Arkadiusz Gola

Application of Fuzzy Logic in Assigning Workers to Production Tasks

The paper demonstrates the concept of selecting workers for production tasks with the use of fuzzy logic. Mamdani-type fuzzy inference method was used to design a controller whose task was to aid the decision-making process. Fuzzy interference system converted a number of qualitative features into quantitative variables, which enabled calculating deviations and their comparison. Moreover, a simulation model of a discrete manufacturing system with an implemented fuzzy controller was developed. conducted simulation provided detailed data regarding the investigated selection process.

A Knowledge-Based Approach to Product Concept Screening

This paper is concerned with developing a knowledge-based approach for selecting portfolio of product concepts for development. The critical success factors for new product development are identified on the basis of information acquired from an enterprise system, including the fields of sales and marketing, project management, and production. The model of new product screening consists of enterprise functional domains and business information systems. The model has been described in terms of a constraint satisfaction problem (CSP) that contains a set of decision variables, their domains, and the constraints. Knowledge base is specified according to CSP framework and it reflects the company’s resources and relationships identified. The illustrative example presents the use of fuzzy neural network to estimating the success of new products and constraint programming to product concept screening in the context of the different search strategies.

Application of Fuzzy Logic Controller for Machine Load Balancing in Discrete Manufacturing System

The paper presents a concept of control of discrete manufacturing system with the use of fuzzy logic. A controller based on the concept of Mamdani was developed. The primary function realized by the controller was the balancing of machine tool loads taking into account the criteria of minimisation of machining times and costs. Two models of analogous manufacturing systems were developed, differing in the manner of assignment of production tasks to machine tools. Simulation experiments were conducted on both models and the results obtained were compared. In effect of the comparison of the results of both experiments it was demonstrated that better results were obtained in the system utilising the fuzzy inference system.

Risk-based estimation of manufacturing order costs with artificial intelligence

The following paper discusses the development of a risk-based cost estimation model for completing non-standard manufacturing orders. The model in question is a hybrid of Monte Carlo Simulation (MCS), which constitutes the main module of the applied model. Vector of order risk probability, which is the input data for the MCS module, is highly difficult to assess and is burdened to a considerable degree with subjectivity, therefore it was resolved that it should be generated with the application of artificial intelligence. Depending on the accessibility of historical data, the model incorporates fuzzy logic or artificial neural networks methods. The presented model could provide support to managers responsible for cost estimation, and moreover, after slight modification also in setting deadlines for non-standard manufacturing orders.

Integer Linear Programming in Optimization of Waste After Cutting in the Furniture Manufacturing

The study was an attempt to develop the model of a decision controller allowing for simultaneous optimisation of the stock of semi-finished product generated during cutting and cut-out waste. The proposed decision controller was designed to select a suitable cut-out programme to account for such factors as: production orders, current stock of semi-finished product, minimum stock limits, the set limit of rejects. The elaboration concerns application of integer linear programming in multicriteria optimisation in constraint.

TECHNICAL AND ORGANIZATIONAL IMPROVEMENTS OF PACKAGING PRODUCTION PROCESS

Due to customer driven economies, today’s world markets are characterized by high fluctuations in market demand and frequent arrival of new technologies and new products. To stay competitive in such markets manufacturing companies require continuous improvements both in technical and organizational areas of their activity. The paper presents results of the diagnosis provided in the manufacturing area of the company producing cardboard packages and recommendations to make the production process more efficient. Especially, among the proposed technical and organizational recommendations the most important ones are: automation of certain elements of the production process and changes in production plant layout.

Accuracy Control in the Machining of Low Rigidity Shafts

The study determines the most suitable pattern of alignment and fixing of low-rigidity shafts; it also presents factors that determine such choice. The part is fixed both by force closing and kinematic closing. A new method for machining low rigidity shafts is developed to control the elastic-deformable state of these shafts in a technological system and to produce parts with the required accuracy during turning. To implement this new developed method for low rigidity shafts, an apparatus is designed. The apparatus allows to increase the rigidity of shafts during machining by the application of axial tensile force to the workpiece. Rational prime costs of preparing technological alignment centers at the stage of production preparation are determined; knowing these costs, it is possible to select a suitable machining technology for low rigidity shafts, to produce a technology-oriented design, and to reduce the costs of machining these shafts.

Application of survival function in robust scheduling of production jobs

Scheduling production jobs in the real production system requires considering a number of factors which may prove to exert a negative effect on the production processes. Hence the need for the identification and compensation of potential disruptions as early as at the production planning stage. The aim of this paper is to employ the survival and the hazard function to anticipate potential disruptions of the schedule so that they could be absorbed to produce a robust job schedule.

Application of Fuzzy Logic and Genetic Algorithms in Automated Works Transport Organization

The paper deals with the problem of works transport organization and control by artificial intelligence with respect to path routing for an automated guided vehicle (AGV). The presented approach is based on non-changeable path during travel along a given loop. The ordered set of stations requesting transport service was determined by fuzzy logic, while the sequence of stations in a loop was optimized by genetic algorithms. A solution for both AGV’s and semi-autonomous transport vehicles wherein the control system informs the driver about optimal route was presented. The obtained solution was verified by a computer simulation.

Mathematical Models for Manufacturing Systems Capacity Planning and Expansion – An Overview

When planning a new manufacturing system, the optimal investment in the system capacity is a major decision to make. The problem of capacity planning is not an easy because of the unpredictable character of the market demand and multi-criteria optimization character of the task. Therefore there is still no one complex methodology of the capacity planning and management. In this paper some mathematical models for capacity planning which can be used at the stage of manufacturing system design or expansion are presented.