A method and system for obtaining climbing angle of underground loader

Abstract

The present invention relates to the field of data processing technology, and more specifically, the present invention relates to a method and system for acquiring the climbing angle of an underground loader, including acquiring the monitoring data collected by the inclination sensor; using an improved weighted moving average method to denoise the monitoring data to obtain the denoised climbing angle, wherein the improved weighted moving average method includes: determining any angle value in the monitoring data as a target angle value, and establishing a left sequence and a right sequence with the target angle value as the center. In the initial weight correction of the weighted moving average method, the present invention not only takes into account the distance of the data, but also the degree of abnormality of the data, and reduces its weight to avoid excessive influence on the current data, thereby ensuring that the current data has better noise filtering effect after being processed by the weighted moving average method, and better retains the trend of data changes.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and more specifically, to a method and system for acquiring a climbing angle of an underground loader. Background Art

[0002] An underground loader is a type of engineering machinery specially used for loading operations in underground mines or tunnels. It can load and transport ore, coal and other materials inside the mine. An underground loader can also be used for road maintenance and construction inside the mine to ensure smooth traffic inside the mine, and to support and assist other heavy operations in the mine, such as rock crushing, concrete pouring, etc.

[0003] During the operation of the loader, obtaining the climbing angle can help the operator better understand the working status of the loader and avoid safety accidents caused by improper operation. By understanding the climbing angle of the loader, the working strategy can be adjusted to improve work efficiency. Real-time monitoring of the climbing angle can also help to promptly detect abnormal conditions of the loader and provide a basis for equipment maintenance.

[0004] In the related technology, for example, the Chinese patent application document with publication number CN119001408A discloses a battery simulator circuit damage prediction method based on multi-time series feature convolution, and a battery simulator circuit damage prediction method based on multi-time series feature convolution. The method includes using an exponentially weighted moving average filtering method to denoise high-frequency current data to obtain a denoised fault data set.

[0005] However, when using the weighted moving average method to filter out noise from data, the weighted moving average method will give a greater weight to the nearest data point, which is better than the simple moving average method that gives the same weight to all data points in the window. However, when the noise or abnormal data is closer, the current data will not be de-noised well after processing because of its larger weight. Summary of the invention

[0006] The present invention provides a method and system for acquiring the climbing angle of an underground loader, aiming to solve the problem in the weighted moving average method in the related art that when the noise or abnormal data is closer, the current data will have a poor denoising effect after processing due to its larger weight.

[0007] In a first aspect, a method for obtaining a climbing angle of an underground loader is provided, comprising two inclination sensors respectively installed on a chassis and a front end of the underground loader, and comprising: obtaining monitoring data collected by the inclination sensor; denoising the monitoring data using an improved weighted moving average method to obtain a denoised climbing angle, wherein the improved weighted moving average method comprises: determining any angle value in the monitoring data as a target angle value, establishing a left sequence and a right sequence with the target angle value as the center, and using an isolated forest algorithm to calculate the abnormal scores of the target angle value in the left sequence and the right sequence respectively, so as to determine the window position of the weighted moving average method; calculating a first influencing factor and a second influencing factor of the initial weight of each angle value in the window, and using the first influencing factor and the second influencing factor to correct the initial weight to obtain a final weight value of each angle value in the window; the first influencing factor is positively correlated with the degree of change of any angle value in the window and the angle values ​​on both sides thereof; the second influencing factor of the initial weight of the angle value is positively correlated with the sum of the difference between the angle value changes at the same time in the two sets of monitoring data, wherein one inclination sensor corresponds to one set of monitoring data. By determining the different characteristics of the turning points between noise abnormal data and normal data, the window of each data is moved to different degrees to obtain a final window that is more conducive to correcting the data. In the setting of weights, not only the distance of the data is taken into consideration, but also the degree of abnormality of the data, and its weight is reduced to avoid excessive impact on the current data, thereby ensuring that the current data has a better noise filtering effect after being processed by the weighted moving average method.

[0008] Furthermore, the final weight value of each angle value in the window is calculated, including: calculating the product of the initial weight of the angle value and the average value of the sum of the first influencing factor and the second influencing factor, and taking the value of the normalized product as the final weight value of the angle value.

[0009] Furthermore, the second influencing factor of the initial weight of the angle value is calculated, and the calculation formula is: ; In the formula, Indicates the first The second influencing factor of the initial weight of the angle value, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The angle value change of the angle value, represents the Pearson correlation coefficient between the first data series and the second data series, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The first data sequence and the second data sequence correspond to two sets of monitoring data respectively. The tilt angle of a loader is monitored simultaneously by the inclination sensors on the chassis and the front end. Therefore, the changes of the two sets of data in the same time period may have similar trends. A more accurate second influencing factor can be calculated based on the change trends of the two sets of monitoring data.

[0010] Further, calculating the first influencing factor of the initial weight of the angle value in the window includes: obtaining the angle value in the window is the starting point and angle value is the first vector of the end point, and the angle value i in the window is the starting point and angle value The second vector of the end point is calculated, and the angle between the first vector and the second vector is calculated, wherein the angle between the first vector and the second vector reflects the degree of change between any angle value in the window and the angle values ​​on both sides adjacent to it; the angle value in the window is calculated The first influencing factor is negatively correlated with the anomaly score and positively correlated with the angle. The angle value in the window is reflected by the angle between the first vector and the second vector. The intensity of the changes on the left and right sides, and the first influencing factor of the initial weight of the angle value in the window is determined according to the intensity of the data changes.

[0011] Furthermore, obtaining the initial weights of the angle values ​​in the window includes: determining that the initial weights of the angle values ​​in the window are the same.

[0012] Furthermore, obtaining the initial weight of each angle value in the window also includes: determining the initial weight of each angle value according to the distance between each angle value in the window and the target angle value, wherein the initial weight of the angle value is positively correlated with the distance between the angle value and the target angle value. Taking into account the distance of the data and the degree of abnormality of the data, and assigning the initial weight to each angle value, the filtering effect is improved.

[0013] Further, determining the window position of the weighted moving average method includes: in response to the abnormal score of the target angle value in the left sequence being greater than the abnormal score in the right sequence, controlling the window of the target angle value to move to the right, wherein the moving distance is positively correlated with the difference between the abnormal score of the target angle value in the left sequence and the abnormal score in the right sequence; in response to the abnormal score of the target angle value in the left sequence being less than the abnormal score in the right sequence, controlling the window of the target angle value to move to the left, wherein the moving distance is negatively correlated with the difference between the abnormal score of the target angle value in the left sequence and the abnormal score in the right sequence. The moving direction and distance of the window are determined by the different characteristics of the turning point of the noise abnormal data and the normal data, which is convenient for subsequent denoising processing.

[0014] Furthermore, a left sequence and a right sequence are established based on the target angle value as the center, including: determining that the target angle value and a preset number of adjacent angle values ​​on the left side constitute the left sequence; determining that the target angle value and a preset number of adjacent angle values ​​on the right side constitute the right sequence.

[0015] Furthermore, the preset number is a constant, and an empirical value of the preset number is 12.

[0016] In a second aspect of the present invention, a system for acquiring a climbing angle of an underground loader is provided, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods for acquiring a climbing angle of an underground loader.

[0017] Beneficial effects:

[0018] (I) By determining the different characteristics of the turning points between abnormal noise data and normal data, the window in the weighted moving average method of each data is moved to different degrees to obtain the final window that is more conducive to data correction and improve the subsequent noise filtering effect.

[0019] (ii) In the initial weight correction of the weighted moving average method, not only the distance of the data is taken into consideration, but also the degree of abnormality of the data, and its weight is reduced to avoid excessive impact on the current data, thereby ensuring that the current data has better noise filtering effect after being processed by the weighted moving average method, and better retaining the trend of data changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The following detailed description is read with reference to the accompanying drawings, which illustrate several embodiments of the present invention in an exemplary and non-limiting manner, and in which like or corresponding reference numerals represent like or corresponding parts, wherein:

[0021] Figure 1 FIG. 4 is a flow chart schematically illustrating noise filtering of monitoring data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] In one embodiment, during the operation of the loader, real-time acquisition of the climbing angle can help the operator better understand the working status of the loader and avoid safety accidents caused by improper operation. By understanding the climbing angle of the loader, the working strategy can be adjusted to improve work efficiency. Real-time monitoring of the climbing angle can also help to promptly detect abnormal conditions of the loader and provide a basis for equipment maintenance. However, the data collected using the inclination sensor may be affected by noise, which makes the collected data inaccurate. The reason is that the inclination sensor is usually interfered by the electromagnetic field, especially when there are other electrical equipment in the working environment. The electromagnetic interference may cause fluctuations in the sensor output signal, which manifests as noise.

[0025] Therefore, when using the inclination sensor to collect angle data, some filtering algorithms will be used to remove the influence of noise in the data, for example, the weighted moving average method is used to filter the data for noise. However, when the weighted moving average method is used to filter the data for noise, the weighted moving average method will give a larger weight to the nearest data point. Compared with the simple moving average method that gives the same weight to all data points in the window, the weighted moving average method is more effective. However, when the noise or abnormal data is closer, the current data will have a poor denoising effect after processing due to its larger weight. So far, the present invention improves the weighted moving average method, specifically, improves the weight of each data point in the window in the weighted moving average method, and improves the filtering effect of each data point. The specific steps are as follows.

[0026] like Figure 1 As shown: S101: Acquire monitoring data collected by the tilt sensor.

[0027] In one embodiment, the climbing angle of the underground loader can be monitored by a tilt sensor, and monitoring data can be collected, wherein the monitoring data is an angle value. In this embodiment, two sets of monitoring data can be obtained by two tilt sensors, specifically, the two tilt sensors are respectively installed on the front end and chassis of the underground loader, and are used to measure the tilt condition of the loader during the travel process. The tilt sensor at the front end of the loader can monitor the tilt angle of the loader when moving forward and downhill, which is very useful for controlling the lifting and lowering of the front end of the loader. The sensor at the center of the chassis of the loader can provide information on the overall tilt of the loader, which is essential to ensure the balanced operation of the loader on uneven ground. Since the tilt sensors on the chassis and the front end simultaneously monitor the tilt angle of a loader, there may be similar trends in the changes of the two sets of data in the same time period, and the following calculations and analyses can be used based on the changing trends of the two sets of monitoring data.

[0028] S102: Calculate a first influencing factor of an initial weight of each angle value in the window.

[0029] In one embodiment, before calculating the first influencing factor of the initial weight of each angle value in the window, it is necessary to first determine the window position of the weighted moving average method, and the determination process includes: determining any angle value in the monitoring data as the target angle value, establishing a left sequence and a right sequence with the target angle value as the center, and using the isolation forest algorithm to calculate the abnormal scores of the target angle value in the left sequence and the right sequence respectively, so as to determine the window position of the weighted moving average method, wherein the target angle value and the adjacent preset number of angle values ​​on the left side are determined to constitute the left sequence; and the target angle value and the adjacent preset number of angle values ​​on the right side are determined to constitute the right sequence. In this embodiment, the preset number is a constant, for example: the preset number is 10 or 12, and in other embodiments, the preset number can be 14 or 16, etc., which can be adjusted according to the specific implementation situation.

[0030] In one embodiment, the specific process of determining the window position of the weighted moving average method includes: if the anomaly score of the target angle value in the left sequence is greater than the anomaly score in the right sequence, controlling the window of the target angle value to move to the right, wherein the moving distance is positively correlated with the difference between the anomaly score of the target angle value in the left sequence and the anomaly score in the right sequence; if the anomaly score of the target angle value in the left sequence is less than the anomaly score in the right sequence, controlling the window of the target angle value to move to the left, wherein the moving distance is negatively correlated with the difference between the anomaly score of the target angle value in the left sequence and the anomaly score in the right sequence.

[0031] In one embodiment, the window of the target angle value is controlled to move, and the moving distance is as follows: ;in, The distance the window representing the target angle value moves, Indicates the length of the window, represents the abnormal score of the target angle value in the left sequence, Represents the anomaly score of the target angle value in the right sequence. It is a hyperparameter with an empirical value of 0.3, which can be adjusted according to the implementation situation. When , it means the window does not move; when When the window moves to the right position; when When the window moves to the left Among them, when hour, The larger the value is, the greater the distance the target angle value window moves to the right. hour, The smaller it is, the more the window of target angle value moves to the left.

[0032] Specifically, when the anomaly scores of the target angle values ​​in the left and right sequences are very different, that is, , indicating that the target angle value is very likely to be at the turning point of the data. In order to retain the change characteristics of the data itself, the anomaly score of the turning data should be reduced. Therefore, moving the window to the end with a smaller anomaly score of the target angle value can reduce the anomaly score of the target pixel in the window.

[0033] In one embodiment, after the position of the window is determined, the first influencing factor of the initial weight of the angle point in the weighted moving average method is calculated by the abnormal score and fluctuation intensity of the angle point in the window. The first influencing factor is positively correlated with the degree of change of any angle value in the window and the angle values ​​on both sides adjacent to it.

[0034] Specifically, the angle value Take the first impact factor as an example to calculate the angle value in the window. is the starting point and angle value is the first vector of the end point, and the angle value within the window is the starting point and angle value The second vector of the end point is used to calculate the angle between the first vector and the second vector. The angle between the first vector and the second vector is used to reflect the angle value in the window. The degree of change on the left and right sides; calculate the angle value within the window The first influencing factor is negatively correlated with the anomaly score and positively correlated with the angle.

[0035] In one embodiment, a calculation formula for a first influencing factor of an initial weight of an angle value within a calculation window is also provided, and the calculation formula is: ;in, Indicates the first The first influencing factor of the angle value weight is Indicates the first Anomaly score for angle values, Indicates the angle value is the starting point, angle value The vector with the end point and the angle value is the starting point, angle value The angle between the first vector and the second vector reflects the degree of change between any angle value in the window and its adjacent two angle values.

[0036] Specifically, for the angle value The first impact factor of the initial weight ,when The larger the value, the greater the angle. The flatter the left and right sides are, the less likely the angle value is to fluctuate abnormally. The first impact factor of the weight The bigger; when The smaller the angle, the sharper the angle, indicating the angle value The more dramatic the changes on the left and right sides, the greater the possibility of fluctuation of the angle value. The first impact factor of the weight The smaller the angle value. Anomaly score The larger the angle, The first impact factor of the weight The smaller the angle value Anomaly score The smaller the angle value The first impact factor of the weight The bigger.

[0037] S103: Calculate a second influencing factor of an initial weight of each angle value in the window.

[0038] In one embodiment, the second influencing factor of the initial weight of the angle value is positively correlated with the sum of the differences in the angle value changes at the same time in the two sets of monitoring data, wherein one inclination sensor corresponds to one set of monitoring data. The reason is that since the inclination sensors on the chassis and the front end simultaneously monitor the inclination angle of a loader, the changes in the two sets of data in the same time period may have similar trends. All data points contained in the window of the target data point are recorded as the first data sequence, and the data measured by another sensor in the same time period as the first data sequence is recorded as the second data sequence. The linear correlation between the first data sequence and the second data sequence is calculated using the Pearson correlation coefficient to reflect the similarity of the change trends of the two sets of data in the time period.

[0039] In one embodiment, the second influencing factor of the initial weight of the angle value is calculated using the following formula: ; In the formula, Indicates the first The second influencing factor of the initial weight of the angle value, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The angle value change of angle values, where The angle value and The angle value change of the angle value is The angle value and The difference in angle values, represents the Pearson correlation coefficient between the first data series and the second data series, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The angle value change of angle values, where The angle value and The angle value change of the angle value is The angle value and The difference of angle values; Represents the maximum value of the difference between adjacent data in two sequences, where the first data sequence and the second data sequence correspond to two groups of monitoring data respectively.

[0040] Among them, when The smaller the value, the more the angle value at the same time in the first data sequence and the second data. Has a similar trend of change. Explanation of angle value The less likely it is caused by noise or abnormality. The Pearson correlation coefficient between the first data series and the second data series is used to reflect the similarity of the changing trends of the two sets of data. Confidence considerations. The bigger, the Reflected angle value The higher the credibility of the abnormality, the greater the possibility that the abnormality reflected is correct. The smaller the reduction, the more the angle value can be preserved. The degree of abnormality; when r is smaller, it means Reflected angle value The lower the reliability of the abnormality, the smaller the possibility of the abnormality reflected is correct, so all abnormalities are The greater the reduction degree, the closer all abnormality degree values ​​are to each other, avoiding calculating the wrong abnormality degree and ensuring the correctness of the second influencing factor of the initial weight.

[0041] S104: Using the first influencing factor and the second influencing factor to correct the initial weight, to obtain a final weight value of each angle value in the window.

[0042] In one embodiment, obtaining the initial weights of the angle values ​​in the window includes: determining that the initial weights of the angle values ​​in the window are the same. For example, the initial weights of the angle values ​​are all 0.3 or 0.4, etc., which can be adjusted according to specific implementation conditions.

[0043] In one embodiment, obtaining the initial weight of each angle value in the window further includes: determining the initial weight of each angle value according to the distance between each angle value in the window and the target angle value, wherein the initial weight of the angle value is positively correlated with the distance between the angle value and the target angle value. The calculation formula is: ; where a=1 or 2, when a=1, Indicates the window to the left of the target angle value. The initial weight of the angle value is Indicates the window to the left of the target angle value. The initial weight of the angle value, Indicates the number of angle values ​​in the left window; when a=2, Indicates the window to the right of the target angle value. The initial weight of the angle value, Indicates the window to the right of the target angle value. The initial weight of the angle value, Indicates the number of angle values ​​within the right window. Indicates the distance between the bth angle value on the left or right side of the target angle value and the target angle value. Indicates the maximum distance from the target angle value among all angle values ​​on the left or right side of the target angle value. It indicates the minimum distance from the target angle value among all angle values ​​on the left or right side of the target angle value. It should be noted that the setting criterion of the initial weight is the distance from the target angle value. The closer the distance to the target angle value, the greater the initial weight; the farther the distance to the target angle value, the smaller the initial weight.

[0044] In one embodiment, the final weight value of each angle value in the window is obtained, the product of the initial weight of the angle value and the average value of the sum of the first influencing factor and the second influencing factor is calculated, and the value of the normalized product is used as the final weight value of the angle value.

[0045] In one embodiment, the final weight value of each angle value in the window is calculated using the following formula: ; Indicates the number of pixels to the left or right of the target angle value within the window. The corrected initial weight of the angle value, Indicates the number of pixels to the left or right of the target angle value within the window. The initial weight of the angle value, The first influencing factor representing the initial weight of the b-th angle value on the left or right side of the target angle value within the window, The second influencing factor representing the initial weight of the bth angle value on the left or right side of the target angle value in the window. Then the corrected initial weight is normalized to obtain the final weight value of each angle value in the window.

[0046] In one embodiment, the modified initial weight is normalized. The normalization formula is: In the formula, Indicates the number of pixels to the left or right of the target angle value within the window. The final weight value of the angle value, Indicates the number of pixels to the left or right of the target angle value within the window. The corrected initial weight of the angle value, when a=1 or 2, It is expressed as the total number of the target angle value and the adjacent preset number on the left or right.

[0047] S105: De-noising the angle values ​​in the window using their final weight values.

[0048] At this point, an improved weighted moving average method can be obtained, and the improved weighted moving average method is used to denoise the monitoring data to obtain a denoised climbing angle.

[0049] Through the above steps, by determining the different characteristics of the turning points between the noise abnormal data and the normal data, the window of each data is moved to different degrees to obtain the final window that is more conducive to correcting the data. In the setting of the weight, not only the distance of the data is taken into account, but also the degree of abnormality of the data, and its weight is reduced to avoid excessive impact on the current data, thereby ensuring that the current data has better noise filtering effect after being processed by the weighted moving average method, and better retaining the trend of data changes.

[0050] The present invention also provides a system for acquiring a climbing angle of an underground loader, the system comprising a processor and a memory, the memory storing computer program instructions, and when the computer program instructions are executed by the processor, a method for acquiring a climbing angle of an underground loader according to the first aspect of the present invention is implemented.

[0051] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0052] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions stored or otherwise maintained in such a computer-readable medium.

[0053] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0054] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for obtaining the climbing angle of an underground loader, comprising two inclination sensors respectively installed on the chassis and the front end of the underground loader, characterized in that: include: Acquiring monitoring data collected by the tilt sensor; The monitoring data is denoised using an improved weighted moving average method to obtain a denoised climbing angle, wherein the improved weighted moving average method includes: Determine any angle value in the monitoring data as a target angle value, establish a left sequence and a right sequence with the target angle value as the center, and use the isolation forest algorithm to calculate the abnormal scores of the target angle value in the left sequence and the right sequence respectively, and determine the window position of the weighted moving average method according to the abnormal scores of the target angle value in the left sequence and the right sequence respectively, including: In response to the anomaly score of the target angle value in the left sequence being greater than the anomaly score in the right sequence, controlling the window of the target angle value to move rightward, wherein the moving distance is positively correlated with the difference between the anomaly score of the target angle value in the left sequence and the anomaly score in the right sequence; In response to the anomaly score of the target angle value in the left sequence being less than the anomaly score in the right sequence, controlling the window of the target angle value to move leftward, wherein the moving distance is negatively correlated with the difference between the anomaly score of the target angle value in the left sequence and the anomaly score in the right sequence; Calculate the first influencing factor and the second influencing factor of the initial weight of each angle value in the window, and use the first influencing factor and the second influencing factor to correct the initial weight to obtain the final weight value of each angle value in the window; the first influencing factor and any angle value in the window are positively correlated with the degree of change of the angle values ​​adjacent to both sides; The second influencing factor of the initial weight of the angle value is positively correlated with the sum of the differences in the angle value changes at the same time in the two sets of monitoring data; Calculate the first influencing factor of the initial weight of each angle value in the window. The calculation formula is: ; In the formula, Indicates the first The first influencing factor of the angle value weight is Indicates the first Anomaly score for angle values, Indicates the angle value is the starting point, angle value The vector with the end point and the angle value is the starting point, angle value is the angle between the vectors of the end points, where the angle between the first vector and the second vector reflects the degree of change between any angle value in the window and the angle values ​​on both sides adjacent to it; The second influencing factor of the initial weight of each angle value in the calculation window is calculated as follows: ； In the formula, Indicates the first The second influencing factor of the initial weight of the angle value, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The angle value change of the angle value, represents the Pearson correlation coefficient between the first data series and the second data series, Indicates the first data sequence The angle value and The angle value change of the angle value, Indicates the first The angle value and The angle value change of each angle value, wherein the first data sequence and the second data sequence correspond to two groups of monitoring data respectively.

2. The method for obtaining the climbing angle of an underground loader according to claim 1, characterized in that: Calculate the final weight value of each angle value in the window, including: The product of the initial weight of the angle value and the average value of the sum of the first influencing factor and the second influencing factor is calculated, and the value of the normalized product is used as the final weight value of the angle value.

3. The method for obtaining the climbing angle of an underground loader according to claim 1, characterized in that: The first influencing factor for calculating the initial weight of the angle value in the window includes: Get the angle value within the window is the starting point and angle value is the first vector of the end point, and the angle value i in the window is the starting point and angle value The second vector of the end point is used as the second vector, and the angle between the first vector and the second vector is calculated, wherein the angle between the first vector and the second vector reflects the degree of change between any angle value in the window and the angle values ​​on both sides thereof; Calculate the angle value within the window The first influencing factor is negatively correlated with the anomaly score and positively correlated with the angle.

4. The method for obtaining the climbing angle of an underground loader according to claim 1, characterized in that: Obtaining the initial weight of each angle value in the window includes: It is determined that the initial weights of the angle values ​​in the window are the same.

5. The method for obtaining the climbing angle of an underground loader according to claim 1, characterized in that: Obtaining the initial weight of each angle value in the window includes: The initial weight of each angle value is determined according to the distance between each angle value in the window and the target angle value, and the initial weight of the angle value is positively correlated with the distance between the angle value and the target angle value.

6. The method for obtaining the climbing angle of an underground loader according to claim 1, characterized in that: The left sequence and the right sequence are established based on the target angle value as the center, including: Determine that the target angle value and a preset number of angle values ​​adjacent to the left side constitute a left sequence; Determine that the target angle value and a preset number of angle values ​​adjacent to the right side constitute a right sequence.

7. The method for obtaining the climbing angle of an underground loader according to claim 6, characterized in that: The preset number is a constant, and an empirical value of the preset number is 12.

8. A system for acquiring a climbing angle of an underground loader, comprising a processor and a memory, characterized in that: The memory stores a computer program, and the processor executes the computer program to implement the method for obtaining the climbing angle of an underground loader as described in any one of claims 1-7.

Images