Intelligent safety management system for mining trackless rubber-tyred vehicle

Abstract

The invention provides an intelligent safety management system for a mining trackless rubber-tyred vehicle, and relates to the technical field of intelligent management systems. Comprising an information management module used for obtaining vehicle basic information of a target trackless rubber-tyred vehicle, obtaining real-time operation data and real-time state data, and generating comprehensive vehicle information according to the real-time operation data and the real-time state data; the operation monitoring module is used for generating a comprehensive area classification set of the target area and carrying out anomaly analysis on the comprehensive vehicle information and the comprehensive area classification set to obtain the real-time abnormal operation condition of the target trackless rubber-tyred vehicle; the analysis and early warning module is used for analyzing the real-time abnormal operation condition and carrying out early warning according to an analysis result to obtain a vehicle early warning result; and the response optimization module is used for optimizing the safety response strategy of the target trackless rubber-tyred vehicle. According to the invention, the safety management of the target trackless rubber-tyred vehicle is more accurate, and the safety management efficiency and the operation safety can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent management system technology, and in particular to an intelligent safety management system for trackless rubber-tired mining vehicles. Background Technology

[0002] As a high-risk industry, especially in underground operations, safety is always the top priority in coal mining. Trackless rubber-tired vehicles, as the primary means of transporting materials and personnel in mines, directly impact the safety of mine operations.

[0003] The conventional safety management method for trackless rubber-tired mining vehicles involves monitoring vehicle information and making judgments and intelligent warnings based on basic vehicle information. However, this method does not establish a connection with the real-time environment in which the trackless rubber-tired mining vehicles operate. Consequently, it cannot effectively manage the safety of the trackless rubber-tired mining vehicles based on the specific conditions of the area in which they operate, which can easily lead to inaccurate safety management.

[0004] Therefore, the present invention provides an intelligent safety management system for trackless rubber-tired mining vehicles. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an intelligent safety management system for trackless rubber-tired mining vehicles. The technical solution of this invention is as follows: This invention provides an intelligent safety management system for trackless rubber-tired mining vehicles, comprising: The information management module is used to acquire real-time operating data and real-time status data of the target trackless rubber-tired vehicle based on preset sensors, and to generate comprehensive vehicle information of the target trackless rubber-tired vehicle based on the real-time operating data and real-time status data. The operation monitoring module is used to generate a comprehensive area classification set of the target area where the target trackless rubber-tired vehicle travels. The comprehensive vehicle information is combined with the comprehensive area classification set and anomaly analysis is performed to obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle. The analysis and early warning module is used to analyze real-time abnormal operating conditions and issue early warnings for abnormal operating conditions of the target trackless rubber-tired vehicle based on the analysis results, thereby obtaining vehicle early warning results; The response optimization module is used to analyze the vehicle warning results to obtain the comprehensive vehicle analysis results, and optimize the safety response strategy of the target trackless rubber-tired vehicle based on the comprehensive vehicle analysis results.

[0006] Preferably, the information management module includes: The acquisition unit is used to acquire the initial real-time operating data and initial real-time status data of the target trackless rubber-tired vehicle based on pre-deployed preset sensors; The information integration unit is used to process the initial real-time operating data and initial real-time status data to obtain real-time operating data and real-time status data, and to integrate the real-time operating data and real-time status data to obtain the comprehensive vehicle information of the target trackless rubber-tired vehicle.

[0007] Preferably, the operation monitoring module includes: Scene extraction unit: used to divide the target area where the trackless rubber-wheeled vehicle travels into multiple unit areas according to the preset unit area size, and extract key scene parameters of all parameter types in each unit area; The comprehensive region classification set unit is used to generate a comprehensive region classification set of the target region based on key scene parameters of all parameter types in each unit region. Anomaly detection unit: Used to combine comprehensive regional classification set and comprehensive vehicle information to perform anomaly analysis on the target trackless rubber-tired vehicle and obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle.

[0008] Preferably, the comprehensive regional classification set unit includes: The first region is divided into sub-units, which are used to calculate the parameter matching degree between the key scene parameters of each parameter type in each unit region and the preset safety factor threshold of the corresponding parameter type, with the driving direction of the target trackless rubber-tired vehicle as the calculation order. The matching degree of each unit region is determined by combining the parameter matching degree of the key scene parameters of all parameter types in each unit region. For any unit region, if the matching degree corresponding to the unit region is greater than the preset minimum matching degree, the unit region is determined to be a first sub-category region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. When the matching degree corresponding to the combined region is greater than the preset minimum matching degree, the combined region is determined to be a first sub-category region. Subsequently, the matching degree corresponding to the next unit region adjacent to the first sub-category region is calculated. After the matching degree corresponding to the last unit region is calculated, all the first sub-category regions constitute the first category region set. The second region is divided into sub-units: the friction coefficient of each unit region is obtained by taking the direction of travel of the target trackless rubber-tired vehicle as the calculation order, and the friction deviation value of each unit region is calculated based on the friction coefficient of each unit region and the preset standard friction value. For any unit region, if the friction deviation value of the unit region is less than the preset friction deviation threshold, the unit region is determined to be a second sub-classification region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. This process continues until the friction deviation value of the combined region is less than the preset friction deviation threshold. Then, the combined region is determined to be a second sub-classification region. The friction deviation values ​​of the unit regions adjacent to the second sub-classification region are calculated. This process continues until the friction deviation value of the last unit region is calculated. Finally, all the second sub-classification regions constitute the second classification region set. The benchmark comparison subunit is used to calculate the ratio of the area of ​​overlap between each first sub-classification region and each second sub-classification region to the area of ​​the target region, and to use each ratio as the benchmark weight of each first sub-classification region. The baseline comprehensive subunit obtains the average baseline weight of all first sub-classification regions. Based on the absolute value deviation between the baseline weight of each first sub-classification region and the average baseline weight, all first sub-classification regions are clustered. Multiple baseline classification regions are generated based on the clustering results. All baseline classification regions constitute the comprehensive region classification set.

[0009] Preferably, the anomaly detection unit includes: The demand determination subunit is used to obtain the real-time vehicle demand of the target trackless rubber-tired vehicle and generate the safety operation requirements of the target trackless rubber-tired vehicle based on the real-time vehicle demand. The threshold determination subunit is used to determine the parameter threshold corresponding to each parameter type in the real-time operation data and real-time status data based on the safety operation requirements. Furthermore, the parameter thresholds corresponding to all parameter types constitute the initial parameter threshold set. The region matching subunit is used to match the comprehensive vehicle information with the key scene parameters of each benchmark classification region in the comprehensive region classification set to obtain the region matching degree of each benchmark classification region. If the region matching degree of the comprehensive vehicle information with any benchmark classification region is greater than the preset minimum region matching degree, no parameter threshold adjustment is required. Otherwise, the initial parameter threshold in the initial parameter threshold set is weighted and optimized based on the region matching degree of each benchmark classification region to obtain the optimized parameter threshold set corresponding to each benchmark classification region. The operation judgment subunit is used to compare the comprehensive vehicle information with the corresponding parameter type of the optimized parameter threshold in the optimized parameter threshold set corresponding to each benchmark classification area, and generate the real-time abnormal operation status of each benchmark classification area based on the comparison results.

[0010] Preferably, the running judgment subunit includes: The judgment block is used to determine whether the target trackless rubber-tired vehicle is operating normally in the benchmark classification area if, for any benchmark classification area, the real-time parameter of each parameter type in the real-time running data and real-time status data is less than the optimized parameter threshold of the corresponding parameter type in the optimized parameter threshold set corresponding to the benchmark classification area, and the real-time normal operation status of the target trackless rubber-tired vehicle is determined based on the real-time running data and real-time status data; otherwise, the target trackless rubber-tired vehicle is operating abnormally in the benchmark classification area. The difference determination block is used to obtain all abnormal real-time parameters of all parameter types that exceed the optimization parameter threshold corresponding to each baseline classification region from real-time running data and real-time status data; The anomaly synthesis block is used to generate real-time abnormal operation status of the target trackless rubber-tired vehicle in each benchmark classification area based on the abnormal real-time parameters of each parameter type in each benchmark classification area.

[0011] Preferably, the analysis and early warning module includes: The integrated early warning unit is used to extract vehicle operation characteristics of each benchmark classification area based on the real-time abnormal operation status of each benchmark classification area, match early warning rules based on vehicle operation characteristics, and determine the integrated early warning information of each benchmark classification area based on the early warning rules. The vehicle early warning unit is used to determine the final early warning release method for each benchmark classification area based on the early warning level in the comprehensive early warning information of each benchmark classification area, and to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area through the final early warning release method of each benchmark classification area, thereby obtaining the vehicle early warning result.

[0012] Preferably, the vehicle warning unit includes: The early warning comparison subunit is used to compare the early warning level in the comprehensive early warning information of each benchmark classification area with the early warning level in the early warning level-initial early warning release method database one by one to obtain all the initial early warning release methods for each benchmark classification area; The early warning judgment subunit is used to determine if all initial early warning release methods in any benchmark classification area meet its release conditions, and then take all initial early warning release methods in the benchmark classification area as its final early warning release method; otherwise, it extracts all initial early warning release methods in the benchmark classification area that meet the release conditions, and uses all initial early warning release methods that meet the release conditions to constitute the final early warning release method of the benchmark classification area. The early warning subunit is used to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area based on the final early warning release method of each benchmark classification area, and obtain vehicle early warning results.

[0013] Preferably, for any baseline classification region, when the response optimization module optimizes the safety response strategy for the target trackless rubber-tired vehicle in the baseline classification region, it includes: The comprehensive analysis unit is used to combine the comprehensive early warning information of the benchmark classification area with the historical early warning information of the target trackless rubber-tired vehicle to adjust the early warning level in the comprehensive early warning information of the benchmark classification area and obtain the comprehensive vehicle analysis result. The strategy formulation unit is used to formulate a safety response strategy for the target trackless rubber-tired vehicle in the benchmark classification area based on the comprehensive vehicle analysis results and vehicle early warning results. The information optimization unit is used to perform comprehensive vehicle information optimization on the target trackless rubber-tired vehicle in the benchmark classification area based on the safety response strategy, and obtain the vehicle information optimization result. The evaluation and optimization unit is used to evaluate the effect of the vehicle information optimization results, obtain the effect evaluation results, and adjust the safety response strategy of the benchmark classification area based on the effect evaluation results.

[0014] Preferably, the evaluation and optimization unit includes: The indicator classification subunit is used to classify all indicators in the vehicle information optimization results based on the indicator types of magnitude indicators and efficiency indicators. The first optimization indicator is obtained by classifying according to the magnitude indicators, and the second optimization indicator is obtained by classifying according to the efficiency indicators. The correlation analysis subunit is used to determine the degree of strategy-type correlation between the security response strategy of the benchmark classification region and the corresponding indicator type of each sub-optimization indicator in the first optimization indicator and the second optimization indicator, based on a preset correlation analysis method. The strategy optimization subunit adjusts the security response strategy of the benchmark classification region according to the index type of the sub-optimization index for each of the first and second optimization indices. If the correlation between the security response strategy of the benchmark classification region and the strategy-type of any sub-optimization index is lower than a preset strategy threshold, the sub-optimization index is used to optimize the security response strategy of the benchmark classification region.

[0015] This invention provides an intelligent safety management system for trackless rubber-tired mining vehicles, comprising: Compared with the prior art, the beneficial effects of the present invention are as follows: By acquiring real-time operational and status data of the target trackless rubber-tired vehicle and combining this data with a comprehensive region classification set generated from the target area where the vehicle travels, anomaly analysis is performed on the vehicle. After obtaining real-time abnormal operational information, further analysis of this information is used to issue early warnings for abnormal vehicle operation. This establishes a connection between the target vehicle and the target area it travels in, enabling effective safety management based on the specific conditions of the target area. This makes safety management more precise and improves the efficiency and operational safety of the target trackless rubber-tired vehicle. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the structure of an intelligent safety management system for trackless rubber-tired mining vehicles provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the operation judgment unit provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0019] Example 1: This embodiment of the invention provides an intelligent safety management system for trackless rubber-tired mining vehicles, such as... Figure 1 As shown, it includes: an information management module, used to acquire real-time operating data and real-time status data of the target trackless rubber-tired vehicle based on preset sensors, and to generate comprehensive vehicle information of the target trackless rubber-tired vehicle based on the real-time operating data and real-time status data; The operation monitoring module is used to generate a comprehensive area classification set of the target area where the target trackless rubber-tired vehicle travels. The comprehensive vehicle information is combined with the comprehensive area classification set and anomaly analysis is performed to obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle. The analysis and early warning module is used to analyze real-time abnormal operating conditions and issue early warnings for abnormal operating conditions of the target trackless rubber-tired vehicle based on the analysis results, thereby obtaining vehicle early warning results; The response optimization module is used to analyze the vehicle warning results to obtain the comprehensive vehicle analysis results, and optimize the safety response strategy of the target trackless rubber-tired vehicle based on the comprehensive vehicle analysis results.

[0020] In this embodiment, the preset sensors refer to various sensing devices pre-installed at specific locations or on the trackless rubber-tired vehicle. Examples include speed sensors, temperature sensors, and pressure sensors. The speed sensor can measure the speed of the target trackless rubber-tired vehicle, the temperature sensor can monitor the temperature of the target trackless rubber-tired vehicle's operating environment or the temperature of its motor, and the pressure sensor can detect the pressure of the target trackless rubber-tired vehicle's pneumatic system.

[0021] In this embodiment, the target trackless rubber-tired vehicle refers to a trackless rubber-tired vehicle that is monitored and tracked in the safety management system.

[0022] In this embodiment, real-time operational data refers to various operational data collected in real time by preset sensors during the actual operation of the target trackless rubber-tired vehicle. This includes data such as speed, acceleration, power, temperature, vehicle body pressure, and load.

[0023] In this embodiment, real-time status data refers to data reflecting the vehicle's status during actual operation of the target trackless rubber-tired vehicle, in addition to operational data. Examples include battery status data (such as remaining battery power), engine status data (such as engine operating temperature and whether power output is normal), and tire status data (such as front tire pressure and rear tire pressure).

[0024] In this embodiment, the comprehensive vehicle information is obtained by integrating real-time operating data and real-time status data.

[0025] In this embodiment, the comprehensive region classification set refers to the set of classification results obtained after dividing the target area where the target trackless rubber-wheeled vehicle travels into unit regions and classifying the unit regions.

[0026] In this embodiment, the target area refers to the area where the target trackless rubber-tired vehicle travels or is about to travel during its operation.

[0027] In this embodiment, real-time abnormal operation refers to the situation where, during the operation of the target trackless rubber-tired vehicle, it is found that the target trackless rubber-tired vehicle exhibits behavior that is inconsistent with the normal expected behavior, such as insufficient power, speeding, or overloading.

[0028] In this embodiment, the warning refers to the alert and warning issued during the operation of the target trackless rubber-tired vehicle regarding potential risks or abnormal states of the vehicle. For example, when the target trackless rubber-tired vehicle exceeds the preset safe speed limit in a certain area, an "overspeed warning" will be issued.

[0029] In this embodiment, the vehicle warning result refers to the warning result obtained after issuing a warning to the target trackless rubber-tired vehicle, including: warning success or failure indicator, warning duration, response time, warning type, etc.

[0030] In this embodiment, the comprehensive vehicle analysis result refers to the conclusion drawn after a comprehensive evaluation of the vehicle warning results of the target trackless rubber-tired vehicle.

[0031] In this embodiment, the safety response strategy refers to a series of emergency response measures and preventative actions formulated based on vehicle warning results during the operation of the target trackless rubber-tired vehicle. For example, if an abnormality is detected during the operation of the target trackless rubber-tired vehicle, such as "low battery power" or "high temperature," and the analysis results show that the fault trend may be increasing, the safety response strategy is to immediately stop the target trackless rubber-tired vehicle and assign maintenance personnel to inspect the target trackless rubber-tired vehicle, especially the battery and temperature control system, to prevent more serious faults or safety accidents.

[0032] The beneficial effects of the above technical solution are as follows: By acquiring the real-time operation data and real-time status data of the target trackless rubber-tired vehicle, and combining this with a comprehensive region classification set generated from the target area where the target trackless rubber-tired vehicle is traveling, anomaly analysis is performed on the target trackless rubber-tired vehicle. After obtaining the real-time abnormal operation status of the target trackless rubber-tired vehicle, further analysis of the real-time abnormal operation status is conducted to provide early warning of the abnormal operation status of the target trackless rubber-tired vehicle. This establishes a correlation between the target trackless rubber-tired vehicle and the target area where it is traveling when managing the safety of the target trackless rubber-tired vehicle. As a result, effective safety management of the trackless rubber-tired vehicle can be carried out based on the scene conditions of the target area, making the safety management of the target trackless rubber-tired vehicle more accurate and improving the safety management efficiency and operational safety of the target trackless rubber-tired vehicle.

[0033] Example 2: Based on the above examples, in a further example of the present invention, the information management module includes: The acquisition unit is used to acquire the initial real-time operating data and initial real-time status data of the target trackless rubber-tired vehicle based on pre-deployed preset sensors; The information integration unit is used to process the initial real-time operating data and initial real-time status data to obtain real-time operating data and real-time status data, and to integrate the real-time operating data and real-time status data to obtain the comprehensive vehicle information of the target trackless rubber-tired vehicle.

[0034] In this embodiment, the initial real-time operating data refers to the unprocessed raw operating data collected by the preset sensor. The initial real-time state data refers to the unprocessed raw state data collected by the preset sensor.

[0035] In this embodiment, the information integration result is achieved by integrating and processing the real-time operating data (such as speed, location, battery status, etc.) and real-time status data (such as temperature, pressure, fault information, etc.) of the target trackless rubber-tired vehicle to form a complete and unified set of vehicle information. Integration refers to constructing a dataset based on the data type of the real-time operating data and the real-time status data.

[0036] In this embodiment, data processing refers to operations performed on the initial real-time running data and initial real-time status data, including data cleaning (removing noisy and erroneous data), data transformation (converting data into a format suitable for analysis), and data analysis (using statistical analysis, data mining, and other methods to conduct in-depth analysis of the data).

[0037] The beneficial effects of the above technical solution are: by integrating real-time operation data and real-time status data, comprehensive vehicle information of the target trackless rubber-tired vehicle is obtained, which facilitates subsequent analysis of the target trackless rubber-tired vehicle's real-time abnormal operation based on the comprehensive vehicle information.

[0038] Example 3: Based on the above examples, in a further example of the present invention, the operation monitoring module includes: Scene extraction unit: used to divide the target area where the trackless rubber-wheeled vehicle travels into multiple unit areas according to the preset unit area size, and extract key scene parameters of all parameter types in each unit area; The comprehensive region classification set unit is used to generate a comprehensive region classification set of the target region based on key scene parameters of all parameter types in each unit region. Anomaly detection unit: Used to combine comprehensive regional classification set and comprehensive vehicle information to perform anomaly analysis on the target trackless rubber-tired vehicle and obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle.

[0039] In this embodiment, the preset unit area size refers to the physical size of each unit area when the target area is divided into multiple unit areas.

[0040] In this embodiment, a unit region refers to the region obtained by dividing the target region according to the size of a preset unit region, and all unit regions extend along a specific direction (the direction of travel of the target trackless rubber-wheeled vehicle) and are arranged linearly in space.

[0041] In this embodiment, key scene parameters refer to the key factors that need to be focused on when analyzing the state and environment of the target area where the target trackless rubber-tired vehicle is traveling, which directly affect the safe operation and handling of the vehicle, such as road surface parameters and environmental data, specifically: visibility, road surface conditions, speed limits, humidity, wind speed, etc.

[0042] The beneficial effects of the above technical solution are as follows: by dividing the target area into multiple unit areas and extracting various types of key scene parameters of each unit area, a comprehensive area classification set is generated. Combined with comprehensive vehicle information, the real-time abnormal operation status of the target trackless rubber-tired vehicle is obtained, realizing effective monitoring of the scene status of multiple unit areas in the target area where the target trackless rubber-tired vehicle is traveling. This increases the factors to be considered when managing the safety of the target trackless rubber-tired vehicle and can further improve the safety of the target trackless rubber-tired vehicle's operation.

[0043] Example 4: Based on the above examples, in a further example of the present invention, the comprehensive region classification set unit includes: The first region is divided into sub-units, which are used to calculate the parameter matching degree between the key scene parameters of each parameter type in each unit region and the preset safety factor threshold of the corresponding parameter type, with the driving direction of the target trackless rubber-tired vehicle as the calculation order. The matching degree of each unit region is determined by combining the parameter matching degree of the key scene parameters of all parameter types in each unit region. For any unit region, if the matching degree corresponding to the unit region is greater than the preset minimum matching degree, the unit region is determined to be a first sub-category region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. When the matching degree corresponding to the combined region is greater than the preset minimum matching degree, the combined region is determined to be a first sub-category region. Subsequently, the matching degree corresponding to the next unit region adjacent to the first sub-category region is calculated. After the matching degree corresponding to the last unit region is calculated, all the first sub-category regions constitute the first category region set. The second region is divided into sub-units: the friction coefficient of each unit region is obtained by taking the direction of travel of the target trackless rubber-tired vehicle as the calculation order, and the friction deviation value of each unit region is calculated based on the friction coefficient of each unit region and the preset standard friction value. For any unit region, if the friction deviation value of the unit region is less than the preset friction deviation threshold, the unit region is determined to be a second sub-classification region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. This process continues until the friction deviation value of the combined region is less than the preset friction deviation threshold. Then, the combined region is determined to be a second sub-classification region. The friction deviation values ​​of the unit regions adjacent to the second sub-classification region are calculated. This process continues until the friction deviation value of the last unit region is calculated. Finally, all the second sub-classification regions constitute the second classification region set. The benchmark comparison subunit is used to calculate the ratio of the area of ​​overlap between each first sub-classification region and each second sub-classification region to the area of ​​the target region, and to use each ratio as the benchmark weight of each first sub-classification region. The baseline comprehensive subunit obtains the average baseline weight of all first sub-classification regions. Based on the absolute value deviation between the baseline weight of each first sub-classification region and the average baseline weight, all first sub-classification regions are clustered. Multiple baseline classification regions are generated based on the clustering results. All baseline classification regions constitute the comprehensive region classification set.

[0044] In this embodiment, the preset safety factor threshold is the maximum or minimum safe value of a parameter-type safety factor. For example, the maximum value of the running speed safety factor is 70 mph, and the minimum value of the running speed safety factor is 40 mph.

[0045] In this embodiment, parameter matching degree refers to the similarity value between a key scene parameter of any parameter type in any unit region and a preset safety coefficient threshold of the corresponding parameter type. When determining the matching degree corresponding to each unit region, the parameter matching degree of the key scene parameter of each parameter type in each unit region is weighted and calculated with the corresponding preset weight coefficient according to the preset weight coefficient of the key scene parameters of all parameter types, so as to obtain the matching degree corresponding to each unit region.

[0046] In this embodiment, the first sub-classification region refers to the combined region or unit region where the matching degree is greater than the preset minimum matching degree.

[0047] In this embodiment, a combined region refers to a new region formed by merging adjacent unit regions in the next calculation order when the matching degree of a certain unit region is not greater than a preset minimum matching degree. For example, if the matching degree of unit region A is 0.7, which is lower than the preset minimum matching degree (e.g., 0.8), and the matching degree of unit region B is 0.6, which is also lower than the preset minimum matching degree, and B is an adjacent unit region in the next calculation order of A, then this embodiment of the invention merges these two unit regions into a combined region and calculates the matching degree of this combined region AB. If the matching degree of AB is 1.3, which is greater than the preset minimum matching degree (0.8), then AB is taken as a first sub-classification region.

[0048] In this embodiment, the preset minimum matching degree represents a minimum matching standard, which is used to measure whether each unit region or combined region meets the minimum matching standard.

[0049] In this embodiment, when obtaining the friction coefficient of each unit region, the road surface parameters, environmental data, and preset speed limit in the key scene parameters of each unit region are input into the pre-trained underground friction model, and the pre-trained underground friction model outputs the friction coefficient of each unit region.

[0050] In this embodiment, the preset standard friction value is a friction coefficient reference value specified in advance according to the design specifications of the target area.

[0051] In this embodiment, the friction deviation value is an index that quantifies the difference between the friction coefficient and the preset standard friction value.

[0052] In this embodiment, the preset friction deviation threshold is a predetermined value used to determine whether the friction performance of the unit area meets the standard.

[0053] In this embodiment, the second sub-classification region is a combined region or unit region whose friction deviation value is less than a preset friction deviation threshold.

[0054] In this embodiment, the overlapping area refers to the area in space where any first sub-classification region and any second sub-classification region overlap.

[0055] In this embodiment, the baseline weight reflects the degree of matching between any first sub-classification region and any second sub-classification region. The larger the ratio, the greater the overlap between the two regions and the higher their similarity. In subsequent clustering, the baseline weight is used to evaluate the importance of each first sub-classification region.

[0056] In this embodiment, clustering is achieved by calculating the absolute value deviation between the baseline weight of each first sub-category region and the average baseline weight of all first sub-category regions. Based on the clustering algorithm, a pre-set number of region categories is selected as the number of clusters. Based on the number of clusters, all first sub-category regions are grouped according to the absolute value deviation between their baseline weight and the average baseline weight, and then further grouped according to the connection relationship of all first sub-category regions to obtain all clustering results. In each clustering result, all first sub-category regions can be connected to generate a baseline category region.

[0057] The beneficial effects of the above technical solution are: by dividing the target area into a first classification region set and a second classification region set, and then combining the first classification sub-regions with the second sub-classification regions for clustering, a comprehensive region classification set is obtained. The target area is accurately classified three times to obtain the comprehensive region classification set, which facilitates different intelligent security management based on real-time regional scenarios with different benchmark classification regions. The security management method is refined to the benchmark classification region, making it more accurate.

[0058] Example 5: Based on the above examples, in a further embodiment of the present invention, the anomaly detection unit includes: The demand determination subunit is used to obtain the real-time vehicle demand of the target trackless rubber-tired vehicle and generate the safety operation requirements of the target trackless rubber-tired vehicle based on the real-time vehicle demand. The threshold determination subunit is used to determine the parameter threshold corresponding to each parameter type in the real-time operation data and real-time status data based on the safety operation requirements. Furthermore, the parameter thresholds corresponding to all parameter types constitute the initial parameter threshold set. The region matching subunit is used to match the comprehensive vehicle information with the key scene parameters of each benchmark classification region in the comprehensive region classification set to obtain the region matching degree of each benchmark classification region. If the region matching degree of the comprehensive vehicle information with any benchmark classification region is greater than the preset minimum region matching degree, no parameter threshold adjustment is required. Otherwise, the initial parameter threshold in the initial parameter threshold set is weighted and optimized based on the region matching degree of each benchmark classification region to obtain the optimized parameter threshold set corresponding to each benchmark classification region. The operation judgment subunit is used to compare the comprehensive vehicle information with the corresponding parameter type of the optimized parameter threshold in the optimized parameter threshold set corresponding to each benchmark classification area, and generate the real-time abnormal operation status of each benchmark classification area based on the comparison results.

[0059] In this embodiment, real-time vehicle demand refers to the requirements related to the transportation task undertaken by the target trackless rubber-tired vehicle at the current moment, including the type and quantity of transported goods, transportation route, transportation time, etc.

[0060] In this embodiment, the safety operation requirements are various requirements determined based on real-time transportation needs to ensure the safety of the target trackless rubber-tired vehicle during operation, such as the driving speed range, load limit, braking performance requirements, etc.

[0061] In this embodiment, the parameter threshold is a safety range limit value set for the real-time operating data and real-time status data of each parameter type. For example, the speed parameter threshold specifies the upper and lower limits of the target trackless rubber-tired vehicle's travel speed.

[0062] In this embodiment, the initial parameter threshold set is a set of parameter thresholds determined based on the real-time operating data and real-time status data of each parameter type, according to the requirements of safe operation.

[0063] In this embodiment, the optimized parameter threshold set is a set of optimized parameter thresholds. The optimized parameter thresholds refer to the new, optimized safety parameter thresholds obtained by weighting and adjusting the initial parameter thresholds based on the region matching degree of each baseline classification region during the operation of the target trackless rubber-tired vehicle.

[0064] In this embodiment, the preset minimum area matching degree is the minimum standard value of the matching degree between the comprehensive vehicle information and the key scene parameters of the benchmark classification area. The value range of the preset minimum area matching degree is generally (0.4, 0.8).

[0065] In this embodiment, the regional matching degree refers to the comprehensive correlation between the integrated vehicle information and all key scenario parameters of each benchmark classification region. Assume the comprehensive vehicle information of the target trackless rubber-wheeled vehicle is as follows: speed: 60km / h, friction coefficient limit: 1.0, battery charge: 80%. The key scenario parameters of a certain benchmark classification region are: humidity: 45%, road friction coefficient: 0.8, vehicle speed limit: 50km / h, length: 10km. The matching coefficient between the integrated vehicle information's speed and the vehicle speed limit of this benchmark classification region is -1 (-1 for no match, 1 for a match). Based on the vehicle speed limit of 50km / h and length of 10km of this benchmark classification region, the battery charge of the target trackless rubber-wheeled vehicle is compared... Battery charge: 80%, matching coefficient 0.8 (weighted based on battery consumption, vehicle speed limit of 50km / h, and length of 10km). The friction coefficient limit for the target trackless rubber-wheeled vehicle is 1.0. Combined with the humidity of the baseline classification area (45%) and the road surface friction coefficient (0.8), the matching coefficient is 0.8 (weighted based on humidity, road surface friction coefficient, and friction coefficient limit). The overall vehicle information of the target trackless rubber-wheeled vehicle and its regional matching degree with the baseline classification area is: 0.8 + 0.8 + -1 = -0.36.

[0066] In this embodiment, parameter threshold adjustment is a process of weighted optimization of the corresponding parameter thresholds in the initial parameter threshold set based on the degree of regional matching, to obtain a new parameter threshold set. Taking the above example again: According to the preset minimum degree of regional matching, it is determined that the degree of regional matching between the comprehensive vehicle information and the benchmark classification area is less than the preset minimum degree of regional matching, and parameter threshold adjustment is required. For the benchmark classification area, when calculating the optimized parameter threshold of any parameter type in the initial parameter threshold set of the benchmark classification area by combining the comprehensive vehicle information of the target trackless rubber-tired vehicle with the degree of regional matching of the benchmark classification area, it is achieved by formula (1):

[0067] In formula (1), This indicates the threshold value of the optimized parameter type. The initial parameter threshold represents the parameter type, and F represents the degree of regional matching between the integrated vehicle information and the benchmark classification area; Taking the above example again: Based on the regional matching degree of -0.36, the vehicle speed threshold in the initial parameter threshold set corresponding to the benchmark classification region is adjusted to 50+50(1-0.36)km / h, the friction coefficient limit threshold is adjusted to 1+1×(1-0.36) times, and the battery power threshold is adjusted to 80%+80%×(1+0.36) times.

[0068] In this embodiment, real-time abnormal operation refers to comparing the comprehensive vehicle information with the parameter types in the optimized parameter threshold set corresponding to each benchmark classification region one by one. If any parameter type of the comprehensive vehicle information is positively correlated (negatively correlated) with the optimized parameter threshold of the corresponding parameter type in the optimized parameter threshold set of a certain benchmark classification region, then any parameter type of the comprehensive vehicle information that is less than (greater than) the corresponding parameter type in the optimized parameter threshold set of that benchmark classification region is judged as abnormal, and an abnormality identifier is added to the parameter type. Real-time abnormal operation includes: the abnormality identifier of each parameter type in the comprehensive vehicle information for each benchmark classification region obtained from the comprehensive vehicle information. Positively correlated (negatively correlated) means that when the real-time parameter value of any parameter type increases, the safety of the real-time parameter value of that parameter type relative to the optimized parameter threshold of the corresponding parameter type in the optimized parameter threshold set also increases (decreases).

[0069] The beneficial effects of the above technical solution are as follows: by determining the set of optimized parameter thresholds for each benchmark classification area based on real-time vehicle demand, safe operation requirements, and the degree of regional matching between comprehensive vehicle information and each benchmark classification area, and generating real-time abnormal operation status for each benchmark classification area based on the comparison results between comprehensive vehicle information and the set of optimized parameter thresholds for each benchmark classification area, the warning for the target trackless rubber-tired vehicle is more accurate by comprehensively considering multiple factors (real-time vehicle demand, safe operation requirements, comprehensive vehicle information and the degree of matching between each benchmark classification area, etc.) when issuing warnings for the target trackless rubber-tired vehicle, thereby improving the safety and safety management efficiency of the target trackless rubber-tired vehicle.

[0070] Example 6: Based on the above examples, in a further example of the present invention, the judgment subunit is run, such as... Figure 2 As shown, it includes: The judgment block is used to determine whether the target trackless rubber-tired vehicle is operating normally in the benchmark classification area if, for any benchmark classification area, the real-time parameter of each parameter type in the real-time running data and real-time status data is less than the optimized parameter threshold of the corresponding parameter type in the optimized parameter threshold set corresponding to the benchmark classification area, and the real-time normal operation status of the target trackless rubber-tired vehicle is determined based on the real-time running data and real-time status data; otherwise, the target trackless rubber-tired vehicle is operating abnormally in the benchmark classification area. The difference determination block is used to obtain all abnormal real-time parameters of all parameter types that exceed the optimization parameter threshold corresponding to each baseline classification region from real-time running data and real-time status data; The anomaly synthesis block is used to generate real-time abnormal operation status of the target trackless rubber-tired vehicle in each benchmark classification area based on the abnormal real-time parameters of each parameter type in each benchmark classification area.

[0071] In this embodiment, real-time parameters refer to the real-time data corresponding to each parameter type in real-time running data and real-time status data.

[0072] In this embodiment, the real-time abnormal operation status is a set of abnormal judgment results for all parameter types of the target trackless rubber-tired vehicle in each benchmark classification area, based on the abnormal judgment results for each parameter type in the abnormal determination block.

[0073] The beneficial effects of the above technical solution are as follows: by judging the real-time operational anomalies of the target trackless rubber-tired vehicle in different benchmark classification areas in real time, and extracting the abnormal real-time parameters of all parameter types exceeding the optimized parameter threshold in each benchmark classification area, and integrating the abnormal real-time parameters of all parameter types in each benchmark classification area to generate the real-time abnormal operation status of each benchmark classification area, it is possible to identify abnormal operation status of the target trackless rubber-tired vehicle when it is driving in each benchmark classification area, which refines the granularity of safety management and thus improves the safety of the target trackless rubber-tired vehicle operation.

[0074] Example 7: Based on the above examples, in a further example of the present invention, the analysis and early warning module includes: The integrated early warning unit is used to extract vehicle operation characteristics of each benchmark classification area based on the real-time abnormal operation status of each benchmark classification area, match early warning rules based on vehicle operation characteristics, and determine the integrated early warning information of each benchmark classification area based on the early warning rules. The vehicle early warning unit is used to determine the final early warning release method for each benchmark classification area based on the early warning level in the comprehensive early warning information of each benchmark classification area, and to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area through the final early warning release method of each benchmark classification area, thereby obtaining the vehicle early warning result.

[0075] In this embodiment, vehicle operation characteristics refer to key parameters that describe the real-time abnormal operation of the target trackless rubber-tired vehicle, such as the degree of speed abnormality, the degree of acceleration abnormality, and the degree of temperature abnormality.

[0076] In this embodiment, the operating characteristics of any vehicle in any benchmark classification region are compared one by one with any condition in the warning rule. For example, if the speed of the target trackless rubber-tired vehicle exceeds the maximum value set in the speed condition of the warning rule, the benchmark classification region matches the warning rule, and the relevant information of the warning rule is added to the comprehensive warning information, including detailed information such as warning type, warning level, warning time, and warning location.

[0077] In this embodiment, the warning rules are a series of pre-defined standards and conditions used to determine whether a warning needs to be issued for the target trackless rubber-wheeled vehicle. The formulation of the warning rules is based on vehicle operation risk factors, industry safety standards, and corporate safety management systems discovered through comprehensive analysis. For example, when the speed exceeds a certain limit and the road surface is slippery, the relevant information of the corresponding warning rules is added to the comprehensive warning information, including: the initial warning issuance method, the warning parameter type, and the matching warning level.

[0078] In this embodiment, the comprehensive early warning information is generated by matching early warning rules with the vehicle operation characteristics of each benchmark classification area. It includes detailed information such as early warning type, early warning level, and initial early warning release method. For example, if the vehicle speed of any benchmark classification area exceeds twice the maximum safety limit (e.g., 40 km / h), the early warning type of the vehicle speed in the early warning rule is matched, and the early warning level is set to Level 1 early warning based on twice the maximum safety limit of the vehicle speed and the early warning level matched in the early warning rule. The initial early warning release method in the early warning rule is also obtained, and the above parameters are added to the comprehensive early warning information of the benchmark classification area.

[0079] In this embodiment, the warning level is a quantitative representation of the severity of the warning in the comprehensive warning information. It is used to distinguish the importance and urgency of different levels of warnings and is usually divided according to the severity of the warning, typically into Level 1 warning (the most severe), Level 2 warning, Level 3 warning, etc. For example, a Level 1 warning may indicate that the target trackless rubber-wheeled vehicle has serious safety hazards, such as engine failure that may cause the target trackless rubber-wheeled vehicle to break down or cause a fire, requiring immediate emergency measures; while a Level 3 warning may indicate some minor risks, such as slightly low tire pressure, which can be dealt with at an appropriate time.

[0080] In this embodiment, the final warning release method refers to the following: if the target trackless rubber-tired vehicle in a certain baseline classification area can execute all the initial warning release methods, then all the initial warning release methods are used as the final warning release method for that baseline classification area; otherwise, the initial warning release methods that the target trackless rubber-tired vehicle can execute are extracted and combined to form the final warning release method for that baseline classification area, which is used to transmit comprehensive warning information to the intelligent management terminal in a timely and accurate manner. The warning level is associated with the final warning release method. For example, a Level 1 warning uses the most urgent and widespread release method, such as issuing a high-decibel alarm through the vehicle-mounted siren, simultaneously sending emergency SMS notifications to relevant personnel's mobile phones, and sending real-time alarm information to the intelligent management terminal for timely rescue and handling. A Level 2 warning can display warning information on the vehicle-mounted display screen and send SMS reminders to relevant personnel's mobile phones, while also recording the warning information on the intelligent management terminal. A Level 3 warning can display warning prompts on the interface of the intelligent management terminal, reminding relevant personnel to check and handle the situation at an appropriate time.

[0081] The beneficial effects of the above technical solution are: by matching real-time abnormal operation status with early warning rules, comprehensive early warning information of the target trackless rubber-tired vehicle is obtained; the vehicle early warning result is generated by selecting the early warning release method according to the early warning level; the accuracy and response efficiency of early warning of abnormal operation of the target trackless rubber-tired vehicle are effectively improved, and operational safety is enhanced.

[0082] Example 8: Based on the above examples, in a further embodiment of the present invention, the vehicle warning unit includes: The early warning comparison subunit is used to compare the early warning level in the comprehensive early warning information of each benchmark classification area with the early warning level in the early warning level-initial early warning release method database one by one to obtain all the initial early warning release methods for each benchmark classification area; The early warning judgment subunit is used to determine if all initial early warning release methods in any benchmark classification area meet its release conditions, and then take all initial early warning release methods in the benchmark classification area as its final early warning release method; otherwise, it extracts all initial early warning release methods in the benchmark classification area that meet the release conditions, and uses all initial early warning release methods that meet the release conditions to constitute the final early warning release method of the benchmark classification area. The early warning subunit is used to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area based on the final early warning release method of each benchmark classification area, and obtain vehicle early warning results.

[0083] In this embodiment, the warning level-initial warning release method database is a pre-built database system that stores the mapping relationship between different warning levels and corresponding initial warning release methods. It records the warning release methods that are suitable for each warning level (such as level 1, level 2, level 3, etc.). The warning release methods include, but are not limited to, vehicle alarms, SMS notifications, monitoring platform alarms, and other methods.

[0084] In this embodiment, the initial warning release method is the initial warning release method corresponding to all warning levels of the comprehensive warning information obtained from the warning level-initial warning release method database based on the comparison results one by one. It is an initial warning release method determined based on preset rules, but in actual applications, it may be limited by the conditions of the target trackless rubber-tired vehicle itself.

[0085] In this embodiment, determining whether the release conditions are met involves conducting a feasibility assessment of the initial warning release method and determining whether the target trackless rubber-tired vehicle has the capability to execute these initial warning release methods. The judgment result is related to the vehicle's technical performance, operating status, and vehicle configuration.

[0086] The beneficial effects of the above technical solution are: by filtering out the final warning release method that meets the conditions based on the comprehensive early warning information of each benchmark classification area, the final warning release method is ensured to be accurate and effective, and the early warning accuracy and response efficiency of the abnormal judgment of the target trackless rubber-tired vehicle are improved, resource waste is reduced, thereby improving the working efficiency of the target trackless rubber-tired vehicle and timely vehicle safety management.

[0087] Example 9: Based on the above examples, in a further example of the present invention, for any baseline classification region, when the response optimization module optimizes the safety response strategy of the target trackless rubber-tired vehicle in the baseline classification region, it includes: The comprehensive analysis unit is used to combine the comprehensive early warning information of the benchmark classification area with the historical early warning information of the target trackless rubber-tired vehicle to adjust the early warning level in the comprehensive early warning information of the benchmark classification area and obtain the comprehensive vehicle analysis result. The strategy formulation unit is used to formulate a safety response strategy for the target trackless rubber-tired vehicle in the benchmark classification area based on the comprehensive vehicle analysis results and vehicle early warning results. The information optimization unit is used to perform comprehensive vehicle information optimization on the target trackless rubber-tired vehicle in the benchmark classification area based on the safety response strategy, and obtain the vehicle information optimization result. The evaluation and optimization unit is used to evaluate the effect of the vehicle information optimization results, obtain the effect evaluation results, and adjust the safety response strategy of the benchmark classification area based on the effect evaluation results.

[0088] In this embodiment, historical early warning information refers to various early warning messages recorded during the historical operation of the target trackless rubber-tired vehicle. This reflects the early warning situation of the trackless rubber-tired vehicle at different times and under different operating conditions, including early warning type (such as overspeed warning, equipment failure warning, etc.), early warning time, early warning location, and subsequent handling. By combining and analyzing historical early warning information with comprehensive early warning information, patterns and trends in vehicle operation risks can be discovered, providing a reference for developing more effective safety response strategies.

[0089] In this embodiment, the comprehensive vehicle analysis result is a comprehensive assessment of the target trackless rubber-tired vehicle's operational status in each baseline classification region, derived from a combined analysis of comprehensive early warning information and historical early warning information. It covers information such as the target trackless rubber-tired vehicle's risk distribution, risk development trends, common fault types, and vehicle performance under different early warning conditions.

[0090] In this embodiment, adjusting the warning level is illustrated by the following example: Suppose that historical warning information for the target trackless rubber-tired vehicle within the baseline classification area A shows that excessive speed or brake failure has occurred multiple times in this area. In these cases, the vehicle's warning system will increase the speed warning level for this area. Based on the comprehensive warning information, if real-time monitoring indicates that the vehicle speed in this area is approaching the set high limit, the warning level will be adjusted to a higher level based on historical data, thereby strengthening the safety response in this area.

[0091] In this embodiment, the safety response strategy is a set of countermeasures against the target trackless rubber-tired vehicle, formulated based on the comprehensive analysis results of vehicles in a certain benchmark classification area and the vehicle early warning results of the target trackless rubber-tired vehicle. These measures include adjusting the operating parameters of the target trackless rubber-tired vehicle, turning on the lights, and adjusting the load capacity.

[0092] In this embodiment, the comprehensive vehicle information optimization is based on a safety response strategy. It optimizes the control system and operating mode of the target trackless rubber-tired vehicle in each baseline classification area to better adapt it to the environmental and fault conditions of the corresponding baseline classification area. For example, it adjusts sensor sensitivity and makes targeted adjustments to various components of the target trackless rubber-tired vehicle (such as the power system, sensor system, and control system) to reduce unnecessary energy consumption and improve performance and safety.

[0093] In this embodiment, the effect evaluation is the process of evaluating the results of vehicle information optimization. It aims to determine whether the optimization measures have achieved the expected results, whether they have effectively reduced the operating risks of the target trackless rubber-tired vehicle, and whether they have improved the safety performance of the target trackless rubber-tired vehicle. The evaluation indicators of the effect evaluation may include the failure rate of the target trackless rubber-tired vehicle, the early warning response time, etc.

[0094] In this embodiment, feedback adjustment involves modifying the original safety response strategy based on the effect evaluation results. For example, if the target trackless rubber-wheeled vehicle's acceleration is still higher than the acceleration threshold after implementing the safety response strategy, new countermeasures can be formulated.

[0095] The beneficial effects of the above technical solution are: by analyzing comprehensive early warning information and historical early warning information to optimize the safety response strategy, the safety of the target trackless rubber-tired vehicle in different benchmark classification areas is improved, and the working efficiency and driving safety of the target trackless rubber-tired vehicle are improved through timely adjustment of the safety response strategy.

[0096] Example 10: Based on the above examples, in a further example of the present invention, the evaluation and optimization unit includes: The indicator classification subunit is used to classify all indicators in the vehicle information optimization results based on the indicator types of magnitude indicators and efficiency indicators. The first optimization indicator is obtained by classifying according to the magnitude indicators, and the second optimization indicator is obtained by classifying according to the efficiency indicators. The correlation analysis subunit is used to determine the degree of strategy-type correlation between the security response strategy of the benchmark classification region and the corresponding indicator type of each sub-optimization indicator in the first optimization indicator and the second optimization indicator, based on a preset correlation analysis method. The strategy optimization subunit adjusts the security response strategy of the benchmark classification region according to the index type of the sub-optimization index for each of the first and second optimization indices. If the correlation between the security response strategy of the benchmark classification region and the strategy-type of any sub-optimization index is lower than a preset strategy threshold, the sub-optimization index is used to optimize the security response strategy of the benchmark classification region.

[0097] In this embodiment, magnitude indicators are used to measure the scale, degree, and quantity of vehicle information optimization results. For example, the increase in mileage or the expansion of onboard equipment storage capacity can directly reflect the scale changes of the target trackless rubber-tired vehicle in certain aspects after optimization. Efficiency indicators reflect the performance of vehicle information optimization results in terms of resource utilization efficiency and operational efficiency. For example, the percentage improvement in energy consumption efficiency or the rate of increase in data processing speed focuses on reflecting the impact of optimization on operational efficiency.

[0098] In this embodiment, the first optimization index is a set of indices that are classified into magnitude in the vehicle information optimization results.

[0099] In this embodiment, the second optimization index is a set of indicators after classifying the efficiency-level indicators in the vehicle information optimization results.

[0100] In this embodiment, the sub-optimization index is a specific index further refined from the first optimization index and the second optimization index, and is used to evaluate and measure the performance of specific aspects during the optimization process.

[0101] In this embodiment, the preset correlation analysis method is used to calculate the correlation strength between the security response strategy and different sub-optimization indicators through the correlation algorithm, so as to obtain the type correlation degree between the security response strategy and different sub-optimization indicators. For example, for the security response strategy of any benchmark classification region, the correlation score between it and all sub-optimization indicators is calculated according to the correlation algorithm. The correlation score between any sub-optimization indicator and the security response strategy of the benchmark classification region represents the strategy-type correlation degree of the corresponding indicator type in the sub-optimization indicator.

[0102] In this embodiment, the strategy-type correlation degree is the mapping relationship between each sub-response strategy of the generated security response strategy and the corresponding indicator type of each sub-optimization indicator in the first optimization indicator and the second optimization indicator, which is obtained through a preset correlation analysis method.

[0103] In this embodiment, adjusting the response strategy according to the indicator type refers to the process of adjusting and improving the existing security response strategy for each benchmark classification region based on the comprehensive effect evaluation results. For example, if the evaluation results show that the security response strategy for a certain benchmark classification region is not effective in improving the optimized indicators, or if the security response strategy for that benchmark classification region is not highly correlated with the indicator type, then optimization and adjustment are needed to improve the effectiveness and adaptability of the security response strategy for that benchmark classification region.

[0104] The beneficial effects of the above technical solution are: by classifying and analyzing the optimization results of vehicle information, the correlation between the safety response strategy and the optimization index of each benchmark classification area can be accurately evaluated, and the strategy can be adjusted based on the evaluation results to optimize the response of the target trackless rubber-tired vehicle, thereby effectively improving the safety management efficiency and operational safety of the target trackless rubber-tired vehicle.

[0105] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent safety management system for trackless rubber-tired mining vehicles, characterized in that, include: The information management module is used to acquire real-time operating data and real-time status data of the target trackless rubber-tired vehicle based on preset sensors, and to generate comprehensive vehicle information of the target trackless rubber-tired vehicle based on the real-time operating data and real-time status data. The operation monitoring module is used to generate a comprehensive area classification set of the target area where the target trackless rubber-tired vehicle travels. The comprehensive vehicle information is combined with the comprehensive area classification set and anomaly analysis is performed to obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle. The analysis and early warning module is used to analyze real-time abnormal operating conditions and issue early warnings for abnormal operating conditions of the target trackless rubber-tired vehicle based on the analysis results, thereby obtaining vehicle early warning results; The response optimization module is used to analyze the vehicle warning results to obtain the comprehensive vehicle analysis results, and optimize the safety response strategy of the target trackless rubber-tired vehicle based on the comprehensive vehicle analysis results.

2. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 1, characterized in that, The information management module includes: The acquisition unit is used to acquire the initial real-time operating data and initial real-time status data of the target trackless rubber-tired vehicle based on pre-deployed preset sensors; The information integration unit is used to process the initial real-time operating data and initial real-time status data to obtain real-time operating data and real-time status data, and to integrate the real-time operating data and real-time status data to obtain the comprehensive vehicle information of the target trackless rubber-tired vehicle.

3. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 1 or 2, characterized in that, The operation monitoring module includes: Scene extraction unit: used to divide the target area where the trackless rubber-wheeled vehicle travels into multiple unit areas according to the preset unit area size, and extract key scene parameters of all parameter types in each unit area; The comprehensive region classification set unit is used to generate a comprehensive region classification set of the target region based on key scene parameters of all parameter types in each unit region. Anomaly detection unit: Used to combine comprehensive regional classification set and comprehensive vehicle information to perform anomaly analysis on the target trackless rubber-tired vehicle and obtain the real-time abnormal operation status of the target trackless rubber-tired vehicle.

4. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 3, characterized in that, The comprehensive regional classification set of units includes: The first region is divided into sub-units, which are used to calculate the parameter matching degree between the key scene parameters of each parameter type in each unit region and the preset safety factor threshold of the corresponding parameter type, with the driving direction of the target trackless rubber-tired vehicle as the calculation order. The matching degree of each unit region is determined by combining the parameter matching degree of the key scene parameters of all parameter types in each unit region. For any unit region, if the matching degree corresponding to the unit region is greater than the preset minimum matching degree, the unit region is determined to be a first sub-category region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. When the matching degree corresponding to the combined region is greater than the preset minimum matching degree, the combined region is determined to be a first sub-category region. Subsequently, the matching degree corresponding to the next unit region adjacent to the first sub-category region is calculated. After the matching degree corresponding to the last unit region is calculated, all the first sub-category regions constitute the first category region set. The second region is divided into sub-units: the friction coefficient of each unit region is obtained by taking the direction of travel of the target trackless rubber-tired vehicle as the calculation order, and the friction deviation value of each unit region is calculated based on the friction coefficient of each unit region and the preset standard friction value. For any unit region, if the friction deviation value of the unit region is less than the preset friction deviation threshold, the unit region is determined to be a second sub-classification region. Otherwise, the unit region is combined with the adjacent unit region in the next calculation order to generate a combined region. This process continues until the friction deviation value of the combined region is less than the preset friction deviation threshold. Then, the combined region is determined to be a second sub-classification region. The friction deviation values ​​of the unit regions adjacent to the second sub-classification region are calculated. This process continues until the friction deviation value of the last unit region is calculated. Finally, all the second sub-classification regions constitute the second classification region set. The benchmark comparison subunit is used to calculate the ratio of the area of ​​overlap between each first sub-classification region and each second sub-classification region to the area of ​​the target region, and to use each ratio as the benchmark weight of each first sub-classification region. The baseline comprehensive subunit obtains the average baseline weight of all first sub-classification regions. Based on the absolute value deviation between the baseline weight of each first sub-classification region and the average baseline weight, all first sub-classification regions are clustered. Multiple baseline classification regions are generated based on the clustering results. All baseline classification regions constitute the comprehensive region classification set.

5. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 4, characterized in that, The anomaly detection unit includes: The demand determination subunit is used to obtain the real-time vehicle demand of the target trackless rubber-tired vehicle and generate the safety operation requirements of the target trackless rubber-tired vehicle based on the real-time vehicle demand. The threshold determination subunit is used to determine the parameter threshold corresponding to each parameter type in the real-time operation data and real-time status data based on the safety operation requirements. Furthermore, the parameter thresholds corresponding to all parameter types constitute the initial parameter threshold set. The region matching subunit is used to match the comprehensive vehicle information with the key scene parameters of each benchmark classification region in the comprehensive region classification set to obtain the region matching degree of each benchmark classification region. If the region matching degree of the comprehensive vehicle information with any benchmark classification region is greater than the preset minimum region matching degree, no parameter threshold adjustment is required. Otherwise, the initial parameter threshold in the initial parameter threshold set is weighted and optimized based on the region matching degree of each benchmark classification region to obtain the optimized parameter threshold set corresponding to each benchmark classification region. The operation judgment subunit is used to compare the comprehensive vehicle information with the corresponding parameter type of the optimized parameter threshold in the optimized parameter threshold set corresponding to each benchmark classification area, and generate the real-time abnormal operation status of each benchmark classification area based on the comparison results.

6. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 5, characterized in that, The operation judgment subunit includes: The judgment block is used to determine whether the target trackless rubber-tired vehicle is operating normally in the benchmark classification area if, for any benchmark classification area, the real-time parameter of each parameter type in the real-time running data and real-time status data is less than the optimized parameter threshold of the corresponding parameter type in the optimized parameter threshold set corresponding to the benchmark classification area, and the real-time normal operation status of the target trackless rubber-tired vehicle is determined based on the real-time running data and real-time status data; otherwise, the target trackless rubber-tired vehicle is operating abnormally in the benchmark classification area. The difference determination block is used to obtain all abnormal real-time parameters of all parameter types that exceed the optimization parameter threshold corresponding to each baseline classification region from real-time running data and real-time status data; The anomaly synthesis block is used to generate real-time abnormal operation status of the target trackless rubber-tired vehicle in each benchmark classification area based on the abnormal real-time parameters of each parameter type in each benchmark classification area.

7. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 5, characterized in that, The analysis and early warning module includes: The integrated early warning unit is used to extract vehicle operation characteristics of each benchmark classification area based on the real-time abnormal operation status of each benchmark classification area, match early warning rules based on vehicle operation characteristics, and determine the integrated early warning information of each benchmark classification area based on the early warning rules. The vehicle early warning unit is used to determine the final early warning release method for each benchmark classification area based on the early warning level in the comprehensive early warning information of each benchmark classification area, and to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area through the final early warning release method of each benchmark classification area, thereby obtaining the vehicle early warning result.

8. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 7, characterized in that, The vehicle warning unit includes: The early warning comparison subunit is used to compare the early warning level in the comprehensive early warning information of each benchmark classification area with the early warning level in the early warning level-initial early warning release method database one by one to obtain all the initial early warning release methods for each benchmark classification area; The early warning judgment subunit is used to determine if all initial early warning release methods in any benchmark classification area meet its release conditions, and then take all initial early warning release methods in the benchmark classification area as its final early warning release method; otherwise, it extracts all initial early warning release methods in the benchmark classification area that meet the release conditions, and uses all initial early warning release methods that meet the release conditions to constitute the final early warning release method of the benchmark classification area. The early warning subunit is used to issue early warnings for abnormal operation of the target trackless rubber-tired vehicle in each benchmark classification area based on the final early warning release method of each benchmark classification area, and obtain vehicle early warning results.

9. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 8, characterized in that, For any baseline classification region, when optimizing the safety response strategy for the target trackless rubber-tired vehicle in that baseline classification region, the response optimization module includes: The comprehensive analysis unit is used to combine the comprehensive early warning information of the benchmark classification area with the historical early warning information of the target trackless rubber-tired vehicle to adjust the early warning level in the comprehensive early warning information of the benchmark classification area and obtain the comprehensive vehicle analysis result. The strategy formulation unit is used to formulate a safety response strategy for the target trackless rubber-tired vehicle in the benchmark classification area based on the comprehensive vehicle analysis results and vehicle early warning results. The information optimization unit is used to perform comprehensive vehicle information optimization on the target trackless rubber-tired vehicle in the benchmark classification area based on the safety response strategy, and obtain the vehicle information optimization result. The evaluation and optimization unit is used to evaluate the effect of the vehicle information optimization results, obtain the effect evaluation results, and adjust the safety response strategy of the benchmark classification area based on the effect evaluation results.

10. The intelligent safety management system for trackless rubber-tired mining vehicles according to claim 9, characterized in that, The evaluation optimization unit includes: The indicator classification subunit is used to classify all indicators in the vehicle information optimization results based on the indicator types of magnitude indicators and efficiency indicators. The first optimization indicator is obtained by classifying according to the magnitude indicators, and the second optimization indicator is obtained by classifying according to the efficiency indicators. The correlation analysis subunit is used to determine the degree of strategy-type correlation between the security response strategy of the benchmark classification region and the corresponding indicator type of each sub-optimization indicator in the first optimization indicator and the second optimization indicator, based on a preset correlation analysis method. The strategy optimization subunit adjusts the security response strategy of the benchmark classification region according to the index type of the sub-optimization index for each of the first and second optimization indices. If the correlation between the security response strategy of the benchmark classification region and the strategy-type of any sub-optimization index is lower than a preset strategy threshold, the sub-optimization index is used to optimize the security response strategy of the benchmark classification region.

Images