Automated vision inspection has become a vital part of computer related industries. Most of the existing inspection systems mainly utilize black and white images. In this paper, we consider an application of automated vision inspection in which cable color has to be recognized in order to detect the quality status of assembled wire harness. A back-propagation neural network is proposed to classify seven different cable colors. To represent a single point in image space, we use the ($L^*,\;a^*,\;b^*$) model which is one of commonly used color-coordinate systems in image processing. After training the neural network with ($L^*,\;a^*,\;b^*$) data obtained from color image, we tested its performance. The results show that the neural network is able to classify cable colors with high performance.

Since anthropometric data are essential to the design of industrial products, the national anthropometric survey was performed three times in Korea. An Anthropometric Data Manager system (ADaM) was implemented based on the 1992 national anthropometric survey to promote the utilization of the data. The system provides graphic user interface to facilitate usability. Anthropometric information can be obtained in various ways by the following statistical analyses; multivariate features analysis, correlation analysis, and regression. In addition, recommendations for design parameters of industrial products were provided in this system.

Optimization in the engineering design is to select the best of many possible design alternatives in a complex design space. One major problem of local minimization algorithm is that they often result in local optima. In this paper, a hybrid method was developed by coupling the genetic algorithm and a traditional direct search method. The proposed method first finds a region for possible global optimum using the genetic algorithm and then searchs for a global optimum using the direct search method. To evaluate the performance of the hybrid method, it was applied to three test problems and a problem of designing corrugate bulkhead of a ship.

This study is intended to develop a technology cost model (TCM) which treats technology costs appropriately under present advanced manufacturing technology environment. TCM is composed of two elements : cost classification system and cost allocation model. It is proposed to include technology-related department expenses as well as technology investment in the categories of technology costs. For the cost allocation, technology activities are divided into four homogeneous groups. Costs are accumulated into one of the four cost pools and allocated to the cost object using the pool's unique allocation base. It is also proposed to use the capital recovery costs including interest expense rather than the depreciation costs for an invested capital. A case study is performed to verify the applicability of the developed model.

Automated Storage and Retrieval System (AS/RS), which is an element of Computer Integrated Manufacturing (CIM), is a widely used material handling equipment with conveyors and Automatic Guided Vehicles (AGVs). Until now the evaluation of operational policies of AS/RS and control algorithms is done theoretically or by computer simulations. In this study, a real-time control and communication software for an AS/RS is developed for actually moving AS/RS miniature. A PC-based real-time operational program can control the AS/RS directly through the communication port. The operational system has additional functions such as storage/retrieval management, inventory management, statistics management, and protocol simulation. The communication protocol simulator of S/R machine can be used for the controller of an S/R machine.

The purpose of this paper is to develop a procedure and a system for the design of manufacturing cells. First, a procedure is developed to create machine cells, to identify part families and to allocate part families to machine cells so that the intercellular movement of part is minimized. Next, a system for solving this procedure is developed and an application example is demonstrated.

Warehouse planning or design is not a static, one-time activity. To survive in the constantly changing market warehouse design should be a continuous process in which the anticipated requirment are reflected on the current warehouse status. Thus, the goal of warehouse management is to effectively utilize the various warehouse resources to meet the varying customer requirment. This paper presents an engineering framework for warehousing system analysis and design from the perspective of a total system approach. The complexity pertinent to warehousing system analysis and design is first discussed, which mainly come from the interplay among product data, order data, equipment types, operating strategies, and functional specification of the overall system. The understanding of the complexity leads to a general structure and a conceptual design procedure for a warehousing system. The general structure is comprehensive enough to represent most warehousing and flexible enough to accommodate the more sophisticated ones. The conceptual design procedure portrays the high-level interelationships the design issues.