Automobile real-time fault diagnosis system and diagnosis method based on cloud interaction

Abstract

The invention provides an automobile real-time fault diagnosis system and method based on cloud interaction, and belongs to the field of automobile fault diagnos.The automobile real-time fault diagnosis system comprises a fault detection module, an edge calculation module, a fault diagnosis and management module and a processing module.The fault detection module monitors the automobile state in real time and inputs automobile state information into the edge calculation module; the edge calculation module performs preliminary analysis on the automobile state information; the edge calculation module sends automobile fault information to the fault diagnosis and management module after detecting an automobile fault; the fault diagnosis and management module analyzes the automobile fault information and sends a control instruction to the processing module according to an automobile fault analysis result; and the processing module processes a fault according to the received control instruction and feeds back a processing result to the fault diagnosis and management module. The method has the advantages of timely fault diagnosis and high diagnosis accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of automobile fault diagnosis, and in particular, the present invention relates to a real-time automobile fault diagnosis system and a diagnosis method based on cloud interaction. Background Art

[0002] As people's living standards improve, users have higher and higher requirements for automobile safety, and the timeliness of automobile fault diagnosis is particularly important. Chinese Patent 102752360A provides a car fault detection system based on cloud computing to solve the problem that general vehicles do not have the function of detecting vehicle faults or the detected faults are not specific, and users cannot repair the vehicles in time, which increases safety hazards and also makes the faults more serious, increasing the maintenance costs. The system includes a vehicle-mounted terminal and a cloud computing end; the vehicle-mounted terminal includes a vehicle data communication interface module, a control module, a network communication module and a display module; the vehicle-mounted terminal is connected to the cloud computing end through the network. This patent solves the problem of automobile fault diagnosis by analyzing the car fault through the cloud computing end, but it has high requirements on the network speed, and there is a delay in the diagnosis of the fault, which will cause hidden dangers to the user's safety. Summary of the invention

[0003] The present invention aims to provide a real-time automobile fault diagnosis system and method based on cloud interaction, so as to achieve the purpose of improving the speed and accuracy of automobile fault diagnosis.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] The present invention provides a real-time automobile fault diagnosis system based on cloud interaction, comprising a fault detection module, an edge computing module, a fault diagnosis and management module and a processing module, wherein the output end of the fault detection module is connected to the input end of the edge computing module, the output end of the edge computing module is connected to the input end of the fault diagnosis and management module, the output end of the edge computing module is connected to the input end of the processing module, the output end of the fault diagnosis and management module is connected to the input end of the processing module, the output end of the fault diagnosis and management module is connected to the input end of the edge computing module, and the output end of the processing module is connected to the input end of the fault diagnosis and management module.

[0006] The fault detection module outputs vehicle status information to the edge computing module, the edge computing module outputs control instructions to the processing module, the edge computing module outputs vehicle fault information to the fault diagnosis and management module, the fault diagnosis and management module outputs control instructions to the processing module, the fault diagnosis and management module outputs fault detection request instructions to the edge computing module, and the processing module inputs processing results to the fault diagnosis and management module.

[0007] The fault detection module adopts a sensor, the edge computing module adopts a microcontroller, the processing module includes a microcontroller and an actuator, and the fault diagnosis and management module adopts a cloud server.

[0008] The present invention provides a real-time automobile fault diagnosis method based on cloud interaction:

[0009] Step 1: The fault detection module monitors the vehicle status in real time and inputs the vehicle status information into the edge computing module, which performs a preliminary analysis of the vehicle status information;

[0010] Step 2: After the edge computing module detects a vehicle fault, it sends the vehicle fault information to the fault diagnosis and management module;

[0011] Step 3: The fault diagnosis and management module analyzes the vehicle fault information and sends a control instruction to the processing module according to the vehicle fault analysis result;

[0012] Step 4: The processing module processes the fault according to the received control instruction and feeds back the processing result to the fault diagnosis and management module.

[0013] In step one, the edge computing module performs a preliminary analysis of the vehicle status, performs a diagnosis, and sends a control instruction to the processing module. The edge computing module sends the diagnosis result to the fault diagnosis and management module. When the edge computing module cannot diagnose the fault, the vehicle fault information is sent to the fault diagnosis and management module.

[0014] In step three, the fault diagnosis and management module analyzes the vehicle fault information through big data technology, and predicts the development trend of the vehicle fault through the intelligent prediction model. The fault diagnosis and management module sends control instructions to the processing module based on the vehicle fault analysis results and the fault development trend prediction results.

[0015] The fault diagnosis and management module updates fault diagnosis and processing cases and maintains the fault database through big data technology.

[0016] The fault diagnosis and management module periodically sends fault detection request instructions to the edge computing module, and the edge computing module inputs the vehicle status information to the fault diagnosis and management module. When the fault diagnosis and management module detects fault data, it resends the fault detailed detection request instruction to the edge computing module. The edge computing module uploads more vehicle status information related to the fault to the fault diagnosis and management module. The fault diagnosis and management module analyzes the uploaded more vehicle status information related to the fault and generates control instructions to send to the processing module.

[0017] The fault diagnosis and management module periodically sends fault tracking instructions to the edge computing module for automobile parts that have previously failed. The edge computing module tracks and monitors the automobile parts that have failed, and transmits the monitored automobile parts information to the fault diagnosis and management module, which diagnoses the automobile parts information.

[0018] The edge computing module and the fault diagnosis and management module, as well as the fault diagnosis and management module and the processing module encrypt data and verify the device during data transmission.

[0019] The technical effects of the present invention are:

[0020] (1) The encryption algorithm of the present invention encrypts data to ensure the confidentiality and integrity of the data during transmission and storage.

[0021] (2) The present invention trains an intelligent prediction model through machine learning algorithms and the various fault problems encountered by vehicles in daily life and the vehicle status data generated during this period and before the fault occurs. The model is continuously trained and iterated to enable the model to have self-learning and prediction capabilities. Relying on the prediction of the intelligent prediction model, it is able to more quickly analyze whether the current vehicle status information has the risk of fault occurrence, and has higher accuracy and efficiency than traditional fault diagnosis.

[0022] (3) The fault diagnosis and management module generates control instructions to the processing module based on the diagnosis results. The processing module executes the control instructions and reports the processing results. The edge computing module detects faults in real time through the fault detection module. The fault diagnosis and management module, the processing module, the fault detection module and the edge computing module form a closed loop. Information is continuously exchanged and instructions are issued between the vehicle and the cloud server to ensure that vehicle faults can be discovered and processed in a timely manner, thereby improving the safety and reliability of the vehicle.

[0023] (4) The fault diagnosis and management module, namely the cloud server and the edge computing module, work together. The cloud server provides powerful data processing capabilities and storage resources, and the edge computing module performs fast processing near the data source, which has the advantages of real-time and reduced latency. The two work together to intelligently distribute the computing load between the cloud and edge computing according to the urgency and complexity of the task, ensuring the real-time and effectiveness of vehicle fault processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] This specification includes the following drawings, which show the following contents:

[0025] Figure 1 This is a logical structure diagram of a real-time automobile fault diagnosis system and a diagnosis method based on cloud interaction of the present invention;

[0026] Figure 1 Marked as: 1. Fault detection module; 2. Edge computing module; 3. Fault diagnosis and management module; 4. Processing module. DETAILED DESCRIPTION

[0027] The specific implementation methods of the present invention are further explained in detail below by describing the embodiments with reference to the accompanying drawings, with the aim of helping those skilled in the art to have a more complete, accurate and in-depth understanding of the inventive concept and technical solution of the present invention and facilitating their implementation.

[0028] The present invention provides a real-time automobile fault diagnosis system based on cloud interaction, comprising a fault detection module 1, an edge computing module 2, a fault diagnosis and management module 3 and a processing module 4, wherein the output end of the fault detection module 1 is connected to the input end of the edge computing module 2, the output end of the edge computing module 2 is connected to the input end of the fault diagnosis and management module 3, the output end of the edge computing module 2 is connected to the input end of the processing module 4, the output end of the fault diagnosis and management module 3 is connected to the input end of the processing module 4, the output end of the fault diagnosis and management module 3 is connected to the input end of the edge computing module 2, and the output end of the processing module 4 is connected to the input end of the fault diagnosis and management module 3.

[0029] The fault detection module 1 outputs the vehicle status information to the edge computing module 2, the edge computing module 2 outputs the control instruction to the processing module 4, the edge computing module 2 outputs the vehicle fault information to the fault diagnosis and management module 3, the fault diagnosis and management module 3 outputs the control instruction to the processing module 4, the fault diagnosis and management module 3 outputs the fault detection request instruction to the edge computing module 2, and the processing module 4 inputs the processing result to the fault diagnosis and management module 3.

[0030] The fault detection module 1 adopts a sensor, the edge computing module 2 adopts a microcontroller, the processing module 4 includes a microcontroller and an actuator, and the fault diagnosis and management module 3 adopts a cloud server.

[0031] The present invention provides a real-time automobile fault diagnosis method based on cloud interaction:

[0032] Step 1: The fault detection module 1 monitors the vehicle status in real time and inputs the vehicle status information into the edge computing module 2, which performs a preliminary analysis of the vehicle status information;

[0033] Step 2: After detecting a vehicle fault, the edge computing module 2 sends the vehicle fault information to the fault diagnosis and management module 3;

[0034] Step 3: The fault diagnosis and management module 3 analyzes the vehicle fault information and sends a control instruction to the processing module 4 according to the vehicle fault analysis result;

[0035] Step 4: The processing module 4 processes the fault according to the received control instruction and feeds back the processing result to the fault diagnosis and management module.

[0036] In step one, the edge computing module 2 performs a preliminary analysis of the vehicle status, performs a diagnosis, and sends a control instruction to the processing module 4. The edge computing module 2 sends the diagnosis result to the fault diagnosis and management module 3. When the edge computing module 2 cannot diagnose the fault, the vehicle fault information is sent to the fault diagnosis and management module 3.

[0037] In step three, the fault diagnosis and management module 3 analyzes the automobile fault information through big data technology, and predicts the development trend of the automobile fault through an intelligent prediction model. The fault diagnosis and management module 3 sends a control instruction to the processing module 4 according to the automobile fault analysis results and the fault development trend prediction results.

[0038] The fault diagnosis and management module 3 updates fault diagnosis and processing cases and maintains the fault database through big data technology.

[0039] The fault diagnosis and management module 3 periodically sends a fault detection request instruction to the edge computing module 2, and the edge computing module 2 inputs the vehicle status information to the fault diagnosis and management module 3. When the fault diagnosis and management module 3 detects fault data, it resends the fault detailed detection request instruction to the edge computing module 2, and the edge computing module 2 uploads more vehicle status information related to the fault to the fault diagnosis and management module 3. The fault diagnosis and management module 3 analyzes the uploaded more vehicle status information related to the fault and generates a control instruction to send to the processing module 4.

[0040] The fault diagnosis and management module 3 periodically sends a request for fault tracking instructions to the edge computing module 2 for automobile parts that have previously failed. The edge computing module 2 tracks and monitors the automobile parts that have failed, and transmits the monitored automobile parts information to the fault diagnosis and management module 3. The fault diagnosis and management module 3 diagnoses the automobile parts information.

[0041] The edge computing module 2 and the fault diagnosis and management module 3, as well as the fault diagnosis and management module 3 and the processing module 4, encrypt the data and verify the device during data transmission.

[0042] The following is a detailed introduction to a real-time automobile fault diagnosis system and a diagnosis method based on cloud interaction of the present invention.

[0043] The present invention provides a real-time automobile fault diagnosis system based on cloud interaction, including a fault detection module 1, an edge computing module 2, a fault diagnosis and management module 3 and a processing module 4, wherein the fault detection module 1 uses a sensor to detect and collect status information and user operation data generated by the automobile. In an embodiment of the present invention, the fault detection module 1 detects the engine, battery and brake. The sensor for detecting the engine uses a speed sensor, the sensor for detecting the battery uses a voltage sensor, a current sensor and a temperature sensor, and the sensor for detecting the brake uses a brake pedal position sensor, a pressure sensor and a brake pad wear sensor; the edge computing module 2 uses multiple microcontrollers, which are distributed near the automobile parts to be monitored. In the embodiment, the multiple microcontrollers are respectively distributed near the engine, battery and brake, and are used to perform preliminary analysis on the data detected by the fault detection module 1, and send the automobile fault information to the fault diagnosis and management module 3. When a simple fault is detected The control command will also be sent to the processing module 4; the fault diagnosis and management module 3 adopts a cloud server to receive the data uploaded by the edge computing module 2, and analyzes the fault of the automobile through big data technology and predicts the development trend of the automobile fault through an intelligent prediction model, and generates control commands according to the automobile fault analysis results and the fault development trend prediction results, and inputs them into the processing module 4; the processing module 4 includes a microcontroller and an actuator. The processing module 4 controls the corresponding actuator to execute the command according to the control command input by the fault diagnosis and management module 3, and feeds back the processing result to the fault diagnosis and management module 3. In an embodiment of the present invention, different actuators are used for the engine, battery and brake. For engine failure, the engine speed can be adjusted by controlling the turbocharger. For the battery, the switch and temperature of the battery are managed by the circuit breaker and the fan. For braking, the brake booster helps the driver to improve the braking effect, and the brake pad wear indicator prompts the driver to replace the brake pad.

[0044] The output end of each sensor is respectively connected to the input end of the corresponding microcontroller in the edge computing module 2. The microcontroller in the edge computing module 2 is connected to the cloud server via a wireless network. The cloud server is connected to the microcontroller in the processing module 4 via a wireless network. The output end of the microcontroller in the processing module 4 is connected to the input end of each actuator.

[0045] The present invention provides a real-time automobile fault diagnosis method based on cloud interaction, and its specific working process is described in detail below.

[0046] The fault diagnosis method of the present invention includes active fault detection and passive fault detection. The specific steps of active fault detection are:

[0047] After the car is powered on, the fault detection module 1 monitors the car state. In the embodiment of the present invention, the engine speed is detected by the speed sensor, the voltage, current and temperature of the car battery are detected by the voltage sensor, current sensor and temperature sensor, and the brake pedal position sensor, pressure sensor and brake pad wear sensor are used to detect the brake position, pressure and wear degree; the fault detection module 1 inputs the detected car state information into the edge computing module 2, and the edge computing module 2 pre-processes the car state information through the edge computing gateway before analyzing the information, specifically, cleaning, format conversion and feature extraction of the collected information data; after pre-processing the car state information, the edge computing module 2 performs a preliminary analysis of the car state information, and when a diagnosis is made In case of a fault, the next operation is performed according to the complexity of the fault. When the detected fault is a simple fault, the edge computing module 2 outputs a control instruction to the processing module 4 according to the detected fault, and sends the diagnosis result to the fault diagnosis and management module 3; when the edge computing module 2 cannot diagnose the fault due to the complexity of the fault, it outputs the vehicle fault information to the fault diagnosis and management module 3, wherein the output vehicle fault information is compressed and the data format is optimized by the edge computing module 2 before transmission; the fault diagnosis and management module 3 analyzes the vehicle fault information through big data technology, and predicts the development trend of the vehicle fault through the intelligent prediction model, and the fault diagnosis and management module 3 sends a control instruction to the processing module 4 according to the vehicle fault analysis results and the prediction results of the fault development trend. In the process of data transmission between the edge computing module 2 and the fault diagnosis and management module, the edge computing module 2 temporarily stores the data to prevent data loss when the network is unstable. The processing module 4 processes the fault according to the received control command. In the embodiment of the present invention, the engine speed can be adjusted by controlling the turbocharger for engine faults, the switch and temperature of the battery can be managed by the circuit breaker and the fan for the battery, the brake booster can help the driver improve the braking effect for braking, and the brake pad wear indicator can be used to remind the driver to replace the brake pad; for faults that the processing module 4 cannot handle, that is, problems that the car cannot repair itself, the processing module 4 will send fault information to the display screen to remind the driver, and the driver will look for professionals to solve the car fault. The processing module 4 will feed back the processing results to the fault diagnosis and management module 3. The fault diagnosis and management module 3 updates the fault diagnosis and processing cases through big data technology, maintains the fault database, and improves the accuracy of the fault diagnosis of the present invention.

[0048] The passive fault detection method of the present invention is as follows: the fault diagnosis and management module 3 periodically sends a fault detection request instruction to the edge computing module 2, the edge computing module 2 inputs the vehicle status information to the fault diagnosis and management module 3, when the fault diagnosis and management module 3 detects fault data, it resends a detailed fault detection request instruction to the edge computing module 2, the edge computing module 2 uploads more vehicle status information related to the fault to the fault diagnosis and management module 3, the fault diagnosis and management module 3 analyzes and diagnoses the uploaded detailed vehicle status information related to the fault, and generates a control instruction to send to the processing module 4, the processing module 4 feeds back the processing result to the fault diagnosis and management module 3. The fault diagnosis and management module 3 periodically sends a request fault tracking instruction to the edge computing module 2 for the fault that has occurred previously, the edge computing module 2 tracks and monitors the fault, that is, it analyzes the vehicle status information detected by the fault detection module 1 at a higher frequency, and transmits the monitored vehicle status information to the fault diagnosis and management module 3 to analyze whether a fault has occurred. Different from active fault detection, the edge computing module 2 sends all vehicle status information to the fault diagnosis and management module 3 to prevent the edge computing module 2 from making an incorrect diagnosis due to a fault and improve the accuracy of the diagnosis. However, due to the large amount of data transmission, the passive fault detection cycle is set to 1 day in the embodiment of the present invention.

[0049] The edge computing module 2 and the fault diagnosis and management module 3, and the fault diagnosis and management module 3 and the processing module 4 encrypt the data and verify the device during the data transmission process. Specifically, the data transmission and instruction sending of the present invention are carried out through a secure communication protocol, and the Https or MQTT over TLS communication protocol can be used to ensure the security of data transmission. In the process of data transmission and instruction sending, both the car and the cloud server take privacy protection measures, and data encryption and device verification are required to ensure that the information will not be stolen by others. Sensitive data is processed in the edge computing module 2, and the data is encrypted using encryption algorithms such as symmetric encryption or public key encryption to ensure the confidentiality and integrity of the data during transmission and storage. The edge computing module 2 processes the data to reduce the risk of data leakage. The present invention adopts encryption and authentication technology, and uses the TLS / SSL protocol to encrypt and transmit data to prevent the data from being eavesdropped or tampered with.

[0050] The present invention trains an intelligent prediction model through machine learning algorithms and various fault problems encountered by vehicles in daily operations and vehicle status data generated during this period and before the occurrence of a fault. The model is continuously trained and iterated to enable the model to have self-learning and prediction capabilities. Relying on the prediction of the intelligent prediction model, it is able to more quickly analyze whether the current vehicle status information poses a risk of a fault, and has higher accuracy and efficiency than traditional fault diagnosis.

[0051] The fault diagnosis and management module 3 generates a control instruction to the processing module 4 according to the diagnosis result. The processing module 4 executes the control instruction and reports the processing result. The edge computing module 2 detects the fault in real time through the fault detection module 1. The fault diagnosis and management module 3, the processing module 4, the fault detection module 1 and the edge computing module 2 form a closed loop. The car and the cloud server continuously exchange information and issue instructions to ensure that the car fault can be discovered and processed in time, thereby improving the safety and reliability of the car.

[0052] The fault diagnosis and management module 3, i.e. the cloud server, works in collaboration with the edge computing module 2. The cloud server provides powerful data processing capabilities and storage resources, and the edge computing module 2 performs fast processing near the data source, which has the advantages of real-time and reduced latency. The two work together to intelligently distribute the computing load between the cloud and edge computing according to the urgency and complexity of the task, thereby ensuring the real-time and effectiveness of vehicle fault processing.

[0053] The present invention is described above by way of example in conjunction with the accompanying drawings. Obviously, the specific implementation of the present invention is not limited to the above-mentioned methods. As long as various non-substantial improvements are made using the method concept and technical solution of the present invention; or the above concept and technical solution of the present invention are directly applied to other occasions without improvement, they are all within the protection scope of the present invention.

Claims

1. A real-time automobile fault diagnosis system based on cloud interaction, characterized in that: It includes a fault detection module, an edge computing module, a fault diagnosis and management module and a processing module, wherein the output end of the fault detection module is connected to the input end of the edge computing module, the output end of the edge computing module is connected to the input end of the fault diagnosis and management module, the output end of the edge computing module is connected to the input end of the processing module, the output end of the fault diagnosis and management module is connected to the input end of the processing module, the output end of the fault diagnosis and management module is connected to the input end of the edge computing module, and the output end of the processing module is connected to the input end of the fault diagnosis and management module.

2. The real-time automobile fault diagnosis system based on cloud interaction as claimed in claim 1, characterized in that: The fault detection module outputs vehicle status information to the edge computing module, the edge computing module outputs control instructions to the processing module, the edge computing module outputs vehicle fault information to the fault diagnosis and management module, the fault diagnosis and management module outputs control instructions to the processing module, the fault diagnosis and management module outputs fault detection request instructions to the edge computing module, and the processing module inputs processing results to the fault diagnosis and management module.

3. The real-time automobile fault diagnosis system based on cloud interaction as claimed in claim 1, characterized in that: The fault detection module adopts a sensor, the edge computing module adopts a microcontroller, the processing module includes a microcontroller and an actuator, and the fault diagnosis and management module adopts a cloud server.

4. A real-time automobile fault diagnosis method based on cloud interaction as claimed in any one of claims 1 to 3, characterized in that: Step 1: The fault detection module monitors the vehicle status in real time and inputs the vehicle status information into the edge computing module, which performs a preliminary analysis of the vehicle status information; Step 2: After the edge computing module detects a vehicle fault, it sends the vehicle fault information to the fault diagnosis and management module; Step 3: The fault diagnosis and management module analyzes the vehicle fault information and sends a control instruction to the processing module according to the vehicle fault analysis result; Step 4: The processing module processes the fault according to the received control instruction and feeds back the processing result to the fault diagnosis and management module.

5. The method for real-time automobile fault diagnosis based on cloud interaction as claimed in claim 4, characterized in that: In step 1, the edge computing module performs a preliminary analysis of the vehicle status and sends a control command to the processing module, and the edge computing module sends the diagnosis result to the fault diagnosis and management module; When the edge computing module is unable to diagnose the fault, the vehicle fault information is sent to the fault diagnosis and management module.

6. A real-time automobile fault diagnosis method based on cloud interaction as claimed in claim 4, characterized in that: In step three, the fault diagnosis and management module analyzes the vehicle fault information through big data technology, and predicts the development trend of the vehicle fault through the intelligent prediction model. The fault diagnosis and management module sends control instructions to the processing module based on the vehicle fault analysis results and the fault development trend prediction results.

7. The real-time automobile fault diagnosis method based on cloud interaction as claimed in claim 4, characterized in that: The fault diagnosis and management module updates fault diagnosis and processing cases and maintains the fault database through big data technology.

8. The real-time automobile fault diagnosis method based on cloud interaction as claimed in claim 4, characterized in that: The fault diagnosis and management module periodically sends fault detection request instructions to the edge computing module, and the edge computing module inputs the vehicle status information to the fault diagnosis and management module. When the fault diagnosis and management module detects fault data, it resends the fault detailed detection request instruction to the edge computing module. The edge computing module uploads more vehicle status information related to the fault to the fault diagnosis and management module. The fault diagnosis and management module analyzes the uploaded more vehicle status information related to the fault and generates control instructions to send to the processing module.

9. The real-time automobile fault diagnosis method based on cloud interaction as claimed in claim 4, characterized in that: The fault diagnosis and management module periodically sends fault tracking instructions to the edge computing module for automobile parts that have previously failed. The edge computing module tracks and monitors the automobile parts that have failed, and transmits the monitored automobile parts information to the fault diagnosis and management module, which diagnoses the automobile parts information.

10. The real-time automobile fault diagnosis method based on cloud interaction as claimed in claim 4, characterized in that: The edge computing module and the fault diagnosis and management module, as well as the fault diagnosis and management module and the processing module encrypt data and verify the device during data transmission.

Images