Powder truck control and safety monitoring system based on artificial intelligence

Abstract

The present invention relates to the field of safety monitoring technology, and in particular to a powder vehicle control and safety monitoring system based on artificial intelligence, including a data acquisition module, a driving state analysis module, a powder state analysis module, a powder transportation risk prediction module, a powder transportation risk warning module and a control module, wherein the driving state analysis module is used to import driving state data into a driving state analysis model of a powder vehicle to analyze the driving state of the powder vehicle; the powder state analysis module is used to import the powder state data in a tank into a powder distribution state analysis model to analyze the powder distribution state in the tank during the driving process of the powder vehicle; the powder transportation risk prediction module is used to predict the powder transportation risk of the powder vehicle during the driving process according to the driving state analysis results and the powder distribution state analysis results of the powder vehicle. It can reduce the burden on drivers, improve the safety and reliability of transportation, and ensure the uniform transportation of powder.

Description

Technical Field

[0001] The present invention relates to the field of safety monitoring technology, and in particular to a powder vehicle control and safety monitoring system based on artificial intelligence. Background Art

[0002] With the continuous development of modern industrial and logistics technology, powder trucks play an increasingly important role in many industries, especially in the fields of mining, chemical industry and building materials. A powder truck is a vehicle specially used to transport powdered materials. Its tank design can ensure the uniform distribution and effective transportation of powder. However, due to the physical properties of powder and the complexity of the transportation environment, powder trucks may face safety risks such as uneven powder distribution, powder leakage, and tank damage during driving. These problems will not only affect transportation efficiency, but may also cause serious safety accidents. Therefore, in recent years, the development of artificial intelligence technology has provided new solutions for the control and safety monitoring of powder trucks. By using various sensors and artificial intelligence algorithms, real-time monitoring and analysis of powder trucks can be achieved, thereby improving the safety and efficiency of transportation.

[0003] However, the existing technology does not take into account that the driving state of the powder truck on different roads will have an important impact on the distribution of powder inside the tank; for example, when the powder truck is driving on a bumpy road, the powder inside the tank will be subjected to greater vibration and impact, resulting in the destruction of the uniformity of the powder, forming local accumulation or voids. This uneven distribution will not only increase the stress of the tank, but may also cause blockage or incomplete unloading of the powder during unloading, thereby affecting transportation efficiency and subsequent production processes.

[0004] In order to solve these problems, this application designs a powder truck control and safety monitoring system based on artificial intelligence. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the existing technology, the present invention provides an artificial intelligence-based powder truck control and safety monitoring system, which comprehensively analyzes the driving status and powder distribution status, and predicts the future powder transportation risks based on the analysis results. It improves the transportation safety of powder trucks, optimizes transportation efficiency, and reduces equipment damage and production delays caused by uneven powder distribution.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An embodiment of the present invention provides an artificial intelligence-based powder truck control and safety monitoring system, comprising a data acquisition module, a driving state analysis module, a powder state analysis module, a powder transportation risk prediction module, a powder transportation risk warning module and a control module, wherein the data acquisition module is used to collect driving state data of the powder truck and powder state data in the tank; the driving state analysis module is used to import the driving state data into a driving state analysis model of the powder truck to analyze the driving state of the powder truck; the powder state analysis module is used to import the powder state data in the tank into a powder distribution state analysis model to analyze the distribution state of the powder in the tank during the driving process of the powder truck; the powder transportation risk prediction module is used to predict the powder transportation risk of the powder truck during the driving process according to the driving state analysis results and the powder distribution state analysis results of the powder truck; the powder transportation risk warning module is used to issue a powder transportation risk warning to the driver of the powder truck according to the powder transportation risk prediction results; the control module is used to control the operation of the data acquisition module, the driving state analysis module, the powder state analysis module, the powder transportation risk prediction module and the powder transportation risk warning module.

[0008] In one implementation of the present invention, a driving state analysis strategy is executed in the driving state analysis module, and the driving state analysis strategy includes the following specific steps:

[0009] S11, extracting the driving status data of the powder vehicle collected by the data collection module;

[0010] S12, substituting the driving state data into a driving state variation coefficient calculation formula to calculate the driving state variation coefficient, the driving state variation coefficient calculation formula is: ; In the formula, Xs represents the driving state change coefficient of the current powder truck driving section, They represent the spectral components of acceleration, speed, and vibration frequency obtained by sampling the i-th time on the current driving section of the powder truck; They respectively represent the average acceleration change rate, average speed, and average vibration frequency of the current driving section of the powder truck; Indicates the acceleration obtained by sampling the i+1th time on the current driving section of the powder truck; It represents the sampling time interval between the i+1th sampling and the ith sampling; n is the sampling number of the current powder truck driving section, and i is any item from 1 to n.

[0011] In one implementation of the present invention, the driving state analysis strategy further includes the following specific steps:

[0012] S13, extracting the calculated driving state change coefficients of all powder vehicle driving sections, dividing the driving state change coefficients of all powder vehicle driving sections according to the types of powder vehicle driving sections, and obtaining a plurality of driving state change coefficient sequences of powder vehicle driving sections; obtaining the type of the next powder vehicle driving section that the powder vehicle is about to arrive at on the preset powder vehicle driving route; obtaining the driving state change coefficient sequence of the powder vehicle driving section corresponding to the next type of powder vehicle driving section; constructing a driving state change time series of the powder vehicle driving section according to the time sequence of the driving state change coefficient sequence of the powder vehicle driving section, and training a driving state change prediction model for the powder vehicle driving section that predicts the driving state change coefficient of the next powder vehicle driving section that the powder vehicle is about to arrive at based on the driving state change time series of the powder vehicle driving section;

[0013] S14, preset the sliding step size to 1 and the sliding window length to W; use the sliding window method to convert all the driving state change coefficients in the driving state change time series of the powder truck driving section into multiple training samples, wherein each training sample is composed of a driving state change coefficient sequence in the sliding window, and the training samples are used as the input of the driving state change prediction model of the powder truck driving section, and the driving state change coefficient of the powder truck driving section after the preset sliding step size is 1 is used as the output, and the prediction accuracy is used as the training target to train the driving state change prediction model of the powder truck driving section; generate a driving state change prediction model for the powder truck driving section that predicts the driving state change coefficient of the next powder truck driving section that the powder truck is about to arrive at according to the driving state change time series of the powder truck driving section; wherein the driving state change prediction model for the powder truck driving section is a recurrent neural network model;

[0014] S15, obtaining the predicted driving state change coefficient of the next driving section of the powder vehicle that the powder vehicle is about to reach.

[0015] In one implementation of the present invention, a powder state analysis strategy is executed in the powder state analysis module, and the powder state analysis strategy includes the following specific steps:

[0016] S21, obtaining the powder state data in the tank of the powder vehicle collected by the data collection module;

[0017] S22, substituting the powder state data in the tank into the powder distribution state abnormality coefficient calculation formula to calculate the powder distribution state abnormality coefficient, the powder distribution state abnormality coefficient calculation formula is: ; In the formula, Fb represents the abnormal coefficient of the powder distribution state of the current powder truck driving section; It represents the powder distribution density at the jth equidistant position inside the tank obtained by sampling the i-th time on the current driving section of the powder truck; m is the number of equidistant positions;

[0018] S23, taking the abnormal coefficient of the powder distribution state of the current powder vehicle driving section as the powder transportation risk coefficient of the current powder vehicle driving section.

[0019] In one implementation of the present invention, a powder transportation risk prediction strategy is run in the powder transportation risk prediction module, and the powder transportation risk prediction strategy includes the following specific steps:

[0020] S31, storing the calculated driving state change coefficients and powder transportation risk coefficients of all powder truck driving sections into a historical driving section data set, wherein the historical driving section data set is used to train a powder transportation risk prediction model, and the historical driving section data set is divided into a 70% historical driving section data training set and a 30% historical driving section data test set;

[0021] S32, constructing a regression network model, taking the driving state change coefficient in the historical driving section data training set as the input of the regression network model, taking the powder transportation risk coefficient in the historical driving section data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model;

[0022] S33, testing the initial regression network model through a historical driving section data test set, and outputting an initial regression network model that meets the preset model accuracy as a powder transportation risk prediction model;

[0023] S34, inputting the driving state change coefficient of the next driving section that the powder truck is about to reach into the powder transportation risk prediction model, and outputting the predicted powder transportation risk coefficient of the next driving section that the powder truck is about to reach.

[0024] In one implementation of the present invention, the powder transportation risk warning module runs a powder transportation risk warning execution strategy, and the powder transportation risk warning execution strategy includes the following specific steps:

[0025] S41, obtaining the powder transportation risk coefficient of the next powder transportation section that the powder transportation risk prediction module is about to arrive at;

[0026] S42. A powder transportation risk threshold is preset, and when the predicted powder transportation risk coefficient of the next powder transportation section that the powder transportation vehicle is about to arrive at is greater than the powder transportation risk threshold, a powder transportation risk warning is issued to the driver of the powder transportation vehicle.

[0027] In one implementation of the present invention, the data acquisition module includes a driving status data acquisition unit and a powder status data acquisition unit. The driving status data acquisition unit is used to collect acceleration data of the powder vehicle during driving through an acceleration sensor, collect speed data of the powder vehicle during driving through a speed sensor, and collect vibration data of the tank body of the powder vehicle during driving through a vibration sensor, and divide the preset powder vehicle driving route into multiple powder vehicle driving sections according to road types through a road database; the powder status data acquisition unit is used to install microwave sensors at multiple equidistant positions in the axial direction and circumferential direction inside the tank body of the powder vehicle, and collect powder distribution density at multiple equidistant positions through microwave sensors.

[0028] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0029] The present invention includes a data acquisition module, a driving state analysis module, a powder state analysis module, a powder transportation risk prediction module, a powder transportation risk warning module and a control module, wherein the driving state analysis module is used to import the driving state data into the driving state analysis model of the powder vehicle to analyze the driving state of the powder vehicle; the powder state analysis module is used to import the powder state data in the tank into the powder distribution state analysis model to analyze the powder distribution state in the tank during the driving process of the powder vehicle; the powder transportation risk prediction module is used to predict the powder transportation risk of the powder vehicle during the driving process according to the driving state analysis results and the powder distribution state analysis results of the powder vehicle. It can reduce the burden on drivers, improve the safety and reliability of transportation, and ensure the uniform transportation of powder. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0031] Figure 1 It is a structural schematic diagram of the powder vehicle control and safety monitoring system based on artificial intelligence of the present invention;

[0032] Figure 2 It is a basic flow chart of the recurrent neural network model in the artificial intelligence-based powder vehicle control and safety monitoring system of the present invention;

[0033] Figure 3 It is a structural schematic diagram of a data acquisition module in the artificial intelligence-based powder vehicle control and safety monitoring system of the present invention;

[0034] Figure 4 It is a schematic structural diagram of the powder truck tank body in the artificial intelligence-based powder truck control and safety monitoring system of the present invention. DETAILED DESCRIPTION

[0035] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0036] Example 1. Figure 1 As shown, this embodiment provides an artificial intelligence-based powder vehicle control and safety monitoring system, which specifically includes a data acquisition module, a driving state analysis module, a powder state analysis module, a powder transportation risk prediction module, a powder transportation risk warning module and a control module, wherein the data acquisition module is used to collect driving state data of the powder vehicle and powder state data in the tank; the driving state analysis module is used to import the driving state data into the driving state analysis model of the powder vehicle to analyze the driving state of the powder vehicle; Figure 4 As shown, the powder state analysis module is used to import the powder state data in the tank into the powder distribution state analysis model to analyze the powder distribution state in the tank during the driving of the powder vehicle; the powder transportation risk prediction module is used to predict the powder transportation risk of the powder vehicle during the driving process according to the driving state analysis results and the powder distribution state analysis results of the powder vehicle; the powder transportation risk warning module is used to issue a powder transportation risk warning to the driver of the powder vehicle according to the powder transportation risk prediction results; the control module is used to control the operation of the data acquisition module, the driving state analysis module, the powder state analysis module, the powder transportation risk prediction module, and the powder transportation risk warning module.

[0037] During the transportation of powder trucks, the driving condition of the vehicle directly affects transportation safety. This embodiment can predict potential transportation risks by analyzing the driving state. For example, during turning or sudden braking, the powder may move violently in the tank, causing the vehicle's center of gravity to be unstable and increasing the risk of rollover. The safety monitoring system can issue early warnings in a timely manner based on the driving state change coefficient to help drivers take preventive measures, thereby effectively improving transportation safety. Transportation efficiency optimization: By analyzing and predicting the driving state change coefficients of different driving sections, the best driving suggestions can be provided to drivers, such as adjusting the driving speed, avoiding driving on certain specific sections, etc., which helps to optimize the transportation route and driving method, thereby improving transportation efficiency, while reducing unnecessary fuel consumption and wear. In this embodiment, the driving state analysis strategy runs in the driving state analysis module, and the driving state analysis strategy includes the following specific steps:

[0038] S11, extracting the driving status data of the powder vehicle collected by the data collection module;

[0039] S12, substituting the driving state data into the driving state change coefficient calculation formula to calculate the driving state change coefficient, the driving state change coefficient calculation formula is: ;

[0040] In the formula, Xs represents the driving state change coefficient of the current powder truck driving section, They represent the spectral components of acceleration, speed, and vibration frequency obtained by sampling the i-th time on the current driving section of the powder truck; They respectively represent the average acceleration change rate, average speed, and average vibration frequency of the current driving section of the powder truck; Indicates the acceleration obtained by sampling the i+1th time on the current driving section of the powder truck; It represents the sampling time interval between the i+1th sampling and the ith sampling; n is the sampling number of the current powder truck driving section, and i is any item from 1 to n.

[0041] In this embodiment, the driving state analysis strategy also includes the following specific steps:

[0042] S13, extracting the calculated driving state change coefficients of all powder vehicle driving sections, dividing the driving state change coefficients of all powder vehicle driving sections according to the types of powder vehicle driving sections, and obtaining a plurality of driving state change coefficient sequences of powder vehicle driving sections; obtaining the type of the next powder vehicle driving section that the powder vehicle is about to arrive at on the preset powder vehicle driving route; obtaining the driving state change coefficient sequence of the powder vehicle driving section corresponding to the next type of powder vehicle driving section; constructing a driving state change time series of the powder vehicle driving section according to the time sequence of the driving state change coefficient sequence of the powder vehicle driving section, and training a driving state change prediction model for the powder vehicle driving section that predicts the driving state change coefficient of the next powder vehicle driving section that the powder vehicle is about to arrive at based on the driving state change time series of the powder vehicle driving section;

[0043] S14, such as Figure 2As shown, the preset sliding step size is 1 and the sliding window length is W; the sliding window method is used to convert all driving state change coefficients in the driving state change time series of the powder truck driving section into multiple training samples, wherein each training sample is composed of a driving state change coefficient sequence in the sliding window, and the training sample is used as the input of the driving state change prediction model of the powder truck driving section, and the driving state change coefficient of the powder truck driving section after the preset sliding step size is 1 is used as the output, and the prediction accuracy is used as the training target to train the driving state change prediction model of the powder truck driving section; a driving state change prediction model of the powder truck driving section is generated to predict the driving state change coefficient of the next powder truck driving section that the powder truck is about to arrive at according to the driving state change time series of the powder truck driving section; wherein the driving state change prediction model of the powder truck driving section is a recurrent neural network model;

[0044] S15, obtaining the predicted driving state change coefficient of the next driving section of the powder vehicle that the powder vehicle is about to reach.

[0045] The distribution of powder during transportation directly affects the balance and stability of the vehicle. If the powder is unevenly distributed or abnormally aggregated in the tank, the center of gravity of the vehicle is more likely to shift when turning, going uphill, downhill or braking suddenly, increasing the risk of accidents such as rollover and skidding. By analyzing the distribution of powder in real time, these potential safety hazards can be discovered and warned in time, helping drivers take appropriate measures to avoid accidents.

[0046] In this embodiment, the powder state analysis module is used to run the powder state analysis strategy, which helps the driver understand the specific distribution of the powder in the tank by calculating the powder distribution state abnormality coefficient. For example, in long-distance transportation or complex road conditions, the driver can adjust the driving speed and operation mode according to the powder distribution state abnormality coefficient to avoid abnormal powder distribution caused by improper operation, thereby optimizing driving operations and improving transportation efficiency and safety. The powder state analysis strategy includes the following specific steps:

[0047] S21, obtaining the powder state data in the tank of the powder vehicle collected by the data collection module;

[0048] S22. Substitute the powder state data in the tank into the powder distribution state abnormality coefficient calculation formula to calculate the powder distribution state abnormality coefficient. The powder distribution state abnormality coefficient calculation formula is:

[0049] ;

[0050] Where, Fb represents the abnormal coefficient of the powder distribution state of the current powder truck driving section; It represents the powder distribution density at the jth equidistant position inside the tank obtained by sampling the i-th time on the current driving section of the powder truck; m is the number of equidistant positions;

[0051] S23, taking the abnormal coefficient of the powder distribution state of the current powder vehicle driving section as the powder transportation risk coefficient of the current powder vehicle driving section.

[0052] During the powder transportation process, the driving state of the vehicle and the distribution state of the powder in the tank directly affect the transportation safety. This embodiment uses the powder transportation risk prediction module to comprehensively analyze these two key factors, predict potential transportation risks, avoid accidents, and ensure the safety of personnel and goods. Common accidents in powder transportation include rollover, skidding, powder leakage, etc. This embodiment can establish a more accurate risk prediction model by training historical driving section data. When a high risk is detected, the system can issue an early warning to prompt the driver to reduce speed, adjust driving style or choose other routes, thereby effectively preventing these accidents from occurring.

[0053] In this embodiment, the powder transportation risk prediction module runs a powder transportation risk prediction strategy, which includes the following specific steps:

[0054] S31, storing the calculated driving state change coefficients of all powder truck driving sections and the powder transportation risk coefficients in a historical driving section data set, the historical driving section data set is used to train a powder transportation risk prediction model, and the historical driving section data set is divided into a 70% historical driving section data training set and a 30% historical driving section data test set;

[0055] S32, constructing a regression network model, taking the driving state change coefficient in the historical driving section data training set as the input of the regression network model, taking the powder transportation risk coefficient in the historical driving section data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model;

[0056] S33, testing the initial regression network model through a historical driving section data test set, and outputting an initial regression network model that meets the preset model accuracy as a powder transportation risk prediction model;

[0057] S34, inputting the driving state change coefficient of the next driving section that the powder truck is about to reach into the powder transportation risk prediction model, and outputting the predicted powder transportation risk coefficient of the next driving section that the powder truck is about to reach.

[0058] In this embodiment, the powder transportation risk warning execution strategy is executed in the powder transportation risk warning module, and the powder transportation risk warning execution strategy includes the following specific steps:

[0059] S41, obtaining the powder transportation risk coefficient of the next powder transportation section that the powder transportation risk prediction module is about to arrive at;

[0060] S42. Preset a powder transportation risk threshold. When the predicted powder transportation risk coefficient of the next powder transportation section that the powder transportation vehicle is about to arrive at is greater than the powder transportation risk threshold, a powder transportation risk warning is issued to the driver of the powder transportation vehicle, wherein the value of the powder transportation risk threshold is determined as follows: obtain 5000 sets of powder status data in the tank of the powder vehicle; import the powder status data in the tank of the powder vehicle into the powder distribution state abnormality coefficient calculation formula to calculate 5000 sets of powder distribution state abnormality coefficients, and use the powder distribution state abnormality coefficient as the powder transportation risk coefficient; obtain the powder transportation risk judgment result; import the powder transportation risk coefficient and the powder transportation risk judgment result into the fitting software, and output the value of the corresponding powder transportation risk threshold that meets the highest powder transportation risk judgment accuracy.

[0061] In this embodiment, if Figure 3 As shown, the data acquisition module includes a driving state data acquisition unit and a powder state data acquisition unit. The driving state data acquisition unit is used to collect acceleration data of the powder vehicle during driving through an acceleration sensor, collect speed data of the powder vehicle during driving through a speed sensor, and collect vibration data of the tank body of the powder vehicle during driving through a vibration sensor, and divide the preset powder vehicle driving route into multiple powder vehicle driving sections according to the road type through a road database; the powder state data acquisition unit is used to install a microwave sensor at multiple equidistant positions in the axial direction and circumferential direction of the tank body of the powder vehicle, and collect the powder distribution density at multiple equidistant positions through a microwave sensor. In this embodiment, the road type can be classified according to the road function, and can be divided into expressways, national roads, provincial roads, county roads, township roads, urban roads, urban main roads, urban secondary roads, urban branches, urban expressways, etc.; it can also be classified according to the materials used in the road, and can be divided into: asphalt roads, cement concrete roads, gravel roads, dirt roads, etc. By dividing the driving sections into the above-mentioned categories, the influence of speed limits and traffic rules of different types of roads on the driving state of the powder truck can be avoided; thereby, the driving state analysis module can analyze the driving state of the powder truck more accurately.

[0062] Embodiment 2. An electronic device according to an embodiment of the present invention comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned data acquisition module, driving state analysis module, powder state analysis module, powder transportation risk prediction module, powder transportation risk warning module and control module by calling the computer program stored in the memory. It should be noted that: all computer programs of the artificial intelligence-based powder vehicle control and safety monitoring system are implemented in C language, wherein the data acquisition module, driving state analysis module, powder state analysis module, powder transportation risk prediction module, powder transportation risk warning module and control module are all controlled by a remote server.

[0063] Embodiment 3. This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0064] When the computer program runs on the computer device, the computer device executes the above-mentioned data acquisition module, driving state analysis module, powder state analysis module, powder transportation risk prediction module, powder transportation risk warning module and control module.

[0065] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0066] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0067] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] 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 comprising 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.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0073] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0075] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. The artificial intelligence-based powder truck control and safety monitoring system is characterized by: It includes a data acquisition module, a driving state analysis module, a powder state analysis module, a powder transportation risk prediction module, a powder transportation risk warning module and a control module, wherein the data acquisition module is used to collect the driving state data of the powder vehicle and the powder state data in the tank; the driving state analysis module is used to import the driving state data into the driving state analysis model of the powder vehicle to analyze the driving state of the powder vehicle; the powder state analysis module is used to import the powder state data in the tank into the powder distribution state analysis model to analyze the powder distribution state of the powder vehicle in the tank during driving; the powder transportation risk prediction module is used to predict the powder transportation risk of the powder vehicle during driving according to the driving state analysis results and the powder distribution state analysis results of the powder vehicle; the powder transportation risk warning module is used to issue a powder transportation risk warning to the driver of the powder vehicle according to the powder transportation risk prediction results; the control module is used to control the operation of the data acquisition module, the driving state analysis module, the powder state analysis module, the powder transportation risk prediction module and the powder transportation risk warning module; The driving state analysis module runs a driving state analysis strategy, which includes the following specific steps: S11, extracting the driving status data of the powder vehicle collected by the data collection module; S12, substituting the driving state data into a driving state variation coefficient calculation formula to calculate the driving state variation coefficient, the driving state variation coefficient calculation formula is: ; In the formula, Xs represents the driving state change coefficient of the current powder truck driving section, They represent the spectral components of acceleration, speed, and vibration frequency obtained by sampling the i-th time on the current driving section of the powder truck; They respectively represent the average acceleration change rate, average speed, and average vibration frequency of the current driving section of the powder truck; Indicates the acceleration obtained by sampling the i+1th time on the current driving section of the powder truck; Indicates the sampling time interval between the i+1th sampling and the ith sampling; n is the sampling number of the current powder vehicle driving section, and i is any one from 1 to n; The driving state analysis strategy also includes the following specific steps: S13, extracting the calculated driving state change coefficients of all powder vehicle driving sections, dividing the driving state change coefficients of all powder vehicle driving sections according to the types of powder vehicle driving sections, and obtaining a plurality of driving state change coefficient sequences of powder vehicle driving sections; obtaining the type of the next powder vehicle driving section that the powder vehicle is about to arrive at on the preset powder vehicle driving route; obtaining the driving state change coefficient sequence of the powder vehicle driving section corresponding to the next type of powder vehicle driving section; constructing a driving state change time series of the powder vehicle driving section according to the time sequence of the driving state change coefficient sequence of the powder vehicle driving section, and training a driving state change prediction model for the powder vehicle driving section that predicts the driving state change coefficient of the next powder vehicle driving section that the powder vehicle is about to arrive at based on the driving state change time series of the powder vehicle driving section; S14, preset the sliding step size to 1 and the sliding window length to W; use the sliding window method to convert all the driving state change coefficients in the driving state change time series of the powder truck driving section into multiple training samples, wherein each training sample is composed of a driving state change coefficient sequence in the sliding window, and the training samples are used as the input of the driving state change prediction model of the powder truck driving section, and the driving state change coefficient of the powder truck driving section after the preset sliding step size is 1 is used as the output, and the prediction accuracy is used as the training target to train the driving state change prediction model of the powder truck driving section; generate a driving state change prediction model for the powder truck driving section that predicts the driving state change coefficient of the next powder truck driving section that the powder truck is about to arrive at according to the driving state change time series of the powder truck driving section; wherein the driving state change prediction model for the powder truck driving section is a recurrent neural network model; S15, obtaining the predicted driving state change coefficient of the next driving section of the powder vehicle that the powder vehicle is about to reach; The powder state analysis module runs a powder state analysis strategy, which includes the following specific steps: S21, obtaining the powder state data in the tank of the powder vehicle collected by the data collection module; S22, substituting the powder state data in the tank into the powder distribution state abnormality coefficient calculation formula to calculate the powder distribution state abnormality coefficient, the powder distribution state abnormality coefficient calculation formula is: ; In the formula, Fb represents the abnormal coefficient of the powder distribution state of the current powder truck driving section; It represents the powder distribution density at the jth equidistant position inside the tank obtained by sampling the i-th time on the current driving section of the powder truck; m is the number of equidistant positions; S23, using the abnormal coefficient of the powder distribution state of the current powder vehicle driving section as the powder transportation risk coefficient of the current powder vehicle driving section; The powder transportation risk prediction module runs a powder transportation risk prediction strategy, and the powder transportation risk prediction strategy includes the following specific steps: S31, storing the calculated driving state change coefficients and powder transportation risk coefficients of all powder truck driving sections into a historical driving section data set, wherein the historical driving section data set is used to train a powder transportation risk prediction model, and the historical driving section data set is divided into a 70% historical driving section data training set and a 30% historical driving section data test set; S32, constructing a regression network model, taking the driving state change coefficient in the historical driving section data training set as the input of the regression network model, taking the powder transportation risk coefficient in the historical driving section data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model; S33, testing the initial regression network model through a historical driving section data test set, and outputting an initial regression network model that meets the preset model accuracy as a powder transportation risk prediction model; S34, inputting the driving state change coefficient of the next driving section that the powder truck is about to reach into the powder transportation risk prediction model, and outputting the predicted powder transportation risk coefficient of the next driving section that the powder truck is about to reach.

2. The artificial intelligence-based powder vehicle control and safety monitoring system according to claim 1 is characterized in that: The powder transportation risk warning module runs a powder transportation risk warning execution strategy, and the powder transportation risk warning execution strategy includes the following specific steps: S41, obtaining the powder transportation risk coefficient of the next powder transportation section that the powder transportation risk prediction module is about to arrive at; S42. A powder transportation risk threshold is preset, and when the predicted powder transportation risk coefficient of the next powder transportation section that the powder transportation vehicle is about to arrive at is greater than the powder transportation risk threshold, a powder transportation risk warning is issued to the driver of the powder transportation vehicle.

3. The artificial intelligence-based powder vehicle control and safety monitoring system according to claim 2 is characterized in that: The data acquisition module includes a driving status data acquisition unit and a powder status data acquisition unit. The driving status data acquisition unit is used to collect acceleration data of the powder vehicle during driving through an acceleration sensor, collect speed data of the powder vehicle during driving through a speed sensor, and collect vibration data of the tank body of the powder vehicle during driving through a vibration sensor, and divide the preset powder vehicle driving route into multiple powder vehicle driving sections according to road types through a road database; the powder status data acquisition unit is used to install microwave sensors at multiple equidistant positions in the axial direction and circumferential direction inside the tank body of the powder vehicle, and collect powder distribution density at multiple equidistant positions through microwave sensors.

Images