No abstract

In industrial control processes, proportional-integral-derivative (PID) control algorithm is widely employed. Therefore, it is meaningful to design advanced PID controllers, especially for nonlinear control objects. One of the advanced PID controllers is a cerebellar model articulation controller (CMAC) PID controller. In this controller, the PID control parameters are calculated and tuned. The CMAC achieves a higher accuracy by increasing the number of labels of each weight table; this requires a larger memory, and the generalization ability of the controller decreases. On the other hand, if the CMAC requires less memory, the generalization ability increases and accuracy decreases. Hence, in this paper, a novel CMAC in which the accuracy is compatible with the generalization ability is proposed in this paper. In the proposed CMAC, the number of labels of each weight table can be decided by using a hierarchical clustering technology. Moreover, the efficiency of the memory allocation is improved. The effectiveness of the proposed method is verified by experiments.

No abstract

[abstFig src='/00280005/14.jpg' width='300' text='Feature extraction for excavator operation' ] In recent years, technology that includes informatization and automation has been introduced in the construction field. On the other hand, those field still require human operation technology based on experience and skills because various environmental conditions vary from hour to hour. Seasoned technicians have made such operation technology effective at various sites and established skillful techniques. However, the decreasing number and aging of skilled technicians are a social issue, making the skill tradition and development of younger technicians difficult at operation sites that require skillful techniques. This study assumed that the operation of machines by an operator was synonymous with the control of systems by a controller; human operation techniques were considered from the viewpoint of control engineering by regarding an operator as a controller. The control system used to represent the operator consisted of a proportional-integral-derivative (PID) controller and a cerebellar model articulation controller (CMAC) that adjusted the PID gains. A CMAC which is a type of neural network learns human skills as variations in the PID gains and expresses them based on the variations. This study applies the proposed method to a hydraulic excavator swing operation to evaluate skills. Moreover, the difference in the operation skills for the excavator is clarified by obtaining operation data for skilled and younger technicians and examining the variation tendency of PID gains.

No abstract