Construction vehicle intelligent control data analysis method and system based on AI technology
Through AI technology, the operation data of construction vehicles are analyzed, their impact on the construction site is identified, and different driving speeds are set according to the impact results, which solves the problems of ground sinking and road wear caused by insufficient vehicle speed regulation in the existing technology, and realizes the Intelligent management and cost reduction of construction vehicles.
Patent Information
- Application Number
- CN202410552827.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-05-07
AI Technical Summary
The prior art cannot regulate its speed according to the driving route of the construction vehicle, resulting in ground sinking on routes with low ground compaction or high road wear, increasing the maintenance cost of the construction site.
Using intelligent control data analysis method of construction vehicles based on AI technology, the operation status data is collected through geomagnetic vehicle detectors, a data drive model is established to identify the impact results of the vehicle, and different driving speeds are set according to the impact results and construction requirements, so as to limit the vehicle to Speeds of different sections to predict and extend the length of sections.
The maximum use time of the road section is achieved, the cost of ground maintenance in the construction site is reduced, the construction efficiency and safety is improved, and the rational use of resources and the smooth progress of construction is ensured.
Smart Images

Figure CN118571002B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of construction vehicle management, and in particular to a construction vehicle intelligent management and control data analysis method and system based on AI technology. Background Art
[0002] Construction generally refers to construction activities carried out in buildings, infrastructure, and engineering projects, which may include civil engineering, building construction, equipment installation, decoration and decoration, etc., while construction vehicles refer to various vehicles used in construction sites or engineering projects. They are used to transport materials, equipment, and perform specific engineering tasks.
[0003] With the advancement of science and technology, driverless vehicles are increasingly being used in construction sites. Driverless construction vehicles can carry construction materials and equipment or carry heavy objects without manual operation on land construction sites, thereby improving transportation efficiency. The use of driverless construction vehicles can not only improve construction efficiency and accuracy, but also significantly reduce labor costs and safety risks. In order to ensure the safety and intelligence of use while reducing manual intervention, it is extremely necessary to carry out intelligent management and control of driverless construction vehicles.
[0004] However, in the prior art, when controlling vehicles in a construction site, it is impossible to adjust the driving speed according to the route. If the vehicle speed is too fast, it will have a greater impact on the route when the ground is less compacted or the road is more worn. For example, the ground may sink at the route location, which will affect the environment of the construction site and increase the cost of subsequent treatment of the sinking. Summary of the invention
[0005] In order to solve the above problems, the present invention proposes a construction vehicle intelligent management and control data analysis method and system based on AI technology, so as to achieve the maximum usage time of road sections and reduce the cost of ground maintenance in construction sites.
[0006] In order to achieve the above object, the present invention adopts the following technical solution:
[0007] In a first aspect, the present invention provides a construction vehicle intelligent control data analysis method based on AI technology, and the construction vehicle intelligent control data analysis method comprises the following steps:
[0008] S1. Mark the vehicles in the construction site as control objects, use the geomagnetic vehicle detector to collect the operation status data of the construction vehicles, and transmit it to the control server using data integration transmission. The operation status data includes the driving route, driving speed and driving time;
[0009] S2. The control server loads the driving trajectory of the construction vehicle according to the operating status data and the environment in the construction site, and establishes a data-driven model to identify the impact results of the construction vehicle;
[0010] S3. Create a new vehicle operation section based on the impact results and construction needs, and set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation section;
[0011] S4, determining the curve relationship between the use time and the driving speed, and setting the vehicle running section as different speed limit zones according to the determination result;
[0012] S5. Use AI technology to convert the vehicle's running section into coordinate points within the construction site, and input them into the construction vehicle controller together with the corresponding speed limit for management and control.
[0013] Preferably, the control server loads the driving trajectory of the construction vehicle according to the running status data and the environment in the construction site, and establishes a data-driven model to identify the impact of the construction vehicle, including the following steps:
[0014] S21. The control server separates the scattering points of the driving routes in the same batch of operation status data through dynamic planning according to the environment in the construction site;
[0015] S22, using the scattering points to obtain a time-varying three-dimensional image of the trajectory change to reconstruct and extract trajectory points, and connecting the trajectory points to obtain the driving trajectory of the construction vehicle;
[0016] S23, construct a data-driven model based on driving trajectory, driving speed, driving duration and construction site environment to simulate environmental changes during driving;
[0017] S24, measuring the straight-line distance between the boundary of the driving track and the result of the environmental change to determine the impact of the construction vehicle when driving.
[0018] Preferably, reconstructing and extracting trajectory points by using scattering points to obtain a time-varying three-dimensional image of trajectory changes, and connecting the trajectory points to obtain the driving trajectory of the construction vehicle comprises the following steps:
[0019] S221, amplifying the signals of the discrete points and inputting them into the micro-motion signal processing model for phase interference processing to determine the phase difference between the discrete points and obtain a time-varying three-dimensional image of the trajectory change;
[0020] S222, performing a three-dimensional coordinate reconstruction and extraction operation on the time-varying three-dimensional image to analyze the trajectory direction and change pattern to obtain trajectory points;
[0021] S223, sorting the track points in chronological order according to the timestamp information, and performing a connection operation on the track points in sequence to form a continuous driving track.
[0022] Preferably, the following steps are included in the process of constructing a data-driven model to simulate environmental changes during driving based on driving trajectory, driving speed, driving duration and construction site environment:
[0023] S231, assigning weight coefficients to driving trajectory, driving speed, and driving duration as decision variables, and setting ground compaction, road wear, and equipment placement in the construction site environment as constraint conditions;
[0024] S232, taking the intersection of the equipment placement position and the driving track as the origin and establishing a coordinate system, selecting the distance between the equipment as the calculation area to determine the coordinate point of the construction vehicle;
[0025] S233, performing a relationship derivation operation on the ground compaction and the road surface wear according to the driving speed, and determining the relationship between the driving speed of the construction vehicle and the ground compaction and the road surface wear in the calculation area;
[0026] S234. Use the judgment results and change simulation algorithm to establish a data-driven model to simulate the changes in ground compaction and road wear in the calculation area under different decision variable conditions.
[0027] Preferably, using the judgment results and the change simulation algorithm to establish a data-driven model to simulate the changes in ground compaction and road wear in the calculation area under different decision variables includes the following steps:
[0028] S2341, using a variation simulation algorithm to randomly generate a number of simulation sub-units in the calculation region, wherein the position of each simulation sub-unit in the calculation region represents a feasible solution;
[0029] S2342, according to the position of the simulator, the search direction and speed are set to find the optimal solution in the calculation area to solve the fitness function of the simulator, and a penalty term is added to the fitness function to determine the relationship between the result and the position of the simulator;
[0030] S2343, if the position relationship is less than the preset value, the fitness function with the penalty term added is used as the optimization function of the judgment result; if the position relationship is greater than the preset value, steps S2341 to S2343 need to be repeated to obtain the optimization function;
[0031] S2344, setting the optimization function of the judgment result as the driving function of the data-driven model, and taking the decision variable as the input independent variable, and the change of the ground compaction degree and the road surface wear as the output target to establish the data-driven model;
[0032] S2345. Use data-driven models to simulate the changes in ground compaction and road wear within the calculation area under different decision variables.
[0033] Preferably, creating a new vehicle operation section according to the impact results and construction requirements, and setting different driving speeds to predict the use time of the vehicle operation section in combination with the environmental information in the construction site includes the following steps:
[0034] S31. Obtain construction demand and impact results to determine the road sections where construction vehicles can travel, divide the reference area into new road networks, and plan several road sections for construction vehicles to travel within the road network;
[0035] S32, setting different driving speeds for construction vehicles according to each operating section, and collecting existing environmental information in the operating section and combining it with the impact results to obtain a correlation curve;
[0036] S33, establishing a prediction model based on the correlation curve and the running section, and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section;
[0037] S34. Calculate the time interval between terrain changes according to the input duration to obtain the usage duration of the vehicle running section under different driving speeds.
[0038] Preferably, establishing a prediction model based on the correlation curve and the running section, and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section includes the following steps:
[0039] S331, using an automatic encoder to set a preset model including input and output functions, and extracting influencing factors from the correlation curve to analyze the correlation between the factors and the terrain changes;
[0040] S332, setting the influencing factor and the driving speed as the input of the preset model, the terrain change as the output of the preset model, and using the optimization algorithm to describe the changing behavior of the terrain in the preset model;
[0041] S333, using an optimization algorithm to simulate the characteristic points of the influencing factors in the running section by means of encirclement and search motion, and selecting the positions where the terrain has changed to update the positions where the terrain has not changed according to the characteristic points;
[0042] S334, repeating steps S331 to S333 to traverse the feature points of all influencing factors, and sorting the feature points to select the optimal feature point;
[0043] S335, extracting the optimal feature points and setting the driving speed to modify the preset model to obtain a prediction model, and determining the terrain changes that occur during the driving of construction vehicles at different driving speeds in the operating section.
[0044] Preferably, the calculation formula for the correlation degree is:
[0045]
[0046] Where, T represents the correlation between the influencing factor and terrain change; M i Indicates the change value of the influencing factor in the i-th operating section; Indicates the average value of the change in the impact factor; N i represents the predicted value of terrain change of the i-th running section; represents the average value of the terrain change prediction value of the operating section; j represents the total number of operating sections.
[0047] Preferably, extracting the optimal feature points and setting the driving speed to modify the preset model to obtain a prediction model, and judging the terrain changes that occur during the driving of construction vehicles at different driving speeds in the operating section includes the following steps:
[0048] S3351, setting different values of driving speed and obtaining the optimal feature points for normalization processing, and using the automatic encoder to change the preset model parameters to set the maximum number of iterations and the regularization coefficient;
[0049] S3352, obtaining the result value of terrain change under driving speed in the running status data, and inputting the same driving speed value into the changed preset model to determine the difference error;
[0050] S3353, according to the output accuracy of the preset model after the error result is changed, if the difference is greater than the preset value, repeat step 3352 to change the preset model for the second time;
[0051] S3354. If the difference is less than the preset value, the preset model is input into the deep extreme learning machine to perform training operations to obtain a prediction model, and different driving speeds are input into the prediction model to determine the terrain changes that occur during the driving process of the construction vehicle.
[0052] In a second aspect, the present invention also provides a construction vehicle intelligent control data analysis system based on AI technology, which includes a control data acquisition module, a vehicle trajectory loading module, a road section new construction prediction module, a speed judgment and restriction module, and a road section speed conversion module;
[0053] Among them, the control data collection module, the vehicle trajectory loading module, the road section new construction prediction module, the speed judgment limit module and the road section speed conversion module are connected in sequence;
[0054] The control data collection module is used to mark the vehicles in the construction site as control objects, collect the operation status data of the construction vehicles using the geomagnetic vehicle detector, and transmit it to the control server using data integration transmission. The operation status data includes the driving route, driving speed and driving time;
[0055] The vehicle trajectory loading module is used to control the server to load the driving trajectory of the construction vehicle according to the operating status data and the environment in the construction site, and establish a data-driven model to identify the impact of the construction vehicle;
[0056] The new section prediction module is used to create new vehicle operation sections according to the impact results and construction needs, and to set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation section;
[0057] The speed judgment and restriction module is used to judge the curve relationship between the use time and the driving speed, and set the vehicle running section as different speed limit areas according to the judgment result;
[0058] The road section speed conversion module is used to use AI technology to convert the vehicle operation section into coordinate points within the construction site, and input them together with the corresponding speed limit into the construction vehicle controller for management and control.
[0059] The beneficial effects of the present invention are:
[0060] 1. The present invention uses historical construction vehicle control data to determine the impact of construction vehicles on the construction site during driving, and according to the judgment results and construction needs, builds different vehicle operation sections in the site and sets different driving speeds to predict when ground subsidence and road surface wear will occur in the section, and determines the duration of use. According to the prediction results, the driving speeds in different driving sections are limited to achieve the maximum usage time of the section, reduce the cost of ground maintenance in the construction site, and ultimately realize the intelligent management of construction vehicles, improve construction efficiency and safety, and also provide strong technical support for the rational use of resources and the smooth progress of construction.
[0061] 2. The present invention utilizes micro-motion signal processing models and dynamic programming algorithms to efficiently process operating status data, and accurately reconstructs the driving trajectory of construction vehicles by extracting trajectory points through time-varying three-dimensional image reconstruction technology. By combining construction site environmental information and driving data to build a data-driven model, the impact of construction vehicle behavior on the environment can be better simulated and predicted. By measuring the straight-line distance between the boundary of the driving trajectory and the result of environmental changes, the actual impact range of the construction vehicle can be accurately determined.
[0062] 3. The present invention divides new road networks and operating sections according to construction needs and impact results to effectively manage construction vehicles, ensuring that they operate in the most suitable sections. At the same time, different driving speeds are set for different operating sections. Combined with on-site environmental information, it is ensured that construction vehicles travel at the most appropriate speed to reduce changes in the terrain within the construction site, so as to achieve the maximum use time of the road section and reduce the cost of ground maintenance within the construction site. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0064] Figure 1 is a flow chart of a construction vehicle intelligent management and control data analysis method based on AI technology according to an embodiment of the present invention;
[0065] Figure 2 It is a principle block diagram of a construction vehicle intelligent management and control data analysis system based on AI technology according to an embodiment of the present invention.
[0066] In the figure:
[0067] 1. Control data collection module; 2. Vehicle trajectory loading module; 3. New section prediction module; 4. Speed judgment and limit module; 5. Section speed conversion module. DETAILED DESCRIPTION
[0068] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0069] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.
[0070] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0071] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.
[0072] See also Figure 1 The present invention provides a construction vehicle intelligent control data analysis method based on AI technology, and the construction vehicle intelligent control data analysis method includes the following steps:
[0073] S1. Mark the vehicles in the construction site as control objects, use the geomagnetic vehicle detector to collect the operation status data of the construction vehicles, and transmit it to the control server using data integration transmission. The operation status data includes the driving route, driving speed and driving time.
[0074] In this embodiment, marking vehicles in the construction site as control objects, using geomagnetic vehicle detectors to collect operation status data of construction vehicles, and transmitting the data to the control server in an integrated data transmission manner includes the following steps:
[0075] Install identification tags, including RFID tags or specific sensors, on unmanned construction vehicles to identify and track the location and status of each vehicle, and install geomagnetic vehicle detectors at important nodes on the construction site to sense the presence and movement status of tagged vehicles.
[0076] The geomagnetic detector is used to collect the vehicle's operating status data, including position, speed, and dwell time, and a wireless network environment is established to ensure that the data is transmitted from the geomagnetic detector in real time and accurately.
[0077] The collected data is summarized and processed through the data integration system, and the processed data is transmitted to the management and control server through the network.
[0078] S2. The control server loads the driving trajectory of the construction vehicle according to the operating status data and the environment in the construction site, and establishes a data-driven model to identify the impact results of the construction vehicle.
[0079] In this embodiment, the control server loads the driving trajectory of the construction vehicle according to the running status data and the environment in the construction site, and establishes a data-driven model to identify the impact of the construction vehicle, including the following steps:
[0080] S21. The control server separates the scattered points of the driving routes in the same batch of operation status data through dynamic planning according to the environment in the construction site.
[0081] Specifically, the control server separates the scattering points of the driving routes in the same batch of operation status data through dynamic planning according to the environment in the construction site, including the following steps:
[0082] According to the environmental characteristics of the construction site, including the terrain and the distribution of the construction area, a processing method suitable for the environment is established to identify and process the micro-motion signals generated by the vehicle during operation.
[0083] The dynamic programming algorithm is used to analyze the collected operating status data to identify key features of vehicle driving, such as acceleration, turning, etc. The scattering points of the driving route, that is, abnormal points or key turning points in the vehicle driving process, are identified in the processed data, and the identified scattering points are analyzed and adjusted to remove the final scattering points.
[0084] S22, using the scattering points to obtain a time-varying three-dimensional image of the trajectory change to reconstruct and extract trajectory points, and connecting the trajectory points to obtain the driving trajectory of the construction vehicle.
[0085] Specifically, the time-varying three-dimensional image reconstruction of the trajectory change obtained by using the scattering points extracts the trajectory points, and the trajectory points are connected to obtain the driving trajectory of the construction vehicle, which includes the following steps:
[0086] S221, amplifying the signals of the discrete points and inputting them into the micro-motion signal processing model for phase interference processing to determine the phase difference between the discrete points and obtain a time-varying three-dimensional image of the trajectory change;
[0087] S222, performing a three-dimensional coordinate reconstruction and extraction operation on the time-varying three-dimensional image to analyze the trajectory direction and change pattern to obtain trajectory points;
[0088] S223, sorting the track points in chronological order according to the timestamp information, and performing a connection operation on the track points in sequence to form a continuous driving track.
[0089] S23. Based on the driving trajectory, driving speed, driving time and construction site environment, a data-driven model is constructed to simulate the environmental changes generated during the driving process.
[0090] Specifically, the following steps are included to construct a data-driven model based on the driving trajectory, driving speed, driving time and construction site environment to simulate the environmental changes during driving:
[0091] S231, assigning weight coefficients to driving trajectory, driving speed, and driving duration as decision variables, and setting ground compaction, road wear, and equipment placement in the construction site environment as constraint conditions;
[0092] S232, taking the intersection of the equipment placement position and the driving track as the origin and establishing a coordinate system, selecting the distance between the equipment as the calculation area to determine the coordinate point of the construction vehicle;
[0093] S233, performing a relationship derivation operation on the ground compaction and the road surface wear according to the driving speed, and determining the relationship between the driving speed of the construction vehicle and the ground compaction and the road surface wear in the calculation area;
[0094] S234. Use the judgment results and change simulation algorithm to establish a data-driven model to simulate the changes in ground compaction and road wear in the calculation area under different decision variable conditions.
[0095] Among them, the change simulation algorithm can adopt the particle swarm algorithm, which is a heuristic optimization algorithm inspired by the group behavior of bird flocks or fish schools. The algorithm searches for the optimal solution or approximate optimal solution in the solution space by simulating information sharing and cooperation between individuals.
[0096] Among them, the data-driven model is established by using the judgment results and the change simulation algorithm to simulate the changes of ground compaction and road wear in the calculation area under different decision variables, including the following steps:
[0097] S2341, using a variation simulation algorithm to randomly generate a number of simulation sub-units in the calculation region, wherein the position of each simulation sub-unit in the calculation region represents a feasible solution;
[0098] S2342, according to the position of the simulator, the search direction and speed are set to find the optimal solution in the calculation area to solve the fitness function of the simulator, and a penalty term is added to the fitness function to determine the relationship between the result and the position of the simulator;
[0099] S2343, if the position relationship is less than the preset value, the fitness function with the penalty term added is used as the optimization function of the judgment result; if the position relationship is greater than the preset value, steps S2341 to S2343 need to be repeated to obtain the optimization function;
[0100] S2344, setting the optimization function of the judgment result as the driving function of the data-driven model, and taking the decision variable as the input independent variable, and the change of the ground compaction degree and the road surface wear as the output target to establish the data-driven model;
[0101] S2345. Use data-driven models to simulate the changes in ground compaction and road wear within the calculation area under different decision variables.
[0102] S24, measuring the straight-line distance between the boundary of the driving track and the result of the environmental change to determine the impact of the construction vehicle when driving.
[0103] Specifically, measuring the straight-line distance between the boundary of the driving trajectory and the environmental change result to determine the impact result of the construction vehicle when driving includes the following steps:
[0104] According to the driving trajectory data of the construction vehicle and the environmental changes of the monitored construction site, the driving trajectory data and the environmental change data are aligned to ensure consistency in time and space.
[0105] GIS spatial analysis technology is used to calculate the straight-line distance between the boundary point and the environmental change point of each driving trajectory, and the impact of the vehicle on environmental changes is analyzed based on the calculated straight-line distance.
[0106] Based on the analysis results, evaluate the specific impact of vehicle driving on the construction environment, including changes in terrain and whether it will cause ground subsidence and collapse.
[0107] Therefore, the micro-motion signal processing model and dynamic programming algorithm can be used to efficiently process the operating status data, and the trajectory points can be extracted through time-varying three-dimensional image reconstruction technology to accurately reconstruct the driving trajectory of the construction vehicle. By combining the construction site environmental information and driving data to build a data-driven model, the impact of the construction vehicle's behavior on the environment can be better simulated and predicted. By measuring the straight-line distance between the boundary of the driving trajectory and the result of the environmental change, the actual impact range of the construction vehicle can be accurately determined.
[0108] S3. Create new vehicle operation sections based on the impact results and construction needs, set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation sections.
[0109] In this embodiment, a new vehicle operation section is created according to the impact result and the construction demand, and different driving speeds are set to predict the use time of the vehicle operation section in combination with the environmental information in the construction site, including the following steps:
[0110] S31. Obtain construction demand and impact results to determine the road sections on which construction vehicles can travel, divide the reference area into new road networks, and plan several road sections for construction vehicles to operate within the road network.
[0111] Specifically, obtaining construction demand and impact results to determine the road sections where construction vehicles can travel, dividing the reference area into new road networks, and planning several sections for construction vehicles to operate in the road network include the following steps:
[0112] Analyze the needs of the construction project including the construction area, expected construction period, construction tasks and resource allocation, and design and divide the road network suitable for construction vehicles based on the construction needs and impact results.
[0113] In the newly built road network, plan several operating sections suitable for construction vehicles, ensure that the sections connect the construction areas, conduct safety assessments on the planned operating sections, and ensure that they meet safety standards.
[0114] S32. Different driving speeds are set for the construction vehicles according to each operating section, and existing environmental information in the operating section is collected and combined with the impact results to obtain a correlation curve.
[0115] Specifically, setting different driving speeds for construction vehicles according to each operating section, and collecting existing environmental information in the operating section and combining it with the impact results to obtain a correlation curve include the following steps:
[0116] For each construction vehicle operating section, an appropriate driving speed is set according to the characteristics of the section (such as the number of curves, road conditions, surrounding environment, etc.).
[0117] The existing road conditions are collected on each operating section, and the collected environmental information is integrated with the vehicle's driving speed and impact result data to form a complete data set.
[0118] Statistical analysis methods are used to establish the correlation curve between impact results and environmental information based on the integrated data.
[0119] S33, establishing a prediction model according to the associated curve and the running section, and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section.
[0120] Specifically, establishing a prediction model based on the correlation curve and the running section, and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section includes the following steps:
[0121] S331. Use an automatic encoder to set a preset model including input and output functions, and extract influencing factors from the correlation curve to analyze the degree of correlation between the factors and terrain changes.
[0122] The calculation formula of the correlation degree is:
[0123]
[0124] Where, T represents the correlation between the influencing factor and terrain change; M i Indicates the change value of the influencing factor in the i-th operating section; Indicates the average value of the change in the impact factor; N i represents the predicted value of terrain change of the i-th running section; represents the average value of the terrain change prediction value of the operating section; j represents the total number of operating sections.
[0125] S332, setting the influencing factor and the driving speed as the input of the preset model, the terrain change as the output of the preset model, and using the optimization algorithm to describe the changing behavior of the terrain in the preset model;
[0126] Among them, the optimization algorithm can adopt the whale algorithm, which generally refers to a type of heuristic optimization algorithm that is inspired by the behavior of whale groups.
[0127] S333, using an optimization algorithm to simulate the characteristic points of the influencing factors in the running section by means of encirclement and search motion, and selecting the positions where the terrain has changed to update the positions where the terrain has not changed according to the characteristic points;
[0128] S334, repeating steps S331 to S333 to traverse the feature points of all influencing factors, and sorting the feature points to select the optimal feature point;
[0129] S335, extracting the optimal feature points and setting the driving speed to modify the preset model to obtain a prediction model, and determining the terrain changes that occur during the driving of construction vehicles at different driving speeds in the operating section.
[0130] Among them, extracting the optimal feature points and setting the driving speed to modify the preset model to obtain the prediction model, and judging the terrain changes that occur during the driving of construction vehicles at different driving speeds in the operating section include the following steps:
[0131] S3351, setting different values of driving speed and obtaining the optimal feature points for normalization processing, and using the automatic encoder to change the preset model parameters to set the maximum number of iterations and the regularization coefficient;
[0132] S3352, obtaining the result value of terrain change under driving speed in the running status data, and inputting the same driving speed value into the changed preset model to determine the difference error;
[0133] S3353, according to the output accuracy of the preset model after the error result is changed, if the difference is greater than the preset value, repeat step 3352 to change the preset model for the second time;
[0134] S3354. If the difference is less than the preset value, the preset model is input into the deep extreme learning machine to perform training operations to obtain a prediction model, and different driving speeds are input into the prediction model to determine the terrain changes that occur during the driving process of the construction vehicle.
[0135] S34. Calculate the time interval between terrain changes according to the input duration to obtain the usage duration of the vehicle running section under different driving speeds.
[0136] Therefore, new road networks and operating sections are divided according to construction needs and impact results to effectively manage construction vehicles and ensure that they operate on the most suitable sections. At the same time, different driving speeds are set for different operating sections. Combined with on-site environmental information, construction vehicles are ensured to travel at the most appropriate speed to reduce changes to the terrain within the construction site, so as to achieve the maximum use time of the road section and reduce the cost of ground maintenance within the construction site.
[0137] S4. Determine the curve relationship between the use time and the driving speed, and set the vehicle running section as different speed limit areas according to the determination result.
[0138] In this embodiment, determining the curve relationship between the use time and the driving speed, and setting the vehicle running section as different speed limit areas according to the determination result includes the following steps:
[0139] Data analysis methods are used to explore the relationship between usage time and driving speed. Based on the analysis results, a curve is drawn to show the relationship between the two. The drawn curve is interpreted in detail to determine the trend of usage time changing with driving speed, and to determine the changing pattern of usage time at different driving speeds.
[0140] According to the analysis results of the curve relationship, the vehicle operation section is divided into different speed limit zones, and an appropriate speed limit is set for each area to optimize the usage time and improve safety.
[0141] Conduct safety assessments on the set speed limits to ensure that they will not have adverse effects on vehicle safety and the surrounding environment, implement new speed limits on corresponding vehicle operating sections, and set up obvious signs in each speed limit area.
[0142] S5. Use AI technology to convert the vehicle's running section into coordinate points within the construction site, and input them into the construction vehicle controller together with the corresponding speed limit for management and control.
[0143] In this embodiment, the vehicle running section is converted into coordinate points in the construction site by using AI technology, and input into the construction vehicle controller together with the corresponding speed limit to implement control, including the following steps:
[0144] Use AI technology to convert road section data into specific coordinate points within the construction site to reflect the geographical location and characteristics of the road section, and match the previously determined speed limits for each section with the corresponding coordinate points.
[0145] The converted coordinate point data and speed limit information are integrated to form a data format that can be used by the construction vehicle controller, and the controller of the unmanned construction vehicle is set to automatically adjust the vehicle's driving route and speed according to the coordinate point and speed limit information.
[0146] The integrated data is input into the construction vehicle's controller, which is then programmed and configured to ensure it can correctly guide the vehicle based on the data.
[0147] See also Figure 2 The present invention also provides a construction vehicle intelligent control data analysis system based on AI technology, which includes a control data acquisition module 1, a vehicle trajectory loading module 2, a road section new construction prediction module 3, a speed judgment and restriction module 4 and a road section speed conversion module 5;
[0148] Among them, the control data collection module 1, the vehicle trajectory loading module 2, the road section new construction prediction module 3, the speed judgment and restriction module 4 and the road section speed conversion module 5 are connected in sequence;
[0149] The control data collection module 1 is used to mark the vehicles in the construction site as control objects, collect the operation status data of the construction vehicles using the geomagnetic vehicle detector, and transmit it to the control server using the data integration transmission method. The operation status data includes the driving route, driving speed and driving time;
[0150] The vehicle trajectory loading module 2 is used to control the server to load the driving trajectory of the construction vehicle according to the running status data and the environment in the construction site, and establish a data-driven model to identify the impact results of the construction vehicle;
[0151] The new section prediction module 3 is used to create a new vehicle operation section according to the impact results and construction needs, and to set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation section;
[0152] The speed judgment and restriction module 4 is used to judge the curve relationship between the use time and the driving speed, and set the vehicle running section as different speed limit areas according to the judgment result;
[0153] The road section speed conversion module 5 is used to convert the vehicle running section into a coordinate point in the construction site by using AI technology, and input it into the construction vehicle controller together with the corresponding speed limit for management and control.
[0154] In summary, with the help of the above technical solution of the present invention, the present invention uses historical construction vehicle control data to judge the impact of construction vehicles on the construction site during driving, and sets different driving speeds according to the judgment results and construction requirements in the site to predict when the ground will sink and the road surface will be worn out. The length of time used is determined, and the driving speed in different driving sections is limited according to the prediction results to achieve the maximum use time of the section, reduce the cost of ground maintenance in the construction site, and finally realize the intelligent management of construction vehicles, improve construction efficiency and safety, and also provide strong technical support for the rational use of resources and the smooth progress of construction. The present invention uses micro-motion signal processing model and dynamic programming algorithm to efficiently process operation status data, and extracts trajectory points through time-varying three-dimensional image reconstruction technology to accurately reconstruct the driving trajectory of construction vehicles. Combined with the construction site environmental information and driving data to build a data-driven model, it can better simulate and predict the impact of the behavior of construction vehicles on the environment. By measuring the straight-line distance between the boundary of the driving trajectory and the result of environmental changes, the actual impact range of the construction vehicle can be accurately determined. The present invention divides new road networks and operating sections according to construction needs and impact results to effectively manage construction vehicles, ensuring that they operate in the most suitable sections. At the same time, different driving speeds are set for different operating sections. Combined with on-site environmental information, it is ensured that construction vehicles travel at the most appropriate speed to reduce changes in the terrain within the construction site, so as to achieve the maximum use time of the road section and reduce the cost of ground maintenance within the construction site.
[0155] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0156] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.
Claims
1. The construction vehicle intelligent control data analysis method based on AI technology is characterized by: The construction vehicle intelligent control data analysis method comprises the following steps: S1. Mark the vehicles in the construction site as control objects, use the geomagnetic vehicle detector to collect the operation status data of the construction vehicles, and transmit them to the control server in a data integration transmission mode. The operation status data includes the driving route, driving speed and driving time; S2. The control server loads the driving trajectory of the construction vehicle according to the operating status data and the environment in the construction site, and establishes a data-driven model to identify the impact results of the construction vehicle; S3. Create a new vehicle operation section based on the impact results and construction needs, and set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation section; S4, determining the curve relationship between the use time and the driving speed, and setting the vehicle running section as different speed limit zones according to the determination result; S5. Use AI technology to convert the vehicle running section into coordinate points within the construction site, and input them into the construction vehicle controller together with the corresponding speed limit for control; The control server loads the driving trajectory of the construction vehicle according to the running status data and the environment in the construction site, and establishes a data-driven model to identify the impact of the construction vehicle, including the following steps: S21. The control server separates the scattering points of the driving routes in the same batch of operation status data through dynamic planning according to the environment in the construction site; S22, using the scattering points to obtain a time-varying three-dimensional image of the trajectory change to reconstruct and extract trajectory points, and connecting the trajectory points to obtain the driving trajectory of the construction vehicle; S23, construct a data-driven model based on driving trajectory, driving speed, driving duration and construction site environment to simulate environmental changes during driving; S24, measuring the straight-line distance between the boundary of the driving track and the environmental change result to determine the impact result of the construction vehicle when driving; The method of reconstructing and extracting trajectory points by using the scattering points to obtain the time-varying three-dimensional image of the trajectory change, and connecting the trajectory points to obtain the driving trajectory of the construction vehicle comprises the following steps: S221, amplifying the signals of the discrete points and inputting them into the micro-motion signal processing model for phase interference processing to determine the phase difference between the discrete points and obtain a time-varying three-dimensional image of the trajectory change; S222, performing a three-dimensional coordinate reconstruction and extraction operation on the time-varying three-dimensional image to analyze the trajectory direction and change pattern to obtain trajectory points; S223, sorting the track points in chronological order according to the timestamp information, and performing a connection operation on the track points in sequence to form a continuous driving track.
2. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 1 is characterized in that: The method of combining the driving trajectory, driving speed, driving time and construction site environment with technology to build a data-driven model to simulate environmental changes during driving includes the following steps: S231, assigning weight coefficients to driving trajectory, driving speed, and driving duration as decision variables, and setting ground compaction, road wear, and equipment placement in the construction site environment as constraint conditions; S232, taking the intersection of the equipment placement position and the driving track as the origin and establishing a coordinate system, selecting the distance between the equipment as the calculation area to determine the coordinate point of the construction vehicle; S233, performing a relationship derivation operation on the ground compaction and the road surface wear according to the driving speed, and determining the relationship between the driving speed of the construction vehicle and the ground compaction and the road surface wear in the calculation area; S234. Use the judgment results and change simulation algorithm to establish a data-driven model to simulate the changes in ground compaction and road wear in the calculation area under different decision variable conditions.
3. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 2 is characterized in that: The method of using the judgment results and the change simulation algorithm to establish a data-driven model to simulate the changes in ground compaction and road wear in the calculation area under different decision variables includes the following steps: S2341, using a variation simulation algorithm to randomly generate a number of simulation sub-units in the calculation region, wherein the position of each simulation sub-unit in the calculation region represents a feasible solution; S2342, according to the position of the simulator, the search direction and speed are set to find the optimal solution in the calculation area to solve the fitness function of the simulator, and a penalty term is added to the fitness function to determine the relationship between the result and the position of the simulator; S2343, if the position relationship is less than the preset value, the fitness function with the penalty term added is used as the optimization function of the judgment result; if the position relationship is greater than the preset value, steps S2341 to S2343 need to be repeated to obtain the optimization function; S2344, setting the optimization function of the judgment result as the driving function of the data-driven model, and taking the decision variable as the input independent variable, and the change of the ground compaction degree and the road surface wear as the output target to establish the data-driven model; S2345. Use data-driven models to simulate the changes in ground compaction and road wear within the calculation area under different decision variables.
4. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 1 is characterized in that: The method of creating a new vehicle operation section according to the impact results and construction requirements, and setting different driving speeds and predicting the use time of the vehicle operation section in combination with the environmental information in the construction site includes the following steps: S31. Obtain construction demand and impact results to determine the road sections where construction vehicles can travel, divide the reference area into new road networks, and plan several road sections for construction vehicles to travel within the road network; S32, setting different driving speeds for construction vehicles according to each operating section, and collecting existing environmental information in the operating section and combining it with the impact results to obtain a correlation curve; S33, establishing a prediction model based on the correlation curve and the running section, and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section; S34. Calculate the time interval between terrain changes according to the input duration to obtain the usage duration of the vehicle running section under different driving speeds.
5. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 4 is characterized in that: The method of establishing a prediction model based on the associated curve and the running section and inputting different driving speeds into the prediction model to determine the terrain changes occurring in the running section comprises the following steps: S331, using an automatic encoder to set a preset model including input and output functions, and extracting influencing factors from the correlation curve to analyze the correlation between the factors and the terrain changes; S332, setting the influencing factor and the driving speed as the input of the preset model, the terrain change as the output of the preset model, and using the optimization algorithm to describe the changing behavior of the terrain in the preset model; S333, using an optimization algorithm to simulate the characteristic points of the influencing factors in the running section by means of encirclement and search motion, and selecting the positions where the terrain has changed to update the positions where the terrain has not changed according to the characteristic points; S334, repeating steps S331 to S333 to traverse the feature points of all influencing factors, and sorting the feature points to select the optimal feature point; S335, extracting the optimal feature points and setting the driving speed to modify the preset model to obtain a prediction model, and determining the terrain changes that occur during the driving of construction vehicles at different driving speeds in the operating section.
6. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 5 is characterized in that: The calculation formula of the correlation degree is: In the formula, T represents the correlation value between the influencing factor and terrain change; M i Indicates the change value of the influencing factor in the i-th operating section; It represents the average value of the change value of the impact factor; N i represents the predicted value of terrain change of the i-th running section; It represents the average value of the terrain change prediction value of the operating section; j represents the total number of running sections.
7. The construction vehicle intelligent management and control data analysis method based on AI technology according to claim 6 is characterized in that: The extracting of the optimal feature points and setting the driving speed to modify the preset model to obtain the prediction model, and judging the terrain changes occurring during the driving of the construction vehicles at different driving speeds in the running section, comprises the following steps: S3351, setting different values of driving speed and obtaining the optimal feature points for normalization processing, and using the automatic encoder to change the preset model parameters to set the maximum number of iterations and the regularization coefficient; S3352, obtaining the result value of terrain change under driving speed in the running status data, and inputting the same driving speed value into the changed preset model to determine the difference error; S3353, according to the output accuracy of the preset model after the error result is changed, if the difference is greater than the preset value, repeat step 3352 to change the preset model for the second time; S3354. If the difference is less than the preset value, the preset model is input into the deep extreme learning machine to perform training operations to obtain a prediction model, and different driving speeds are input into the prediction model to determine the terrain changes that occur during the driving process of the construction vehicle.
8. A construction vehicle intelligent control data analysis system based on AI technology, used to implement the construction vehicle intelligent control data analysis method based on AI technology as described in any one of claims 1 to 7, characterized in that: The AI-based construction vehicle intelligent control data analysis system includes a control data acquisition module, a vehicle trajectory loading module, a road section new construction prediction module, a speed judgment and restriction module, and a road section speed conversion module; Among them, the control data acquisition module, the vehicle trajectory loading module, the road section new construction prediction module, the speed judgment and restriction module and the road section speed conversion module are connected in sequence; The control data acquisition module is used to mark the vehicles in the construction site as control objects, collect the operation status data of the construction vehicles using the geomagnetic vehicle detector, and transmit it to the control server using the data integration transmission method. The operation status data includes the driving route, driving speed and driving time; The vehicle trajectory loading module is used for the control server to load the driving trajectory of the construction vehicle according to the running status data and the environment in the construction site, and establish a data-driven model to identify the impact results of the construction vehicle; The road section new construction prediction module is used to create a new vehicle operation section according to the impact results and construction needs, and set different driving speeds and combine the environmental information in the construction site to predict the use time of the vehicle operation section; The speed judgment and restriction module is used to judge the curve relationship between the use time and the driving speed, and set the vehicle running section as different speed restriction areas according to the judgment result; The road section speed conversion module is used to convert the vehicle running section into coordinate points within the construction site using AI technology, and input them together with the corresponding speed limit into the construction vehicle controller for management and control.
