Modelling job complexity in garment manufacture by inductive learning

Abstract

Introduction and backgroundIn the past, a large number of garment manufacturing models [1][2][3][4][5] have been developed to model garment production behaviour for improving productivity, reducing costs and improving quality. These models range from full deterministic to full stochastic models. Representation of uncertainty in these models is often necessary because, in the garment industry, uncertainty arises not only in the marketplace but also during the production cycle. It is especially true when predicting the complexity of production orders.The complexity of production orders, when properly measured, can reflect the degree of difficulty in handling an order. Knowing how difficult it is to handle an order allows us to predict accurately the requirement for resources (such as operators, equipment and materials) and to prepare for an effective order scheduling.Under normal circumstances, an order could be divided into three main operations -cutting, assembling, and finishing (Figure 1). Within each operation, a series of jobs such as cuff making, placket making and sleeve making could be determined by customer requirements.When a complicated production job is encountered, the apparel manufacturer should plan to allocate the appropriate resources very carefully prior to carrying out real production in order to be able to deliver on time, minimize cost and achieve good quality. A field expert is normally required to produce the capacity plan based on his or her experience and expertise. The capacity plan includes a production schedule, manpower allocation, machinery utilization and materials requirements. If the degree of complexity of a production job is high, it will put a lot of effort on some operations during the production. For instance, the fashioned style men's shirts may require a lot of effort on colour/pattern matching during assembling resulting in it becoming the bottleneck for the production job.

Machine-learning techniques and their applications in manufacturing

“…Other applications include generating decision rules for the conceptual design of steel members under bending [152], diagnosing engine faults [153], detecting defects in disk drive manufacturing [154], diagnosing motor pumps [155], analysing nondestructive testing of spotweld quality [156], managing and controlling the procurement of raw materials [157], accelerating rotogravure printing [158,159], optimizing processes in electrochemical machining [160], selecting appropriate cutting tools in grinding [161], determining suitable cutting conditions in operation planning [162,163], re-formulating and generalizing the machining knowledge from a machining database [164], choosing sheet metal working conditions [165], discovering the laws governing metallic behaviour [166], modelling job complexity in clothing production systems [167], acquiring and refining operational knowledge in industrial processes [168,169], and identifying arbitrary geometric and manufacturing categories in CAD databases [170].…”

Analysis of Impacts of Production Order Complexity and Lot Size on Apparel Production Systems Using Simulation Technique

“…Under common circumstances, a production order is divided into numbers of operations for the completion of a garment. The criteria used to determine the complexity level of operations include the operation type (if the task requires special operational skills), bundle size and type (if the garment is a fashionable style), SAM, machinery type (if the operation only runs on a special machine) and degree of labor skills required for manufacturing (Hui et al, 1997).…”

“…Our study of the literature on apparel production systems shows that the performance of a production system is closely related to the complexity of production orders which reflects the level of difficulty in handling them (Hui et al, 1997) and the allocation of lot sizes (Habchi & Labrune, 1995). However, decision makers rarely consider these factors when selecting a production system.…”