Search

Machine learning has been widely used in diagnosing system faults as an integration part in modern intelligent manufacturing. However, sensor selection and index for machine tools are versatile and not standardized at this moment for manufacturing equipment. Without supporting of appropriate domain knowledge for selecting appropriate sensors and adequate performance index, pure data-driven approach might suffer from unsatisfied prediction accuracy and needing of excessive training data, as well as the possibility of misjudgment. As a result, a thoughtful flow for identifying key sensor index and to evaluate its impact on the performance of subsequent machine learning scheme would be essential. In this work, the status monitoring and prediction of a milling cutter wear problem is investigated as an example to address the above concerns and to demonstrate the possible solutions by hiring a 5-axis machine center equipped with milling cutters of different wear levels. In parallel, the well-used multilayer perception (MLP) artificial neural network (ANN) models are also used to elucidate the importance of the problem. Transducers including accelerometers, microphones, current transformer, and acoustic emission sensors are mounted on the spindle, fixture, and nearby structures to monitor the milling process. The collected data are processed to extract various signatures. A procedure is developed to evaluate the sensitivity of each index and the key dominated indexes are eventually identified. To elucidate the importance of proper sensor index selection, three MLP ANN models are established based on different sensor features to examine the influence of selected sensors indexes on the prediction accuracy. The results show that with appropriate sensors signatures, even with less amount of experimental data, the model can indeed achieve a better prediction (98.7%) in comparison with that without proper sensor index selection (90.3). This implies that a rigorous process for identifying key feature is essential for system diagnosis in future intelligent manufacturing. [ABSTRACT FROM AUTHOR]

In the machining process, the machining performance which mainly refers to machined surface quality and cutting forces is hard to predict under different tool wear status. In this work, an improved case-based reasoning (ICBR) method is proposed to predict both the cutting force and machined surface roughness. With the emergence of new problem, ICBR method obtains solutions to new problem through case retrieval and reuse. In case retrieval stage, K similar cases to the new problem were retrieved using K nearest neighbor method. By means of the K similar cases, support vector regression machine (SVR) model was established to give the solution of the new problem in case of the reuse stage of ICBR method. Artificial neural network (ANN) was introduced to estimate the influence of machining parameters and tool wear on machining performance. As the ANN and SVR models contain unknown parameters, the novel particle swarm optimization algorithm was proposed to train these models for its capability of fast convergence and global optimum. The proposed ICBR method was used to predict the surface roughness and cutting force. The results showed the proposed ICBR method can give superior prediction accuracy and lower Mean square error than other popular intelligent models. Meantime, the ICBR method possesses good robustness and can be used for the actual machining process. [ABSTRACT FROM AUTHOR]