Automatic inspection of metallic surface defects using genetic algorithms

This paper is concerned with the problem of automatic inspection of metallic surface using machine vision. An experimental system has been developed to take images of external metallic surfaces and an intelligent approach based on morphology and genetic algorithms is proposed to detect structural defects on bumpy metallic surfaces. The approach employs genetic algorithms to automatically learn morphology processing parameters such as structuring elements and defect segmentation threshold. This paper describes the detailed procedures which include encoding scheme, genetic operation and evaluation function.

The proposed method has been implemented and tested on a number of metallic surfaces. The results suggest that the method can provide an accurate identification to the defects and can be developed into a viable commercial visual inspection system.

Generalized pseudo-likelihood estimates for markov random fields on lattice

In this paper we generalize Besag's pseudo-likelihood function for spatial statistical models on a region of a lattice. The correspondingly defined maximum generalized pseudo-likelihood estimates (MGPLEs) are natural extensions of Besag's maximum pseudo-likelihood estimate (MPLE). The MGPLEs connect the MPLE and the maximum likelihood estimate. We carry out experimental calculations of the MGPLEs for spatial processes on the lattice. These simulation results clearly show better performances of the MGPLEs than the MPLE, and the performances of differently defined MGPLEs are compared. These are also illustrated by the application to two real data sets.

Aggregate planning for seasonal demand : reconciling theory with practice

Purpose: The paper reports on the ramifications for production planning when monthly sales exhibit predictable seasonal highs and lows. The literature first acknowledged and dealt with the (aggregate planning) problem 50 years ago. Nevertheless, there is neither evidence that industry has adopted any of the mathematical techniques that were subsequently developed, nor a convincing explanation as to why not. Hence this research sets out to discover the methods manufacturers use to cope with seasonal demand, and how germane the published algorithms really are.

Design/methodology/approach: Forty-two case studies were compiled by interviewing senior managers and then conducting plant tours. No prior assumptions were made and the list of questions covered the gamut of production planning.

Findings: The main finding is that manufacturers select a straightforward production strategy, right from the outset, so the fundamental cost-balancing format is not relevant. The majority pick a “chase” strategy, since most organizations subscribe to a “just in time” ethos. Whenever a different strategy is preferred the rationale springs from skilled labour considerations or binding facilities constraints. The chosen strategy serves as a road map for resources acquisitions, and the master production schedule is constructed directly. So, the complex issue of how to disaggregate an optimal aggregate plan never even arises. Managers do not seek perfect solutions, but strive to eliminate, or contain, the most significant marginal costs. The nature of the business determines the most appropriate tactics to employ.

Originality/value: These findings break the mould as far as orthodox aggregate planning is concerned and show why theory is at odds with practice, whilst reaffirming the importance of concepts such as “flexibility”, “integration”, and “just-in-time production”.