Neural network models become increasingly popular as dynamic modeling tools in the control community. They have many appealing features including nonlinear structures, being able to approximate any functions. While most researchers hold optimistic attitudes towards such models, this paper questions the capability of (deep) neural networks for the modeling of dynamic systems using input-output data. For the identification of linear time-invariant (LTI) dynamic systems, two representative neural network models, Long Short-Term Memory (LSTM) and Cascade Foward Neural Network (CFNN) are compared to the standard Prediction Error Method (PEM) of system identification. In the comparison, four essential aspects of system identification are considered, then several possible defects and neglected issues of neural network based modeling are pointed out. Detailed simulation studies are performed to verify these defects: for the LTI system, both LSTM and CFNN fail to deliver consistent models even in noise-free cases; and they give worse results than PEM in noisy cases.

翻译：神经网络模型作为控制领域的动态建模工具日益流行。它们具有诸多吸引人的特性，包括非线性结构以及能够逼近任意函数。尽管多数研究者对此类模型持乐观态度，本文却质疑了（深度）神经网络利用输入-输出数据对动态系统进行建模的能力。在线性时不变（LTI）动态系统辨识中，将两种代表性神经网络模型——长短期记忆网络（LSTM）和级联前馈神经网络（CFNN）——与系统辨识的标准预测误差方法（PEM）进行了比较。比较中考虑了系统辨识的四个关键方面，进而指出了基于神经网络的建模中若干可能的缺陷及被忽视的问题。通过详细仿真研究验证了这些缺陷：对于LTI系统，即使在无噪声情况下，LSTM和CFNN均无法提供一致的模型；而在有噪声情况下，它们给出的结果劣于PEM。