Digital Radio Receiver for Adaptive EV Interference Rejection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electric Vehicles (EVs) produce diverse interference signals that degrade or prevent the reception of Digital Audio Broadcasting (DAB) data and audio streams, and existing DAB receivers either use multiple antennas or treat interference as noise without effectively mitigating it.
Innovation Solution
A three-stage AI/ML-based interference rejection system that utilizes Bayesian probability theory and Hidden Markov Models (HMM) to construct, tailor, and continuously fine-tune signal and interference models, incorporating trellis representations and neural networks for rapid adaptation to EV interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing DAB receivers use multiple antennas or treat interference as noise, then the reception system remains simple, but interference mitigation effectiveness is insufficient
Solution Approach 1:
The system performs preliminary training in two stages: off-device training to initialize signal and interference models, and on-device training to refine models using actual received signals. This preliminary modeling of interference characteristics enables effective mitigation without requiring complex real-time processing or multiple antennas
Solution Approach 2:
The system changes parameters by constructing and updating signal and interference models that represent the statistical characteristics of desired signals and EV interference. By continuously adapting model parameters (transition probability matrices, observation likelihoods) based on received signals, the system achieves adaptive interference rejection without increasing hardware complexity
2Adaptability or versatility
If the system rapidly adapts to real-time EV interference conditions, then reception quality is maintained, but computational complexity increases
Solution Approach 1:
The off-device training stage performs preliminary initialization of signal and interference models using domain knowledge and sample data. This pre-computation of model structures and parameters reduces the computational burden during real-time operation, enabling rapid adaptation without excessive computational complexity
Solution Approach 2:
The system implements dynamic model updating through on-device training that continuously refines signal and interference models based on actual received signals. The models adapt dynamically to changing EV interference conditions while maintaining computational efficiency through iterative parameter optimization rather than complete re-computation
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
The present disclosure relates to a digital radio signal receiver, including: wherein the receiver is configured to be coupled to a device; wherein the device is coupled to receive an RF signal; wherein the RF signal includes a desired signal and interference; wherein the receiver is configured to receive a first signal and interference model from an off-device training stage; an on-device training stage configured to construct a second signal and interference model based on the first signal and interference model and the RF signal received by the device; and a decoder configured to generate a set of data from the RF signal based on the second signal and interference model.