Tire code and tire state identification method based on machine learning

Abstract

The invention provides a tire code and tire state identification method based on machine learning, comprising the following steps: S1, acquiring a tire image, and preprocessing the image; S2, establishing a single-layer neural network model, and calculating a model output function; S3, based on an error back propagation algorithm, iteratively updating S2, and establishing a multi-layer neural network model which comprises an input layer, a hidden layer and an output layer; S4, establishing a convolutional neural network as a hidden layer in the multi-layer neural network; S5, establishing a full connection layer to connect the hidden layer with the output layer, and outputting the tire code and the tire state of the tire by the output layer; S6, carrying out supervising learning on the multilayer neural network through the artificially marked verification set, and updating neural network parameters; and S7, processing the tire image by using the trained multi-layer neural network to obtain a corresponding tire code and a tire state. According to the method, the tire inspection time is effectively shortened, the identification precision is high, and convenience is provided for automobile safety inspection, accurate tire maintenance, tire leasing service and the like.

Description

technical field [0001] The invention relates to a method for automatically processing tire pictures to identify tire codes and tire states, and belongs to the technical field of automobile safety. Background technique [0002] As a major part of a car, car tires consume a lot in daily travel, and high-quality testing methods are required to provide guarantees in terms of use time, mileage, energy consumption, and use safety. [0003] At present, the use status and safety inspection of automobile tires are mainly carried out by manpower, requiring maintenance personnel to check under the vehicle or disassemble the tires for inspection, which is not only time-consuming and labor-intensive, but also has different accuracy rates for workers with different experience. In addition, manual inspection is difficult to accurately determine the degree of tire wear, remaining service life, etc., and it is impossible to detect potential safety problems in time, temporary emergencies such...

AI Technical Summary

Problems solved by technology

[0004] In view of the time-consuming and labor-intensive and poor timeliness of manual inspection of tire conditions at present, the present invention proposes a tire code and tire status recognition method based on machine learning, constructs a multi-layer neural network to automatically identify tire tire codes and tire status, and utilizes manual processing The verification set trains the neural network, improves the recognition accuracy of the neural network, and realizes fully automatic, real-time and accurate tire information recognition

Images