and responsive network of agents, which are intra-holonic entities that inherit the same characteristics as the holons. This network of agents can be termed an autonomous agent network. The agent is formed by the parties, which are the functional units of the holonic manufacturing system. The aim of this paper is to specify the communication protocols and subsequently synthesise and cluster the individual parties into autonomous agents in accordance with the basic constraints of a holonic manufacturing system. Here a fuzzy c-means clustering algorithm is proposed to club the parties to capture effectively the uncertainty and imprecision associated with them. Besides the grouping of the parties to form agents, the proposed fuzzy-based clustering algorithm ensures that the agents formed are more amenable to the dynamic environment prevailing on the shop floor of present day automated manufacturing systems and thus makes the essence of a holonic manufacturing system successful. Keeping in mind the imprecision, uncertainty, and conflicting nature of objectives, the proposed approach aptly models the problem, and its applicability is exemplified by a test problem.