Search results

The use of AI for operations management, with its ability to evolve solutions, handle uncertainty and perform optimisation continues to be a major field of research. The growing body of publications over the last two decades means that it can be difficult to keep track of what has been done previously, what has worked, and what really needs to be addressed. Hence, the purpose of this paper is to present a survey of the use of AI in operations management aimed at presenting the key research themes, trends and directions of research.

The paper builds upon our previous survey of this field which was carried out for the ten‐year period 1995‐2004. Like the previous survey, it uses Elsevier's Science Direct database as a source. The framework and methodology adopted for the survey is kept as similar as possible to enable continuity and comparison of trends. Thus, the application categories adopted are: design; scheduling; process planning and control; and quality, maintenance and fault diagnosis. Research on utilising neural networks, case‐based reasoning (CBR), fuzzy logic (FL), knowledge‐Based systems (KBS), data mining, and hybrid AI in the four application areas are identified.

The survey categorises over 1,400 papers, identifying the uses of AI in the four categories of operations management and concludes with an analysis of the trends, gaps and directions for future research. The findings include: the trends for design and scheduling show a dramatic increase in the use of genetic algorithms since 2003 that reflect recognition of their success in these areas; there is a significant decline in research on use of KBS, reflecting their transition into practice; there is an increasing trend in the use of FL in quality, maintenance and fault diagnosis; and there are surprising gaps in the use of CBR and hybrid methods in operations management that offer opportunities for future research.

This is the largest and most comprehensive study to classify research on the use of AI in operations management to date. The survey and trends identified provide a useful reference point and directions for future research.

Many supply contracts are employed in practice to improve the performance of supply chains. But there is a lack of research that can offer guidance to practitioners in choosing the best supply contract among a group of popular contracts. This paper aims to fill this gap by developing an intelligent rule‐based supply contract design system for choosing the best contract and its parameters from a supplier's point of view.

The approach used in this paper is based on the comparison of several supply contracts that are encountered in supply chain practice. The paper aims at identifying the conditions under which one supply contract outperforms another from the supplier's perspective. To facilitate the implementation of the decision‐making rules that are developed in this research, an intelligent decision support system is developed.

Six popular contracts are analysed; returns policy (RP), quantity discount (QD), target rebate (TR), backup agreement (BA), quantity flexibility (QF), and quantity commitment (QC). The main findings are: QD contracts generate larger expected profits for the supplier than TR contracts do when the demand is exogenous, an RP contract is better than a QD contract when the wholesale profit margin is sufficiently large and that the optimal QC contract always provides a higher expected service level than BA and QF contracts.

The paper presents an approach for developing an intelligent supply contract design system that can offer guidance to practitioners in choosing the best supply contract for a particular supplier.

Global competition and rapidly changing customer requirements are demanding increasing changes in manufacturing environments. Enterprises are required to constantly redesign their products and continuously reconfigure their manufacturing systems. Traditional approaches to manufacturing systems do not fully satisfy this new situation. Many authors have proposed that artificial intelligence (AI) will bring the flexibility and efficiency needed by manufacturing systems. This paper is a review of AI techniques used in manufacturing systems. The paper first defines the components of a simplified intelligent manufacturing systems (IMS), the different AI techniques to be considered and then shows how these AI techniques are used for the components of IMS.

Develops practical models for preventive maintenance policies using Bayesian methods of statistical inference. Considers the analysis of a delayed renewal process and a delayed alternating renewal process with exponential times to failure. This approach has the advantage of generating predictive distributions for numbers of failures and downtimes rather than relying on estimated renewal functions. Demonstrates the superiority of this approach in analysing situations with non‐linear cost functions, which arise in reality, by means of an example.

The purpose of this paper is to introduce a method for modelling the multi-state repairable systems subject to stochastic degradation processes by using the coloured stochastic Petri nets (CSPN). The method is a compact and flexible Petri nets model for multi-state repairable systems and offers an alternative to the combinatory of Markov graphs.

The method is grounded on specific theorems used to design an algorithm for systematic construction of multi-state repairable systems models, whatever is their size.

Stop and constraint functions were derived from these theorems and allow to considering k-out-of-n structure systems and to identifying the minimal cut sets, useful to monitoring the states evolution of the system.

The properties of this model will be studied, and new investigations will help to demonstrate the feasibility of the approach in real world, and more complex structure will be considered.

The simulation models based on CSPN can be used as a tool by maintenance decision makers, for prediction of the effectiveness of maintenance strategies.

The proposed approach and model provide an efficient tool for advanced investigations on the development and implementation of maintenance policies and strategies in real life.

In this paper, the authors are concerned with a maintenance workshop (MW) centralizing all corrective maintenance activities. The purpose of this paper is to propose a methodology for designing a central maintenance workshop, enabling the evaluation of performance in terms of cost and sojourn time, for a given budget.

The authors propose a modeling framework based on queuing networks. The aim is to maximize operational availability of the production workshop, by reducing the sojourn time of failed equipment in the MW.

The proposed methodology leads to a maintenance decision support tool enabling to give the structure of the MW, performing at a higher level, but at a reasonable configuration cost. Simulation results illustrate the influence of different parameters, such as the number of stations and the level of spare parts in the MW, on the sojourn time of the equipment.

Only corrective maintenance is taken into account and only equipment that can be taken out of the production workshop are considered. The preventive replacement of some equipment items can be taken into account by the repair process by considering them as failed.

The work falls within a more general framework for optimizing maintenance costs, in the context of integration of multi-site services in a distributed context. The paper is concerned with centralized maintenance, and proposes to integrate the so-called repair by replacement technique in a MW, used for a multi-site production workshop.

The purpose of this research is to improve efficiency of the traditional scheduling methods and explore a more effective approach to solving the scheduling problem in supply networks with genetic algorithms (GAs).

This paper develops two methods with GAs for detailed production scheduling in supply networks. The first method adopts a GA to job shop scheduling in any node of the supply network. The second method is developed for collective scheduling in an industrial cluster using a modified GA (MGA). The objective is to minimize the total makespan. The proposed method was verified on some experiments.

The suggested GAs can improve detailed production scheduling in supply networks. The results of the experiments show that the proposed MGA is a very efficient and effective algorithm. The MGA creates the manufacturing schedule for each factory and transport operation schedule very quickly.

For future research, an expert system will be adopted as an intelligent interface between the MRPII or ERP and the MGA.

From the mathematical point of view, a supply network is a digraph, which has loops and therefore the proposed GAs take into account loops in supply networks. The MGA enables dividing jobs between factories. This algorithm is based on operation codes, where each chromosome is a set of four‐positions genes. This encoding method includes both manufacture operations and long transport operations.

The purpose of this paper is to raise awareness among manufacturing researchers and practitioners of the potential of Bayesian networks (BNs) to enhance decision making in those parts of the manufacturing domain where uncertainty is a key characteristic. In doing so, the paper describes the development of an intelligent decision support system (DSS) to help operators in Motorola to diagnose and correct faults during the process of product system testing.

The intelligent (DSS) combines BNs and an intelligent user interface to produce multi‐media advice for operators.

Surveys show that the system is effective in considerably reducing fault correction times for most operators and most fault types and in helping inexperienced operators to approach the performance levels of experienced operators.

Such efficiency improvements are of obvious value in manufacturing. In this particular case, additional benefit was derived when the product testing facility was moved from the UK to China as the system was able to help the new operators to get close to the historical performance level of experienced operators.

Spare parts management plays a relevant role for equipment-intensive companies. An important step of such process is the spare parts classification, enabling properly managing different items by taking into account their peculiarities. The purpose of this paper is to review the state of the art of classification of spare parts for manufacturing equipment by presenting an extensive literature analysis followed by an industrial assessment, with the final aim to identify eventual discrepancies.

Not only is the attention put on the literature about the subject, but also on an on-field analysis, that is presented comprehending an extensive survey and two in-depth exploratory case studies. The copper mining sector was chosen being representative for the case of capital intensive plants where the cost of maintenance has relevant weight on the total operating cost.

The paper highlights the status of the scientific literature on spare parts classification by showing the current situation in the real industrial world. The paper depicts the existing barriers that leave gaps between theory and real practice for the application of an effective multi-criteria spare parts classification.

The paper provides a review of the theory on spare parts classification methods and criteria, as well as empirical evidences especially for what concern current situation and barriers for an effective implementation in the industrial environment. The paper should be of interest to both academics and practitioners, since it provides original insights on the discrepancies between scientific and industrial world.