Neural Network State Prediction for Wireless Feedback Control Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Prior feedback control systems face challenges in migrating to wireless networks for fast dynamics and high reliability requirements, as wireless networks introduce latency that can lead to performance degradation and instability in control systems, particularly in Class B and C industrial systems.
Innovation Solution
The implementation of a predictive wireless feedback control system using a state prediction neural network that accounts for communication latencies in wireless networks, providing time synchronization and using timestamps to predict future states of the target system, allowing for accurate control signal generation despite latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If wireless networks are used to convey control signals and measurements, then flexibility and mobility are improved, but latency increases leading to performance degradation and instability
Solution Approach 1:
The neural network predicts future states of the target system in advance of when control actions need to be taken. By forecasting system states ahead of time, the controller can compensate for wireless network latency without sacrificing stability or performance
Solution Approach 2:
The neural network acts as an intermediary between the wireless network and the controller. It processes delayed measurements and predictions to generate accurate state estimates that the controller can use, effectively mediating the impact of network latency on control stability
2Adaptability or versatility
If wireless networks are used to convey control signals and measurements, then flexibility and mobility are improved, but latency increases leading to performance degradation
Solution Approach 1:
The neural network performs preliminary prediction of system states before control actions are executed. This advance prediction allows the controller to maintain high performance despite the time delays inherent in wireless communication
Solution Approach 2:
The neural network creates a computational model (copy) of the target system's dynamics. This model replicates system behavior and can be used to predict future states without requiring real-time data, thereby maintaining performance despite wireless latency
3Reliability
If neural network prediction is implemented to compensate for latency, then control system reliability is improved, but device complexity increases
Solution Approach 1:
The patent replaces traditional mechanical timing synchronization with a data-driven neural network prediction system. Instead of relying on precise timing mechanisms, the system uses learned models to predict system states, reducing mechanical complexity while improving reliability
Data Source
AI summary
Example wireless feedback control systems disclosed herein include a receiver to receive a first measurement of a target system via a first wireless link. Disclosed example systems also include a neural network to predict a value of a state of the target system at a future time relative to a prior time associated with the first measurement, the neural network to predict the value of the state of the target system based on the first measurement and a prior sequence of values of a control signal previously generated to control the target system during a time interval between the prior time and the future time, and the neural network to output the predicted value of the state of the target system to a controller. Disclosed example systems further include a transmitter to transmit a new value of the control signal to the target system via a second wireless link.