In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

대부분의 소비자들이 질 좋은 음식을 선호하기 때문에, 농장에서는 소비자들의 욕구를 충족시키기 위해 다양한 시설을 이용하고 있다. 가장 대표적인 시설은 플라스틱 온실과 유리온실이다. 국내의 플라스틱 온실 과 유리 온실의 측고는 3m 내외이다. 결과적으로 작물의 생산성이 제한되고, 이를 해결하기 위해서는 기둥의 높이를 증가시켜 온실의 측고를 높이는 것이다. 온실 기둥상승 장치는 멈춤장치, 공압 실린더 및 수직 부재 등으로 구성된다. 공압 실린더는 안전계수 1.5를 고려하여 직경 160mm와 행정길이 50mm로 설계하였으며, 노즐을 통하여 공기의 압력을 제어하였다. 1행정 시간을 30초 내외로 설계하기 위해서는 21.5L·min-1 공기가 필요한 것으로 나타났다. 따라서 노즐의 직경은 0.5mm로 설계하였다. 압력이 0.9 MPa일 때 평균 인상력은 13,805N으로 계산된 값 15,612N에 근접하였다. 현장 시험결과 같은 열의 기둥과 오차가 발생하지 않았으며, 실제 유리 및 플라스틱 온실에 적용 가능한 것으로 판단되었다

Pneumatic cylinder actuators are significantly utilized for industry automatic systems in the fields of mechanical applications. We propose a novel control method for pneumatic cylinder actuator systems including stochastic friction dynamics. The proposed control mechanism is linearly composed of nominal control and auxiliary control variables. The former is designed from linear system model without friction terms by using a previous linear system theory and the latter is constructed as a function of friction estimation which is carried out by a well-known least square algorithm for reducing the control error due to random friction dynamics. We accomplish numerical simulation to demonstrate reliability of the proposed control method and conduct a comparative study to improve its superiority.