Heavy vehicle maintenance system based on data analysis

Abstract

The invention discloses a heavy vehicle maintenance system based on data analysis, which relates to the technical field of data analysis, comprises a detection module, an analysis module and a compensation module, and is used for calculating the daily average bearing capacity, obtaining the distance of a branch, the vehicle departure time of a starting node of the branch, the vehicle arrival time of a tail node of the branch and the distance of an uneven road section, and calculating the average preparation speed and the unevenness of the branches, calculating the daily average preparation speed and the daily average unevenness, constructing a maintenance model, and compensating the maintenance model. According to the invention, the accuracy and efficiency of information acquisition are improved through the identification of the vehicle identity code, the collected vehicle information provides a rich data basis for the subsequent analysis, and the maintenance strategy is optimized through the analysis of the stop cargo record, the segmentation of the track line into the sub-lines, the calculation of the average allocation speed and the unevenness, and the maintenance efficiency is improved. And on the basis of data-driven prediction analysis, potential maintenance requirements can be identified in advance, the maintenance model is automatically adjusted, and it is ensured that the maintenance model is always kept efficient and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a heavy vehicle repair and maintenance system based on data analysis. Background Art

[0002] In recent years, data analysis technology has been widely used in vehicle maintenance and repair. Modern heavy-duty vehicles are generally equipped with advanced sensors and monitoring systems that can monitor vehicle status in real time, provide fault warnings and maintenance recommendations. Through big data analysis and machine learning, they can predict the failure probability of vehicle components, implement more scientific maintenance strategies, reduce downtime, and improve maintenance efficiency and cost-effectiveness.

[0003] At present, a VR-based vehicle repair and maintenance assistance system is disclosed in a Chinese invention patent with publication number CN 111507488 B. The method reproduces the vehicle repair process through virtual reality technology. Maintenance personnel can understand the repair process more intuitively by watching the virtual repair process demonstration, which lays a foundation for vehicle maintenance. However, the relevant technology does not predict the maintenance of the vehicle according to the actual operation trajectory of the vehicle, which makes the system lack foresight, does not analyze the vehicle's operating parameters based on multi-party data linkage, and lacks comprehensiveness and objectivity of the analysis. Summary of the invention

[0004] The technical problem solved by the present invention is that the related art does not predict the maintenance of the vehicle according to the actual operation trajectory of the vehicle, which makes the system lack foresight, does not analyze the operating parameters of the vehicle based on the linkage of multi-party data, and lacks comprehensiveness and objectivity of the analysis.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A heavy vehicle repair and maintenance system based on data analysis includes a detection module, an analysis module and a compensation module;

[0006] The detection module identifies the vehicle identification code, sends an acquisition instruction according to the identification result, acquires the tire maintenance record corresponding to the vehicle identification code according to the acquisition instruction, and acquires the vehicle information within the interval time of adjacent tire maintenance records, wherein the vehicle information includes the vehicle model, track route and stop sites, wherein the basic cycle of the track route and the stop sites is one day;

[0007] The analysis module assigns a first number to the stop stations, obtains the cargo receiving record and cargo assembly record, the vehicle arrival time and the vehicle departure time of the stop stations after the first number, calculates the vehicle's load-bearing capacity according to the cargo receiving record and cargo assembly record of the stop stations, traverses the load-bearing capacity, calculates the daily average load-bearing capacity, divides the trajectory line into sub-lines according to the stop stations, sets the sub-lines as branches, uses the two end nodes of the branches to represent the second number of the branches, sets the stop stations as nodes, obtains the distance of the branches, the vehicle departure time of the starting node of the branches, the vehicle arrival time of the end node of the branches and the distance of the uneven road section, calculates the average speed and unevenness of the branches, traverses the average speed and unevenness of each branch, calculates the daily average speed and daily average unevenness, and constructs a maintenance model according to the daily average speed, daily average unevenness and daily average load-bearing capacity;

[0008] The compensation module obtains the current daily average pace, the current daily average unevenness, the current daily average load-bearing capacity and the last tire maintenance date, predicts the maintenance date according to the maintenance model, obtains the actual maintenance date, subtracts the actual maintenance date from the predicted maintenance date to obtain an error time period, and compensates the maintenance model according to the error time period.

[0009] As a preferred solution of the heavy vehicle maintenance system based on data analysis described in the present invention, the detection module identifies the vehicle identity code, sends an acquisition instruction according to the recognition result, and acquires the tire maintenance record corresponding to the vehicle identity code according to the acquisition instruction. The recognition logic of the vehicle identity code includes:

[0010] A vehicle sensing fence is set, and a sensing pressure threshold is preset. When the vehicle sensing fence senses pressure and the pressure is greater than or equal to the sensing pressure threshold, a camera start instruction is sent. According to the camera start instruction, the camera focal length, camera angle and light compensation value are adjusted, and the corresponding captured image is obtained. The number of pixels belonging to the vehicle identity code in the captured image is counted, recorded as the first number, the total number of pixels is counted, recorded as the second number, the ratio of the first number to the second number is calculated, recorded as the validity, and the second value is set as the validity threshold. When the validity is greater than or equal to the validity threshold, a scan instruction is sent, the network is connected, and the vehicle identity code is scanned through the camera to obtain a scan result. The scan result includes vehicles belonging to site management and vehicles not belonging to site management. A first operation is performed according to the scan result. When the scan result is a vehicle belonging to site management, the first operation is set to send an acquisition instruction. When the scan result is a vehicle not belonging to site management, the first operation is set to jump to the next vehicle.

[0011] As a preferred solution of the heavy-duty vehicle maintenance system based on data analysis described in the present invention, the detection module obtains vehicle information within the time period between adjacent tire maintenance records, the adjacent tire maintenance records are represented as two tire maintenance records that are close in time sequence, the vehicle information includes vehicle model, trajectory route and stopover site, wherein the basic cycle of the trajectory route and the stopover site is one day, the trajectory route is obtained by remote sensing technology, and the stopover site is provided with a radio frequency identification tag, and the radio frequency identification tag and the vehicle identity code recognize each other.

[0012] As a preferred solution of the heavy-duty vehicle maintenance system based on data analysis described in the present invention, the analysis module assigns a first number to the stop stations, the first number is represented by Xi, which is a natural number, and obtains the goods receiving record and goods assembling record, vehicle arrival time and vehicle departure time corresponding to the stop stations after the first number, the goods receiving record includes the weight of the received goods and the corresponding warehouse manager number, and the goods assembling record includes the weight of the assembled goods and the corresponding warehouse manager number.

[0013] As a preferred solution of the heavy vehicle maintenance system based on data analysis described in the present invention, the analysis module calculates the vehicle's load-bearing capacity according to the cargo receiving and cargo assembly records of the stopover station, and the calculation logic of the load-bearing capacity includes:

[0014] Obtain the initial load-bearing capacity of the vehicle when it arrives at the stopover station, obtain the weight of the received cargo and the weight of the assembled cargo, set the initial load-bearing capacity and the weight of the assembled cargo to positive values, set the weight of the received cargo to negative values, calculate the initial load-bearing capacity, the weight of the assembled cargo and the weight of the received cargo after distinguishing between positive and negative values, perform weighted calculation, obtain a first sum, and set the first sum as the load-bearing capacity.

[0015] The analysis module traverses the load-bearing capacity of each stop station and calculates the average daily load-bearing capacity. The calculation logic of the average daily load-bearing capacity includes: obtaining the load-bearing capacity of each stop station, performing weighted calculation on the load-bearing capacity of each stop station to obtain a second sum value, counting the number of stop stations, calculating the quotient of the second sum value and the number of stop stations, and setting the quotient of the second sum value and the number of stop stations as the average daily load-bearing capacity.

[0016] As a preferred solution of the heavy vehicle maintenance system based on data analysis of the present invention, the analysis module divides the track route into sub-routes according to the stop sites, sets the sub-routes as branches, and uses the nodes at both ends of the branches to represent the second number of the branches, and the second number of the branches is represented by X i X i+1, set the stopover station as a node, construct a vehicle operation topology map, and mark the relevant data of the node and the relevant data of the branch on the vehicle operation topology map, the relevant data of the node includes the vehicle departure time and the vehicle arrival time, the nodes are distributed at both ends of the branch, and are represented as the starting node and the end node of the branch according to the direction of the vehicle trajectory, and the relevant data of the branch includes the distance of the branch and the distance of the uneven road section;

[0017] The distance of the branch, the vehicle departure time of the starting node of the branch, the vehicle arrival time of the end node of the branch and the distance of the uneven road section are obtained, the average speed and unevenness of the branch are calculated, the average speed and unevenness of each branch are traversed, the average daily speed and the average daily unevenness are calculated, and a maintenance model is constructed according to the average daily speed, the average daily unevenness and the average daily load.

[0018] As a preferred solution of the heavy vehicle maintenance system based on data analysis described in the present invention, the calculation logic of the average daily speed includes:

[0019] According to the vehicle departure time of the starting node of the branch and the vehicle arrival time of the end node of the branch, the time period of the vehicle driving on the branch is calculated, recorded as the first time period, the ratio of the distance of the branch to the first time period is calculated, recorded as the first ratio, the first ratios are traversed, each first ratio is weighted to obtain a third sum, the number of branches is counted, the ratio of the third sum to the number of branches is calculated, and the ratio of the third sum to the number of branches is set as the daily average pace;

[0020] The calculation logic of the daily average roughness includes: calculating the ratio of the distance of the uneven road section to the distance of the branch, recording it as the second ratio, setting the second ratio as the roughness, the roughness is distributed between [0,1], traversing the roughness, calculating the sum of each roughness, recording it as the fourth sum, calculating the ratio of the fourth sum to the number of branches, and setting the ratio of the fourth sum to the number of branches as the daily average roughness.

[0021] As a preferred solution of the heavy vehicle maintenance system based on data analysis described in the present invention, the construction logic of the maintenance model includes:

[0022] The interval time between adjacent tire maintenance records is obtained and recorded as the second time period. The second time period is used as the dependent variable, and the average daily speed, the average daily unevenness and the average daily load are used as the dependent variables. Multiple regression analysis is performed to obtain a maintenance model. The calculation expression of the maintenance model is:

[0023] M=C 1 V+C 2 L+C 3 W

[0024] Where M is the maintenance interval, V, L and W are the average daily speed, average daily roughness and average daily load, respectively, and C 1 ~C 3 They are the coefficients corresponding to the average daily pace, average daily roughness and average daily load-bearing capacity respectively.

[0025] As a preferred solution of the heavy-duty vehicle maintenance system based on data analysis described in the present invention, wherein: the compensation module obtains the current daily average speed, the current daily average unevenness, the current daily average load and the last tire maintenance date, inputs the current daily average speed, the current daily average unevenness and the current daily average load into the maintenance model, obtains the predicted maintenance interval time period, the last tire maintenance date and the predicted maintenance interval time period to obtain the predicted maintenance date, consults with the maintenance staff to obtain the consulted maintenance date, and sets the consulted maintenance date as the actual maintenance date;

[0026] The actual maintenance date is subtracted from the predicted maintenance date to obtain an error time period, and the maintenance model is compensated according to the error time period.

[0027] As a preferred solution of the heavy vehicle maintenance system based on data analysis described in the present invention, the logic of compensating the maintenance model includes:

[0028] Obtain an error time period, calculate the square value of the error time period, traverse the square values ​​of the error time period, calculate the sum of the square values ​​of the error time period, record it as the fifth sum value, count the number of error time periods, record it as the number of samples, calculate the ratio of the fifth sum value to the number of samples, record it as the fifth ratio, set the fifth ratio as the compensation amount, weight the compensation amount and the predicted maintenance date, and obtain the compensated predicted maintenance date.

[0029] The beneficial effects of the present invention are as follows: through the identification of the vehicle identity code, the maintenance records related to the specific vehicle can be quickly obtained, thereby improving the accuracy and efficiency of information acquisition; the collected vehicle information, such as model, track and stopover stations, provides a rich data basis for subsequent analysis, and facilitates the identification of factors affecting vehicle performance; by analyzing the cargo records at the stopover stations, the system can dynamically evaluate the vehicle's load-bearing capacity, help determine the vehicle's performance under different conditions of use, divide the track line into sub-lines and calculate the average speed and unevenness, which helps to identify sections that affect tire wear, thereby optimizing maintenance strategies; combined with the average daily load-bearing capacity, speed and unevenness, the system can build a scientific maintenance model, which is based on data-driven predictive analysis and helps to identify potential maintenance needs in advance; by comparing the actual maintenance date with the predicted maintenance date, the maintenance model is automatically adjusted to ensure that it always remains efficient and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1A schematic diagram of the basic flow of a heavy vehicle maintenance system based on data analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0032] Example, see Figure 1 , as one embodiment of the present invention, provides a heavy vehicle repair and maintenance system based on data analysis, including a detection module, an analysis module and a compensation module;

[0033] The detection module identifies the vehicle identification code, sends an acquisition instruction according to the identification result, acquires the tire maintenance record corresponding to the vehicle identification code according to the acquisition instruction, and acquires the vehicle information within the interval time of adjacent tire maintenance records, wherein the vehicle information includes the vehicle model, track route and stop sites, wherein the basic cycle of the track route and the stop sites is one day;

[0034] The analysis module assigns a first number to the stop stations, obtains the cargo receiving record and cargo assembly record, the vehicle arrival time and the vehicle departure time of the stop stations after the first number, calculates the vehicle's load-bearing capacity according to the cargo receiving record and cargo assembly record of the stop stations, traverses the load-bearing capacity, calculates the daily average load-bearing capacity, divides the trajectory line into sub-lines according to the stop stations, sets the sub-lines as branches, uses the two end nodes of the branches to represent the second number of the branches, sets the stop stations as nodes, obtains the distance of the branches, the vehicle departure time of the starting node of the branches, the vehicle arrival time of the end node of the branches and the distance of the uneven road section, calculates the average speed and unevenness of the branches, traverses the average speed and unevenness of each branch, calculates the daily average speed and daily average unevenness, and constructs a maintenance model according to the daily average speed, daily average unevenness and daily average load-bearing capacity;

[0035] The compensation module obtains the current daily average pace, the current daily average unevenness, the current daily average load-bearing capacity and the last tire maintenance date, predicts the maintenance date according to the maintenance model, obtains the actual maintenance date, subtracts the actual maintenance date from the predicted maintenance date to obtain an error time period, and compensates the maintenance model according to the error time period.

[0036] The present invention can quickly obtain maintenance records related to a specific vehicle by identifying the vehicle identity code, thereby improving the accuracy and efficiency of information acquisition. The collected vehicle information, such as model, trajectory and stopover stations, provides a rich data basis for subsequent analysis, and is convenient for identifying factors that affect vehicle performance. By analyzing the cargo records at the stopover stations, the system can dynamically evaluate the vehicle's load-bearing capacity, help determine the vehicle's performance under different conditions of use, divide the trajectory line into sub-lines and calculate the average speed and unevenness, which helps to identify sections that affect tire wear, thereby optimizing maintenance strategies. Combined with the average daily load-bearing capacity, speed and unevenness, the system can build a scientific maintenance model, which is based on data-driven predictive analysis and helps to identify potential maintenance needs in advance. By comparing the actual maintenance date with the predicted maintenance date, the maintenance model is automatically adjusted to ensure that it always remains efficient and accurate.

[0037] The detection module identifies the vehicle identity code, sends an acquisition instruction according to the recognition result, and acquires the tire maintenance record corresponding to the vehicle identity code according to the acquisition instruction. The recognition logic of the vehicle identity code includes:

[0038] A vehicle sensing fence is set, and a sensing pressure threshold is preset. When the vehicle sensing fence senses pressure and the pressure is greater than or equal to the sensing pressure threshold, a camera start instruction is sent. According to the camera start instruction, the camera focal length, camera angle and light compensation value are adjusted, and the corresponding captured image is obtained. The number of pixels belonging to the vehicle identity code in the captured image is counted, recorded as the first number, the total number of pixels is counted, recorded as the second number, the ratio of the first number to the second number is calculated, recorded as the validity, and the second value is set as the validity threshold. When the validity is greater than or equal to the validity threshold, a scan instruction is sent, the network is connected, and the vehicle identity code is scanned through the camera to obtain a scan result. The scan result includes vehicles belonging to site management and vehicles not belonging to site management. A first operation is performed according to the scan result. When the scan result is a vehicle belonging to site management, the first operation is set to send an acquisition instruction. When the scan result is a vehicle not belonging to site management, the first operation is set to jump to the next vehicle.

[0039] In the specific implementation, by setting the vehicle sensing fence and presetting the sensing pressure threshold, it is ensured that the camera is started only when it is actually needed, thereby reducing misidentification and invalid operations, and adjusting the focal length, angle and light compensation value of the camera to effectively improve the clarity of the captured image, and provide higher quality image data for subsequent pixel statistics and identity code recognition. By calculating the effectiveness, the ratio of effective pixels to total pixels, it is ensured that the identity code scan is only performed when the image quality is high enough, thereby improving the reliability of recognition. The scanning results are used to determine whether the vehicle belongs to the site management vehicle, ensuring that subsequent operations are only performed on related vehicles, improving management efficiency, and enabling the system to collect and manage data more accurately, providing strong support for subsequent maintenance decisions.

[0040] The detection module obtains vehicle information within the time period between adjacent tire maintenance records, wherein the adjacent tire maintenance records are represented as two tire maintenance records that are close in time sequence, and the vehicle information includes vehicle model, track route and stop sites, wherein the basic cycle of the track route and the stop sites is one day, the track route is obtained by remote sensing technology, and the stop sites are provided with radio frequency identification tags, and the radio frequency identification tags and the vehicle identity code recognize each other.

[0041] In specific implementation, by obtaining vehicle information in the time period between adjacent tire maintenance records, the vehicle's usage status can be understood more accurately, providing a comprehensive maintenance basis. Recording tire maintenance data that is close in time sequence is helpful to identify the vehicle's usage pattern, thereby optimizing maintenance timing and extending the service life of tires and vehicles. Using remote sensing technology to obtain trajectory routes, it is possible to track vehicle driving conditions in real time, ensure the accuracy and timeliness of data, and provide reliable support for subsequent analysis. Stops are equipped with radio frequency identification tags that recognize each other with the vehicle's identity code, thereby improving the data collection efficiency at stop sites and ensuring the accuracy of information. Through comprehensive analysis of vehicle models, trajectories and stop sites, the system can formulate more dynamic and scientific strategies to respond to different situations in a timely manner.

[0042] The analysis module assigns a first number to the stopover station, where the first number is represented by Xi and is a natural number, and obtains the goods receiving record and goods assembling record, vehicle arrival time and vehicle departure time corresponding to the stopover station after the first number, where the goods receiving record includes the weight of the goods received and the corresponding warehouse manager number, and the goods assembling record includes the weight of the goods assembled and the corresponding warehouse manager number.

[0043] In the specific implementation, the stopover stations are numbered to make management more orderly and facilitate subsequent data tracking and statistical analysis. By obtaining the records of receiving and assembling goods, the flow of goods at each stopover station can be fully understood, providing reliable data for inventory management. Recording the weight of received and assembled goods and the relevant administrator numbers helps to track responsibilities and improve the transparency and responsibility of goods management.

[0044] The analysis module calculates the vehicle's load-bearing capacity according to the cargo receiving and cargo assembling records of the stopover station. The calculation logic of the load-bearing capacity includes:

[0045] Obtain the initial load-bearing capacity of the vehicle when it arrives at the stopover station, obtain the weight of the received cargo and the weight of the assembled cargo, set the initial load-bearing capacity and the weight of the assembled cargo to positive values, set the weight of the received cargo to negative values, calculate the initial load-bearing capacity, the weight of the assembled cargo and the weight of the received cargo after distinguishing between positive and negative values, perform weighted calculation, obtain a first sum, and set the first sum as the load-bearing capacity.

[0046] The analysis module traverses the load-bearing capacity of each stop station and calculates the average daily load-bearing capacity. The calculation logic of the average daily load-bearing capacity includes: obtaining the load-bearing capacity of each stop station, performing weighted calculation on the load-bearing capacity of each stop station to obtain a second sum value, counting the number of stop stations, calculating the quotient of the second sum value and the number of stop stations, and setting the quotient of the second sum value and the number of stop stations as the average daily load-bearing capacity.

[0047] In the specific implementation, through clear calculation logic, the received goods are set as negative values ​​and the assembled goods are set as positive values, ensuring that the load-bearing capacity assessment is more accurate and reflects the actual load situation of the vehicle. The load-bearing capacity is dynamically calculated at each stop based on the actual weight of the received and assembled goods, so that the system can adapt to changes in different transportation stages. Through weighted calculation of the load-bearing capacity of each stop, the average daily load-bearing capacity obtained can better reflect the operating conditions of the vehicle under different conditions, which is helpful for subsequent maintenance decisions.

[0048] The analysis module divides the track route into sub-routes according to the stop sites, sets the sub-routes as branches, and uses the nodes at both ends of the branches to represent the second number of the branches, and the second number of the branches is represented by X i X i+1 , set the stopover station as a node, construct a vehicle operation topology map, and mark the relevant data of the node and the relevant data of the branch on the vehicle operation topology map, the relevant data of the node includes the vehicle departure time and the vehicle arrival time, the nodes are distributed at both ends of the branch, and are represented as the starting node and the end node of the branch according to the direction of the vehicle trajectory, and the relevant data of the branch includes the distance of the branch and the distance of the uneven road section;

[0049] The distance of the branch, the vehicle departure time of the starting node of the branch, the vehicle arrival time of the end node of the branch and the distance of the uneven road section are obtained, the average speed and unevenness of the branch are calculated, the average speed and unevenness of each branch are traversed, the average daily speed and the average daily unevenness are calculated, and a maintenance model is constructed according to the average daily speed, the average daily unevenness and the average daily load.

[0050] The calculation logic of the daily average pace includes:

[0051] According to the vehicle departure time of the starting node of the branch and the vehicle arrival time of the end node of the branch, the time period of the vehicle driving on the branch is calculated, recorded as the first time period, the ratio of the distance of the branch to the first time period is calculated, recorded as the first ratio, the first ratios are traversed, each first ratio is weighted to obtain a third sum, the number of branches is counted, the ratio of the third sum to the number of branches is calculated, and the ratio of the third sum to the number of branches is set as the daily average pace;

[0052] The calculation logic of the daily average roughness includes: calculating the ratio of the distance of the uneven road section to the distance of the branch, recording it as the second ratio, setting the second ratio as the roughness, the roughness is distributed between [0,1], traversing the roughness, calculating the sum of each roughness, recording it as the fourth sum, calculating the ratio of the fourth sum to the number of branches, and setting the ratio of the fourth sum to the number of branches as the daily average roughness.

[0053] In the specific implementation, by constructing a vehicle operation topology map, the vehicle's operation trajectory and stop locations are intuitively displayed, which is convenient for managers to monitor and analyze the operation status in real time. The node and branch related data are marked on the topology map to provide detailed information background for subsequent analysis, enhance the readability and traceability of the data, traverse the average speed and unevenness of each branch, calculate the average daily speed and daily average unevenness, and provide management with more comprehensive vehicle operation data.

[0054] The construction logic of the maintenance model includes:

[0055] The interval time between adjacent tire maintenance records is obtained and recorded as the second time period. The second time period is used as the dependent variable, and the average daily speed, the average daily unevenness and the average daily load are used as the dependent variables. Multiple regression analysis is performed to obtain a maintenance model. The calculation expression of the maintenance model is:

[0056] M=C 1 V+C 2 L+C 3 W

[0057] Where M is the maintenance interval, V, L and W are the average daily speed, average daily roughness and average daily load, respectively, and C 1 ~C 3They are the coefficients corresponding to the average daily pace, average daily roughness and average daily load-bearing capacity respectively.

[0058] In specific implementation, the time periods of adjacent tire maintenance records are used as dependent variables to scientifically predict maintenance intervals and help formulate reasonable maintenance plans. The average daily speed, average daily unevenness and average daily load are used as independent variables. Through multiple regression analysis, the accuracy and reliability of the model are improved. Based on the calculation results of the model, managers can make more data-driven decisions and optimize vehicle maintenance and management processes.

[0059] The compensation module obtains the current daily average speed, the current daily average unevenness, the current daily average load and the last tire maintenance date, inputs the current daily average speed, the current daily average unevenness and the current daily average load into the maintenance model, obtains the predicted maintenance interval time period, obtains the predicted maintenance date from the last tire maintenance date and the predicted maintenance interval time period, consults with the maintenance staff to obtain the consulted maintenance date, and sets the consulted maintenance date as the actual maintenance date;

[0060] The actual maintenance date is subtracted from the predicted maintenance date to obtain an error time period, and the maintenance model is compensated according to the error time period.

[0061] The logic for compensating the maintenance model includes:

[0062] Obtain an error time period, calculate the square value of the error time period, traverse the square values ​​of the error time period, calculate the sum of the square values ​​of the error time period, record it as the fifth sum value, count the number of error time periods, record it as the number of samples, calculate the ratio of the fifth sum value to the number of samples, record it as the fifth ratio, set the fifth ratio as the compensation amount, weight the compensation amount and the predicted maintenance date, and obtain the compensated predicted maintenance date.

[0063] In specific implementation, by inputting the current average daily speed, unevenness and load-bearing capacity, combined with the maintenance model, the maintenance date of the tire can be effectively predicted. By comparing the actual maintenance date with the predicted maintenance date, errors can be identified, providing a basis for dynamic adjustment, and improving the accuracy of the model. By consulting the maintenance date and combining the actual situation, it can ensure that the maintenance arrangement is closer to reality, improve the flexibility and response speed of management, and optimize the maintenance model based on compensation for the error time period, improve the ability to predict future maintenance needs, and improve the accuracy of the prediction.

[0064] The present invention can quickly obtain maintenance records related to a specific vehicle by identifying the vehicle identity code, thereby improving the accuracy and efficiency of information acquisition. The collected vehicle information, such as model, trajectory and stopover stations, provides a rich data basis for subsequent analysis, and is convenient for identifying factors that affect vehicle performance. By analyzing the cargo records at the stopover stations, the system can dynamically evaluate the vehicle's load-bearing capacity, help determine the vehicle's performance under different conditions of use, divide the trajectory line into sub-lines and calculate the average speed and unevenness, which helps to identify sections that affect tire wear, thereby optimizing maintenance strategies. Combined with the average daily load-bearing capacity, speed and unevenness, the system can build a scientific maintenance model, which is based on data-driven predictive analysis and helps to identify potential maintenance needs in advance. By comparing the actual maintenance date with the predicted maintenance date, the maintenance model is automatically adjusted to ensure that it always remains efficient and accurate.

[0065] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A heavy vehicle maintenance system based on data analysis, characterized in that: It includes a detection module, an analysis module and a compensation module; The detection module identifies the vehicle identification code, sends an acquisition instruction according to the identification result, acquires the tire maintenance record corresponding to the vehicle identification code according to the acquisition instruction, and acquires the vehicle information within the interval time of adjacent tire maintenance records, wherein the vehicle information includes the vehicle model, track route and stop sites, wherein the basic cycle of the track route and the stop sites is one day; The analysis module assigns a first number to the stop stations, obtains the cargo receiving record and cargo assembly record, the vehicle arrival time and the vehicle departure time of the stop stations after the first number, calculates the vehicle's load-bearing capacity according to the cargo receiving record and cargo assembly record of the stop stations, traverses the load-bearing capacity, calculates the daily average load-bearing capacity, divides the trajectory line into sub-lines according to the stop stations, sets the sub-lines as branches, uses the two end nodes of the branches to represent the second number of the branches, sets the stop stations as nodes, obtains the distance of the branches, the vehicle departure time of the starting node of the branches, the vehicle arrival time of the end node of the branches and the distance of the uneven road section, calculates the average speed and unevenness of the branches, traverses the average speed and unevenness of each branch, calculates the daily average speed and daily average unevenness, and constructs a maintenance model according to the daily average speed, daily average unevenness and daily average load-bearing capacity; The compensation module obtains the current daily average pace, the current daily average unevenness, the current daily average load-bearing capacity and the last tire maintenance date, predicts the maintenance date according to the maintenance model, obtains the actual maintenance date, subtracts the actual maintenance date from the predicted maintenance date to obtain an error time period, and compensates the maintenance model according to the error time period.

2. The heavy vehicle maintenance system based on data analysis as claimed in claim 1, characterized in that: The detection module identifies the vehicle identity code, sends an acquisition instruction according to the recognition result, and acquires the tire maintenance record corresponding to the vehicle identity code according to the acquisition instruction. The recognition logic of the vehicle identity code includes: A vehicle sensing fence is set, and a sensing pressure threshold is preset. When the vehicle sensing fence senses pressure and the pressure is greater than or equal to the sensing pressure threshold, a camera start instruction is sent. According to the camera start instruction, the camera focal length, camera angle and light compensation value are adjusted, and the corresponding captured image is obtained. The number of pixels belonging to the vehicle identity code in the captured image is counted, recorded as the first number, the total number of pixels is counted, recorded as the second number, the ratio of the first number to the second number is calculated, recorded as the validity, and the second value is set as the validity threshold. When the validity is greater than or equal to the validity threshold, a scan instruction is sent, the network is connected, and the vehicle identity code is scanned through the camera to obtain a scan result. The scan result includes vehicles belonging to site management and vehicles not belonging to site management. A first operation is performed according to the scan result. When the scan result is a vehicle belonging to site management, the first operation is set to send an acquisition instruction. When the scan result is a vehicle not belonging to site management, the first operation is set to jump to the next vehicle.

3. The heavy vehicle maintenance system based on data analysis as claimed in claim 2, characterized in that: The detection module obtains vehicle information within the time period between adjacent tire maintenance records, wherein the adjacent tire maintenance records are represented as two tire maintenance records that are close in time sequence, and the vehicle information includes vehicle model, track route and stop sites, wherein the basic cycle of the track route and the stop sites is one day, the track route is obtained by remote sensing technology, and the stop sites are provided with radio frequency identification tags, and the radio frequency identification tags and the vehicle identity code recognize each other.

4. The heavy vehicle maintenance system based on data analysis as claimed in claim 1, characterized in that: The analysis module assigns a first number to the stopover station, where the first number is represented by Xi and is a natural number, and obtains the goods receiving record and goods assembling record, vehicle arrival time and vehicle departure time corresponding to the stopover station after the first number, where the goods receiving record includes the weight of the goods received and the corresponding warehouse manager number, and the goods assembling record includes the weight of the goods assembled and the corresponding warehouse manager number.

5. The heavy vehicle maintenance system based on data analysis as claimed in claim 4, characterized in that: The analysis module calculates the vehicle's load-bearing capacity according to the cargo receiving and cargo assembling records of the stopover station. The calculation logic of the load-bearing capacity includes: Obtain the initial load-bearing capacity of the vehicle when it arrives at the stopover station, obtain the weight of the received cargo and the weight of the assembled cargo, set the initial load-bearing capacity and the weight of the assembled cargo to positive values, set the weight of the received cargo to negative values, calculate the initial load-bearing capacity, the weight of the assembled cargo and the weight of the received cargo after distinguishing between positive and negative values, perform weighted calculation, obtain a first sum, and set the first sum as the load-bearing capacity. The analysis module traverses the load-bearing capacity of each stop station and calculates the average daily load-bearing capacity. The calculation logic of the average daily load-bearing capacity includes: obtaining the load-bearing capacity of each stop station, performing weighted calculation on the load-bearing capacity of each stop station to obtain a second sum value, counting the number of stop stations, calculating the quotient of the second sum value and the number of stop stations, and setting the quotient of the second sum value and the number of stop stations as the average daily load-bearing capacity.

6. The heavy vehicle maintenance system based on data analysis as claimed in claim 5, characterized in that: The analysis module divides the track route into sub-routes according to the stop sites, sets the sub-routes as branches, and uses the nodes at both ends of the branches to represent the second number of the branches, and the second number of the branches is represented by X i X i+1 , set the stopover station as a node, construct a vehicle operation topology map, and mark the relevant data of the node and the relevant data of the branch on the vehicle operation topology map, the relevant data of the node includes the vehicle departure time and the vehicle arrival time, the nodes are distributed at both ends of the branch, and are represented as the starting node and the end node of the branch according to the direction of the vehicle trajectory, and the relevant data of the branch includes the distance of the branch and the distance of the uneven road section; The distance of the branch, the vehicle departure time of the starting node of the branch, the vehicle arrival time of the end node of the branch and the distance of the uneven road section are obtained, the average speed and unevenness of the branch are calculated, the average speed and unevenness of each branch are traversed, the average daily speed and the average daily unevenness are calculated, and a maintenance model is constructed according to the average daily speed, the average daily unevenness and the average daily load.

7. The heavy vehicle maintenance system based on data analysis as claimed in claim 6, characterized in that: The calculation logic of the daily average pace includes: According to the vehicle departure time of the starting node of the branch and the vehicle arrival time of the end node of the branch, the time period of the vehicle driving on the branch is calculated, recorded as the first time period, the ratio of the distance of the branch to the first time period is calculated, recorded as the first ratio, the first ratios are traversed, each first ratio is weighted to obtain a third sum, the number of branches is counted, the ratio of the third sum to the number of branches is calculated, and the ratio of the third sum to the number of branches is set as the daily average pace; The calculation logic of the daily average roughness includes: calculating the ratio of the distance of the uneven road section to the distance of the branch, recording it as the second ratio, setting the second ratio as the roughness, the roughness is distributed between [0,1], traversing the roughness, calculating the sum of each roughness, recording it as the fourth sum, calculating the ratio of the fourth sum to the number of branches, and setting the ratio of the fourth sum to the number of branches as the daily average roughness.

8. The heavy vehicle maintenance system based on data analysis as claimed in claim 6, characterized in that: The construction logic of the maintenance model includes: The interval time between adjacent tire maintenance records is obtained and recorded as the second time period. The second time period is used as the dependent variable, and the average daily speed, the average daily unevenness and the average daily load are used as the dependent variables. Multiple regression analysis is performed to obtain a maintenance model. The calculation expression of the maintenance model is: M=C1V+C2L+C3W Among them, M is the maintenance interval time period, V, L and W are the average daily pace, average daily roughness and average daily load-bearing capacity, respectively, and C1~C3 are the coefficients corresponding to the average daily pace, average daily roughness and average daily load-bearing capacity, respectively.

9. The heavy vehicle maintenance system based on data analysis as claimed in claim 1, characterized in that: The compensation module obtains the current daily average speed, the current daily average unevenness, the current daily average load and the last tire maintenance date, inputs the current daily average speed, the current daily average unevenness and the current daily average load into the maintenance model, obtains the predicted maintenance interval time period, obtains the predicted maintenance date from the last tire maintenance date and the predicted maintenance interval time period, consults with the maintenance staff to obtain the consulted maintenance date, and sets the consulted maintenance date as the actual maintenance date; The actual maintenance date is subtracted from the predicted maintenance date to obtain an error time period, and the maintenance model is compensated according to the error time period.

10. The heavy vehicle maintenance system based on data analysis as claimed in claim 9, characterized in that: The logic for compensating the maintenance model includes: Obtain an error time period, calculate the square value of the error time period, traverse the square values ​​of the error time period, calculate the sum of the square values ​​of the error time period, record it as the fifth sum value, count the number of error time periods, record it as the number of samples, calculate the ratio of the fifth sum value to the number of samples, record it as the fifth ratio, set the fifth ratio as the compensation amount, weight the compensation amount and the predicted maintenance date, and obtain the compensated predicted maintenance date.

Images