TDNN and LLM fused lithium battery electrolyte ultrasonic quantitative detection method

By integrating TDNN and LLM methods, a highly sensitive sensing and robust processing of lithium-ion battery electrolyte content was achieved, solving the problems of insensitivity to minute changes and uneven wetting in existing technologies, making it suitable for industrial online detection.

CN121725918APending Publication Date: 2026-03-24BEIJING UNIV OF TECH +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202511806257.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-03
Publication Date
2026-03-24

AI Technical Summary

Technical Problem

Existing quantitative detection methods for lithium-ion battery electrolytes are insensitive to minute changes, cannot effectively handle uneven wetting, have poor model generalization ability, and are complex to deploy, making them difficult to apply on a large scale in industrial fields.

Method used

By employing a method that integrates TDNN and LLM, high-dimensional deep features are extracted from the original ultrasonic wave pattern through the time-delay neural network TDNN, and the semantic reasoning ability of the large language model LLM is combined with physical correction using the immersion area ratio, thereby achieving high-sensitivity perception and robust processing of electrolyte content.

Benefits of technology

It improves the ability to detect minute changes in the electrolyte, enhances the predictive reliability and physical rationality of the model under non-uniform wetting conditions, simplifies the detection process, and facilitates online industrial applications.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a TDNN and LLM fused lithium battery electrolyte ultrasonic quantitative detection method, and relates to the field of lithium ion battery health management, and the method comprises the steps: obtaining original ultrasonic waveform data, and carrying out the preprocessing; based on a pre-trained time delay neural network TDNN, extracting a high-dimensional depth feature vector; mapping to a text embedding space of a large language model LLM through a linear projection layer, generating a text prototype and constructing a complete prompt sequence; reasoning to obtain an electrolyte content predicted value based on a pre-trained large language model LLM; calculating a global estimated value, and carrying out physical correction on the global estimated value by utilizing the infiltration area ratio to obtain the corrected electrolyte content; and outputting the corrected electrolyte content and the two-dimensional distribution diagram of the electrolyte in the battery. According to the method, deep features of ultrasonic signals are learned through a cascade architecture of TDNN and LLM, reasoning is carried out, physical correction is supplemented, and high-sensitivity and reliable quantitative detection of the content of the lithium battery electrolyte is achieved.
Need to check novelty before this filing date? Find Prior Art