基于神经网络专家系统的钻井事故诊断

结合石油钻井工程的实际情况，依据钻井过程的监测参数，设计了利用神经网络进行知识获取、专家系统进行事故诊断的钻井工程事故智能诊断系统。通过神经网络对钻井复杂问题实例的不断学习训练，获得用于智能诊断的知识，完成对事故发生可能性的初步诊断。经过专家系统的进一步启发式反向推理验证事故是否存在，给出最后确诊，以此监控钻井参数，指导钻井参数调整的实施。应用实例结果表明，该智能诊断系统应用于钻井事故诊断是有效的，对减少钻井事故的发生与发展具有重大的实际应用价值。

Application of neural network-based expert system in drilling fault diagnosis

Combining the practical conditions and the drilling variables, the drilling fault diagnosis system utilizing the Artificial Neural Network (ANN) to obtain the knowledge and the expert system to reason and diagnose the faults was designed. The knowledge was acquired through constantly learning and training the ANN with varieties of the intricate drilling problems. The definite diagnosis results can be drawn by the reverse reasoning of the expert system. According to the results the drilling parameters will be adjusted automotively. The drilling fault diagnosis system has proved to be practical and effective by the living examples.