论文部分内容阅读
开发出的神经网络专家系统由神经元网络知识库和推理机组成，特征为：①知识库体现在神经元之间的连结强度（权值）上，采用分布式存储，适于并行处理；②推理机基于神经元的信息处理过程，采用数值计算方法；③神经元网络学习算法成熟；④容错性好。在总结经验、找出规律以解决复杂的多因素影响问题方面，神经网络专家系统有特殊的优点。应用该系统，可解决压裂酸化的选井选层问题和油、气、水层识别及产能预测等问题。以开鲁盆地科尔沁油田庙７块压裂选井选层为例，介绍了该系统的实际应用方法，验证了系统的有效性。图３表１参７（陈志宏摘）
The developed neural network expert system is composed of neural network knowledge base and inference engine. The characteristics of the neural network expert system are as follows: (1) The knowledge base is embodied in the strength (weight) of the connection between the neurons, and is distributed storage and suitable for parallel processing; Reasoning machine based on neuron information processing, using numerical methods; ③ neural network learning algorithm is mature; ④ fault-tolerant. Neural network expert systems have particular advantages in summing up experience and finding laws to solve the complex multi-factor impact issues. The application of this system can solve the problems of fracturing and acidizing well selection and oil layer, oil and gas, water layer identification and production capacity prediction. Taking the 7 fracturing wells in Horqin Oilfield, Kaerqin Oilfield, as an example, the practical application of the system is introduced and the effectiveness of the system is verified. Figure 3 Table 1 Reference 7 (Chen Zhihong)