Generative adversarial network for optimization of operational parameters based on shield posture requirements

To mitigate the potential hazards of shield tunneling misalignment (STM) caused by tunneling posture deviation, a method for optimizing operational parameters tailored to tunneling posture adjustment is developed. This paper presents a generative adversarial network (GAN) framework that incorporate a conditional generative adversarial network (CGAN) and two distinct discriminators (WGAN and Path GAN) to enhance the performance of the multi operational parameter generator. Based on engineering data, comparative experiments are designed to investigate the impact of the feature extraction methods, discriminators, and training strategies on the generation performance. Research has shown that an optimal generator scheme, comprising independent convolutional neural networks (CNNs), a summation feature fusion strategy, and a shared decoder, achieves remarkable performance with an MAE of 0.009, RMSE of 0.012, and average error scope of 0.073. Applications of the model confirm its ability to provide optimization suggestions for shield tunneling posture adjustments in engineering scenarios. •A new method for adjusting the operational parameters of the shield is proposed.•The method has been validated through the data collected from the railway.•Obtained a multi-parameter generator with high accuracy.•The influence of different factors on the performance of the generator are analyzed.