A knowledge-based approach for automated process planning

Automated process planning (APP) is a critical interface to both design and manufacturing. Several evolving systems have employed artificial intelligence (AI) procedures to capture the basic logic used by a process planner. However, no effort has been directed to systemize the knowledge in the field of process planning. In this paper process planning knowledge extraction and formalization will be discussed. A framework for the development of intelligent APP systems capable of learning through user interaction is also presented.     

A knowledge-based approach to the generation of IDEF0 models

Though a powerful tool for modelling manufacturing systems, IDEF0 is not without weaknesses. It is generally recognised that the process of IDEF0 modelling can be time-consuming and inconsistent. However, the process may be automated to improve time-effectiveness and consistency. This paper proposes a knowledgebased system for automating the process. The system, which is meant for the discrete manufacturing industry, is based on the concept of reference models. It is intended for the modellers of manufacturing systems, as an aid rather than as their replacement. A prototype of the proposed system has been developed. The paper explains the knowledge-based approach to the generation of IDEF0 models and describes the work that has been done at Gintic on the development of the prototype system.     

A knowledge-based approach to the evaluation of fault trees

A list of critical components is useful for determining the potential problems of a complex system. However, to find this list through evaluating the fault trees is expensive and time consuming. This paper intends to propose an integrated software program which consists of a fault tree constructor, a knowledge base, and an efficient algorithm for evaluating minimal cut sets of a large fault tree. The proposed algorithm uses the approaches of top-down heuristic searching and the probability-based truncation. That makes the evaluation of fault trees obviously efficient and provides critical components for solving the potential problems in complex systems. Finally, some practical fault trees are included to illustrate the results.     

A knowledge-based approach to instrument fault detection andisolation

A knowledge-based instrument fault detection and isolation (IFDI) technique is proposed and described. It is based on the “duplication” of measurement devices by means of suitable mathematical relationships and is implemented on an expert system. The latter allows a mathematical model to be substituted by integrating qualitative models with empirical knowledge, thereby reducing overall computer effort without any corresponding decrease in diagnostic capabilities. This technique is particularly efficient when applied to detect and isolate faults in measurement systems integrated in control architectures. It is applied to an automatic measurement station for induction motor testing to illustrate its characteristics and performance. The experimental results are also reported, illustrating IFDI performance mainly in terms of promptness, sensitivity, and selectivity     

A case study on measuring inspection performance for inspection job design

In the quality control system, most of the information for decision making and problem solving can be obtained by inspection activities. Therefore, the inspection work should be organized to maximize meeting the quality objectives. It has already been publicized that data obtained from measurement of inspection performance will supply an effective basis for assessment and design of the inspection station and inspection job. This paper is intended to report on a case study of measurement of inspection performance conducted for the assessment and design of an inspection job in a manufacturing company. Quality control specialists selected three groups of items having representative deficiencies under routine inspection, inspected as inspection job samples. They had individual inspectors inspect each sample to obtain data consisting of the rate of defects detected out of all the defects, and the proportion of erroneous findings in the total number of findings by each inspector. Thus they identified many problems in the inspection job to be corrected to enhance the inspection accuracy. Appropriate action was taken to remedy the situation. In the first place, the inspection job was redesigned. In the second, the method of training inspectors was reviewed and modified. As a result, the probability of defects passing the inspection undetected was greatly reduced.     

A freeform surface manufacturing approach by integration of inspection and tool path generation

Freeform surfaces have been widely used in various engineering applications. Increasing requirements for the accuracy of freeform surfaces have led to significant challenges for the manufacturing of these surfaces. A method for manufacturing of freeform surfaces is introduced in this paper by integrating inspection and tool path generation to improve manufacturing quality while reducing manufacturing efforts. Inspection is conducted by comparing the digitised manufactured surface with the design surface to identify the error regions. In this new inspection technique, the areas on the manufactured surface that are beyond the design tolerance boundaries are used as the objective function during the localisation process, in order to minimise post-inspection machining efforts. The tool path generation methods are then selected based on the geometric characteristics of the identified error regions, for creating tool paths to remove the errors. Computational efficiency, machining efficiency, and quality are considered in this integrated method.     

A transfer learning framework for traffic video using neuro-fuzzy approach

One of the main challenges in the Traffic Anomaly Detection (TAD) system is the ability to deal with unknown target scenes. As a result, the TAD system performs less in detecting anomalies. This paper introduces a novelty in the form of Adaptive Neuro-Fuzzy Inference System-Lossy-Count-based Topic Extraction (ANFIS-LCTE) for classification of anomalies in source and target traffic scenes. The process of transforming the input variables, learning the semantic rules in source scene and transferring the model to target scene achieves the transfer learning property. The proposed ANFIS-LCTE transfer learning model consists of four steps. (1) Low level visual items are extracted only for motion regions using optical flow technique. (2) Temporal transactions are created using aggregation of visual items for each set of frames. (3) An LCTE is applied for each set of temporal transaction to extract latent sequential topics. (4) ANFIS training is done with the back-propagation gradient descent method. The proposed ANFIS model framework is tested on standard dataset and performance is evaluated in terms of training performance and classification accuracies. Experimental results confirm that the proposed ANFIS-LCTE approach performs well in both source and target datasets.     

An investigation of knowledge-based models for automated procedure generation in the arc welding domain

The potential of expert systems in manufacturing is now well documented, if not unanimously accepted. However, particularly in the welding domain, there is comparatively little evidence of their practical realisation or regular utilisation in industry. The main objective of this work was to evaluate recent computing advances in the context of planning for arc welding. Thus the objectives of this study were not so much concerned with simply producing another 'expert system7apos;, but rather to extract more generic knowledge about the application of expert system techniques to advanced manufacturing problems. Furthermore it was intended to evaluate the claims made about expert systems regarding their ease of use, extendability and modifiability. A prototype system is described which can generate welding procedures to the specification of BS4870.     

Automatic sampling for CMM inspection planning of free-form surfaces

Coordinate measuring machines (CMMs) are used to examine the conformity of the produced parts with the designer's intent. The inspection of free-form surfaces is a difficult process due to their complexity and irregularity. Many tasks are performed to ensure a reliable and efficient inspection using CMMs. Sampling is an essential and vital step in inspection planning. Efficient and reliable approaches to determine the locations of the points to be sampled from free-form surfaces using the CMM were developed. Four heuristic algorithms for sampling based on the NURBS features of free-form surfaces are presented. The sampling criteria are equiparametric, surface patch size and the surface patch mean curvature. An algorithm for automatic selection of sampling algorithms performs complexity checks on NURBS surfaces, including the surface curvature changes and surface patch size changes, and selects the suitable sampling algorithm. Extensive simulations were performed using the developed methodologies to evaluate their performance using free-form surfaces with different degrees of complexity and compared with the uniform sampling pattern. The CMM measurement errors and manufacturing form errors have been simulated in these studies. The developed algorithms provide a useful tool in selecting the effective sampling plans for the tactile CMM inspection planning of free-form surfaces.     

Mission planning optimization for the visual inspection of multiple geosynchronous satellites

In this article, a new manoeuvring strategy for the multiple geosynchronous satellites inspection problem is proposed. In contrast to previous research, it can be used to visit multiple geosynchronous satellites orbiting in different orbital planes in an economical way. In the proposed mission scenario, several chasers are initially placed in an equatorial high eccentric orbit. Two orbital manoeuvres are exerted at perigee to adjust the apogee of the chaser for every inspection. Subsequently, the targets will be visited when they fly through the ascending or descending nodes of their orbits. Based on the proposed strategy, a two-level optimization approach is developed to optimize visitation order and time regarding fuel consumption. Meanwhile, the manoeuvre velocity and time are determined. Finally, the proposed method is applied to several numerical test cases to demonstrate its validity for mission planning optimization for the visual inspection of multiple geosynchronous satellites.     

节水产品认证工厂检查要点

我国节水产品认证包括了城镇生活服务业产品、工业、农业和非传统水资源利用类节水产品共四大类39种产品.由于产品涉及专业多,生产工艺差别大,且生产水平参差不齐,使得节水产品认证工厂检查的难度比较大,对检查员自身的要求也比较高.为保证认证的有效性,使获证产品能持续满足认证的要求,在工厂检查中,检查员应从以下几方面入手,逐步深入地进行工厂检查,为认证决定提供准确可靠的保证.