{"title":"Practical neural network applications in the mining industry","authors":"L. Miller-Tait, R. Pakalnis","doi":"10.1109/IPMM.1999.791515","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791515","url":null,"abstract":"The mining industry relies heavily upon empirical analysis for design and prediction. Neural networks are computer programs that use parallel processing, similar to the human brain, to analyze data for trends and correlation. Two practical neural network applications in the mining industry would be rockburst prediction and stope dilution estimates. This paper summarizes neural network data analysis results for a 1995 Goldcorp/Canmet study on rockbursting and a 1986 UBC/Canmet study on open stope dilution at the Ruttan Mine.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hybrid simulation objects using fuzzy set theory for simulation of innovative process chains","authors":"T. Menzel, M. Geiger","doi":"10.1109/IPMM.1999.792563","DOIUrl":"https://doi.org/10.1109/IPMM.1999.792563","url":null,"abstract":"The purpose of introducing new manufacturing process chains, such as innovative sheet metal processing technologies, is to increase production efficiency. Their success can be quantified by assessing the expected reduction of manufacturing time or costs and the increase in flexibility. However, the implementation of new process chains is usually inhibited by the financial effort and the lack of exact knowledge about their real effect on production efficiency. Furthermore, the economic efficiency is mainly dependent on the vaguely known quantity and variety of products which have been planned for future production. Therefore, a hybrid system using dynamic simulation objects and fuzzy set theory is designed to assess its efficiency and flexibility in advance. Its design and application are explained by the example of the hydroforming process chain of sheet metal pairs, an innovative sheet metal forming technology.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131724754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Relationship between groove cross-sectional area per pulse of YAG laser and strength of processing sound","authors":"T. Kurita, T. Ono, T. Nakai, N. Morita","doi":"10.1109/IPMM.1999.792481","DOIUrl":"https://doi.org/10.1109/IPMM.1999.792481","url":null,"abstract":"Laser processing is an important manufacturing technology in machining difficult-to-cut materials. A sound generates when a laser processing is carried out, and the intensity of a sound changes according to processing conditions. The goal of the research is to construct a laser processing system for the manufacture of free form surface. In order to achieve this goal, this study aims to clarify the relationship between the strength of laser processing sound and groove cross-sectional area per pulse when Q-switched YAG laser beam was applied for laser grooving.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114788815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Neural network-based resistance spot welding control and quality prediction","authors":"Nenad Ivezic, John D. Allen, Thomas Zacharia","doi":"10.1109/IPMM.1999.791516","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791516","url":null,"abstract":"This paper describes the development and evaluation of neural network-based systems for industrial resistance spot welding process control and weld quality assessment. The developed systems utilize recurrent neural networks for process control and both recurrent networks and static networks for quality prediction. The first section describes a system capable of both welding process control and real-time weld quality assessment. The second describes the development and evaluation of a static neural network-based weld quality assessment system that relied on experimental design to limit the influence of environmental variability. Relevant data analysis methods are also discussed. The weld classifier resulting from the analysis successfully balances predictive power and simplicity of interpretation. The results presented for both systems demonstrate clearly that neural networks can be employed to address two significant problems common to the resistance spot welding industry, control of the process itself, and nondestructive determination of resulting weld quality.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115063410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Intelligent design methods for smart materials","authors":"M. Fathi-Torbaghan, L. Hildebrand","doi":"10.1109/IPMM.1999.791519","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791519","url":null,"abstract":"The design process of modern smart materials often require the use of complex system models. These models cannot be derived easily due to the complex knowledge that describe the process. In some cases, model parameters can be gained using neural networks, but these systems allow only a one-way simulation from input values to learned output values. If evaluation in the other direction is needed, these models allow no direct evaluation. This task can be solved using modern techniques like evolutionary algorithms and fuzzy logic. The use of such a combination allows evaluation of the learned simulation models in the direction from output to the input. An example can be given from the field of screw rotor design.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121410792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Team scheduling by genetic search","authors":"Tiehua Zhang, William A. GruveP, Michael H. Smith","doi":"10.1109/IPMM.1999.791495","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791495","url":null,"abstract":"We consider a photographic studio that must schedule multiple teams of photographers to a large number of elementary and secondary schools. The photographers' schedules are to be optimized so that time constraints are satisfied and each team is able to at least visit two schools daily. A multiple travelling salesman model is used where the total distance traveled and time consumed can be evaluated in a single cost function to achieve overall optimality. A genetic algorithm has been applied to solve the problem. The results show that this approach rapidly provides an effective means for solving the problem.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121233632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic reconfiguration of holonic lower level control","authors":"Xiaokun Zhang, D. Norrie","doi":"10.1109/IPMM.1999.791502","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791502","url":null,"abstract":"In this paper, a new approach to dynamic reconfiguration of holon controllers is presented. Based on metamorphic mechanisms for distributed decision-making in agent-based manufacturing systems, the concept of the dynamic virtual cluster is extended to manufacturing process control at the lower levels. Event-driven dynamic clustering of resource control services and cooperative autonomous activities are emphasized in this approach.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132647812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Artificial neural networks (ANN) as simulators and emulators-an analytical overview","authors":"G. M. Nicoletti","doi":"10.1109/IPMM.1999.791476","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791476","url":null,"abstract":"Because of their ability to exploit the tolerance for imprecision and uncertainty in real-world problems, and their robustness and parallelism, artificial neural networks (ANNs) and their techniques have become increasingly important for modeling and optimization in many areas of science and engineering. As a consequence, the market is flooded with new, increasingly technical software and hardware products. This paper presents an analytical overview of the most popular ANNs, both in hardware and software modes. After an overview of ANN, the paper discusses global optimization for ANN training, and the NOVEL hybrid method is presented and its performance is discussed. The paper then discusses the techniques and means for parallelizing neurosimulations of ANNs, both at a high programming level and at a low hardware-emulation level. It then presents vector microprocessor architectures and the Spert II fixed-point system as applied to multimedia and human-machine interface. Finally, it introduces the most recently explored concept of cellular neural networks (CNN), its performance and operation are analyzed. Conclusions and recommendations conclude the paper.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116810086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Computer-aided integrated design for injection molding","authors":"Y. Chen, C. Ho, R. Lee","doi":"10.1109/IPMM.1999.791527","DOIUrl":"https://doi.org/10.1109/IPMM.1999.791527","url":null,"abstract":"A high quality, cost effective product can not be consistently and economically produced unless product design is developed based on a comprehensive understanding of all relevant factors and their interactions. This research aims to: (1) develop an integrated design for injection molding methodology that accommodates concepts of concurrent engineering; and (2) develop a computer-integrated design for injection molding based on this methodology to provide interactive design aids and consistent design assessment to improve injection molding product design quality, producibility, and cost effectiveness.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134377406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Manohar, S. S. Shivathaya, M. Ferry, T. Chandra
{"title":"Development of an integrated system for designing steelmaking aim compositions","authors":"P. Manohar, S. S. Shivathaya, M. Ferry, T. Chandra","doi":"10.1109/IPMM.1999.792459","DOIUrl":"https://doi.org/10.1109/IPMM.1999.792459","url":null,"abstract":"A new integrated approach is proposed in this paper to generate and evaluate the alternative steelmaking aim compositions which not only meet the customer requirements but also suit the established rolling schedules. The methodology developed is based on hybrid approach combining knowledge-bases as well as mathematical modelling and is applicable for C-Mn steel grades. The system consists of two modules. The first module utilises various empirical models for the relationship between mechanical properties and the elements in steelmaking aim compositions, along with knowledge bases containing expert and heuristic knowledge of expert metallurgists to generate a list of alternative steelmaking aim compositions. The second module uses the output of the first module and computes the microstructural evolution during processing depending on steel composition and known processing conditions such as strain, strain rate, temperature, interpass time and plate cooling rate. Calculated values of the metallurgical parameters are then used to estimate the achievable mechanical properties in the final hot rolled product using knowledge-bases. System output is expected to assist product development metallurgists in the selection of appropriate steelmaking aim compositions for any combination of property specifications required by the customer.","PeriodicalId":194215,"journal":{"name":"Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114662118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}