Thread Content
Due to the different models of reducers and motors used in chain conveyor systems on various work surfaces, the interfaces available for sensor installation also vary. Therefore, the installation location of the reducer sensor is determined after thorough investigation. Due to the special environment in which the chain conveyor at the working face operates, sensors are inevitably subject to collisions or damage. To prevent sparks generated when the sensors are damaged – particularly when the sensor signal wires and circuits become exposed – from causing an explosion in the explosive gas environment surrounding them, both the power supply for the sensors and the signals transmitted by them must meet intrinsically safe requirements. In other words, the sensor itself should be at least a intrinsically safe sensor, and its power supply must meet the intrinsically safe requirements. http://www.yuyin.sh.cn/images/zwlbssj.jpg Fault diagnosis involves determining the operating condition or any abnormalities of a chain conveyor. It has two meanings: one is to predict and forecast the operating condition of the conveyor equipment before any faults occur in the chain conveyor ； Second, after a device fails, it is necessary to determine the location of the fault, its cause, type, and severity, and to make a decision regarding repairs. Its main tasks include fault detection, identification, evaluation, estimation, and decision-making. Fault diagnosis methods include two main categories: fault diagnosis methods based on mathematical models and fault diagnosis methods based on artificial intelligence. A fault diagnosis method based on neural networks and information fusion techniques is presented, explaining the basic principles of neural networks and information fusion. Meanwhile, examples of fault diagnosis using neural networks and examples using evidence theory are given. Neural networks for chain conveyor systems can be divided into two main categories based on the way neurons are connected: feedback-free feedforward networks and interconnected networks. A feedforward network without feedback consists of an input layer, intermediate layers, and an output layer, where the intermediate layer can be composed of multiple layers; each neuron in these layers can only receive the outputs from the neurons in the layer above it. In a interconnected network, connections can exist between any two neurons; the input signal is transmitted back and forth among the neurons, and after several transformations, the chain conveyor tends to reach a stable state or enters other states such as periodic oscillation.