Commercial vehicle operation, maintenance and overhaul prediction system and operation, maintenance and overhaul prediction method

Abstract

The invention relates to the technical field of vehicle fault prediction, and discloses a commercial vehicle operation and maintenance prediction system and method, and the system integrates a data collection terminal, a data middle platform, a fault prediction evaluation module, a remote supervision platform, and a self-learning and optimization module. The data acquisition terminal acquires vehicle core data through a plurality of sensors and transmits the vehicle core data in real time through the data transmission interface; the data middle platform comprises a local data platform and a cloud data platform, ensures that the data can be safely stored when the network is unstable, and synchronizes the data to the cloud for cleaning processing to obtain target data when the condition is met; the fault prediction and evaluation module receives the target data, performs fault prediction and evaluation by using a built-in fault prediction model, and generates a report; the remote supervision platform receives the report and realizes remote supervision and decision support; and the self-learning and optimization module continuously optimizes the fault prediction model according to the vehicle operation characteristic data.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault prediction, and in particular to a commercial vehicle operation and maintenance prediction system and an operation and maintenance prediction method. Background Art

[0002] In the operation of commercial vehicles, vehicle operation and maintenance are crucial and directly related to transportation efficiency, operating costs and driving safety. The traditional commercial vehicle maintenance method mainly relies on regular manual inspections and post-fault repairs, which has many disadvantages. On the one hand, the cycle of regular manual inspections is difficult to accurately determine, which may cause sudden vehicle failures during the inspection interval, affecting normal operations; on the other hand, post-fault repairs are often carried out after the failure has occurred, which not only has high maintenance costs, but may also cause economic losses such as cargo transportation delays, and even endanger driving safety in some cases.

[0003] With the rapid development of information technology, the degree of vehicle electrification is constantly improving, and more and more sensors are being used in commercial vehicles, which enables vehicles to collect a large amount of operating data in real time. However, how to effectively collect, process and analyze these massive amounts of data and extract valuable information from them for fault prediction and operation and maintenance decision-making has become an urgent problem to be solved. Summary of the invention

[0004] The main purpose of the present invention is to provide a commercial vehicle operation and maintenance prediction system and operation and maintenance prediction method, aiming to solve the technical problems of low efficiency and high cost of commercial vehicle operation and maintenance in the prior art.

[0005] To achieve the above objectives, in a first aspect, an embodiment of the present application provides a commercial vehicle operation and maintenance prediction system, the system comprising: A data acquisition terminal, comprising a plurality of data acquisition sensors, wherein the plurality of data acquisition sensors are used to acquire core data of a target component of a vehicle, and the data acquisition terminal is provided with a data transmission interface for transmitting the acquired core data to the outside; A data middle platform, which is in communication connection with the data acquisition terminal, comprises a local data platform and a cloud data platform, wherein the local data platform is used to receive and store the first collected data of the multiple data acquisition sensors when the vehicle network status does not meet the preset conditions, and transmit the first collected data to the cloud data platform when the vehicle network status meets the preset conditions; the cloud data platform is used to receive and store the first collected data and the second collected data of the multiple data acquisition sensors when the vehicle network status meets the preset conditions, and perform data cleaning processing on the first collected data and the second collected data to obtain the target data; A fault prediction and evaluation module is connected to the data center for receiving the target data and performing fault prediction and evaluation on the vehicle using a built-in fault prediction model to obtain a fault prediction and evaluation report; A remote supervision platform, connected to the fault prediction and evaluation module, for receiving the fault prediction and evaluation report to achieve remote supervision and decision support for the operation, maintenance and repair of commercial vehicles; The self-learning and optimization module is used to collect vehicle operation characteristic data and adjust or optimize parameters of the built-in fault prediction model according to the vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data and driving condition data.

[0006] In a possible implementation, the local data platform includes: A storage management unit, the storage management unit is used to monitor the local storage capacity of the local data platform in real time, and when the local storage capacity reaches a preset threshold, selectively delete or compress the first collected data according to the data collection time sequence or importance level; A lightweight analysis unit, wherein the lightweight analysis unit is used to perform a preliminary analysis on the first collected data to obtain lightweight fault warning information, and when the vehicle network status does not meet a preset condition and exceeds a preset time, the lightweight fault warning information is sent to the cloud data platform.

[0007] In a possible implementation, the lightweight analysis unit works in conjunction with the storage management unit. When the storage management unit performs a selective deletion or compressed storage operation, the lightweight analysis unit prioritizes rapid analysis of the first collected data and extracts and saves key feature information in the analysis results.

[0008] In a possible implementation, the data collection terminal further includes: An adaptive sampling management unit, wherein the adaptive sampling management unit dynamically adjusts the sampling frequency of the data acquisition sensor according to the operating state of the vehicle, wherein the sampling frequency is reduced when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a state of high load operation of key components or a fault warning state.

[0009] In a second aspect, an embodiment of the present application further provides a commercial vehicle operation and maintenance prediction method, which is applied to a commercial vehicle operation and maintenance prediction system, and the method includes: Acquire first collected data and second collected data, wherein the first collected data is collected data stored in a local data platform, including collected data from a data collection terminal when the network status of the vehicle does not meet a preset condition, and the second collected data is collected data stored in a cloud data platform, including collected data from a data collection terminal when the network status of the vehicle meets a preset condition; Performing data cleaning on the first collected data and the second collected data to obtain target data; Inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report; The fault prediction assessment report is sent to a remote monitoring platform, which includes a user terminal APP.

[0010] In a possible implementation manner, before acquiring the first collected data and the second collected data, the method further includes: According to the data collection instruction, the data collection terminal is started to collect data to obtain the collected data; Acquiring a network status of a vehicle, wherein the network status of the vehicle includes a normal status and an abnormal status; The collected data is stored according to the network status of the vehicle, wherein when the network status of the vehicle is abnormal, the collected data of the data collection terminal is stored in a local data platform, and when the network status of the vehicle is normal, the collected data of the data collection terminal is stored in a cloud data platform.

[0011] In a possible implementation, starting the data collection terminal to collect data according to the data collection instruction to obtain the collected data includes: Acquiring the vehicle operation status, wherein the vehicle operation status includes a stable driving state, a key component high-load operation or a fault warning state; The sampling frequency of the data acquisition sensor is dynamically adjusted according to the operating status of the vehicle, wherein the sampling frequency is lowered when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a state of high-load operation of key components or a fault warning state.

[0012] In a possible implementation, when the network status of the vehicle is abnormal, storing the collected data of the data collection terminal in the local data platform includes: Acquire the local storage capacity of the local data platform in real time, and when the local storage capacity reaches a preset threshold, selectively screen the local storage data of the local data platform according to the data collection time sequence or importance level to obtain the data to be processed; The collected data of the local data platform is quickly analyzed by the lightweight analysis unit of the local data platform, and key feature information in the analysis result is extracted and saved; After the analysis is completed, the data to be processed is deleted or compressed and stored.

[0013] In a possible implementation, obtaining the network status of the vehicle includes: Obtain signal strength parameters, bandwidth parameters, and delay parameters of the network link; Inputting the signal strength parameter, bandwidth parameter and delay parameter of the network link into a network status evaluation model to obtain a comprehensive network status score value; If the network status comprehensive score value is less than a preset threshold, the vehicle is judged to be in an abnormal network state; if the network status comprehensive score value is greater than or equal to a preset threshold, the vehicle is judged to be in a normal network state; the network status evaluation model satisfies the following expression: P=W s *f(S)+W b xg(B)+W p xh(D), where P is the comprehensive score of the network status, and functions f(S), g(B), and h(D) are normalized processing functions for signal strength, bandwidth, and delay, respectively. s , W b , W p They are the weight coefficients of the impact of network link signal strength, bandwidth, and delay on the network status.

[0014] In a possible implementation, before inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report, the method further includes: Acquiring vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data, and driving condition data; According to the vehicle operation characteristic data, parameters of the pre-trained original fault prediction model are adjusted or optimized to obtain a target fault prediction model; The target data is input into the target fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report.

[0015] Different from the prior art, the commercial vehicle operation and maintenance prediction system provided by the embodiment of the present application integrates a data acquisition terminal, a data middle platform, a fault prediction and evaluation module, a remote supervision platform, and a self-learning and optimization module. The data acquisition terminal collects core vehicle data through multiple sensors and transmits it in real time through a data transmission interface; the data middle platform includes a local data platform and a cloud data platform to ensure that the data can be stored safely even when the network is unstable, and when the network conditions meet the preset requirements, the locally stored collected data is synchronized to the cloud for data cleaning and processing to obtain the target data; the fault prediction and evaluation module receives the target data, uses the built-in fault prediction model to perform fault prediction and evaluation, and generates a fault prediction report; the remote supervision platform receives the fault prediction report to achieve remote supervision and decision support; the self-learning and optimization module continuously optimizes the fault prediction model according to the vehicle operation characteristic data. In this way, the commercial vehicle operation and maintenance prediction system of the present application realizes efficient and accurate prediction and management of commercial vehicle operation and maintenance through comprehensive and real-time data collection and analysis, combined with advanced fault prediction models and remote supervision platforms. At the same time, through continuous adjustment of self-learning and optimization modules, the system's prediction accuracy and adaptability are continuously improved, providing strong technical support for commercial vehicle operation, maintenance and inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 the structures shown in these drawings without paying creative work.

[0017] Figure 1 This is a schematic diagram of the structure of a commercial vehicle operation and maintenance prediction system in some embodiments of the present application; Figure 2 This is a flow chart of a commercial vehicle operation and maintenance prediction method in some embodiments of the present application; Figure 3 A schematic diagram of a flow chart of a commercial vehicle operation and maintenance prediction method in other embodiments of the present application; Figure 4 This is a schematic diagram of the module structure of a commercial vehicle operation and maintenance prediction system in some embodiments of the present application.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0021] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] In the operation of commercial vehicles, vehicle operation and maintenance are crucial and directly related to transportation efficiency, operating costs and driving safety. The traditional commercial vehicle maintenance method mainly relies on regular manual inspections and post-fault repairs, which has many disadvantages. On the one hand, the cycle of regular manual inspections is difficult to accurately determine, which may cause sudden vehicle failures during the inspection interval, affecting normal operations; on the other hand, post-fault repairs are often carried out after the failure has occurred, which not only has high maintenance costs, but may also cause economic losses such as cargo transportation delays, and even endanger driving safety in some cases.

[0023] With the rapid development of information technology, the degree of vehicle electrification is constantly improving, and more and more sensors are being used in commercial vehicles, which enables vehicles to collect a large amount of operating data in real time. However, how to effectively collect, process and analyze these massive amounts of data and extract valuable information from them for fault prediction and operation and maintenance decision-making has become an urgent problem to be solved.

[0024] like Figure 1As shown, in the embodiment of the present application, the commercial vehicle operation and maintenance prediction system includes a data acquisition terminal 100, a data center (including a local data platform 200 and a cloud data platform 300), a fault prediction and evaluation module 400, a remote monitoring platform 500, and a self-learning and optimization module 600. Among them, The data acquisition terminal 100 includes a plurality of data acquisition sensors, which are used to collect core data of vehicle target components, and the data acquisition terminal has a data transmission interface for transmitting the collected core data to the outside; the vehicle target components may include an engine, a gearbox, a braking system, etc., and the core data may include temperature, pressure, vibration, speed, etc. The data acquisition sensors may include temperature sensors, pressure sensors, vibration sensors, speed detectors, cameras, etc.

[0025] The data middle station is connected to the data acquisition terminal 100 in communication. The local data platform 200 is used to receive and store the first collected data of the multiple data acquisition sensors when the vehicle network status does not meet the preset conditions, and transmit the first collected data to the cloud data platform 300 when the vehicle network status meets the preset conditions; the cloud data platform 300 is used to receive and store the first collected data and the second collected data of the multiple data acquisition sensors when the vehicle network status meets the preset conditions, and perform data cleaning processing on the first collected data and the second collected data to obtain the target data; The fault prediction and evaluation module 400 is connected to the data center for receiving the target data and performing fault prediction and evaluation on the vehicle using a built-in fault prediction model to obtain a fault prediction and evaluation report; The remote supervision platform 500 is connected to the fault prediction and evaluation module 400 and is used to receive the fault prediction and evaluation report to achieve remote supervision and decision support for the operation, maintenance and repair of commercial vehicles; The self-learning and optimization module 600 is used to collect vehicle operation characteristic data and adjust or optimize parameters of a built-in fault prediction model according to the vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data, and driving condition data.

[0026] The commercial vehicle operation and maintenance prediction system of the embodiment of the present application integrates a data acquisition terminal, a data middle platform (local data platform and cloud data platform), a fault prediction and evaluation module, a remote supervision platform, and a self-learning and optimization module. The data acquisition terminal collects the core data of the vehicle target components through multiple data acquisition sensors and transmits it to the data middle platform. The local data platform receives and stores the first collected data of the data acquisition sensor when the vehicle network status does not meet the preset conditions (for example, the network status is not good), and transmits the first collected data to the cloud data platform when the vehicle network status meets the preset conditions (for example, the network status is good). At the same time, the cloud data platform also receives and stores the second collected data of the data acquisition sensor, so that the first collected data and the second collected data form a continuous and complete data chain. After obtaining the complete data chain, the cloud data platform performs data cleaning to obtain the target data; after obtaining the target data, the advanced fault prediction model is used to accurately predict and evaluate the vehicle fault, and decision support is provided through the remote supervision platform. At the same time, the system can also automatically optimize the fault prediction model according to the vehicle operation characteristic data to realize intelligent operation and maintenance management.

[0027] For example, a commercial vehicle engine is equipped with multiple sensors to monitor its operating status, including temperature sensors, pressure sensors, vibration sensors, etc. These sensors will collect data in real time and transmit the data to local and cloud storage. After obtaining a complete data chain, the cloud data center can use its powerful computing power and prediction model to process and analyze the data to obtain the prediction results of vehicle failures, thereby realizing the prediction and early warning of vehicle operation and maintenance.

[0028] In one embodiment, the data acquisition terminal 100 also includes an adaptive sampling management unit 110, which dynamically adjusts the sampling frequency of the data acquisition sensor according to the operating state of the vehicle, wherein the sampling frequency is reduced when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a state of high-load operation of key components or a fault warning state.

[0029] Specifically, in the embodiment of the present application, the adaptive sampling management unit 110 of the data acquisition terminal can dynamically adjust the sampling frequency of the data acquisition sensor according to the vehicle's operating status. When the vehicle is running stably, the system will automatically reduce the sampling frequency in order to save resources; when the key components of the vehicle are under high load or receive a fault warning signal, the sampling frequency will be increased accordingly to ensure that more key data is captured. This method helps to optimize the data collection process and reduce resource consumption while ensuring data quality.

[0030] In one embodiment, the local data platform 200 includes a storage management unit 210 and a lightweight analysis unit 220. The storage management unit 210 is used to monitor the local storage capacity of the local data platform in real time. When the local storage capacity reaches a preset threshold, the first collected data is selectively deleted or compressed for storage according to the data collection time sequence or importance level; the lightweight analysis unit 220 is used to perform a preliminary analysis on the first collected data to obtain lightweight fault warning information, and when the vehicle network status does not meet the preset conditions and exceeds the preset time, the lightweight fault warning information is sent to the cloud data platform.

[0031] Exemplarily, the lightweight analysis unit 220 works in conjunction with the storage management unit 210. When the storage management unit 210 performs a selective deletion or compressed storage operation, the lightweight analysis unit 220 prioritizes the first collected data (including the data to be processed) for rapid analysis, and extracts and saves the key feature information in the analysis result. It is particularly important that when the vehicle network status is poor and the duration exceeds a preset threshold, the lightweight analysis unit 220 can send these key warning information to the cloud data platform in a timely manner to ensure that important information is not lost.

[0032] like Figure 1-Figure 3 As shown, the following takes the commercial vehicle operation and maintenance prediction system executing the commercial vehicle operation and maintenance prediction method as an example for explanation. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here. Figure 2 The method includes the following steps S200 to S800: Step S200, obtaining first collected data and second collected data, wherein the first collected data is collected data stored in a local data platform, including collected data from a data collection terminal when the network status of the vehicle does not meet a preset condition, and the second collected data is collected data stored in a cloud data platform, including collected data from a data collection terminal when the network status of the vehicle meets a preset condition; Specifically, in the embodiment of the present application, the system obtains the first collected data from the local data platform, which is collected and stored by the data collection terminal when the vehicle network status is poor; at the same time, the system obtains the second collected data from the cloud data platform, which is collected and uploaded to the cloud by the data collection terminal when the vehicle network status is good. The first collected data and the second collected data together constitute a comprehensive data set of vehicle operation, providing accurate and comprehensive data support for subsequent vehicle operation and maintenance forecasts.

[0033] In order to improve the comprehensiveness and accuracy of data collection, and thus improve the accuracy of vehicle operation and maintenance forecasting, in one embodiment, before the step S200: obtaining the first collected data and the second collected data, it also includes: Step S110, starting the data acquisition terminal to acquire data according to the data acquisition instruction; Step S120, obtaining the network status of the vehicle, wherein the network status of the vehicle includes a normal status and an abnormal status; Step S130, storing the collected data according to the network status of the vehicle, wherein when the network status of the vehicle is abnormal, the collected data of the data collection terminal is stored in the local data platform, and when the network status of the vehicle is normal, the collected data of the data collection terminal is stored in the cloud data platform.

[0034] Specifically, after the system receives the data collection instruction, it immediately starts the data collection terminal and begins to comprehensively collect the operating data of the key components of the vehicle to ensure the integrity and real-time nature of the data. Then, the system will monitor the vehicle's network connection in real time and accurately determine whether the vehicle is in a normal network state or an abnormal network state. Finally, according to the vehicle's network status, the system intelligently selects the data storage location. When the vehicle's network status is abnormal, the system will store the collected data of the data collection terminal on the local data platform first to ensure that the data is not lost; when the vehicle's network status is normal, the collected data will be uploaded and stored on the cloud data platform for subsequent data analysis and processing.

[0035] It should be noted that, in the embodiment of the present application, the network status of the vehicle refers to the stability of the vehicle when communicating with the outside world. The normal network status of the vehicle indicates that the vehicle is relatively stable when communicating with the outside world, and the abnormal network status of the vehicle indicates that the vehicle is unstable when communicating with the outside world. In one embodiment, obtaining the network status of the vehicle includes: obtaining the signal strength parameters, bandwidth parameters and delay parameters of the network link; inputting the signal strength parameters, bandwidth parameters and delay parameters of the network link into the network status evaluation model to obtain a comprehensive network status score; determining that the comprehensive network status score is less than a preset threshold, determining that the vehicle is in an abnormal network state; determining that the comprehensive network status score is greater than or equal to a preset threshold, determining that the vehicle is in a normal network state; the network status evaluation model satisfies the following expression: P=Ws*f(S)+Wbxg(B)+Wpxh(D), where P is the comprehensive score of the network status, functions f(S), g(B), and h(D) are the normalized processing functions of signal strength, bandwidth, and delay, respectively, and Ws, Wb, and Wp are the weight coefficients of the impact of network link signal strength, bandwidth, and delay on the network status, respectively.

[0036] In one embodiment, the functions f(S), g(B), and h(D) are respectively expressed as follows: ; ; ; Specifically, when the signal strength S is less than or equal to the minimum signal strength S min When , f(S) = 0. This means that if the signal strength is below a certain lower limit, its normalized score is 0. min and the maximum signal strength S max When the signal strength S is greater than or equal to the maximum signal strength S max When , f(S) = 1, indicating that if the signal strength is above a certain upper limit, its normalized score is 1. Since the bandwidth B has a very large range of values, from very low bandwidth (such as a few kbps) to very high bandwidth (such as several Gbps or even higher), the use of a logarithmic function can compress this large range of data into a relatively small range, which is convenient for processing and comparison. The normalization process is similar to the normalization process of signal strength and will not be repeated here. Similarly, the normalization process of latency will not be repeated. It can be understood that when the comprehensive network status score exceeds the preset threshold, it indicates that the vehicle's network status is normal, and when the comprehensive network status score is lower than the preset threshold, it indicates that the vehicle's network status is abnormal.

[0037] It should be noted that since the vehicle contains large-capacity data such as images, the bandwidth requirement for vehicle data transmission is relatively high. The embodiment of the present application appropriately increases the value of Wb to make the network status assessment model more reasonable, that is, Ws is 0.3, Wb is 0.4, and Wp is 0.3.

[0038] In the embodiment of the present application, by combining the normalized processing functions of signal strength, bandwidth, and delay with their respective weight coefficients, the network status evaluation model can comprehensively consider the impact of these three key network parameters on the vehicle network status, so that it can simply and effectively determine whether the vehicle is in a normal network state, providing a strong basis for vehicle network management and troubleshooting.

[0039] In order to ensure the accuracy and validity of the data and optimize the efficiency of data collection. In one embodiment, the steps: starting the data collection terminal to collect data according to the data collection instruction to obtain the collected data include: obtaining the vehicle operation state, the vehicle operation state includes a stable driving state, a key component high-load operation or a fault warning state; dynamically adjusting the sampling frequency of the data collection sensor according to the vehicle operation state, wherein the sampling frequency is reduced when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a key component high-load operation or a fault warning state.

[0040] Specifically, first, the system acquires the running status of the vehicle in real time, including whether the vehicle is in a stable driving state, whether the key components are in high-load operation, or whether a fault warning signal is issued. Then, the system dynamically adjusts the sampling frequency of the data acquisition sensor according to the running status of the vehicle. Specifically, when the vehicle is in a stable driving state, the load and performance parameters of the key components do not change much because the vehicle runs smoothly, so the system will reduce the sampling frequency of the data acquisition sensor to reduce unnecessary data redundancy and reduce the cost of data acquisition and storage. When the vehicle is in a state of high-load operation of key components or a fault warning, the system will immediately increase the sampling frequency of the data acquisition sensor. This is because in these two cases, the performance parameters of the key components of the vehicle may change rapidly, and even abnormal conditions may occur. By increasing the sampling frequency, the system can capture these changes more accurately, providing more detailed and accurate data support for subsequent data analysis and fault prediction.

[0041] In this way, by dynamically adjusting the sampling frequency of the data acquisition sensor according to the vehicle's operating status, the system can optimize the efficiency of data acquisition while ensuring data accuracy and effectiveness, providing more accurate data support for vehicle operation and maintenance predictions.

[0042] In one embodiment, the step: when the network status of the vehicle is abnormal, the collected data of the data collection terminal is stored on the local data platform, including: obtaining the local storage capacity of the local data platform in real time, and when the local storage capacity reaches a preset threshold, selectively screening the local storage data of the local data platform according to the data collection time sequence or importance level to obtain the data to be processed; quickly analyzing the collected data of the local data platform by the lightweight analysis unit of the local data platform, and extracting and saving the key feature information in the analysis results; deleting or compressing and storing the data to be processed after the analysis is completed.

[0043] Specifically, when the network status of the vehicle is judged to be abnormal, the system will first obtain the local storage capacity information of the local data platform in real time. This is to ensure that there is enough space available on the local data platform before storing new data, so as to avoid data loss caused by insufficient storage space. If the local storage capacity approaches or reaches the preset threshold, the system will start the selective screening mechanism. This mechanism will evaluate the locally stored data based on the time sequence of data collection or the level of importance. Specifically, data collected earlier or with lower importance may be given priority as pending data to make room for the storage of new data. Then, the system will use the built-in lightweight analysis unit of the local data platform to quickly analyze the collected data. This analysis process aims to extract key feature information from the data, which is crucial for subsequent fault prediction and operation and maintenance decision-making. Through lightweight analysis, the system can greatly reduce the storage requirements of data without sacrificing too much analysis accuracy. After the analysis is completed, the system will delete or compress the data to be processed. For data that is no longer needed or of lower importance, the system will directly delete it; for data that still has a certain value but occupies a large space, the system will use a compression algorithm to store it to further save storage space.

[0044] In this way, through real-time monitoring of local storage capacity, selective data screening, lightweight analysis, and data deletion or compressed storage processing, the system can ensure effective storage management of the local data platform when the vehicle network status is abnormal, and provide reliable data support for subsequent data analysis and fault prediction.

[0045] Step S400: performing data cleaning processing on the first collected data and the second collected data to obtain target data; In the embodiment of the present application, the purpose of performing data cleaning on the first collected data and the second collected data is to remove noise, errors and incomplete data therein to obtain high-quality target data. The data cleaning process includes but is not limited to removing duplicate data, filling missing values, and identifying and correcting outliers.

[0046] Step S600: input the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report; The fault prediction model is pre-trained, and during its training process, it uses a large amount of historical vehicle data, which covers data from the normal operation of the vehicle and data before the fault is about to occur. The model can be built based on a variety of machine learning algorithms, such as decision trees, support vector machines, and neural networks. By learning from a large amount of data, the model can accurately capture various features and patterns in the data. For example, when the vehicle engine oil temperature shows a gradual upward trend while the oil pressure gradually decreases, the model can recognize that this combination pattern may indicate that the engine is at risk of failure.

[0047] Therefore, by inputting the target data obtained after a series of processing of the data collected by the data acquisition terminal into this pre-trained fault prediction model, the prediction and evaluation of vehicle faults can be realized, and the corresponding fault prediction and evaluation report can be generated. This method can efficiently and accurately provide a strong basis for vehicle fault prevention and maintenance, reduce the losses caused by sudden faults, and ensure the safety and reliability of vehicle operation.

[0048] It can be understood that the parameters in the fault prediction model are affected by external factors such as the vehicle operating environment. Therefore, in one embodiment, the step of: before inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report, also includes: obtaining vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data, and driving condition data; adjusting or optimizing the parameters of the pre-trained original fault prediction model according to the vehicle operation characteristic data to obtain a target fault prediction model; and inputting the target data into the target fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report.

[0049] Specifically, assume that the vehicle model information, driving environment data, and driving condition data are as follows: The target vehicle is a certain brand of SUV, model A-2023. The design specifications and performance parameters of its engine are different from those of other models. The maximum power of this model of engine is 180kW and the maximum torque is 350 N・m. The vehicle is driving in a mountainous area with an ambient temperature of 10℃ and a humidity of 80%. The mountain roads are undulating and often require climbing and descending. The average vehicle speed is 60km / h, with frequent acceleration and an engine speed between 2000 and 3000 rpm.

[0050] The principles for adjusting or optimizing the parameters of the original fault prediction model are as follows: 1) Based on the vehicle model: Since the engine power of this model is large, its normal operating temperature range is relatively high. In the original model, the threshold parameters of the engine temperature may need to be adjusted. For example, the upper limit of the normal engine temperature in the original model is 100°C, which can be adjusted to 110°C for this model of engine. 2) Based on the driving environment: The probability of electrical system failure of the engine increases with high humidity. In the original model, parameters related to electrical system failure (such as short circuit failure probability) may need to be adjusted. Assume that the probability of electrical system failure in the original model is 0.05, and it is adjusted to 0.1 in a high humidity environment. 3) Based on driving conditions: The wear rate of the engine will increase if the vehicle accelerates frequently. Parameters related to engine wear in the original model (such as wear coefficient) need to be adjusted. Assume that the wear coefficient of the engine per 1,000 kilometers in the original model is 0.05, and it is adjusted to 0.08 under frequent acceleration.

[0051] After adjusting or optimizing the parameters of the pre-trained original fault prediction model according to the vehicle operation characteristic data to obtain the target fault prediction model, the target data is input into the target fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report.

[0052] Step S800: sending the fault prediction assessment report to a remote monitoring platform, wherein the remote monitoring platform includes a user terminal APP.

[0053] In the embodiment of the present application, the report content may include information such as the failure probability, expected failure time, possible impact range of the failure, etc. of each key component of the vehicle. For example, the report points out that the front tires of the vehicle are expected to have a 30% probability of excessive wear and tear and cause a blowout after 5,000 kilometers, and recommends tire inspection and replacement in advance. After obtaining the fault prediction assessment report, the fault prediction assessment report is sent to the remote supervision platform. After the remote supervision platform (such as the user terminal APP) learns of the fault prediction assessment report, it can contact the owner by phone or other means to exchange information, thereby reminding the vehicle driver to perform maintenance operations.

[0054] The commercial vehicle operation and maintenance prediction system provided in an embodiment of the present application also includes a memory 1000 and a processor 2000, wherein the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the commercial vehicle operation and maintenance prediction method as described above.

[0055] Among them, the processor 2000 is used to provide computing and control capabilities to control the commercial vehicle operation and maintenance prediction system to perform corresponding tasks, for example, to control the commercial vehicle operation and maintenance prediction system to execute the commercial vehicle operation and maintenance prediction method in any of the above method embodiments, the method comprising: obtaining first collected data and second collected data, the first collected data being collected data stored in a local data platform, including collected data of a data collection terminal when the network status of the vehicle does not meet preset conditions, and the second collected data being collected data stored in a cloud data platform, including collected data of a data collection terminal when the network status of the vehicle meets preset conditions; performing data cleaning processing on the first collected data and the second collected data to obtain target data; inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report; and sending the fault prediction evaluation report to a remote supervision platform, the remote supervision platform including a user terminal APP.

[0056] The processor 2000 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or any combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0057] The memory 1000 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the commercial vehicle operation and maintenance prediction method in the embodiment of the present application. The processor 2000 can implement the commercial vehicle operation and maintenance prediction method in any of the above method embodiments by running the non-transient software programs, instructions and modules stored in the memory 1000.

[0058] Specifically, the memory 1000 may include a volatile memory (VM), such as a random access memory (RAM); the memory 1000 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD) or other non-transitory solid-state storage device; the memory 1000 may also include a combination of the above-mentioned types of memory.

[0059] To sum up, the commercial vehicle operation and maintenance prediction system of the present application adopts the technical solution of any one of the above-mentioned commercial vehicle operation and maintenance prediction method embodiments, and therefore, it has at least the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here one by one.

[0060] The present application also provides a computer-readable storage medium, such as a memory including a program code, and the program code can be executed by a processor to complete the commercial vehicle operation and maintenance prediction method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0061] The present application also provides a computer program product, which includes one or more program codes stored in a computer-readable storage medium. The processor of the commercial vehicle operation and maintenance prediction system reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the commercial vehicle operation and maintenance prediction method provided in the above embodiment.

[0062] A person skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be accomplished by hardware or by hardware associated with a program code, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0063] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or by hardware. It can be understood by those skilled in the art that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0065] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A commercial vehicle operation and maintenance prediction system, characterized in that: The system comprises: A data acquisition terminal, comprising a plurality of data acquisition sensors, wherein the plurality of data acquisition sensors are used to acquire core data of a target component of a vehicle, and the data acquisition terminal is provided with a data transmission interface for transmitting the acquired core data to the outside; A data middle platform, which is in communication connection with the data acquisition terminal, comprises a local data platform and a cloud data platform, wherein the local data platform is used to receive and store the first collected data of the multiple data acquisition sensors when the vehicle network status does not meet the preset conditions, and transmit the first collected data to the cloud data platform when the vehicle network status meets the preset conditions; the cloud data platform is used to receive and store the first collected data and the second collected data of the multiple data acquisition sensors when the vehicle network status meets the preset conditions, and perform data cleaning processing on the first collected data and the second collected data to obtain the target data; A fault prediction and evaluation module is connected to the data center for receiving the target data and performing fault prediction and evaluation on the vehicle using a built-in fault prediction model to obtain a fault prediction and evaluation report; A remote supervision platform, connected to the fault prediction and evaluation module, for receiving the fault prediction and evaluation report to achieve remote supervision and decision support for the operation, maintenance and repair of commercial vehicles; The self-learning and optimization module is used to collect vehicle operation characteristic data and adjust or optimize parameters of the built-in fault prediction model according to the vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data and driving condition data.

2. The commercial vehicle operation and maintenance prediction system according to claim 1, characterized in that: The local data platform includes: A storage management unit, the storage management unit is used to monitor the local storage capacity of the local data platform in real time, and when the local storage capacity reaches a preset threshold, selectively delete or compress the first collected data according to the data collection time sequence or importance level; A lightweight analysis unit, wherein the lightweight analysis unit is used to perform a preliminary analysis on the first collected data to obtain lightweight fault warning information, and when the vehicle network status does not meet a preset condition and exceeds a preset time, the lightweight fault warning information is sent to the cloud data platform.

3. The commercial vehicle operation and maintenance prediction system according to claim 2, characterized in that: The lightweight analysis unit works in coordination with the storage management unit. When the storage management unit performs a selective deletion or compression storage operation, the lightweight analysis unit preferentially performs a quick analysis on the first collected data and extracts and saves key feature information in the analysis result.

4. The commercial vehicle operation and maintenance prediction system according to claim 1, characterized in that: The data acquisition terminal also includes: An adaptive sampling management unit, wherein the adaptive sampling management unit dynamically adjusts the sampling frequency of the data acquisition sensor according to the operating state of the vehicle, wherein the sampling frequency is reduced when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a state of high load operation of key components or a fault warning state.

5. A commercial vehicle operation and maintenance forecasting method, characterized in that: Applied to a commercial vehicle operation and maintenance forecasting system, the method comprises: Acquire first collected data and second collected data, wherein the first collected data is collected data stored in a local data platform, including collected data from a data collection terminal when the network status of the vehicle does not meet a preset condition, and the second collected data is collected data stored in a cloud data platform, including collected data from a data collection terminal when the network status of the vehicle meets a preset condition; Performing data cleaning on the first collected data and the second collected data to obtain target data; Inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report; The fault prediction assessment report is sent to a remote monitoring platform, which includes a user terminal APP.

6. The commercial vehicle operation and maintenance prediction method according to claim 5, characterized in that: Before acquiring the first collected data and the second collected data, the method further includes: According to the data collection instruction, the data collection terminal is started to collect data to obtain the collected data; Acquiring a network status of a vehicle, wherein the network status of the vehicle includes a normal status and an abnormal status; The collected data is stored according to the network status of the vehicle, wherein when the network status of the vehicle is abnormal, the collected data of the data collection terminal is stored in a local data platform, and when the network status of the vehicle is normal, the collected data of the data collection terminal is stored in a cloud data platform.

7. The commercial vehicle operation and maintenance prediction method according to claim 6, characterized in that: The step of starting the data acquisition terminal to acquire data according to the data acquisition instruction includes: Acquiring the vehicle operation status, wherein the vehicle operation status includes a stable driving state, a key component high-load operation or a fault warning state; The sampling frequency of the data acquisition sensor is dynamically adjusted according to the operating status of the vehicle, wherein the sampling frequency is lowered when the vehicle is in a stable driving state, and the sampling frequency is increased when the vehicle is in a state of high-load operation of key components or a fault warning state.

8. The commercial vehicle operation and maintenance prediction method according to claim 6, characterized in that: When the network status of the vehicle is abnormal, storing the collected data of the data collection terminal on the local data platform includes: Acquire the local storage capacity of the local data platform in real time, and when the local storage capacity reaches a preset threshold, selectively screen the local storage data of the local data platform according to the data collection time sequence or importance level to obtain the data to be processed; The collected data of the local data platform is quickly analyzed by the lightweight analysis unit of the local data platform, and key feature information in the analysis result is extracted and saved; After the analysis is completed, the data to be processed is deleted or compressed and stored.

9. The commercial vehicle operation and maintenance prediction method according to claim 6, characterized in that: The obtaining of the network status of the vehicle includes: Obtain signal strength parameters, bandwidth parameters, and delay parameters of the network link; Inputting the signal strength parameter, bandwidth parameter and delay parameter of the network link into a network status evaluation model to obtain a comprehensive network status score value; If the network status comprehensive score value is less than a preset threshold, the vehicle is judged to be in an abnormal network state; if the network status comprehensive score value is greater than or equal to a preset threshold, the vehicle is judged to be in a normal network state; the network status evaluation model satisfies the following expression: P=W s *f(S)+W b xg(B)+W p xh(D), where P is the comprehensive score of the network status, and functions f(S), g(B), and h(D) are normalized processing functions for signal strength, bandwidth, and delay, respectively. s , W b , W p They are the weight coefficients of the impact of network link signal strength, bandwidth, and delay on the network status.

10. The commercial vehicle operation and maintenance prediction method according to claim 5, characterized in that: Before inputting the target data into a pre-trained fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report, the method further includes: Acquiring vehicle operation characteristic data, wherein the vehicle operation characteristic data includes vehicle model information, driving environment data, and driving condition data; According to the vehicle operation characteristic data, parameters of the pre-trained original fault prediction model are adjusted or optimized to obtain a target fault prediction model; The target data is input into the target fault prediction model to perform fault prediction evaluation on the vehicle to obtain a fault prediction evaluation report.

Images