Non-traditional machining processes selection using data envelopment analysis (DEA)

The generic term ‘non-traditional machining’ (NTM) refers to a variety of thermal, chemical, electrical and mechanical material removal processes which have been developed due to lack of efficiency of the traditional machining processes to generate complex and intricate shapes in materials with ‘high strength-to-weight’ ratio. For effective utilization of the capabilities of different NTM processes, utmost care is needed for the selection of the most suitable process for a given machining application. Due to the lack of experienced experts in the domain of NTM processes, there is a need for a simple scientific/mathematical tool for selecting the most suitable NTM process when a particular shape feature is to be generated on a given work material. This paper focuses on the development of a two-phase decision model in this aspect. In the first phase, the most efficient NTM processes are selected for a given shape feature and work material combination having the best combination of performance parameters with the help of input-minimized-based Charnes, Cooper and Rhodes (CCR) model of data envelopment analysis (DEA). In the second phase, those efficient NTM processes are ranked in descending order of priority using the weighted-overall efficiency ranking method of multi-attribute decision-making (MADM) theory. Two real time machining applications are cited which prove the applicability, versatility and adaptability of this two-phase NTM process selection decision-making model as the results are quite consistent with those as derived by the past researches.     

Selection of non-traditional machining processes using analytic network process

Non-traditional machining (NTM) processes are now being widely used to generate intricate and accurate shapes in materials, like titanium, stainless steel, high strength temperature resistant (HSTR) alloys, fiber-reinforced composites, ceramics, refractories and other difficult-to-machine alloys having higher strength, hardness, toughness and other diverse material properties. Generation of complex shapes in such materials by the traditional machining processes is experienced to be difficult. For effective utilization of the capabilities of different NTM processes, careful selection of the most suitable process for a given machining application is often required. Selection of the best suited NTM process for a work material and shape feature combination requires the consideration of several criteria. In this paper, an analytic network process (ANP)-based approach is proposed to select the most appropriate NTM process for a given machining application taking into account the interdependency and feedback relationships among various criteria affecting the NTM process selection decision. To avoid the difficult and time consuming mathematical calculations of the ANP, a computer program is also developed in Visual Basic 6.0 with graphical user interface to automate the entire NTM selection decision process. It simply acts as an ANP solver. The observed results from the ANP solver are quite satisfactory and match well with those obtained by the past researchers.     

基于专家知识的字典序优化决策方法及工业应用

为有效实现有色冶金配料过程的实时优化,首先根据氧化铝配料过程特点,建立一种字典序区间目标规划模型;然后通过整理长期积累的专家经验知识,构建了具有优先级的分类知识库;接着基于专家知识库的分类结构,提出一种字典序专家推理策略,以实现区间约束条件下的多质量指标的优化控制．工业应用结果表明,所提出的方法能够很好地实现生料浆质量的优化控制,为其他有色冶金工业配料过程的控制提供了一种优化模式．     

Near-term memory in programming: a simulation-based analysis

Near-term memory (NTM) is proposed as a construct for analysing the memory that experts build up and use as they solve a problem in their domain of expertise. Large amounts of information are processed in such situations, and any particular detail could become important later, so performance is facilitated by maintaining long-term memory access to as much detail as possible. Precise analysis of such memory is difficult to achieve with experimentation or observation alone, so computational simulation is used as the analytical method. A computational process model grounded in cognitive theory (Soar) is constructed to fit extensive fine-grained behavioral data from an expert programmer. The model's structures and processes are then inspected for insights into NTM. Structurally, the model's NTM consists of fine-grain perceptual, semantic, and episodic items whose availability is tied to cues from the encoding context. Quantitatively, much more detail enters NTM than is ever retrieved, but when retrieval does occur it can change the course of behavior. To illustrate applications of the construct, the model is used to examine how a cluttered interface might impose cognitive costs by increasing retrieval demands on memory.     

水泥回转窑多因素智能控制系统

针对复杂的水泥回转窑热工过程．提出了一种基于系统运行模式的智能控制算法。依据专家操作模式下。对影响系统各因素的在线测量数据．运用改进聚类分析算法．建立系统的运行模式．并针对每个运行模式在线学习生成一条控制规则。进而自动生成控制规则库．实现复杂的水泥回转窑热工制度的最优控制。     

A new approach for multiple attribute group decision making with interval-valued intuitionistic fuzzy information

This paper proposes a novel method for multiple attribute group decision making (MAGDM) with interval-valued intuitionistic fuzzy information. The interval-valued intuitionistic fuzzy numbers of each expert preference matrix are first mapped into two dimensions. Thus, the values of each membership degree and non-membership degree are considered as points in the two-dimensional representation. Moreover, the distance between the points represents the variance among the different experts preferences. The preference points of the same character are considered as a point set. We employ the plant growth simulation algorithm (PGSA) to calculate the optimal rally points of every point set, the sum of whose Euclidean distances to other given points is minimal, and these optimal rally points reflect the preferences of the entire expert group. These points are used to establish an expert preference aggregation matrix. Suitable points from the matrix are chosen to constitute an ideal point matrix, a projection method is employed to calculate the sum of its Euclidean distance to the expert preference aggregation matrix, and the score of each alternative is evaluated. Finally, the overall ranking of alternatives is obtained. In addition, this study develops a process to evaluate the pros and cons of different aggregation methods. Two typical examples are presented to illustrate the feasibility and effectiveness of the proposed approach.     

Parametric optimization of some non-traditional machining processes using artificial bee colony algorithm

Selection of the optimal values of different operating parameters is of utmost importance for enhancing the performance of various non-traditional machining (NTM) processes. The performance measures (responses) of different NTM processes usually include metal removal rate, surface roughness, radial overcut, tool wear rate, heat affected zone, etc. In this paper, artificial bee colony (ABC) algorithm is employed to search out the optimal combinations of different operating parameters for three widely used NTM processes, i.e. electrochemical machining, electrochemical discharge machining and electrochemical micromachining processes. Both the single and multi-objective optimization problems for the considered NTM processes are solved using this algorithm. The results obtained while applying the ABC algorithm for parametric optimization of these three NTM processes are compared with those derived by the past researchers, which prove the applicability and suitability of the ABC algorithm in enhancing the performance measures of the considered NTM processes.     

分布式棒线材轧制生产线在线生产调度系统

在分析棒线材生产作业计划特点的基础上，建立了精轧工序轧制批量调度的数学模型，其中考虑了轧机的维护约束等实际应用约束，采用混合局部搜索的自适应遗传算法进行求解，给出了基于多智能体系统（MAS）的分布式在线生产调度系统的总体结构，描述了进化计算、专家系统、启发式规则和人机交互相结合的集成化实现方法．实际运行结果表明，该系统各项功能运行良好，可快速编制出接近最优的生产调度计划，调度质量得到很大地改进．     

A rule-based expert system approach to process selection for cast components

A knowledge-based expert system at the discretion of casting product designers can be employed as a real-time expert advisor to assist product designers to achieve the correct casting design and select the most appropriate casting process for a given component. This paper proposes a rule-based expert system approach for casting process selection, and describes an ongoing rule prototype development. The system in its present development state consists of five interconnected levels each concerning a particular process selection parameter or group of parameters including alloy to be cast, casting geometric features, casting accuracy, production quantity and overall comparative costs. The system progressively evaluates the user's specifications against the capabilities of various casting processes and in each level selects the processes that satisfy the design parameters specified. The final comparative cost level compares the processes that have satisfied all the criteria in the previous levels and recommends the most economical option.     

A hybrid approach for supervisory control of furnace temperature

The temperature control of the reheat furnace is very difficult due to its complex characteristics. Based on expert knowledge and pyrology mechanism, a hybrid supervisory control system (an optimal setting model) has been developed innovatively to control its temperature. With the help of a statistical process controller, this hybrid supervisory control system can replace the human operator for most of operations in the process. Since an expert compensator is designed to suppress the external disturbance, the proposed model can automatically update the optimal set-point value for the furnace temperature of each zone under the varying boundary conditions. Both simulation and industrial experiment show the viability and effectiveness of the suggested model and its bright application foreground in thermal process.     

Optimal process design of two-stage multiple responses grinding processes using desirability functions and metaheuristic technique

Two-stage grinding processes in mass-scale manufacturing unit are usually too complex to optimize, due to large number of interacting process variables, between and within the stages. Furthermore, statistical design of experiment techniques, such as factorial design, fractional factorial and response surface design by sequential experimentations, to determine the exact optimal process design for the overall interdependent two-stage system, are sometimes too difficult to implement, if not impossible. In this context, considering each stage in isolation and determining individual optimal conditions may not result in an optimal process design, when the entire two-stage system is considered. The aim of this study is to apply empirical modelling technique based on direct observations, for prediction of a two-stage grinding process behaviour having multiple response characteristics of continuous variables, and determine overall optimal process design to meet the specific customer requirements. In order to achieve the above goal, the study proposes an integrated approach using multivariate regression, desirability function, and metaheuristic search technique. Three different metaheuristic search techniques, viz. real-coded genetic algorithm, simulated annealing, and a modified Tabu search based on novel Mahalanobis multivariate distance approach to identify Tabu moves, are employed to determining near optimal path conditions for an industrial case study of two-stage CNC grinding (honing) optimization problem, having various process and variable constraints. Computational study results based on different metaheuristics, and applied on the same two-stage optimization problem, show that the modified Tabu search performs better and also offer opportunities to be extended for other multi-stage metal-cutting process optimization problems.     

AI approaches to identification and control of total plant production systems

Recent progress in intelligent control techniques has enabled complex systems such as cultivation and fruit-storage processes to be dealt with. This paper presents the application of a hierarchical intelligent control system, which consists of an expert system and an optimizer based on neural networks and genetic algorithms, for optimizing a total plant production process. Environmental factors in the cultivation and storage processes are optimally controlled, based on the physiological status of the plant (or fruit). The expert system determines suitable environmental setpoints throughout growth, and the optimizer determines optimal environmental setpoints during important growth stages and during storage, based on plant responses. In the optimizer, neural networks were used for the identification of plant responses to environmental factors, and genetic algorithms were used to search for the optimal environmental setpoints through the simulation of the identified models. Optimal setpoints of the nutrient concentration in hydroponic tomato cultivation and optimal setpoints of the temperature during tomato storage were determined using this control technique.     

Expert system for clustering prokaryotic species by their metabolic features

Studying the communities of microbial species is highly important since many natural and artificial processes are mediated by groups of microbes rather than by single entities. One way of studying them is the search of common metabolic characteristics among microbial species, which is not only a potential measure for the differentiation and classification of closely-related organisms but also their study allows the finding of common functional properties that may describe the way of life of entire organisms or species. In this work we propose an expert system (ES), making the main contribution, to cluster a complex data set of 365 prokaryotic species by 114 metabolic features, information which may be incomplete for some species. Inspired on the human expert reasoning and based on hierarchical clustering strategies, our proposed ES estimates the optimal number of clusters adequate to divide the dataset and afterwards it starts an iterative process of clustering, based on the Self-organizing Maps (SOM) approach, where it finds relevant clusters at different steps by means of a new validity index inspired on the well-known Davies Bouldin (DB) index. In order to monitor the process and assess the behavior of the ES the partition obtained at each step is validated with the DB validity index. The resulting clusters prove that the use of metabolic features combined with the ES is able to handle a complex dataset that can help in the extraction of underlying information, gaining advantage over other existing approaches, that may relate metabolism with phenotypic, environmental or evolutionary characteristics in prokaryotic species.     

层次分析法的电子音乐音质评估模型

为准确评估电子音乐音质,提出了基于层次分析法的电子音乐音质评估模型。首先将电子音乐音质评估作为目标层,将声源特性、信号特征、声场特性、听觉特性和立体感作为准则层,将十音质评估元素作为方案层,从而电子音乐音质评估指标体系结构,然后根据各层次间元素的从属关系或并列关系,构建电子音乐音质判断矩阵,通过判断矩阵的最大特征值归一化后特征向量分量,获取电子音乐音质评估指标体系各层元素的权重,最后采用电子音乐音质评估元素权重和专家评分,得到电子音乐音质评估结果。仿真测试结果表明,这种方法能获取各电子音乐音质评估元素对音质的影响权重,得到准确的电子音乐音质评估结果。     

一种解决蕴含不确定性信息的氧化铝配料问题的智能优化方法

针对原料质量不稳定和成分检测大滞后带来的信息不确定性,提出了一种两级智能优化方法实现氧化铝配料过程中生料浆质量的优化控制.该方法通过引入中间优化同标,将优化问题分解为原料配比优化和料浆调配优化,逐步弱化不确定信息对生料浆质量的影响.配比优化基于入槽生料浆质量预测模型,设计了专家分级推理机制,实现多质量指标约束条件下的配比优化设定:调配优化将不确定的生料浆质量信息引入调配优化模型约束中,采用改进遗传算法求解最优渊配方案,配制高质量的生料浆.将提出的方法应用于国内某厂氧化铝配料过程,实现了生料浆质量指标的优化控制,简化了工艺流程,为存在信息不确定的长流程工业过程的优化控制提供了范例.     

Computer-aided design for manufacturing process selection

This paper describes an expert system that helps designers select a manufacturing process in the early stage of product design. First, the paper focuses on net-shape manufacturing processes and identifies the major factors that affect the selection of an appropriate process. Examples of these factors include shape, production volume and material. A versatile methodology should consider all the factors simultaneously in assessing the suitability of the candidate processes. The proposed system uses the concept of design compatibility analysis to represent the suitability of candidate processes with respect to the given product specifications. The system uses this knowledge to eliminate incompatible candidates and rank the compatible set of processes. A prototype system called DFPS uses HyperCard and Prolog to implement the proposed methodology. DFPS also contains information related to each process.     

Soft sensor and expert control for blending and digestion process in alumina metallurgical industry

This paper presents a soft sensor model for a high-pressure digestion process to control the raw material proportioning for the bauxite slurry blending process in the alumina metallurgical industry. By dividing the sample data set into several clusters with an improved rival penalized competitive learning clustering algorithm, a distributed support vector machine-based soft sensor is presented to measure the quality of the digested slurry online. Based on expert knowledge and the mechanism of the blending and digestion process, a hybrid expert control system for supervisory control of the blending process is developed to optimize the raw material proportioning. Both the experiments and the industrial applications demonstrate the feasibility and effectiveness of the soft sensor and the developed expert control system.     

Knowledge-based approach to quality control assurance using bar code identification systems

A knowledge-based approach to quality assurance using bar code identification systems can be carried out in three different stages. In the first stage, a complete study of the manufacturing processes, raw materials, and procedures of inspection has to be conducted. Data collection forms are prepared and potential trouble areas located to get more information on the types of problems occurring. In the second stage, inspection procedures are established for in-coming raw material. Acceptance Sampling plans have to be agreed upon to facilitate inspection of raw materials. The procedures are based on Acceptance Sampling Military Standards (MIL-STD 105 E and MIL-STD 414). In the last stage an expert system can be developed and integrated with automatic identification of the in-coming raw material packages for acceptance sampling, and with inprocess goods for establishing and monitoring statistical process control.     

Validation of biochemical laboratory results using the DNSev expert system

In a modern hospital biochemical laboratory, the efficiency and quality of the analysis result production process are fundamental. With respect to quality, an important step in the process is validation. In this step, laboratory physicians, who are physicians specialized in laboratory work, check the analysis result reports in order to verify that no error has occurred during their production. The application described in this paper is an expert system named DNSev. DNSev has been developed in order to improve the quality of the validation process performed by a specific laboratory information system (LIS), called ITALAB C/S, a system used in about thirty percent of Italian hospital laboratories. Objectives achieved by DNSev are: analysis result validation support (medical laboratory expertise in the process is translated into rules and automatically applied by DNSev), help for laboratory automation (checks that are usually manually executed are now automatically executed), clarity (reasoning performed by DNSev in issuing alarms is documented in order to explain it to laboratory physicians), flexibility (new types of reasoning can be easily added to the system by simply upgrading its knowledge base), reliability (checks may be tailored, based on patient characteristics) and time saving and cost reduction. During the development of DNSev, the knowledge acquisition and elicitation task was performed by interviewing laboratory physicians, and also by using available documents and laboratory guidelines. In order to conduct a significant trial test, we installed DNSev in the centralized biochemical laboratory of ‘Sant'Orsola-Malpighi’ Hospital in Bologna (Italy). This is one of the largest Italian biochemical laboratories, managed entirely by ITALAB C/S LIS. During this test we achieve a time saving of around 63% for each analysis request and a reduction on the overall number of analysis requests to be manually examined by laboratory physicians by around 20–25%. About performance of DNSev checks we achieved good accuracy and sensibility levels and a very low false normal level. These results demonstrate that an expert system may be a valid solution for improving quality and efficiency of well-defined medical tasks.     

A knowledge-based system for conveyor equipment selection

Conveyor equipment selection is a complex, and sometimes, tedious task since there are literally hundreds of equipment types and manufacturers to choose from. The expert system approach to conveyor selection provides advantages of unbiased decision making, greater availability, faster response, and reduced cost as compared to human experts. This paper discusses the development of a prototype expert system for industrial conveyor selection. The system, which was developed on Level V Object, provides the user with a list of conveyor solutions for their material handling needs along with a list of suppliers for the suggested conveyor devices. Conveyor types are selected on the basis of a suitability score, which is a measure of the fulfillment of the material handling requirements by the characteristics of the conveyor. The computation of the score is performed through the Weighted Evaluation Method, and the Expected Value Criterion for decision making under risk. The prototype system was successfully validated through two industrial case studies.