Search

Process planning and scheduling are two major sub-systems in a modern manufacturing system. In traditional manufacturing system, they were regarded as the separate tasks to perform sequentially. However, considering their complementarity, integrating process planning and scheduling can further improve the performance of a manufacturing system. Meanwhile, the multiple objectives are needed to be considered during the realistic decision-making process in a manufacturing system. Based on the above requirements from the real manufacturing system, developing effective methods to deal with the multi-objective integrated process planning and scheduling (MOIPPS) problem becomes more and more important. Therefore, this research proposes a multi-objective genetic algorithm based on immune principle and external archive (MOGA-IE) to solve the MOIPPS problem. In MOGA-IE, the fast non-dominated sorting approach used in NSGA-II is utilized as the fitness assignment scheme and the immune principle is exploited to maintain the diversity of the population and prevent the premature condition. Moreover, the external archive is employed to store and maintain the Pareto solutions during the evolutionary process. Effective genetic operators are also designed for MOIPPS. To test the performance of the proposed algorithm, three different scale instances have been employed. And the proposed method is also compared with other previous algorithms in literature. The results show that the proposed algorithm has achieved good improvement and outperforms the other algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a new method for on-line monitoring discharge pulse in wire electrical discharge machining-middle speed (WEDM-MS) process based on digital image processing and machine learning. Discharge pulse monitoring is a key aspect of the WEDM-MS control system, as it directly guides the direction and the speed of the machining. In the proposed system, the discharge pulse is captured using a high-bandwidth oscilloscope because the shortest period of discharge is less than 40 ms. The proposed system workflow consists of image reconstruction, pre-processing, feature extraction, and pulse classification. Wavelet moment analysis (WMA), Hu moment analysis (HMA), fractal dimension analysis (FDA), local geometric characteristics (LGC), and global geometric characteristics (GGC) are all applied in the image pre-processing to extract waveform image features and reduce image dimension. These features are then used in a two-stage classification technique that employs support vector machine (SVM) and random forests (RF) for pulse classification and identification. The first stage method, which uses SVM, discriminates between open circuit, short circuit, and mixed status pulses, while the second stage method, which uses RF, divides the mixed status pulse into spark, transition arc, and arc pulse. In test experiments conducted under different electrical parameters and with different materials, the WEDM-MS discharge pulse monitoring systems were successfully employed with an accuracy of 93.13 %. The proposed SVM-RF approach outperforms learning vector quantization (LVQ) neural network, SVM, or RF discharge pulse WEDM discrimination methods. [ABSTRACT FROM AUTHOR]

In the modern manufacturing system, many flexible manufacturing system and NC machines are introduced to improve the production efficiency. Therefore, most parts have a large number of flexible process plans. However, a part can use only one process plan in the manufacturing process. So, the process planning problem has become a crucial problem in the manufacturing environment. It is a combinatorial optimization problem to conduct operations selection and operations sequencing simultaneously with various constraints deriving from the practical workshop environment as well as the parts to be processed. It is a NP-hard problem. In order to solve this problem effectively, this paper proposes a novel modified particle swarm optimization (PSO) algorithm to optimize the process planning problem. To improve the performance of the approach, efficient encoding, updating, and random search methods have been developed. To verify the feasibility and effectiveness of the proposed approach, seven cases have been conducted. The proposed algorithm has also been compared with the genetic algorithm and simulated annealing algorithm. The results show that the proposed modified PSO algorithm can generate satisfactory solutions and outperform other algorithms. [ABSTRACT FROM AUTHOR]