S. Kumanan

Modeling and prediction of machining quality in CNC turning process using intelligent hybrid decision making tools

Decision-making process in manufacturing environment is increasingly difficult due to the rapid changes in design and demand of quality products. To make decision making process (selection of machining parameters) online, effective and efficient artificial intelligent tools like neural networks are being attempted. This paper proposes the development of neural network models for prediction of machining parameters in CNC turning process. Experiments are designed based on Taguchis Design of Experiments (DoE) and conducted with cutting speed, feed rate, depth of cut and nose radius as the process parameters and surface roughness and power consumption as objectives. Results from experiments are used to train the developed neuro based hybrid models. Among the developed models, performance of neural network model trained with particle swarm optimization model is superior in terms of computational speed and accuracy. Developed models are validated and reported. Signal-to-noise (S/N) ratios of responses are calculated to identify the influences of process parameters using analysis of variance (ANOVA) analysis. The developed model can be used in automotive industries for deciding the machining parameters to attain quality with minimum power consumption and hence maximum productivity.

A Review on Current Research Aspects in Tool-Based Micromachining Processes

Technology development has led to the need of micro and miniaturized products in the field of automobile, aerospace, electronics, medical implants, biomedicine, robotics, and so on. Micromachining is the key technology to satisfy the need of the industry in terms of functionality and miniaturization in size. In this article, state-of-the-art review on tool-based micromachining processes such as microturning, microdrilling, micromilling, electric discharge micromachining (Micro-EDM), and electrochemical micromachining (Micro-ECM) has been carried out. The review begins with an overview of micromachining, classifications, and discussions about different aspects of tool-based micromachining processes. The research works carried out for the past 10 years are analyzed in terms of materials perspective, process parameters, size effects, performance characteristics, condition monitoring, product development, micro features generation, and fabrication of micro tools. A statistical analysis has been performed with respect to the previous review articles, numbers of publications in the related area, and their research gap. Finally, the possible future research direction is presented.

Optimization of parameters of submerged arc weld using non conventional techniques

In submerged arc welding (SAW), weld quality is greatly affected by the weld parameters such as welding current, welding speed; arc voltage and electrode stickout since they are closely related to the geometry of weld bead, a relationship which is thought to be complicated because of the non-linear characteristics. However, trial-and-error methods to determine optimal conditions incur considerable time and cost. In order to overcome these problems, non-traditional methods have been suggested. Bead-on-plate welds were carried out on mild steel plates using semi automatic SAW machine. Data were collected as per Taguchis Design of Experiments and regression analysis was carried to establish input-output relationships of the process. By this relationship, an attempt was made to minimize weld bead width, a good indicator of bead geometry, using optimization procedures based on the genetic algorithm (GA) and particle swarm optimization (PSO) algorithm to determine optimal weld parameters. The optimized values obtained from these techniques were compared with experimental results and presented.

TASK SCHEDULING OF AGV IN FMS USING NON-TRADITIONAL OPTIMIZATION TECHNIQUES

Flexible Manufacturing System (FMS), which is equipped with several CNC machines and Automated Guided Vehicle (AGV) based material handling system is designed and implemented to gain the flexibility and efficiency of production. After the implementation of FMS, in practice, the scheduling of the resources, such as frequent variation in the parts, tools, AGV routings, becomes a complex task. This is being done traditionally using various mathematical programming techniques. In recent years, random search algorithms have been attempted for scheduling. Most of the research has been emphasized only on single objective optimization. Multi objective problems in scheduling with conflicting objectives are more complex and combinatorial in nature and hardly have a unique solution. This paper addresses multi objective task scheduling of AGV in a flexible manufacturing environment using nontraditional optimization algorithms. In this paper the authors made an attempt to find the nearoptimum schedule for two AGVs based on the balanced workload and the minimum traveling time for maximum utilization. The proposed methods are exemplified with illustrations. (Received in March 2009, accepted in September 2009. This paper was with the authors 3 months for 1 revision.)

SURFACE ROUGHNESS PREDICTION USING HYBRID NEURAL NETWORKS

Surface roughness is an important outcome in the machining process and it forms a major part in the manufacturing system. Surface roughness depends on different machining parameters and its prediction and control is a challenge to the researchers. There is a need to predict surface roughness prior to machining to attain higher productivity levels. Owing to advances in computing power there is an increase in the demand for the use of intelligent techniques. Recent research is directed towards hybridization of intelligent techniques to make the best out of each technique. This article proposes the development of a novel hybrid Neural Network (NN) trained with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for the prediction of surface roughness. The proposed hybrid neural network is found to be competent in terms of computational speed and efficiency over the neural network model.

A Multi-Objective Discrete Particle Swarm Optimisation Algorithm for supply chain network design

Strategic supply chain network optimisation is significant, as it involves long-term decisions with conflicting goals. It is an NP-hard problem and researchers are constantly attempting to use meta-heuristics as a solution approach. In this paper, a Multi-Objective Discrete Particle Swarm Algorithm (MODPSA) is proposed to optimise the supply chain network with the objectives of minimisation of supply chain cost, minimisation of demand fulfilment lead time and maximisation of volume flexibility. Two different global guide selection techniques are implemented in the proposed algorithm. Numerical tests are conducted using the real-life data of a farm equipment manufacturer and the computational analyses are performed on two stages. In the first stage, the performance of two global guide selection techniques are evaluated and in the second stage the proposed MODPSA is compared with Non-dominated Sorting Genetic Algorithm-II (NSGA II). The results indicate that the proposed approach is effective in producing high-quality Pareto-optimal solutions.

A hybrid fuzzy logic?artificial neural network algorithm-based fault detection and isolation for industrial robot manipulators

The adoption of an efficient online Fault Detection and Isolation (FDI) tool is becoming of utmost importance for robots, especially for those operating in remote or hazardous environments, where a high degree of safety and self-diagnostics capabilities are required. This saves time and cost in repairing the robot. A number of researchers have proposed fault diagnosis architectures for robotic manipulators using the model-based analytical and redundancy approach. One of the main issues in the design of fault detection systems is how to model the rigid-link robotic manipulators with modelling uncertainties. In this paper, a new approach - hybrid intelligence-based fault detection and isolation for robot manipulators - is discussed. A learning architecture, with neural network approximates the off-nominal system behaviour, which is used for monitoring the robotic system for the faults. This generates the residual by comparing the actual output from the robot. The fuzzy inference system is applied to identify and isolate the faults which provide the adoptive threshold under varying conditions. The concepts discussed are validated through a simulation study using a Scorbot-ER 5Plus manipulator to illustrate the ability of the neuro fuzzy-based fault-diagnosis scheme to detect and isolate faults.

Application of multicriteria decision making for selection of robotic system using fuzzy analytic hierarchy process

Selection of a robotic system is an important task for the dynamic scenario. Improper selection may adversely affect a firms production by reducing the quality of the product, thereby reducing productivity as well as profitability. In order to select a suitable robotic system for a specified job, several factors have to be considered. Investment decisions for robotic system are capital intensive and are usually made by a committee of experts from different functional backgrounds within a company. Ignoring this factor, most models for robot or robotic system selection assume that there is only a single decision maker. This paper discuss, a robotic system selection model incorporating the inputs from multiple decision makers. This model is based on the Fuzzy Analytic Hierarchy Process (FAHP) method and both the subjective and objective criteria for robotics system selection are used. It does not assume the consensus of the decision makers; that is, they may not agree on evaluations of the system with respect to each of the criteria. The objective of this work is to explain how, the FAHP model is used in the selection of robotics system. Some technical requirement factors also have been considered for the case study.

Optimisation of supply chain logistics network using random search techniques

Fierce market competition is making companies move from their traditional business strategies towards integrated strategic alliances. In order to integrate and manage their business processes like procurement, inventory, manufacturing, logistics and sales, a new technological and quantitative tool is needed. In this paper, a supply chain logistics network model is developed with the objective of minimising the total cost of production and distribution. The Genetic Algorithm (GA) and Particle Swarm (PS) search techniques are proposed for optimising the supply chain logistics network. The computational results of these algorithms are validated with the results obtained using Excels Solver Optimizer.

Multi-objective optimisation of CNC turning process using grey based fuzzy logic

Computerised numerical control (CNC) machining is one of the most commonly used manufacturing processes. This paper presents the effect of CNC turning parameters on power consumption and material removal rate using grey based fuzzy logic approach. Through this approach, optimisation of complicated multi-objectives can be converted into optimisation of a single grey-fuzzy reasoning grade. Based on grey-fuzzy reasoning grade, optimum level of parameters has been identified. The significant contributions of parameters are estimated using analysis of variance (ANOVA). Confirmation test is conducted for validation and reported.