Automobile tire quality detection method and system based on infrared and deep learning technology

Through the automotive tire quality detection method based on infrared and deep learning technology, using infrared thermal imaging and surface imaging images to recognize features, the problem of subjectivity and low efficiency of the existing detection methods is solved, and intelligence is achieved under different temperatures and pressures Quality inspection improves inspection efficiency and accuracy.

CN118730580BActive Publication Date: 2024-11-08Hankook Tire Co., Ltd.
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411227010.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-08
Estimated Expiration
2044-09-03

AI Technical Summary

Technical Problem

The existing automotive tire quality inspection methods rely on manual inspection, which has problems of subjectivity and low efficiency. The traditional equipment is costly and cannot be dynamically simulated and tested under different temperatures and pressures, and cannot effectively evaluate the heat resistance of tires when driving at high speeds. and application.

Method used

Using detection methods based on infrared and deep learning technology, by acquiring infrared thermal imaging images and surface imaging images of tires under different temperatures and pressures, the preset tire quality detection model is used to identify the thermal imaging temperature distribution characteristics and surface image characteristics, and calculate the The proportion is determined to determine whether the tire is qualified or unqualified, and unmanned intelligent quality inspection is achieved.

Benefits of technology

Unmanned intelligent quality inspection is realized, the detection efficiency and accuracy are improved, and simulation inspection can be carried out under different temperatures and pressures. The heat resistance and application of tire surface quality are comprehensively considered, reducing labor costs and subjective deviations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118730580B_ABST
    Figure CN118730580B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for automobile tire quality inspection based on infrared and deep learning technology. The method collects images of tires through the industrial Internet of Things, performs image recognition in the background, and uses an intelligent model to identify infrared thermal imaging image features and surface image features in the image, so as to perform statistical judgment on the corresponding features. It can realize unmanned intelligent quality inspection operation throughout the process, does not need to rely on the experience and attention of quality inspectors, and saves labor costs; at the same time, it can allow the system to objectively inspect each tire according to a unified standard to avoid detection deviations caused by subjectivity. It can adapt to surface quality inspection of large-scale tire production and tire application, and greatly improves detection efficiency compared to manual inspection. Simulation inspection is carried out under different temperatures and pressures, and surface thermal imaging inspection is carried out on tires to detect the surface heat resistance and applicability of the tires, so as to further improve the high-performance inspection quality of tire surface inspection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of detection technology, and in particular to a vehicle tire quality detection method based on infrared and deep learning technology, a vehicle tire quality detection system based on infrared and deep learning technology, an electronic device, and a computer-readable storage medium. Background Art

[0002] In daily automobile tire production and subsequent applications, it is necessary to conduct real-time inspections on the application quality of tires to determine whether the tire quality meets application requirements and whether the application quality is qualified.

[0003] The necessity of tire quality testing is to ensure driving safety, extend tire service life, and reduce traffic accidents caused by tire problems.

[0004] Tire surface quality inspection usually includes visual inspection, tactile inspection and inspection using special inspection equipment. Visual inspection mainly relies on manual inspection to check whether there are defects such as cracks, bubbles, and foreign objects embedded on the tire surface. Tactile inspection is to feel irregular wear or bulges by touching the tire surface. Specialized inspection equipment such as laser scanners and optical inspection systems can detect tiny defects on the tire surface more accurately.

[0005] However, these detection methods also have some disadvantages. The main detection defects are as follows:

[0006] 1. Visual inspection and tactile inspection rely on the operator's experience and attention, and are easily affected by fatigue and subjective judgment, resulting in inconsistent test results. Moreover, the test requires a certain cost and requires the tester to have good professional quality and experience. Therefore, the test results are subjective and cannot provide objective test standards. Moreover, the test efficiency is low due to the manual test method, which is difficult to meet the needs of large-scale production.

[0007] 2. During the inspection process, the use of specialized inspection equipment improves the accuracy and efficiency of inspection, but the equipment is expensive, requires regular maintenance and calibration, and may still not be sensitive enough to some minor defects;

[0008] 3. Traditional testing is a static test, which is to test the tire in a static environment. It is unable to test the practicality of the tire under different temperatures and pressures, and lacks dynamic simulation testing. Especially for newly produced tires, dynamic simulation testing of their practicality is needed under different temperature and pressure environments to judge their practicality, so as to make up for the shortcomings of conventional testing.

[0009] 4. When the tire is running at high speed, due to friction and compression, its surface temperature will rise significantly, and this high temperature may cause the following defects: Rubber aging: High temperature will accelerate the oxidation process of tire rubber, causing rubber aging and reducing the elasticity and strength of the tire; Structural damage: The internal structure of the tire may change at high temperature, such as cord relaxation or breakage, which will weaken the tire's load-bearing capacity and stability; Abnormal air pressure: High temperature will cause the gas inside the tire to expand, and if the air pressure is too high, it may cause the tire to burst; Tread wear: High temperature softens the tread rubber, causing faster wear and reducing the service life of the tire; Tread peeling: Under extreme high temperatures, the adhesion between the tread and the carcass may fail, causing the tread to peel. However, existing tests do not take into account the test of tire surface heat resistance and applicability at high temperatures. Summary of the invention

[0010] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0011] On the one hand, a method for detecting the quality of automobile tires based on infrared and deep learning technology is provided, the method being implemented by an electronic device, and the method comprising:

[0012] S1. Obtaining infrared thermal imaging images and surface camera images of the tire to be tested in different temperature and pressure testing environments of a tire quality inspection center;

[0013] S2, performing image cutting processing on the surface infrared thermal imaging image and the surface camera image to generate a first image set consisting of a plurality of infrared thermal imaging slices and a second image set consisting of a plurality of surface camera slices;

[0014] S3, traversing the first image set, randomly extracting a number of groups of the infrared thermal imaging slices and importing them into a preset tire quality detection model, and identifying and outputting the thermal imaging temperature distribution features in the infrared thermal imaging slices through the tire quality detection model;

[0015] S4, traversing the second image set, randomly extracting a plurality of groups of the surface camera slices and importing them into a preset tire quality detection model, and identifying and outputting surface image features in the surface camera slices through the tire quality detection model;

[0016] S5. Count the number T1 of the thermal imaging temperature distribution features that do not meet the tire quality inspection rules and the number T2 of the surface image features that do not meet the tire quality inspection rules, and calculate and output the corresponding proportions: ρ=(T1+T2) / W, where ρ is the proportion, W is the total number of samples and W≥500;

[0017] S6. Unqualified judgment:

[0018] If T1 / W ≥ A% or T2 / W ≥ B% or ρ ≥ C%, the tire to be tested is judged as unqualified; A, B, and C are all percentage thresholds greater than 0 pre-set by the system, with a value range of 0 to 0.5;

[0019] Otherwise qualified;

[0020] The judgment result is fed back to the testing terminal of the tire quality inspection center.

[0021] As a preferred embodiment of the present invention, preferably, in step S1, the step of obtaining the infrared thermal imaging image of the surface of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes:

[0022] The tire quality inspection center adjusts the inspection environment with different temperatures and pressures in sequence, and informs the background server of the adjustment result of the inspection environment through the inspection terminal;

[0023] After receiving the adjustment result of the detection environment, the backend server generates a first sampling instruction, and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway;

[0024] The first sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the first sampling instruction to control the infrared thermal imager to collect the infrared thermal imaging image of the surface of the tire to be inspected;

[0025] According to the above steps, the surface infrared thermal imaging images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface infrared thermal imaging images are uploaded to the backend server through the industrial gateway.

[0026] As a preferred embodiment of the present invention, preferably, in step S1, the step of obtaining the surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes:

[0027] After the backend server generates a first sampling instruction and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway, a second sampling instruction is generated at an interval of 0.5 to 1.5 ms and the second sampling instruction is forwarded to the tire quality inspection center through the industrial gateway;

[0028] The second sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the second sampling instruction to control the 3D camera to collect a surface camera image of the tire to be inspected;

[0029] According to the above steps, the surface camera images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface camera images are uploaded to the backend server through the industrial gateway.

[0030] As a preferred embodiment of the present invention, preferably, before step S1, the method further comprises:

[0031] Scan the QR code of the tire to be tested by the infrared scanner of the tire quality inspection center, obtain the identity information of the tire to be tested, and upload it to the backend server through the industrial gateway;

[0032] The backend server creates a quality inspection file of the tire to be inspected in the tire management module according to the identity information of the tire to be inspected and saves it in the backend database;

[0033] The quality inspection file is used to record: the surface infrared thermal imaging image and surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center and the judgment results thereof.

[0034] As a preferred embodiment of the present invention, preferably, the method for generating the tire quality detection model comprises:

[0035] Prepare a surface infrared thermal imaging image set and a surface camera image set of several unqualified tires;

[0036] Performing feature engineering on the surface infrared thermal imaging image set to construct a thermal imaging temperature distribution feature set including temperature hot spots, temperature gradients, and temperature distribution patterns;

[0037] Performing feature engineering on the surface camera image set to construct a surface image feature set containing different surface defect types;

[0038] Adding unqualified labels to each feature element in the thermal imaging temperature distribution feature set and the surface image feature set to construct a training data set;

[0039] Prepare the convolutional neural network model and adjust the model parameters;

[0040] The thermal imaging temperature distribution features and surface image features in the training data set are randomly put into the convolutional neural network model for training and learning to generate an initial quality inspection model;

[0041] Preparing surface infrared thermal imaging images and surface camera images for verification, and importing the initial quality inspection model, and cross-validating the detection performance of the initial quality inspection model;

[0042] If the verification is successful, the tire quality detection model is obtained, and the tire quality detection model is deployed on the background server.

[0043] As a preferred embodiment of the present invention, preferably, the step of preparing a set of surface infrared thermal imaging images and a set of surface camera images of a plurality of unqualified tires comprises:

[0044] Reading the historical quality inspection files of each tire from the background database of the background server;

[0045] Screening out the historical quality inspection files of unqualified tires from the historical quality inspection files of each tire;

[0046] From the historical quality inspection files of unqualified tires, surface infrared thermal imaging images and surface camera images of unqualified tires in different temperature and pressure testing environments are read respectively, and corresponding surface infrared thermal imaging image sets and surface camera image sets are constructed.

[0047] On the other hand, a car tire quality detection system based on infrared and deep learning technology is provided, and the car tire quality detection system based on infrared and deep learning technology is used to implement the above-mentioned car tire quality detection method based on infrared and deep learning technology. The system includes a tire quality inspection center, an industrial gateway and a background server, wherein:

[0048] The tire quality inspection center is used to collect infrared thermal imaging images and surface camera images of the tire to be inspected in different temperature and pressure inspection environments and upload them to the backend server, as well as the QR code of the tire to be inspected and upload them to the backend server;

[0049] An industrial gateway is used to provide data communication services between the tire quality inspection center and the backend server;

[0050] The backend server is used to record the collected information of the tire to be tested, and make a non-conforming judgment on the tire to be tested based on the surface infrared thermal imaging image and the surface camera image, and feed back the judgment result to the tire quality inspection center;

[0051] The tire quality inspection center and the backend server are respectively connected to the industrial gateway for communication.

[0052] As a preferred embodiment of the present invention, preferably, the tire quality inspection center comprises:

[0053] Controller;

[0054] Infrared barcode scanner, used to scan the QR code of the tire to be tested to obtain the identity information of the tire to be tested;

[0055] Infrared thermal imager, used to collect infrared thermal imaging images of the surface of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center;

[0056] 3D camera, used to collect surface images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center;

[0057] A communication module, used for communicating with the industrial gateway;

[0058] A detection terminal, used to display the judgment result of the tire to be detected, and send a corresponding detection instruction to the backend server;

[0059] The infrared scanner, infrared thermal imager, 3D camera and communication module are electrically connected to the controller respectively, the communication module is connected to the industrial gateway for communication, and the detection terminal is connected to the background server for communication:

[0060] The backend server comprises:

[0061] The tire management module is used to create the quality inspection file of the tire to be tested and write the judgment result of the tire to be tested;

[0062] A tire quality inspection model is used to identify and output thermal imaging temperature distribution characteristics and surface image characteristics of the tire to be inspected;

[0063] The quality inspection and evaluation module is used to judge the unqualified tires to be inspected and output the judgment results;

[0064] Backend database, used for data storage;

[0065] The tire management module and the tire quality detection model are respectively connected to the background database in communication; the quality inspection and evaluation module is connected to the tire quality detection model in communication.

[0066] On the other hand, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned methods for automobile tire quality detection based on infrared and deep learning technologies is implemented.

[0067] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned automobile tire quality detection methods based on infrared and deep learning technology.

[0068] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0069] Based on the implementation of the present invention, the present invention collects images of the tire through the industrial Internet of Things, and performs image recognition in the background, and uses an intelligent model to identify the infrared thermal imaging image features and surface image features in the image, so as to make statistical judgments on the corresponding features and perform quality control inspection on the tire. It can realize unmanned intelligent quality inspection operation throughout the process, without relying on the experience and attention of quality inspectors, saving labor costs; at the same time, it can enable the system to objectively inspect each tire according to unified standards, avoiding detection deviations caused by subjectivity.

[0070] The intelligent automated quality inspection system of this solution can adapt to surface quality inspection of large-scale tire production and tire applications. Compared with manual inspection, it can greatly improve inspection efficiency and tire productivity.

[0071] The present invention can also perform simulated testing at different temperatures and pressures, perform surface thermal imaging testing on tires, and determine whether the surface thermal imaging images at different temperatures and pressures show corresponding unqualified defect characteristics, so as to detect the surface heat resistance and applicability of the tire. By detecting surface defects and infrared thermal imaging features, the surface quality application requirements of the tire can be comprehensively considered, and the high-performance detection quality of the tire surface detection can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0073] Figure 1 This is a flow chart of a method for detecting automobile tire quality based on infrared and deep learning technology provided by an embodiment of the present invention;

[0074] Figure 2 This is an application block diagram of an automobile tire quality detection system based on infrared and deep learning technology provided by an embodiment of the present invention;

[0075] Figure 3 It is an application block diagram of another automobile tire quality detection system based on infrared and deep learning technology provided by an embodiment of the present invention;

[0076] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0077] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0078] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0079] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0080] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0081] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments. Example 1

[0082] The embodiment of the present invention provides a method for detecting the quality of automobile tires based on infrared and deep learning technology. The method can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the automobile tire quality detection method based on infrared and deep learning technology is shown in the figure. The processing flow of the method may include the following steps:

[0083] S1. Obtaining infrared thermal imaging images and surface camera images of the tire to be tested in different temperature and pressure testing environments of a tire quality inspection center;

[0084] S2, performing image cutting processing on the surface infrared thermal imaging image and the surface camera image to generate a first image set consisting of a plurality of infrared thermal imaging slices and a second image set consisting of a plurality of surface camera slices;

[0085] S3, traversing the first image set, randomly extracting a number of groups of the infrared thermal imaging slices and importing them into a preset tire quality detection model, and identifying and outputting the thermal imaging temperature distribution features in the infrared thermal imaging slices through the tire quality detection model;

[0086] S4, traversing the second image set, randomly extracting a plurality of groups of the surface camera slices and importing them into a preset tire quality detection model, and identifying and outputting surface image features in the surface camera slices through the tire quality detection model;

[0087] S5. Count the number T1 of the thermal imaging temperature distribution features that do not meet the tire quality inspection rules and the number T2 of the surface image features that do not meet the tire quality inspection rules, and calculate and output the corresponding proportions: ρ=(T1+T2) / W, where ρ is the proportion, W is the total number of samples and W≥500;

[0088] S6. Unqualified judgment:

[0089] If T1 / W ≥ A% or T2 / W ≥ B% or ρ ≥ C%, the tire to be tested is judged as unqualified; A, B, and C are all percentage thresholds greater than 0 pre-set by the system, with a value range of 0 to 0.5, otherwise it is qualified;

[0090] The judgment result is fed back to the testing terminal of the tire quality inspection center.

[0091] The present invention collects images of tires through the industrial Internet of Things, performs image recognition in the background, and uses an intelligent model to identify infrared thermal imaging image features and surface image features in the image, so as to make statistical judgments on the corresponding features and perform quality control inspection on the tires.

[0092] like Figure 2 and Figure 3 The schematic diagram of the quality inspection system of the present invention is shown.

[0093] The tire quality inspection center can be configured with testing environments corresponding to different temperatures and pressures, so that the tires to be tested can be simulated tested in different testing environments, and the various image acquisition devices deployed in the tire quality inspection center can respectively collect infrared thermal imaging images (infrared thermal imaging images) and surface camera images (surface images) of the tire surface.

[0094] The deployment of the specific testing environment can be completed by the administrator in the tire quality inspection center to build the corresponding tire simulation driving environment (because the tire will be subjected to pressure and high temperature during driving, which will affect the performance of the tire).

[0095] Therefore, the images of the tires under different testing environments are simulated and image recognition is performed to determine whether the tires have unqualified image features under the corresponding testing environments. If the model detection finds unqualified image features (for example, the thermal imaging temperature gradient value is too small or too large, or there are spots, pits and other defects on the surface), the tires are deemed unqualified.

[0096] The tire quality inspection center is equipped with infrared scanners, infrared thermal imagers, and 3D cameras that are controlled by controllers. The infrared scanner can scan the QR code on the tire to be inspected to obtain its identity information, such as its serial number, etc., and the controller (after formatting) uploads it to the industrial gateway through the communication module (5G module), and then uploads it to the backend server by the industrial gateway. The backend server builds the quality inspection file of the current tire to be inspected to record its quality inspection information.

[0097] Infrared thermal imagers can be used to collect thermal imaging images of the tire surface, and 3D cameras can collect 3D images of the tire surface, which are also uploaded to the backend server by the industrial gateway.

[0098] A tire quality inspection model is pre-trained and deployed on the background server, which can perform image recognition and detection on the thermal imaging temperature features in the collected thermal imaging images and the surface defect features in the surface camera images, and output the corresponding identification features. On the background server, quality assessment is performed based on the identified features, and the corresponding tire quality inspection results are output.

[0099] The backend server sends the tire quality inspection results, that is, the judgment results, to the inspection terminal of the tire quality inspection center, allowing the administrator to check whether the current tire surface quality inspection is qualified.

[0100] The testing terminal of the tire quality inspection center allows the administrator to perform quality inspection management and operations, view the current test results of each tire, and communicate with the background server through the testing terminal according to needs, issue corresponding quality inspection requests or instructions, etc., or request to view the corresponding quality inspection files.

[0101] The installation and deployment of various electronic equipment in the specific tire quality inspection center can be carried out according to the on-site quality inspection needs, habits or convenience.

[0102] The detection terminal can be a PC or other mobile terminal, etc.

[0103] As for the communication mode between the background server and the detection terminal, corresponding networking configuration can be carried out according to needs, such as 5G communication, etc.

[0104] The selection of industrial gateways and the communication configuration of the backend through the industrial gateway and the communication module of the tire quality inspection center for routing communication also connect to the network based on the selected and supported communication protocols and communication modes.

[0105] Each step will be described in detail below.

[0106] As a preferred embodiment of the present invention, preferably, in step S1, the step of obtaining the infrared thermal imaging image of the surface of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes:

[0107] The tire quality inspection center adjusts the inspection environment with different temperatures and pressures in sequence, and informs the background server of the adjustment result of the inspection environment through the inspection terminal;

[0108] After receiving the adjustment result of the detection environment, the backend server generates a first sampling instruction, and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway;

[0109] The first sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the first sampling instruction to control the infrared thermal imager to collect the infrared thermal imaging image of the surface of the tire to be inspected;

[0110] According to the above steps, the surface infrared thermal imaging images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface infrared thermal imaging images are uploaded to the backend server through the industrial gateway.

[0111] After the tire to be tested is fixed in the tire quality inspection center and the administrator has adjusted the testing environment, the administrator can send a corresponding notification to the background server through the testing terminal to inform the background server that the current testing environment has been adjusted. The background server starts to send the first sampling instruction, which is sent to the communication module of the tire quality inspection center through the industrial gateway, and is received and forwarded to the controller. The controller controls the infrared thermal imager to work and collect the corresponding thermal imaging images.

[0112] like Figure 2 As shown, to collect thermal imaging images, the tire quality inspection center can use the automatic control device (quality inspection equipment configured by the center) to make the tire to be inspected perform corresponding actions, such as angle rotation, coaxial rotation, etc., to collect images of the left and right sides of the tire. At the same time, a transmission shaft can be added to it to rotate the tire, simulate driving, and collect more realistic thermal imaging tire application images.

[0113] When collecting data, it is necessary to collect data under different testing environments. Therefore, the tire quality inspection center can automatically adjust the testing environment of corresponding pressure (pressure system) and temperature (temperature control system), and after adjustment, inform the background server to collect images.

[0114] By using the above method and steps, infrared thermal imaging images of the tire surface under different detection environments can be obtained. The background uses the model to perform infrared image feature recognition and extraction on the infrared imaging images under different detection environments, and judge whether the infrared temperature distribution pattern, temperature hot spots, temperature gradient and other thermal imaging temperature distribution features presented on the tire surface under various temperatures and pressures are preset unqualified features, so as to perform feature recognition and output. The background server can make qualified and unqualified judgments based on this when conducting quality inspection and evaluation.

[0115] As a preferred embodiment of the present invention, preferably, in step S1, the step of obtaining the surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes:

[0116] After the backend server generates a first sampling instruction and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway, a second sampling instruction is generated at an interval of 0.5 to 1.5 ms and the second sampling instruction is forwarded to the tire quality inspection center through the industrial gateway;

[0117] The second sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the second sampling instruction to control the 3D camera to collect a surface camera image of the tire to be inspected;

[0118] According to the above steps, the surface camera images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface camera images are uploaded to the backend server through the industrial gateway.

[0119] In order to avoid image processing pressure on the background, sampling is performed at intervals. The 3D camera sampling is controlled at intervals of 0.5~1.5ms. Similarly, the images sampled by the 3D camera are uploaded to the background for image recognition to identify whether there are surface defect features on the image, such as spots, missing blocks, etc. For details, please refer to the above thermal imaging image acquisition and processing process.

[0120] In order to record the sampling and quality inspection information of each tire to be tested, this department has set up a method of scanning codes to obtain identity information, and the background will build a quality inspection file based on the identity information of the tire to be tested reported by the center to record the data during the quality inspection process, so as to facilitate the storage of quality inspection big data in the background database, facilitate the administrator to inspect the quality inspection results and form a historical quality inspection file of the tire (for model training).

[0121] like Figure 3 As shown, as a preferred embodiment of the present invention, preferably, before step S1, it also includes:

[0122] Scan the QR code of the tire to be tested by the infrared scanner of the tire quality inspection center, obtain the identity information of the tire to be tested, and upload it to the backend server through the industrial gateway;

[0123] The backend server creates a quality inspection file of the tire to be inspected in the tire management module according to the identity information of the tire to be inspected and saves it in the backend database;

[0124] The quality inspection file is used to record: the surface infrared thermal imaging image and surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center and the judgment results thereof.

[0125] Scan the QR code to collect the tire's identity information, which usually includes key data such as the tire model, production date, batch number (similar to identity ID), size, etc. Then, create an electronic archive system to store and manage this information. Next, assign each tire a unique identification code (which can be a batch number), which can be a barcode or QR code for easy tracking and retrieval. Associate the collected information with the identification code and enter it into the electronic archive system. Ensure that the archive system has search, update and reporting functions to facilitate data management and analysis.

[0126] A file template can be pre-set in the tire management module. After receiving the identity information of the tire to be tested, a file template can be called and the identity information can be written to obtain the tire quality inspection file and save it in the background database (the saving address needs to be recorded in the tire management module for easy file retrieval). The sampling data and qualified judgment results can be written into the file.

[0127] After the backend server receives the infrared thermal imaging image and the surface camera image of the tire, it will use the model to perform intelligent image recognition on the image to identify whether there are unqualified features in the image. In order to improve the recognition accuracy of the backend model for the image, this solution adopts a cutting method to cut the image into several slices, and perform traversal sampling recognition on each slice. Through random sampling, the model is used to perform feature recognition on the sampled slices to improve the randomness of the sampling detection and improve the robustness of the model for feature recognition detection.

[0128] Specifically, in steps S2 and S3, the image is sliced ​​to generate a number of slices as follows:

[0129] 1. Set up the Slice tool:

[0130] In your image editing software, find the slice tool. In Photoshop, for example, the slice tool is usually located at the bottom of the toolbar, or you can display the slice grid by selecting View > Show > Slices.

[0131] 2. Create slices:

[0132] Use the Slice tool to drag along the edge of the image to create the slice area. Make sure the slice boundaries are clear and avoid overlap.

[0133] If necessary, you can manually adjust the size and position of the slices to ensure that they accurately cover parts of the image.

[0134] 3. Optimize slices:

[0135] Optimize the settings for each slice. In Photoshop, you can right-click the slice and select "Export Settings" to set the export format, quality, and other parameters.

[0136] Typically, for web design, slices are exported as JPEG, PNG, or GIF formats.

[0137] 4. Export slices:

[0138] In your image editing software, export the slices by selecting File > Export > Export As… (or similar option).

[0139] In the Export dialog box, select a save location, set the file name and format, and then click Save.

[0140] After exporting the slices, check the folder to make sure all the slices were exported correctly and that the file format and size are as expected. If you sliced ​​in Photoshop, you can delete the original image files and keep only the slice folder to save space.

[0141] Therefore, by cutting the images, the surface infrared thermal imaging image and the surface camera image can be cut to generate a first image set consisting of a number of infrared thermal imaging slices and a second image set consisting of a number of surface camera slices.

[0142] Next, the model is used for image recognition. Several slice images are input into the tire quality inspection model by randomly sampling from the image set. The tire quality inspection model performs feature recognition detection on the slice images to determine whether there are unqualified image features on the slice images.

[0143] Unqualified thermal imaging temperature distribution features may include unqualified temperature hot spots, temperature gradients, and temperature distribution patterns.

[0144] The unqualified surface image features may be different types of surface defects, such as spots, cracks, and surface defects.

[0145] The administrator sets the corresponding quality inspection rules and standards for the specific unqualified features and configures them on the background server. The background performs statistics on unqualified features based on the features output by the model recognition, and respectively counts the number of thermal imaging temperature distribution features T1 and the number of surface image features T2 that do not meet the tire quality inspection rules, and calculates and outputs the corresponding proportion ρ: ρ=(T1+T2) / W, where W is the total number of samples and W≥500;

[0146] Failure judgment:

[0147] If T1 / W ≥ A% or T2 / W ≥ B% or ρ ≥ C% (A, B, C are all greater than 0, determined by the on-site quality inspector based on the model of the tire to be tested), the tire to be tested is judged to be unqualified;

[0148] Otherwise qualified;

[0149] The judgment result is fed back to the testing terminal of the tire quality inspection center.

[0150] A, B, and C are all percentage thresholds greater than 0 that are preset by the system, and their value range is 0~0.5.

[0151] In this solution, the thresholds for A, B, and C can be set by the administrator (they can be set according to the model of the tires to be tested in this batch, because different models and sizes of tires have different corresponding usage scenarios and requirements, so the administrator can set the upper limit of the unqualified ratio). For example, if the proportion of unqualified features on the thermal imaging image exceeds 0.5%, it is considered unqualified; or if the sum of the proportions of unqualified features of the two features exceeds 0.8%, it is considered unqualified. The background records the current tire to be tested as a product with unqualified surface quality and writes it into the quality inspection file.

[0152] The above-mentioned specific application parameters may have corresponding thresholds set by a site administrator, and this embodiment does not limit this.

[0153] As a preferred embodiment of the present invention, preferably, the method for generating the tire quality detection model comprises:

[0154] Prepare a surface infrared thermal imaging image set and a surface camera image set of several unqualified tires;

[0155] Performing feature engineering on the surface infrared thermal imaging image set to construct a thermal imaging temperature distribution feature set including temperature hot spots, temperature gradients, and temperature distribution patterns;

[0156] Performing feature engineering on the surface camera image set to construct a surface image feature set containing different surface defect types;

[0157] Adding unqualified labels to each feature element in the thermal imaging temperature distribution feature set and the surface image feature set to construct a training data set;

[0158] Prepare the convolutional neural network model and adjust the model parameters;

[0159] The thermal imaging temperature distribution features and surface image features in the training data set are randomly put into the convolutional neural network model for training and learning to generate an initial quality inspection model;

[0160] Preparing surface infrared thermal imaging images and surface camera images for verification, and importing the initial quality inspection model, and cross-validating the detection performance of the initial quality inspection model;

[0161] If the verification is successful, the tire quality detection model is obtained, and the tire quality detection model is deployed on the background server.

[0162] In this embodiment, since it involves using a model to identify and detect images, a convolutional neural network (CNN) is preferably used for model training and application. The steps of preparing the surface infrared image and surface video of an unqualified tire and using CNN training to generate a tire quality detection model are as follows:

[0163] 1. Data collection: Collect a large number of tire surface infrared images and surface camera images to ensure that they include various unqualified conditions, such as cracks, wear, bubbles, etc., as well as substandard temperature distribution gradients, hot spots and other features under the corresponding test environment.

[0164] 2. Data preprocessing: Preprocess the collected images, including adjusting image size, normalization, enhancing contrast, etc., to improve the efficiency and accuracy of model training.

[0165] 3. Feature Engineering: The goal of image feature engineering is to extract features that represent the content of the image for subsequent analysis and processing. When dealing with the problem of defective product detection, feature engineering can help identify image features that do not meet quality standards. Color histograms, texture features, edge detection, shape features, and depth features can be used to extract defective features and train models to identify whether the product has defects. After extracting the features, machine learning or deep learning algorithms can be used to classify and identify the features to achieve defective product detection. Adding a defective label to the identification feature tells the CNN that the feature set is used to train a model to identify defective features.

[0166] 4. Divide the data set: Divide the data set into training set, validation set and test set. The ratio is usually 70% training set, 15% validation set and 15% test set. In this case, additional surface infrared thermal imaging images and surface camera images can be prepared for verification, and feature engineering can be performed separately to extract corresponding verification features for model verification.

[0167] 5. Design CNN architecture: Design a convolutional neural network architecture suitable for tire quality inspection. You can use common network structures such as LeNet, AlexNet, VGGNet, etc. as the basis and adjust them as needed.

[0168] 6. Model training: Use the training set data to train the CNN model, and use the validation set data to adjust hyperparameters such as learning rate, batch size, number of convolutional layers, etc. to prevent overfitting and improve model performance.

[0169] 7. Model evaluation: Evaluate the performance of the model on the test set, using indicators such as accuracy, recall, F1 score, ROC curve, etc. to measure the detection ability of the model.

[0170] 8. Model optimization: Optimize the model based on the evaluation results, which may include adjusting the network structure, adding data enhancement, using regularization techniques, etc.

[0171] 9. Deploy the model: Deploy the trained model to the actual tire quality inspection system to ensure that the model can process images of tires on the production line in real time and provide quality assessments.

[0172] 10. Model monitoring and maintenance: Continuously monitor model performance in actual applications and regularly update the model with new data (the model can be updated using data from newly added unqualified quality inspection files in the background database) to adapt to new situations and new defect types that may arise during tire production.

[0173] Please implement the above model training in combination with the training application principles of CNN.

[0174] As a preferred embodiment of the present invention, preferably, the step of preparing a set of surface infrared thermal imaging images and a set of surface camera images of a plurality of unqualified tires comprises:

[0175] Reading the historical quality inspection files of each tire from the background database of the background server;

[0176] Screening out the historical quality inspection files of unqualified tires from the historical quality inspection files of each tire;

[0177] From the historical quality inspection files of unqualified tires, surface infrared thermal imaging images and surface camera images of unqualified tires in different temperature and pressure testing environments are read respectively, and corresponding surface infrared thermal imaging image sets and surface camera image sets are constructed.

[0178] The present invention collects corresponding historical big data from the quality inspection files of each unqualified tire stored in the background database, and screens out the historical quality inspection files of unqualified tires, extracts training image sets from them, and can quickly obtain the training big data required for model training through the quality inspection files, thereby improving the model training efficiency. Example 2

[0179] like Figure 3 As shown, on the other hand, a car tire quality detection system based on infrared and deep learning technology is provided, and the car tire quality detection system based on infrared and deep learning technology is used to implement the car tire quality detection method based on infrared and deep learning technology described in the above embodiment 1, and the system includes a tire quality inspection center, an industrial gateway and a background server, wherein:

[0180] The tire quality inspection center is used to collect infrared thermal imaging images and surface camera images of the tire to be inspected in different temperature and pressure inspection environments and upload them to the backend server, as well as the QR code of the tire to be inspected and upload them to the backend server;

[0181] An industrial gateway is used to provide data communication services between the tire quality inspection center and the backend server;

[0182] The backend server is used to record the collected information of the tire to be tested, and make a non-conforming judgment on the tire to be tested based on the surface infrared thermal imaging image and the surface camera image, and feed back the judgment result to the tire quality inspection center;

[0183] The tire quality inspection center and the backend server are respectively connected to the industrial gateway for communication.

[0184] As a preferred embodiment of the present invention, preferably, the tire quality inspection center comprises:

[0185] Controller;

[0186] Infrared barcode scanner, used to scan the QR code of the tire to be tested to obtain the identity information of the tire to be tested;

[0187] Infrared thermal imager, used to collect infrared thermal imaging images of the surface of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center;

[0188] 3D camera, used to collect surface images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center;

[0189] A communication module, used for communicating with the industrial gateway;

[0190] A detection terminal, used to display the judgment result of the tire to be detected, and send a corresponding detection instruction to the backend server;

[0191] The infrared scanner, infrared thermal imager, 3D camera and communication module are electrically connected to the controller respectively, the communication module is connected to the industrial gateway for communication, and the detection terminal is connected to the background server for communication:

[0192] The backend server comprises:

[0193] The tire management module is used to create the quality inspection file of the tire to be tested and write the judgment result of the tire to be tested;

[0194] A tire quality inspection model is used to identify and output thermal imaging temperature distribution characteristics and surface image characteristics of the tire to be inspected;

[0195] The quality inspection and evaluation module is used to judge the unqualified tires to be inspected and output the judgment results;

[0196] Backend database, used for data storage;

[0197] The tire management module and the tire quality detection model are respectively connected to the background database in communication; the quality inspection and evaluation module is connected to the tire quality detection model in communication.

[0198] like Figure 3 The figure is an application block diagram of the system. Please refer to the description of Example 1 for understanding the specific functions and interactive control of each subject, which will not be described in detail in this example. Example 3

[0199] Figure 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device may include the above Figure 2 or Figure 3 The automobile tire quality detection system based on infrared and deep learning technology is shown. Optionally, the electronic device 410 may include a first processor 2001.

[0200] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0201] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0202] Combine the following Figure 4 The components of the electronic device 410 are described in detail:

[0203] The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0204] Optionally, the first processor 2001 can perform various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0205] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in FIG.

[0206] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 4 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0207] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0208] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0209] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0210] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0211] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0212] It should be noted that Figure 4 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0213] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the automobile tire quality detection method based on infrared and deep learning technology described in the above method embodiment, and will not be repeated here.

[0214] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0215] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0216] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0217] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0218] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0219] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0220] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0221] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0222] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the system or unit, which can be electrical, mechanical or other forms.

[0223] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0224] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0225] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0226] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting automobile tire quality based on infrared and deep learning technology, characterized in that: The method comprises: S1. Obtaining infrared thermal imaging images and surface camera images of the tire to be tested in different temperature and pressure testing environments of a tire quality inspection center; S2, performing image cutting processing on the surface infrared thermal imaging image and the surface camera image to generate a first image set consisting of a plurality of infrared thermal imaging slices and a second image set consisting of a plurality of surface camera slices; S3, traversing the first image set, randomly extracting a number of groups of the infrared thermal imaging slices and importing them into a preset tire quality detection model, and identifying and outputting the thermal imaging temperature distribution features in the infrared thermal imaging slices through the tire quality detection model; S4, traversing the second image set, randomly extracting a plurality of groups of the surface camera slices and importing them into a preset tire quality detection model, and identifying and outputting surface image features in the surface camera slices through the tire quality detection model; S5, respectively counting the number T1 of the thermal imaging temperature distribution features that do not meet the tire quality inspection rules and the number T2 of the surface image features that do not meet the tire quality inspection rules, and calculating and outputting the corresponding proportions: ρ=(T1+T2) / W, Among them, ρ is the proportion, W is the total number of samples and W ≥ 500; S6. Unqualified judgment: If T1 / W ≥ A% or T2 / W ≥ B% or ρ ≥ C%, the tire to be tested is judged as unqualified; A, B, and C are all percentage thresholds greater than 0 pre-set by the system, with a value range of 0 to 0.5; Otherwise qualified; The judgment result is fed back to the testing terminal of the tire quality inspection center.

2. The automobile tire quality detection method based on infrared and deep learning technology according to claim 1 is characterized in that: In step S1, the step of obtaining infrared thermal imaging images of the surface of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes: The tire quality inspection center adjusts the inspection environment with different temperatures and pressures in sequence, and informs the background server of the adjustment result of the inspection environment through the inspection terminal; After receiving the adjustment result of the detection environment, the backend server generates a first sampling instruction, and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway; The first sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the first sampling instruction to control the infrared thermal imager to collect the infrared thermal imaging image of the surface of the tire to be inspected; According to the above steps, the surface infrared thermal imaging images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface infrared thermal imaging images are uploaded to the backend server through the industrial gateway.

3. The automobile tire quality detection method based on infrared and deep learning technology according to claim 2 is characterized in that: In step S1, the step of obtaining the surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center includes: After the backend server generates a first sampling instruction and forwards the first sampling instruction to the tire quality inspection center through the industrial gateway, a second sampling instruction is generated at an interval of 0.5 to 1.5 ms and the second sampling instruction is forwarded to the tire quality inspection center through the industrial gateway; The second sampling instruction is received by a communication module of the tire quality inspection center and forwarded to a controller, and the controller executes the second sampling instruction to control the 3D camera to collect a surface camera image of the tire to be inspected; According to the above steps, the surface camera images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center are collected in sequence, and the surface camera images are uploaded to the backend server through the industrial gateway.

4. The automobile tire quality detection method based on infrared and deep learning technology according to claim 1 is characterized in that: Before step S1, the method further includes: Scan the QR code of the tire to be tested with the infrared scanner of the tire quality inspection center to obtain the identity information of the tire to be tested, and upload it to the backend server through the industrial gateway; The backend server creates a quality inspection file of the tire to be inspected in the tire management module according to the identity information of the tire to be inspected and saves it in the backend database; The quality inspection file is used to record: the surface infrared thermal imaging image and surface camera image of the tire to be inspected in different temperature and pressure inspection environments of the tire quality inspection center and the judgment results thereof.

5. The automobile tire quality detection method based on infrared and deep learning technology according to claim 1 is characterized in that: The method for generating the tire quality detection model comprises: Prepare a surface infrared thermal imaging image set and a surface camera image set of several unqualified tires; Performing feature engineering on the surface infrared thermal imaging image set to construct a thermal imaging temperature distribution feature set including temperature hot spots, temperature gradients, and temperature distribution patterns; Performing feature engineering on the surface camera image set to construct a surface image feature set containing different surface defect types; Adding unqualified labels to each feature element in the thermal imaging temperature distribution feature set and the surface image feature set to construct a training data set; Prepare the convolutional neural network model and adjust the model parameters; The thermal imaging temperature distribution features and surface image features in the training data set are randomly put into the convolutional neural network model for training and learning to generate an initial quality inspection model; Preparing surface infrared thermal imaging images and surface camera images for verification, and importing the initial quality inspection model, and cross-validating the detection performance of the initial quality inspection model; After the verification is passed, the tire quality detection model is obtained and deployed on a background server.

6. The automobile tire quality detection method based on infrared and deep learning technology according to claim 5 is characterized in that: The step of preparing a plurality of surface infrared thermal imaging image sets and surface camera image sets of unqualified tires comprises: Reading the historical quality inspection files of each tire from the background database of the background server; Screening out the historical quality inspection files of unqualified tires from the historical quality inspection files of each tire; From the historical quality inspection files of unqualified tires, surface infrared thermal imaging images and surface camera images of unqualified tires in different temperature and pressure testing environments are read respectively, and corresponding surface infrared thermal imaging image sets and surface camera image sets are constructed.

7. A car tire quality detection system based on infrared and deep learning technology, wherein the car tire quality detection system based on infrared and deep learning technology is used to implement the car tire quality detection method based on infrared and deep learning technology as described in any one of claims 1 to 6, characterized in that: The system includes a tire quality inspection center, an industrial gateway and a backend server, wherein: The tire quality inspection center is used to collect infrared thermal imaging images and surface camera images of the tire to be inspected in different temperature and pressure inspection environments and upload them to the backend server, as well as the QR code of the tire to be inspected and upload them to the backend server; An industrial gateway is used to provide data communication services between the tire quality inspection center and the backend server; The backend server is used to record the collected information of the tire to be tested, and make a non-conforming judgment on the tire to be tested based on the surface infrared thermal imaging image and the surface camera image, and feed back the judgment result to the tire quality inspection center; The tire quality inspection center and the backend server are respectively connected to the industrial gateway for communication.

8. The automobile tire quality detection system based on infrared and deep learning technology according to claim 7 is characterized in that: The tire quality inspection center includes: Controller; Infrared barcode scanner, used to scan the QR code of the tire to be tested to obtain the identity information of the tire to be tested; Infrared thermal imager, used to collect infrared thermal imaging images of the surface of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center; 3D camera, used to collect surface images of the tire to be tested in different temperature and pressure testing environments of the tire quality inspection center; A communication module, used for communicating with the industrial gateway; A detection terminal, used to display the judgment result of the tire to be detected, and send a corresponding detection instruction to the backend server; The infrared scanner, infrared thermal imager, 3D camera and communication module are electrically connected to the controller respectively, the communication module is connected to the industrial gateway for communication, and the detection terminal is connected to the background server for communication: The backend server comprises: The tire management module is used to create the quality inspection file of the tire to be tested and write the judgment result of the tire to be tested; A tire quality inspection model is used to identify and output thermal imaging temperature distribution characteristics and surface image characteristics of the tire to be inspected; The quality inspection and evaluation module is used to judge the unqualified tires to be inspected and output the judgment results; Backend database, used for data storage; The tire management module and the tire quality detection model are respectively connected to the background database in communication; the quality inspection and evaluation module is connected to the tire quality detection model in communication.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.