Active Shock Absorber Control Based on Time-Delay Neural Network

Abstract

A controlled suspension usually consists of a high-level and a low-level controller. The purpose the high-level controller is to analyze external data on vehicle conditions and make decisions on the required value of the force on the shock absorber rod, while the purpose of the low-level controller is to ensure the implementation of the desired force value by controlling the actuators. Many works have focused on the design of high-level controllers of active suspensions, in which it is considered that the shock absorber can instantly and absolutely accurately implement a given control input. However, active shock absorbers are complex systems that have hysteresis. In addition, electro-pneumatic and hydraulic elements are often used in the design, which have a long response time and often low accuracy. The application of methods of control theory in such systems is often difficult due to the complexity of constructing their mathematical models. In this article, the authors propose an effective low-level controller for an active shock absorber based on a time-delay neural network. Neural networks in this case show good learning ability. The low-level controller is implemented in a simplified suspension model and the simulation results are presented for a number of typical cases.Energies 2020, 13, 1091 2 of 16 of a semi-active shock absorber lies in I and III quadrants; thus, the force vector F is always in one direction with the velocity vector v.Energies 2020, 13, 1091 2 of 15In an active shock absorber, the set of dissipative characteristics cover all IV quadrants due to an external energy source, and force and velocity vectors can be oppositely directed. This property is the great advantage of active shock absorbers, and it allows, in theory, the achievement of a complete absence of movement of the vehicle body for the given planes.

Feedforward Compensation Analysis of Piezoelectric Actuators Using Artificial Neural Networks with Conventional PID Controller and Single-Neuron PID Based on Hebb Learning Rules

“…A common approach of ANN black-box identification is with non-linear auto-regressive networks (NARX) [16]. In this research, an alternative NARX framework was used for prediction, which is a time delay ANN (TDNN) [17,18] where the inputs are added as specified delays for prediction. Even though this approach might reduce the ANN performance but still, the architecture complexity can be simpler and the self-learning ability is sufficiently powerful.…”

Using Neural Networks by Modelling Semi-Active Shock Absorber

“…To ensure an efficient way for providing training samples to the agent, the training environment can be built based on a digital twin with NN [11]. Although it is possible to use a NN for the controller design directly [12], an advanced approach can include elements of an autonomous self-learning control system [13]. In this way, the system behavior of the shock absorber can de facto be emulated offline.…”

“…The table outlining the test program is given in Appendix. After recording the data, a scaling ( 5) is performed to transfer all the variables to a range of values of W = [0, 1], following the approach from [12]. This step is required to ensure a more stable training of the model [14].…”

High-Performance Tracking for Piezoelectric Actuators Using Super-Twisting Algorithm Based on Artificial Neural Networks

“…Thus, these properties based on the mathematical formulation can lead the ability to perform approximations of nonlinear dynamic systems [79,80]. Recently, these type of system identification technique was implemented, like Time Delay Neural Network (TDNN), which has shown good results in fitting performance [81,82].…”