Automatic driving longitudinal control method and system based on underground mining scraper

By evaluating the vehicle speed and pitch angle of the well industrial and mining shoveling machine in real time, analyzing the coupling degree and information entropy changes, and adjusting the vehicle speed in real time, the problem of vertical control of the well industrial and mining shoveling machine in complex environments is solved, and safety and efficiency are improved.

CN118618382BActive Publication Date: 2024-11-01JCHX MINING MANAGEMENT
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411122968.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-01
Estimated Expiration
2044-08-15

AI Technical Summary

Technical Problem

Existing well mining shovelers are difficult to adjust longitudinal vehicle speeds in real time and flexibly and accurately in complex mines or built environments, resulting in the impact of operational safety and efficiency.

Method used

By obtaining the vehicle speed and pitch angle of the well mining shovel machine in real time, analyzing the degree of coupling between the IMU and mechanical components and the change in information entropy, comprehensively assessing the credibility of the bump strength, and adjusting the vehicle speed in real time based on the search radius and the bump strength. .

Benefits of technology

Improve the driving safety and efficiency of well mining shovelers in complex terrain, ensure that the navigation system operates within the optimal detection range, reduce operational errors caused by data errors, reduce accident risks, and optimize the driving status of the vehicle. and work efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118618382B_ABST
    Figure CN118618382B_ABST
Patent Text Reader

Abstract

The present invention discloses an automatic driving longitudinal control method and system based on an underground mining scraper, which specifically relates to the field of vehicle control technology, and is used to solve the problem that the existing underground mining scraper cannot adjust the vehicle speed flexibly and accurately in real time when facing complex road conditions; by real-time monitoring of the vehicle speed and adjusting the search radius, it is ensured that the vehicle's navigation system operates within the optimal detection range, and the standard deviation of the vehicle's pitch angle is calculated in real time to accurately quantify the vehicle's bump intensity; considering the coupling effect between the IMU and other mechanical components, by analyzing the coupling degree and the unpredictability of the IMU data, it is determined whether the quantified result of the bump intensity is credible; when the bump data is confirmed to be reliable, the system will dynamically adjust the vehicle speed according to the bump intensity and the search radius adjustment frequency to cope with different ground conditions, thereby significantly improving the driving safety and efficiency of the underground mining scraper in complex terrain.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and more specifically, to an automatic driving longitudinal control method and system based on an underground mining shovel loader. Background Art

[0002] An underground mining loader is a heavy-duty machine specially designed for earthwork in mining, construction or heavy industrial environments. Underground mining loader usually has powerful digging, shoveling and transportation capabilities, and can efficiently move large amounts of materials in mines, mining sites and other engineering environments. Underground mining loader is usually designed for specific working environments and mission requirements, such as shoveling ore, crushed stone, etc. in underground mines or open-pit mines.

[0003] The main task of autonomous driving longitudinal control is to adjust and control the acceleration and speed of the underground mining shovel loader to ensure safety and efficiency under complex road conditions; however, when existing underground mining shovel loaders face complex road conditions such as mines, buildings or heavy industrial environments, for example, in underground mining areas, the operating environment of underground mining shovel loaders is complex and highly uncertain, including irregular road surfaces, sharp turns and protruding rocks, etc., their longitudinal control will be affected by complex road conditions and cannot flexibly and accurately adjust the vehicle speed in real time to adapt to road conditions. This may cause the underground mining shovel loader to encounter difficulties when coping with rapidly changing ground conditions, thereby affecting the safety and efficiency of the operation.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic driving longitudinal control method and system based on an underground mining shovel loader to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The automatic driving longitudinal control method based on the underground mining scraper comprises the following steps:

[0008] S1: obtaining the real-time speed of the underground mining loader in real time, adjusting the search radius based on the real-time speed, and obtaining the search radius adjustment frequency within a preset interval;

[0009] S2: Based on the IMU, the pitch angle of the underground mining loader is collected in real time, and the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader;

[0010] S3: By analyzing the degree of coupling between the IMU and other mechanical components of the underground mining loader, the adverse effect of the coupling degree on the IMU data error is evaluated; by measuring the change in information entropy of the IMU signal under different operating states, the unpredictability of the IMU data is evaluated;

[0011] S4: Comprehensively analyze the adverse effect of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible;

[0012] S5: When the jolting intensity of the underground mining shovel loader is credible, the frequency is adjusted according to the search radius and the jolting intensity of the underground mining shovel loader, and the speed of the underground mining shovel loader is adjusted in real time.

[0013] In a preferred embodiment, the real-time speed of the underground mining loader is obtained in real time, the search radius is adjusted based on the real-time speed, and the search radius adjustment frequency within a preset interval is obtained, specifically:

[0014] Get the real-time speed of underground mining loader in real time;

[0015] Adjust the search radius by the following formula: ;in, is the search radius, is the real-time speed of the underground mining loader. is the proportionality constant;

[0016] The number of times the search radius is adjusted within the preset interval is counted, and the ratio of the number of times the search radius is adjusted within the preset interval to the time length of the preset interval is marked as the search radius adjustment frequency.

[0017] In a preferred embodiment, the pitch angle of the underground mining loader is collected in real time based on the IMU, and the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader, specifically:

[0018] Collect pitch angle data in real time; pre-process the collected pitch angle data;

[0019] The turbulence intensity index is calculated within the preset time window, and its expression is: ;in, is the turbulence intensity index, is the number of data points in the time window, is the number of the data point in the time window, It is The pitch angle of the data point, is the mean of the pitch angles within the time window.

[0020] In a preferred embodiment, by analyzing the coupling degree between the IMU and other mechanical components of the underground mining loader, the degree of adverse effect of the coupling degree on the IMU data error is evaluated, specifically:

[0021] Obtain IMU data and mechanical component data;

[0022] forming a time series of IMU data based on the IMU data, and forming a time series of mechanical component data based on the mechanical component data;

[0023] Align the timestamps of IMU data and mechanical component data; determine the time window;

[0024] The mutual information evaluation index is calculated using mutual information spectrum analysis, and its expression is: ;in, is the mutual information evaluation index, and Represent the time series of IMU data and the time series of mechanical component data respectively, is the joint probability density function, They are the marginal probability density functions of the time series of IMU data and the time series of mechanical component data, respectively.

[0025] In a preferred embodiment, the unpredictability of IMU data is evaluated by measuring the change in information entropy of the IMU signal under different operating states, specifically:

[0026] Acquire three-axis acceleration data and three-axis angular velocity data and perform data preprocessing;

[0027] Select the time window length and sliding interval; split the IMU data into multiple time windows and perform multi-scale entropy analysis in each window;

[0028] Define a set of scale factors ; For each scale factor , calculate the resampled time series;

[0029] Calculate sample entropy for the resampled time series;

[0030] For each scale factor , resample the time series; for each scale factor , construct a new time series ;

[0031] Use the sample entropy formula to calculate the scale factor The multi-scale entropy value under , its expression is: ;in, For the scale factor The multi-scale entropy value under Indicates the total length of the time series data, is the embedding dimension, It's tolerance. is the index to traverse the time series data, For the scale factor The sample entropy calculated below.

[0032] In a preferred embodiment, in S4, a comprehensive analysis is performed on the adverse effect of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantified result of the turbulence intensity of the underground mining shovel loader is credible, specifically:

[0033] The mutual information evaluation index and the scale factor The multi-scale entropy value under the non-dimensional processing is processed, and the mutual information evaluation index after non-dimensional processing and the scale factor are The multi-scale entropy values ​​under the above conditions are assigned weight coefficients respectively and the credible assessment coefficient of the turbulence intensity is calculated.

[0034] Set the turbulence intensity credible assessment threshold and compare the turbulence intensity credible assessment coefficient with the turbulence intensity credible assessment threshold:

[0035] When the credible evaluation coefficient of the turbulence intensity is greater than the credible evaluation threshold of the turbulence intensity, it is determined that the quantitative result of the turbulence intensity of the underground mining scraper is not credible;

[0036] When the credible assessment coefficient of the turbulence intensity is less than or equal to the credible assessment threshold of the turbulence intensity, it is determined that the quantitative result of the turbulence intensity of the underground mining shovel loader is credible.

[0037] In a preferred embodiment, when the jolting intensity of the underground mining shovel loader is credible, the frequency and the jolting intensity of the underground mining shovel loader are adjusted according to the search radius, and the speed of the underground mining shovel loader is adjusted in real time, specifically:

[0038] Set the search radius adjustment frequency threshold and compare the search radius adjustment frequency with the search radius adjustment frequency threshold:

[0039] When the search radius adjustment frequency is greater than the search radius adjustment frequency threshold, it is determined that a vehicle speed reduction signal is generated, and at this time, the vehicle speed adjustment system of the underground mining scraper reduces the vehicle speed;

[0040] When the search radius adjustment frequency is less than or equal to the search radius adjustment frequency threshold, it is determined that a vehicle speed continuous analysis signal is generated;

[0041] When the vehicle speed continues to analyze the signal, the speed of the underground mining loader is adjusted according to the bump intensity index:

[0042] If the bump intensity index exceeds its corresponding threshold, the speed control system of the underground mining loader takes action to automatically adjust the speed and reduce the speed of the underground mining loader;

[0043] If the bump severity index does not exceed its corresponding threshold, the vehicle speed is not automatically adjusted.

[0044] On the other hand, the present invention provides an automatic driving longitudinal control system based on an underground mining scraper, comprising a search radius adjustment module, a bump intensity assessment module, a data credibility analysis module, a data credibility judgment module and a vehicle speed comprehensive adjustment module;

[0045] The search radius adjustment module obtains the real-time vehicle speed of the underground mining scraper in real time, adjusts the search radius based on the real-time vehicle speed, and obtains the search radius adjustment frequency within a preset range;

[0046] The bump intensity assessment module collects the pitch angle of the underground mining loader in real time based on the IMU, and quantifies the bump intensity of the underground mining loader through the standard deviation of the pitch angle of the underground mining loader;

[0047] The data trust analysis module analyzes the coupling degree between the IMU and other mechanical components of the underground mining loader to evaluate the adverse effect of the coupling degree on the IMU data error; and evaluates the unpredictability of the IMU data by measuring the change in information entropy of the IMU signal under different operating states;

[0048] The data credibility judgment module conducts a comprehensive analysis of the adverse effects of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible;

[0049] When the bump intensity of the underground mining shovel loader is credible, the vehicle speed comprehensive regulation module adjusts the vehicle speed of the underground mining shovel loader in real time according to the search radius adjustment frequency and the bump intensity of the underground mining shovel loader.

[0050] The technical effects and advantages of the automatic driving longitudinal control method and system of the present invention based on the underground mining scraper are as follows:

[0051] 1. By monitoring the vehicle speed in real time and adjusting the search radius, the system can adapt to changing environmental conditions and ensure that the vehicle's navigation system operates within the optimal detection range, which is essential for maintaining efficient path planning and obstacle detection in unstable or changing terrain. In addition, real-time calculation of the standard deviation of the vehicle's pitch angle can not only accurately quantify the vehicle's bump intensity, but also intuitively reflect the road conditions, providing a scientific basis for speed adjustment.

[0052] 2. Considering the coupling effect between IMU and other mechanical components, by analyzing the coupling degree and the unpredictability of IMU data, the reliability of data can be evaluated more accurately, because in harsh environments such as mining areas, the mechanical performance of the equipment may be greatly challenged, and conventional navigation systems may not accurately reflect the actual situation. Through this comprehensive evaluation, the system can determine whether the quantitative results of the bump intensity are credible, thereby avoiding operational errors caused by data errors. In addition, when the bump data is confirmed to be reliable, the system will dynamically adjust the vehicle speed according to the bump intensity and the search radius adjustment frequency to cope with different ground conditions and reduce the safety risks caused by the vehicle passing through the bumpy section too fast; it significantly improves the driving safety and efficiency of underground mining shovel loaders in complex terrain, not only can it respond to environmental changes in real time and optimize the driving status of the vehicle, but also can ensure the accuracy and reliability of operations through precise data analysis. The implementation of this system has greatly reduced the workload of drivers, reduced the risk of accidents caused by operating errors or equipment failures, and improved the operating efficiency and vehicle maintenance management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the longitudinal control method of the automatic driving based on the underground mining scraper of the present invention;

[0054] Figure 2 It is a structural schematic diagram of the automatic driving longitudinal control system of the underground mining shovel loader according to the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1

[0057] Figure 1 The present invention provides an automatic driving longitudinal control method based on an underground mining scraper, which includes the following steps:

[0058] S1: obtaining the real-time vehicle speed of the underground mining shovel loader in real time, adjusting the search radius based on the real-time vehicle speed, and obtaining the search radius adjustment frequency within a preset range.

[0059] S2: Based on the IMU, the pitch angle of the underground mining loader is collected in real time, and the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader.

[0060] S3: By analyzing the degree of coupling between the IMU and other mechanical components of the underground mining loader, the adverse effect of the coupling degree on the IMU data error is evaluated; by measuring the change in information entropy of the IMU signal under different operating states, the unpredictability of the IMU data is evaluated.

[0061] S4: Comprehensively analyze the adverse effects of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the turbulence intensity of the underground mining loader are credible.

[0062] S5: When the jolting intensity of the underground mining shovel loader is credible, the frequency is adjusted according to the search radius and the jolting intensity of the underground mining shovel loader, and the speed of the underground mining shovel loader is adjusted in real time.

[0063] In heavy machinery such as underground mining loader, IMU is used to monitor the dynamic behavior of underground mining loader. IMU is an inertial measurement unit used to evaluate road conditions and underground mining loader posture to ensure the safety and efficiency of operation. IMU data can be combined with other sensor data and processed by advanced algorithms to provide more accurate motion and position estimates.

[0064] In S1, the real-time speed of the underground mining loader is obtained in real time, the search radius is adjusted based on the real-time speed, and the search radius adjustment frequency within the preset interval is obtained, specifically:

[0065] The real-time vehicle speed of the underground mining loader is obtained in real time by installing a speed sensor (such as a wheel speed sensor or a GPS module) on the underground mining loader.

[0066] In order to improve the ability of autonomous underground mining loaders to cope with complex terrain, a laser positioning system based on SLAM (simultaneous localization and mapping) technology is adopted. This improvement significantly improves the accuracy and reliability of positioning, especially in environments where GPS signals are weak or unavailable, such as mining areas or other complex working scenes.

[0067] The search radius refers to the perception range radius defined by the front end of the mine loader as the center of the circle based on the real-time positioning data of the laser scanner (such as lidar) in the mine loader automatic driving system. Specifically, the search radius is a dynamically adjusted parameter used to determine the effective detection distance of the front perception system of the mine loader to ensure that the loader can safely and efficiently perceive the front environment and potential obstacles under different vehicle speeds and road conditions.

[0068] The search radius is proportional to the real-time speed of the underground mining loader, and is dynamically adjusted according to the real-time speed of the underground mining loader. The higher the real-time speed of the underground mining loader, the larger the search radius is, so as to provide the underground mining loader with sufficient reaction time for safe operation; the lower the real-time speed of the underground mining loader, the smaller the search radius is, reducing unnecessary reactions and energy consumption.

[0069] Using SLAM technology, the laser positioning system continuously updates the precise location of the underground mining loader in the surrounding environment and adjusts the search radius in real time. The search radius can be adjusted using the following formula: ;in, is the search radius, is the real-time speed of the underground mining loader. It is a proportional constant set according to the performance and safety requirements of the underground mining loader. Among them, the positioning information (precise position) of the underground mining loader can be compared with the stored bumpy road section data to determine whether the current position of the underground mining loader has entered a known bumpy area. If it has entered, the system will automatically issue a speed reduction command to ensure smooth and safe passage through the area; if the current position has not entered any known bumpy area, the underground mining loader will maintain the current speed or adjust to a suitable speed according to the actual road conditions.

[0070] Among them, when dealing with a bumpy road section that is encountered suddenly, the function of recording the coordinates of the starting point and the end point of the bumpy road section, as well as the strategy of dynamically updating the bumpy road section record file according to the actual road conditions, can also be used.

[0071] When the underground mining loader suddenly encounters a bumpy road section, the system will automatically record the starting coordinates of the bumpy road section. As the underground mining loader drives until the bump ends, the system will record the ending coordinates of the bumpy road section. The system can accurately determine the location and range of the bumpy road section.

[0072] When the underground mining loader passes through an area that has been recorded as a bumpy section multiple times, the system will continue to monitor the road conditions. If it is found that there is no bump when passing through the area now, the system will delete the section information from the record file. This dynamic update strategy ensures the timeliness and accuracy of the record file and avoids repeated recording and processing of invalid bumpy sections.

[0073] In actual operation, the system will record and update bumpy sections based on the real-time location information of the underground mining loader provided by the laser positioning system and the road bump data provided by the on-board sensors. When the underground mining loader passes through a bumpy section, the system will record the starting and ending coordinates based on the duration and intensity of the bump. If the underground mining loader passes through it multiple times without detecting bumps again, the system will automatically remove the section from the record file.

[0074] By using SLAM technology and laser positioning, the operating accuracy and safety of underground mining loader in complex terrain have been significantly improved. Laser positioning is more accurate than traditional GPS, especially suitable for environments with obstructed vision or unstable GPS signals; the strategy of dynamically adjusting the search radius ensures safe response at different speeds, enhances the adaptability and flexibility of the autonomous driving system, and thus optimizes the overall driving performance and efficiency of underground mining loader.

[0075] Obtaining the frequency of adjusting the search radius within a preset interval: counting the number of times the search radius is adjusted within the preset interval, and marking the ratio of the number of times the search radius is adjusted within the preset interval to the time length of the preset interval as the frequency of adjusting the search radius.

[0076] The greater the frequency of search radius adjustment, the more sensitive the vehicle speed change is, resulting in frequent search radius adjustments. Frequent adjustments may increase the computing load and energy consumption of the system and may affect the stability of the underground mining shovel loader.

[0077] Among them, the time length of the preset interval is set according to actual monitoring needs, and can be set according to specific needs, such as 20 seconds, 25 seconds or 30 seconds, etc. The preset interval is usually set to real-time, that is, the end point of the preset interval is the real-time time point.

[0078] In S2, the pitch angle of the underground mining loader is collected in real time based on the IMU, and the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader, specifically:

[0079] The IMU installed on the underground mining loader collects pitch angle data in real time. The IMU usually includes an accelerometer and a gyroscope, which provide the motion status of the underground mining loader in space.

[0080] Calculate the pitch angle using the formula: ;in, It's time The pitch angle at the moment, The time The acceleration of the IMU on the y-axis and z-axis at the moment.

[0081] The collected pitch angle data is preprocessed to eliminate noise and outliers to ensure the accuracy and stability of the data. The preprocessing includes using a low-pass filter Kalman filter, which will not be described here.

[0082] The pitch intensity index (standard deviation of pitch angle) is calculated within a preset time window to quantify the pitch intensity.

[0083] Calculate the turbulence intensity index, the expression is: ;in, is the turbulence intensity index, is the number of data points in the time window, is the number of the data point in the time window, It is The pitch angle of the data point, is the mean of the pitch angles within the time window.

[0084] The greater the vibration intensity index, the higher the vibration intensity of the underground mining loader.

[0085] The time window is determined based on actual monitoring needs and will not be elaborated here.

[0086] In S3, by analyzing the coupling degree between the IMU and other mechanical components of the underground mining loader, the adverse effect of the coupling degree on the IMU data error is evaluated, specifically:

[0087] Mutual information spectral analysis is used to explore the degree of coupling between the inertial measurement unit (IMU) and other mechanical components of the underground mining loader. Mutual information spectral analysis is a method for evaluating the interdependence between two time series, and is particularly suitable for identifying the complex interaction between IMU data errors and the motion of mechanical components. This analysis can not only quantify the strength of the coupling, but also reveal how the coupling adversely affects the accuracy of the IMU data.

[0088] Obtaining IMU data: IMU data usually includes information such as acceleration, angular velocity, and direction, which reflects the dynamic behavior of underground mining loader during operation. IMU data is crucial for determining the spatial position and motion state of the equipment. Any data distortion caused by external mechanical components may lead to operational errors or safety accidents.

[0089] Obtain mechanical component data, including engine speed, vibration level, temperature, etc., which are operating status indicators of key components of underground mining loader. The status of mechanical components directly affects the performance and life of the entire system. Coupling analysis can reveal how the behavior of these components affects or distorts the sensor data of the IMU.

[0090] A time series of IMU data is formed based on the IMU data, and a time series of mechanical component data is formed based on the mechanical component data.

[0091] Ensure that the timestamps of IMU data and mechanical component data are aligned to allow for accurate comparative analysis.

[0092] Use low-pass filters or other digital filtering techniques to process data to remove high-frequency noise and reduce errors during data acquisition and transmission.

[0093] Determine an appropriate time window for analysis to capture the dynamic relationship between the mechanical component data and the IMU data.

[0094] The mutual information evaluation index is calculated using mutual information spectrum analysis. The mutual information evaluation index is the mutual information value of the IMU data and the mechanical component data at different frequencies. The expression of the mutual information evaluation index is: ;in, is the mutual information evaluation index, and Represent the time series of IMU data and the time series of mechanical component data respectively, is the joint probability density function, They are the marginal probability density functions of the time series of IMU data and the time series of mechanical component data, respectively.

[0095] The degree of coupling between the IMU and other mechanical components of the underground mining loader is evaluated by the size of the mutual information evaluation index. A higher mutual information evaluation index indicates strong coupling, which may indicate that the IMU data is significantly affected by the movement of mechanical components.

[0096] The larger the mutual information evaluation index, the greater the degree of adverse effect of the coupling degree on the IMU data error: This indicates that there is a strong mutual dependence or coupling between the IMU data and the mechanical component data, indicating that the motion state or behavior of the mechanical component is highly correlated with the motion state sensed by the IMU. This high correlation may mean that the vibration, movement or other physical manifestations of the mechanical component directly affect the measurement output of the IMU. Due to the high degree of coupling, any abnormal or non-standard operation of the mechanical component may directly lead to an increase in the error of the IMU data. For example, if the abnormal vibration of a component is mistaken by the IMU as a change in the movement of an underground mining loader, this will lead to decision-making or operational errors based on the IMU data.

[0097] in, Represents the probability distribution of the co-occurrence of IMU data and mechanical component data It can be estimated by kernel density estimation (KDE) or other statistical methods, which will not be described here. It is the basis for calculating mutual information, which provides a quantitative representation of the interdependence between two sets of data.

[0098] They respectively represent the probability distribution of IMU data and mechanical component data, which are usually estimated by KDE and will not be repeated here. The marginal probability density function is an indispensable component in calculating mutual information, which helps to understand the behavior pattern of a single data set from a statistical perspective.

[0099] By using kernel density estimation, a smooth and continuous probability density function estimate can be obtained without prior assumptions about the data distribution. This is particularly important for resolving the complex relationship between IMU data and mechanical component data, as these data may not conform to any simple standard distribution. In addition, the continuous probability density function provided by KDE is an ideal basis for mutual information calculation, because mutual information requires an accurate probability measure to effectively evaluate the mutual dependence between two random variables.

[0100] Mutual information spectrum analysis can comprehensively evaluate the dynamic interaction between IMU data and mechanical components, not only limited to linear relationships, but also including nonlinearities and more complex dependencies, which is crucial for a deep understanding of coupling effects. It can effectively evaluate the degree of coupling between IMU and other mechanical components of underground mining loader and its impact on IMU data errors. This method is not only scientific and accurate, but also provides a practical basis and guidance for system optimization, ultimately promoting the stability and efficiency of underground mining loader operation.

[0101] The unpredictability of IMU data is evaluated by measuring the change in information entropy of IMU signals under different operating states, specifically:

[0102] The three-axis acceleration data and three-axis angular velocity data are obtained from the IMU sensor on the underground mining loader.

[0103] Perform data preprocessing: Use a low-pass filter or Kalman filter to denoise the data to reduce the impact of high-frequency noise; normalize the data so that it can be analyzed on a uniform scale; fill in or remove missing values ​​in the data to ensure data integrity.

[0104] Select an appropriate time window length and sliding interval, for example, the window length is 1000 data points and the sliding interval is 10 data points.

[0105] The IMU data is split into multiple time windows and multi-scale entropy analysis is performed within each window.

[0106] Define a set of scale factors ,For example , the scale factor represents the resampling interval of the time series.

[0107] For each scale factor , calculate the resampled time series.

[0108] Calculate the sample entropy of the resampled time series. The sample entropy formula is: ;in, is the sample entropy, is the embedding dimension, It's tolerance. The length of the matching template is The probability of The length of the matching template is The probability of Indicates the total length of the time series data (i.e. the total number of data points).

[0109] The embedding dimension is used to construct the phase space reconstruction and is typically chosen to be 2 or 3 to ensure that the time series has enough dimensions in phase space for analysis.

[0110] Tolerance is defined as the similarity tolerance in the sample entropy calculation, which is usually 0.2 times the standard deviation to ensure that similar patterns in the time series can be identified in the sample entropy calculation.

[0111] For each scale factor , resample the time series. For each scale factor , construct a new time series .

[0112] in, ; is the scale factor The resampled data points below.

[0113] ;in, It is the index of traversing time series data, used to identify the position of the current data point. is another index for traversing time series data, used with Subsequences of positions are compared.

[0114] Using the sample entropy formula Calculate the scale factor The multi-scale entropy value under , its expression is: ;in, For the scale factor The multi-scale entropy value under For the scale factor The sample entropy calculated below.

[0115] The scale factor can be The multi-scale entropy values ​​under the scale factor are plotted into a curve to analyze the complexity and unpredictability of IMU data at different time scales. The multi-scale entropy value below indicates that the data is more complex and unpredictable at that scale.

[0116] In the scale factor The larger the multiscale entropy value under , the higher the unpredictability of the IMU data. This is because multiscale entropy is a measure of the complexity and randomness of data, which takes into account the statistical properties of data at different time scales. A higher entropy value means that the data exhibits more complexity and fewer repetitive patterns at this scale, that is, the behavior of the data is more random and irregular. This characteristic is particularly important in practical applications because it indicates the sensitivity and diversity of the response of IMU sensing data to external changes at a certain time scale. When IMU data exhibits high unpredictability, this may reflect the dynamic changes of the external environment or the instability of the internal system state, which is crucial for monitoring and adjusting the operation of underground mining shovel loaders. Therefore, understanding and interpreting these entropy values ​​can help optimize the configuration of the IMU system and improve its performance in complex environments.

[0117] In S4, a comprehensive analysis is conducted on the adverse effect of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible, specifically:

[0118] The mutual information evaluation index and the scale factor The multi-scale entropy value under the non-dimensional processing is processed, and the mutual information evaluation index after non-dimensional processing and the scale factor are The multi-scale entropy values ​​under the above conditions are assigned weight coefficients respectively and the credible assessment coefficient of turbulence intensity is calculated, and its expression is as follows: ;in, is the credible assessment coefficient of turbulence intensity, are the mutual information evaluation index and the scale factor The weight coefficient of the multi-scale entropy value under Both are greater than 0.

[0119] The larger the credible assessment coefficient of the turbulence intensity is, the worse the credibility of the quantitative result of the turbulence intensity of the underground mining loader is.

[0120] Set the turbulence intensity credible assessment threshold and compare the turbulence intensity credible assessment coefficient with the turbulence intensity credible assessment threshold:

[0121] When the credible assessment coefficient of the bump intensity is greater than the credible assessment threshold of the bump intensity, the quantification result of the bump intensity of the underground mining loader is determined to be unreliable. This indicates that the coupling degree between the IMU data and the mechanical components is high, or the unpredictability of the IMU data increases, resulting in a decrease in the credibility of the quantification result of the bump intensity.

[0122] When the quantitative results of the bump strength of underground mining loader are determined to be unreliable, the following measures can be taken:

[0123] Data Review and Re-Analysis: Perform a detailed review of the IMU data to look for possible errors or anomalous data points.

[0124] Equipment Inspection and Maintenance: Perform a physical inspection to confirm that all mechanical components are functioning properly, especially those that may affect the IMU measurements.

[0125] System Calibration: Recalibrate the IMU system to ensure its accuracy and reliability.

[0126] Improve data processing algorithms: Optimize data processing algorithms to better handle data with high noise or high variability.

[0127] Operating parameter adjustment: Adjust the operating parameters or strategies of the underground mining loader to reduce bumps or vibrations.

[0128] When the credible assessment coefficient of the bump intensity is less than or equal to the credible assessment threshold of the bump intensity, the quantified result of the bump intensity of the underground mining loader is determined to be credible. This indicates that the coupling and unpredictability of the IMU data are within an acceptable range, and the quantified result of the bump intensity is considered to be credible. This shows that the underground mining loader is in good operating condition and the measurement of the IMU system matches the actual bump state.

[0129] The threshold for the reliable assessment of the turbulence intensity is usually set based on historical data and expert experience. In actual operation, this threshold can be determined by statistically analyzing the historical turbulence data and analyzing the correlation between these data and the actual operation of the underground mining loader. For example, a threshold can be selected that minimizes the error between the quantification result of the turbulence intensity and the actual equipment failure record. In addition, this threshold can also be adjusted on the validation data set through machine learning methods, such as through optimization algorithms, to maximize the accuracy of the prediction.

[0130] The comprehensive mutual information evaluation index and the scale factor The multi-scale entropy values ​​under the condition of the data can fully understand the uncertainty and complexity of the data, which helps to identify possible sources of error and risk points in the data. Secondly, the use of dimensionless and weighted methods can evaluate different statistical metrics under a unified standard, improving the fairness and consistency of the evaluation. In addition, by setting a threshold and comparing it with the credible evaluation coefficient of the bump intensity, the credibility of the data can be clearly judged, which is crucial to ensure the stable operation and timely maintenance of underground mining shovel loaders, and ensure the continuity and efficiency of the production process.

[0131] In S5, when the jolting intensity of the underground mining loader is credible, the frequency and the jolting intensity of the underground mining loader are adjusted according to the search radius, and the speed of the underground mining loader is adjusted in real time, specifically:

[0132] Set the search radius adjustment frequency threshold and compare the search radius adjustment frequency with the search radius adjustment frequency threshold:

[0133] When the search radius adjustment frequency is greater than the search radius adjustment frequency threshold, it is determined that a vehicle speed reduction signal is generated. At this time, the speed adjustment system of the underground mining scraper reduces the vehicle speed: the greater the search radius adjustment frequency, the greater the corresponding reduction in vehicle speed. The specific implementation methods include:

[0134] Linear response algorithm: This method directly links the search radius adjustment frequency with the speed adjustment amplitude by setting a linear relationship model. The reduction in speed is proportional to the search radius adjustment frequency. For example, a baseline speed reduction ratio can be set, and then this ratio can be adjusted based on the actual value of the search radius adjustment frequency exceeding the threshold.

[0135] PID control algorithm: This is a commonly used feedback control algorithm that can adjust the vehicle speed according to the change of the search radius adjustment frequency. In this method, the adjustment of the vehicle speed depends not only on the current deviation of the search radius adjustment frequency from its threshold, but also takes into account the rate of change of the deviation and the integral of the deviation over time to optimize the response and stability of the vehicle speed.

[0136] Generating a speed reduction signal indicates that the underground mining loader needs to slow down, because the high-frequency search radius adjustment means that the underground mining loader may be experiencing an unstable environment or encountering frequent obstacle changes, and more time is needed for data processing and decision-making to ensure safe driving. In this case, the speed reduction is to provide sufficient reaction time and reduce the risk of operating errors or accidents that may be caused by fast driving on complex or unstable roads. The higher the frequency of search radius adjustment, the more drastic the changes in road conditions faced by the underground mining loader, so a greater reduction in speed is required to ensure sufficient processing time and safety buffer to prevent potential safety accidents due to untimely response. This method of dynamically adjusting the vehicle speed based on environmental response needs is an effective risk management strategy aimed at optimizing the performance of underground mining loader and ensuring the safety of occupants.

[0137] When the search radius adjustment frequency is less than or equal to the search radius adjustment frequency threshold, it is determined that a vehicle speed continuation analysis signal is generated, which means that the current vehicle speed and search radius adjustment frequency are appropriate and there is no need to adjust the vehicle speed immediately, but the system will continue to monitor the bump intensity index to determine whether subsequent speed adjustments are required.

[0138] When the vehicle speed continues to analyze the signal, the speed of the underground mining loader is adjusted according to the bump intensity index:

[0139] If the bump intensity index exceeds its corresponding threshold, the speed control system of the underground mining loader will immediately take action to automatically adjust the speed to reduce the speed of the underground mining loader. This is done to reduce the difficulty in controlling the underground mining loader and potential safety risks that may be caused by driving at high speed on bumpy roads. The reduction in speed depends on the specific value of the standard deviation. The higher the bump intensity index, the more severe the bump, and the greater the reduction in speed should be. And during the reduction process, the underground mining loader tends to be stable, and the underground mining loader will maintain this speed and continue to drive. The specific implementation methods include:

[0140] Threshold control algorithm: This is a basic implementation method, in which the adjustment of vehicle speed depends directly on the comparison result of the bump intensity index with the preset threshold. When the bump intensity index exceeds the threshold, the system directly reduces the vehicle speed by a preset ratio.

[0141] Fuzzy Logic Controller: Fuzzy logic controllers can handle uncertain and fuzzy inputs, making them particularly suitable for dynamic and rapidly changing environments. By defining fuzzy rules and membership functions, the controller can make more subtle adjustments to the vehicle speed at different levels of the bump intensity index.

[0142] If the bump severity index does not exceed its corresponding threshold, the vehicle speed is not automatically adjusted.

[0143] Among them, the search radius adjustment frequency threshold is usually based on historical data analysis and underground mining loader performance testing. By analyzing the underground mining loader response data under different road conditions and vehicle speeds, a frequency threshold can be determined, and when this threshold is exceeded, the operation of the underground mining loader may become unstable. This threshold can also be adjusted through simulation tests and actual driving experience to ensure that it can effectively reflect the underground mining loader's ability to adapt to rapid environmental changes.

[0144] The threshold value corresponding to the bump intensity index is set based on the design standards and safety requirements of underground mining loader. By testing the performance of underground mining loader under different bumpy road conditions, the safety limit of the bump intensity index can be determined. Beyond this limit, the underground mining loader may not be able to effectively absorb the bumps, thus affecting operational safety and passenger comfort. This threshold should also take into account the load, suspension system performance and tire condition of the underground mining loader to ensure its accuracy and applicability.

[0145] By dynamically adjusting the speed of underground mining loader to cope with different road conditions, especially when facing bumpy sections, the driving stability and safety of underground mining loader can be effectively enhanced. By setting the threshold of the search radius adjustment frequency and the bump intensity index, the speed adjustment system can respond to environmental changes in real time and slow down in time to cope with complex or unstable road conditions, thereby significantly reducing the control problems and safety risks of underground mining loader that may be caused by fast driving on uneven roads. In addition, this intelligent speed adjustment not only protects the driver and passengers, but also reduces the mechanical wear of the underground mining loader itself and extends the service life of the equipment. By finely controlling the speed, fuel efficiency can also be improved and unnecessary energy consumption can be reduced. Overall, this solution not only enhances safety by improving the adaptability of underground mining loader to different road conditions, but also optimizes operating costs, making the operation of underground mining loader in difficult environments more efficient and economical. This approach demonstrates the important role of modern underground mining loader automation technology in improving industrial transportation efficiency and safety.

[0146] Example 2

[0147] The difference between Example 2 of the present invention and Example 1 is that this example introduces an automatic driving longitudinal control system based on an underground mining shovel loader.

[0148] Figure 2 A structural schematic diagram of the automatic driving longitudinal control system based on an underground mining shovel loader of the present invention is given. The automatic driving longitudinal control system based on the underground mining shovel loader includes a search radius adjustment module, a bump intensity assessment module, a data credibility analysis module, a data credibility judgment module and a vehicle speed comprehensive adjustment module.

[0149] The search radius adjustment module obtains the real-time vehicle speed of the underground mining shovel loader in real time, adjusts the search radius based on the real-time vehicle speed, and obtains the search radius adjustment frequency within a preset range.

[0150] The bump intensity assessment module collects the pitch angle of the underground mining loader in real time based on the IMU, and quantifies the bump intensity of the underground mining loader through the standard deviation of the pitch angle of the underground mining loader.

[0151] The data trust analysis module analyzes the degree of coupling between the IMU and other mechanical components of the underground mining shovel loader to evaluate the adverse impact of the coupling degree on the IMU data error; and evaluates the unpredictability of the IMU data by measuring the change in information entropy of the IMU signal under different operating states.

[0152] The data credibility judgment module conducts a comprehensive analysis on the adverse effect of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining shovel loader are credible.

[0153] When the bump intensity of the underground mining shovel loader is credible, the vehicle speed comprehensive regulation module adjusts the vehicle speed of the underground mining shovel loader in real time according to the search radius adjustment frequency and the bump intensity of the underground mining shovel loader.

[0154] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0155] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0156] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0159] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0161] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0162] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0163] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic driving longitudinal control method based on an underground mining shovel loader is characterized in that: The steps include: S1: obtaining the real-time speed of the underground mining loader in real time, adjusting the search radius based on the real-time speed, and obtaining the search radius adjustment frequency within a preset interval; S2: Based on the IMU, the pitch angle of the underground mining loader is collected in real time, and the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader; S3: By analyzing the degree of coupling between the IMU and other mechanical components of the underground mining loader, the adverse effect of the coupling degree on the IMU data error is evaluated; by measuring the change in information entropy of the IMU signal under different operating states, the unpredictability of the IMU data is evaluated; S4: Comprehensively analyze the adverse effect of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible; S5: When the bumping intensity of the underground mining loader is credible, the frequency is adjusted according to the search radius and the bumping intensity of the underground mining loader, and the speed of the underground mining loader is adjusted in real time; By analyzing the coupling degree between IMU and other mechanical components of underground mining loader, the adverse effect of coupling degree on IMU data error is evaluated, specifically: Obtain IMU data and mechanical component data; forming a time series of IMU data based on the IMU data, and forming a time series of mechanical component data based on the mechanical component data; Align the timestamps of IMU data and mechanical component data; Determine the time window; The mutual information evaluation index is calculated using mutual information spectrum analysis, and its expression is: ;in, is the mutual information evaluation index, and Represent the time series of IMU data and the time series of mechanical component data respectively, is the joint probability density function, They are the marginal probability density functions of the time series of IMU data and the time series of mechanical component data, respectively; The unpredictability of IMU data is evaluated by measuring the change in information entropy of IMU signals under different operating states, specifically: Acquire three-axis acceleration data and three-axis angular velocity data and perform data preprocessing; Select the time window length and sliding interval; split the IMU data into multiple time windows and perform multi-scale entropy analysis in each window; Define a set of scale factors ; For each scale factor , calculate the resampled time series; Calculate sample entropy for the resampled time series; For each scale factor , resample the time series; for each scale factor , construct a new time series ; Use the sample entropy formula to calculate the scale factor The multi-scale entropy value under , its expression is: ;in, For the scale factor The multi-scale entropy value under Indicates the total length of the time series data, is the embedding dimension, It's tolerance. is the index to traverse the time series data, For the scale factor The sample entropy calculated below; A comprehensive analysis is conducted on the adverse effects of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible. Specifically: The mutual information evaluation index and the scale factor The multi-scale entropy value under the non-dimensional processing is processed, and the mutual information evaluation index after non-dimensional processing and the scale factor are The multi-scale entropy values ​​under the above conditions are assigned weight coefficients respectively and the turbulence intensity credible assessment coefficient is calculated, and its expression is as follows: ;in, is the credible assessment coefficient of turbulence intensity, are the mutual information evaluation index and the scale factor The weight coefficient of the multi-scale entropy value under All are greater than 0; Set the turbulence intensity credible assessment threshold and compare the turbulence intensity credible assessment coefficient with the turbulence intensity credible assessment threshold: When the credible evaluation coefficient of the turbulence intensity is greater than the credible evaluation threshold of the turbulence intensity, it is determined that the quantitative result of the turbulence intensity of the underground mining scraper is not credible; When the credible assessment coefficient of the turbulence intensity is less than or equal to the credible assessment threshold of the turbulence intensity, it is determined that the quantitative result of the turbulence intensity of the underground mining shovel loader is credible.

2. The method for longitudinal control of an automatic driving system based on an underground mining shovel loader according to claim 1, characterized in that: The real-time speed of the underground mining loader is obtained in real time, the search radius is adjusted based on the real-time speed, and the search radius adjustment frequency within the preset range is obtained, specifically: Get the real-time speed of underground mining loader in real time; Adjust the search radius by the following formula: ;in, is the search radius, is the real-time speed of the underground mining loader. is the proportionality constant; The number of times the search radius is adjusted within the preset interval is counted, and the ratio of the number of times the search radius is adjusted within the preset interval to the time length of the preset interval is marked as the search radius adjustment frequency.

3. The method for longitudinal control of automatic driving based on underground mining shovel loader according to claim 1, characterized in that: Based on the real-time acquisition of the pitch angle of the underground mining loader by IMU, the bump intensity of the underground mining loader is quantified by the standard deviation of the pitch angle of the underground mining loader, specifically: Collect pitch angle data in real time; pre-process the collected pitch angle data; The turbulence intensity index is calculated within the preset time window, and its expression is: ;in, is the turbulence intensity index, is the number of data points in the time window, is the number of the data point in the time window, It is The pitch angle of the data point, is the mean of the pitch angles within the time window.

4. The method for longitudinal control of automatic driving based on underground mining shovel loader according to claim 1, characterized in that: When the bumping intensity of the underground mining loader is credible, the frequency is adjusted according to the search radius and the bumping intensity of the underground mining loader, and the speed of the underground mining loader is adjusted in real time, specifically: Set the search radius adjustment frequency threshold and compare the search radius adjustment frequency with the search radius adjustment frequency threshold: When the search radius adjustment frequency is greater than the search radius adjustment frequency threshold, it is determined that a vehicle speed reduction signal is generated, and at this time, the vehicle speed adjustment system of the underground mining scraper reduces the vehicle speed; When the search radius adjustment frequency is less than or equal to the search radius adjustment frequency threshold, it is determined that a vehicle speed continuous analysis signal is generated; When the vehicle speed continues to analyze the signal, the speed of the underground mining loader is adjusted according to the bump intensity index: If the bump intensity index exceeds its corresponding threshold, the speed control system of the underground mining loader takes action to automatically adjust the speed and reduce the speed of the underground mining loader; If the bump severity index does not exceed its corresponding threshold, the vehicle speed is not automatically adjusted.

5. An automatic driving longitudinal control system based on an underground mining loader, used to implement the automatic driving longitudinal control method based on an underground mining loader according to any one of claims 1 to 4, characterized in that: It includes a search radius adjustment module, a bump intensity assessment module, a data credibility analysis module, a data credibility judgment module, and a vehicle speed comprehensive adjustment module; The search radius adjustment module obtains the real-time vehicle speed of the underground mining scraper in real time, adjusts the search radius based on the real-time vehicle speed, and obtains the search radius adjustment frequency within a preset range; The bump intensity assessment module collects the pitch angle of the underground mining loader in real time based on the IMU, and quantifies the bump intensity of the underground mining loader through the standard deviation of the pitch angle of the underground mining loader; The data trust analysis module evaluates the adverse effect of the coupling degree on the IMU data error by analyzing the coupling degree between the IMU and other mechanical components of the underground mining loader; and evaluates the unpredictability of the IMU data by measuring the change in information entropy of the IMU signal under different operating states; The data credibility judgment module conducts a comprehensive analysis of the adverse effects of the coupling degree on the IMU data error and the unpredictability of the IMU data to determine whether the quantitative results of the bump intensity of the underground mining loader are credible; When the bump intensity of the underground mining shovel loader is credible, the vehicle speed comprehensive regulation module adjusts the vehicle speed of the underground mining shovel loader in real time according to the search radius adjustment frequency and the bump intensity of the underground mining shovel loader.