A method and system for monitoring the running status of underground railcar

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for monitoring the running status of underground rail mining vehicles. The method comprises the steps of: presetting the length of an initial window, constructing an initial window with a target data point as the end, determining a first stability index and a second stability index of an extreme point in the initial window; using the modulus of a vector composed of the first stability index and the second stability index as the rate of change of the extreme point to obtain the stability of the initial window; obtaining the area enclosed by the mining vehicle speed curve and the mining vehicle load curve corresponding to the data point in the initial window, and determining the correlation between the mining vehicle speed and the mining vehicle load in the initial window; adjusting the length of the initial window based on the ratio of the correlation to the stability to obtain a target window, and processing the data points in the target window by an RRCF algorithm to obtain the monitoring result of the mining vehicle, so that the accuracy of the running status monitoring result of the underground rail mining vehicle can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring the operating status of an underground railcar. Background Art

[0002] Underground rail transport mine cars are important transportation equipment in mining production, mainly used for the transportation of underground ore, waste rock, personnel and materials. However, the underground environment is special and the transportation conditions are limited. In order to ensure the safe operation of underground rail transport mine cars, the speed of the mine cars needs to be strictly controlled. By monitoring and analyzing the speed of the mine cars, overspeeding and sudden braking of rail transport mine cars can be discovered in time, thereby reducing safety hazards.

[0003] The existing patent application document with publication number CN116432131A discloses an online identification method for abnormal state of a mine car braking system. The method obtains a reduced set of characteristic parameters under different working conditions; trains a neural network through a simplified set of characteristic parameters under different working conditions to obtain a corresponding braking system state identification model under each working condition, and finally obtains an online identification result.

[0004] The above-mentioned existing technical solutions can obtain the online identification results of the mine car through the neural network model. However, the underground environment in actual operation is relatively complex and requires rapid response, while the neural network often takes a long time to train and reason, and cannot meet the strict requirements of real-time monitoring underground. In addition, the running speed of the mine car may change with time and changes in operating conditions, resulting in the inability to accurately obtain the operating status monitoring results of the underground rail mine car.

[0005] Based on this, how to accurately obtain the operating status monitoring results of underground rail mining vehicles is a technical problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0006] In order to solve the above-mentioned technical problem of how to accurately obtain the running status monitoring result of the underground rail mining car, the present invention provides a running status monitoring method and system for the underground rail mining car.

[0007] In a first aspect, the present invention provides a method for monitoring the running status of an underground railcar, which adopts the following technical solution:

[0008] A method for monitoring the running status of an underground railcar comprises the following steps:

[0009] The method comprises the following steps: obtaining a plurality of data points in a time series of speed data of a mine car; presetting the length of an initial window, taking any data point as a target data point, constructing an initial window with the target data point as the end, obtaining an extreme point in the initial window, taking the slope of a line between the extreme point and the next extreme point as a first stability index of the extreme point, obtaining an absolute value of a speed difference between each data point on the line and the next data point, determining a second stability index of the extreme point, and the second stability index is positively correlated with the absolute value of the speed difference; taking the modulus of a vector composed of the first stability index and the second stability index as a change rate of the extreme point, obtaining the stability of the initial window, and the stability is negatively correlated with the change rate; obtaining an area enclosed by a mine car speed curve and a mine car load curve corresponding to a data point in the initial window, determining a correlation between the mine car speed and the mine car load in the initial window, and the correlation is negatively correlated with the area; adjusting the length of the initial window based on the ratio of the correlation to the stability to obtain a target window, and processing the data points in the target window by an RRCF algorithm to obtain a monitoring result of the mine car.

[0010] The present invention takes into account that when the monitoring results of the mine car are obtained by the RRCF algorithm, if a fixed window is used for processing, it is impossible to respond to the changes in the speed data in a timely manner, and the accuracy of the monitoring results obtained is low. Based on this, the embodiment of the present invention obtains the stability of the initial window by obtaining the speed data fluctuation in the initial window; in addition, the present invention also takes into account the mine car load that affects the speed change, and adjusts the initial window by combining the correlation and stability between the mine car speed and the mine car load, which can effectively improve the accuracy of the monitoring results of the mine car obtained based on this.

[0011] According to a method for monitoring the operating status of an underground rail mine car provided by the present invention, the method of obtaining multiple data points in a time series sequence of speed data of the mine car includes: collecting original speed data generated during the operation of the mine car, preprocessing the original speed data to obtain a time series sequence of speed data of the mine car, and obtaining multiple data points in the time series sequence of speed data.

[0012] The present invention takes into account that the overall quality of the collected original speed data is relatively poor, and therefore the original speed data needs to be preprocessed to ensure the consistency and comparability of the data.

[0013] According to a method for monitoring the running status of an underground railcar provided by the present invention, the second stability index of the extreme point satisfies the relationship:

[0014] ;

[0015] In the formula, represents the second stability index of the i-th extreme point, represents the number of data points on the line connecting the ith extreme point and the i+1th extreme point, represents the velocity value of the jth data point on the line, Represents the velocity value of the j+1th data point on the line, Represents the absolute value symbol.

[0016] According to a method for monitoring the running status of an underground railcar provided by the present invention, the stability of the initial window satisfies the relationship:

[0017] ;

[0018] In the formula, represents the stability of the initial window, represents the number of extreme points in the initial window, represents the rate of change of the i-th extreme point, represents the mean value of the rate of change of all extreme points in the initial window, Represents an exponential function with base e.

[0019] According to a method for monitoring the running status of an underground railcar provided by the present invention, the correlation between the speed of the railcar and the load of the railcar in the initial window satisfies the relationship:

[0020] ;

[0021] In the formula, represents the correlation between the minecart speed and the minecart load in the initial window, Indicates the acquisition time corresponding to the first velocity value in the initial window, Indicates the acquisition time corresponding to the last velocity value in the initial window, The expression representing the minecart speed curve in the initial window, The expression representing the minecart load curve for the initial window, represents the absolute value symbol, represents the integral symbol, Represents the integral variable The differential of represents the cosine similarity function, Represents the area enclosed by the mine car speed curve and the mine car load curve.

[0022] The present invention provides a method for calculating the correlation between the mine car speed and the mine car load accurately. The correlation between the curve data is evaluated by obtaining the area enclosed by the mine car speed curve and the mine car load curve, and the credibility of the correlation is verified in combination with the cosine similarity function. The accuracy of the correlation between the mine car speed and the mine car load can be effectively improved.

[0023] According to a method for monitoring the running status of an underground railcar provided by the present invention, the length of the initial window is adjusted based on the ratio of the correlation to the stability to obtain a target window, comprising: obtaining the length of the target window based on the ratio of the correlation to the stability:

[0024] ;

[0025] In the formula, Indicates the length of the target window, represents the length of the initial window, represents the logarithmic function with base 2, represents the correlation between the minecart speed and the minecart load in the initial window, represents the stability of the initial window; and adjusting the length of the initial window based on the length of the target window to obtain the target window.

[0026] The present invention provides an accurate formula for calculating the length of a target window, and the length of an initial window can be accurately obtained through the ratio of correlation and stability, so that the initial window can be accurately adjusted as the speed data in the initial window changes.

[0027] According to a method for monitoring the running status of an underground railcar provided by the present invention, the step of obtaining the monitoring result of the underground railcar further includes: issuing an early warning for abnormal monitoring result.

[0028] The present invention takes into account that when the running status of the rail mining car is monitored as abnormal, there may be a greater safety hazard. Therefore, by issuing an early warning to the outside, the staff can be reminded in time to handle it and reduce the risk.

[0029] In a second aspect, the present invention provides an operation status monitoring system for an underground railcar, which adopts the following technical solution:

[0030] A running status monitoring system for an underground rail mining car comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned running status monitoring method for an underground rail mining car is implemented.

[0031] By adopting the above technical solution, the above-mentioned method for monitoring the operating status of an underground railcar is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0032] The present invention has the following technical effects:

[0033] Based on the above technical scheme, the present invention can accurately obtain the stability of the initial window by analyzing the changes in speed data and slope in the initial window, and realize accurate adjustment of the initial window through the correlation between the mine car speed and the mine car load, effectively avoiding the influence of speed data fluctuations on the monitoring results of the tram, and determining the monitoring results based on the target window obtained after adjustment, which can effectively improve the accuracy of the operating status monitoring results of the underground rail mine car. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0035] Figure 1 A schematic flow chart of a method for monitoring the operating status of an underground railcar provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] 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.

[0037] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0038] It should be noted that neural networks often require a long time for training and reasoning, and cannot meet the requirements of real-time anomaly monitoring in the well. Compared with neural networks, anomaly detection algorithms pay more attention to real-time performance. For example, the Robust Random Cut Forest (RRCF) algorithm can analyze and process the collected operating data in a short time, realize real-time anomaly detection on the data stream, quickly adapt to changes in data distribution, and quickly provide monitoring results.

[0039] However, the running speed of the mine car may change with time and operating conditions. If the algorithm uses a fixed window size, it cannot quickly adapt to such changes, resulting in low accuracy of the running status monitoring results of the rail mine car.

[0040] Based on this, the embodiment of the present invention discloses a method for monitoring the running status of an underground railcar. The method adjusts the initial window by analyzing the speed change in the initial window, and can accurately obtain monitoring results to ensure that when the running status of the mine car is abnormal, it can be immediately detected and measures can be taken. Figure 1 As shown, Figure 1 A schematic flow chart of a method for monitoring the operating status of an underground railcar is provided in an embodiment of the present invention. The method comprises the following steps S1 to S5.

[0041] S1: Get multiple data points in the time series of the minecart's speed data.

[0042] It should be noted that the mine car operation status data is streaming data. Using the RRCF algorithm to process such data can monitor anomalies in real time without saving historical data, effectively reducing storage costs. However, the speed of the mine car will change with time and load, and the use of a fixed window size in data processing cannot adapt to such changes in a timely and effective manner. Based on this, the embodiment of the present invention adjusts the initial window by analyzing the change in speed in the initial window, so that the operation monitoring results of the mine car can be accurately obtained based on this.

[0043] For example, in an embodiment of the present invention, when obtaining multiple data points in a speed data time series sequence of a mine car, the original speed data generated during the operation of the mine car can be collected, the original speed data can be preprocessed to obtain a speed data time series sequence of the mine car, and multiple data points in the speed data time series sequence can be obtained.

[0044] The preprocessing method of the original speed data may be denoising processing, normalization processing, etc., which may be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0045] Specifically, sensors are placed on the mine car, and the collection frequency is set according to actual needs. The original speed data generated during the operation of the mine car is collected in real time. The data points in the speed data time series obtained after preprocessing each correspond to a speed value and a collection time.

[0046] After obtaining multiple data points in the speed data time series sequence based on the above method, continue to perform the following steps.

[0047] S2: Preset the length of the initial window, take any data point as the target data point, build the initial window with the target data point as the end, obtain the extreme point in the initial window, and determine the first stability index and the second stability index of the extreme point.

[0048] It should be noted that the stability of the speed data change in the initial window is directly related to the safety and operating efficiency of the mine car. If the speed fluctuates greatly, it may cause accidents such as the mine car losing control or derailing. Based on this, the stability index in the initial window can be obtained by analyzing the speed data fluctuation in the initial window.

[0049] The length of the initial window may be preset to 60, and the sliding step length of the window may be the same as the length of the window, which may be specifically set according to actual needs.

[0050] It can be understood that the length of the initial window is the number of data points contained in the window. For example, if the length of the initial window is 60, the initial window can be constructed with the target data point as the end, and the obtained initial window includes the target data point and the 59 data points before the target data point.

[0051] It should be noted that the extreme points in the initial window can represent significant changes or fluctuations in the data. By analyzing the data changes at the extreme points, the operating characteristics of the speed can be directly reflected. In addition, the variance can be used to measure the magnitude of the speed change. By analyzing the variance changes at the extreme points, the speed data stability in the initial window of the mine car can be obtained.

[0052] Specifically, the collection time corresponding to the data point in the speed data time series is used as the horizontal coordinate, and the speed value corresponding to the data point is used as the vertical coordinate to construct a line graph of the mine car speed under the initial window; the slope of the line between the extreme point and the next extreme point is used as the first stability indicator of the extreme point; the absolute value of the speed difference between each data point on the line and the next data point is obtained to determine the second stability indicator of the extreme point.

[0053] Among them, the first stability index of the extreme point is determined, and the specific relationship can be found in the following formula:

[0054] ;

[0055] In the formula, represents the first stability index of the i-th extreme point, represents the velocity value of the i-th extreme point, represents the velocity value of the i+1th extreme point, represents the collection time corresponding to the ith extreme point, Indicates the collection time corresponding to the i+1th extreme point.

[0056] In the above formula, Represents the slope of the i-th extreme point.

[0057] After obtaining the first stability index of the i-th extreme point, continue to determine the second stability index of the i-th extreme point based on the speed change, wherein the second stability index is positively correlated with the absolute value of the speed difference between each data point on the line between the extreme point and the next extreme point and the next data point.

[0058] It can be understood that, in the mine cart speed line graph under the initial window, the data points on the line between the extreme point and the next extreme point include the extreme point and the next extreme point.

[0059] Specifically, the second stability index of the extreme point can be determined by referring to the following relationship:

[0060] ;

[0061] In the formula, represents the second stability index of the i-th extreme point, represents the number of data points on the line connecting the ith extreme point and the i+1th extreme point, represents the velocity value of the jth data point on the line, Represents the velocity value of the j+1th data point on the line, Represents the absolute value symbol.

[0062] After the first stability index and the second stability index of the extreme point are obtained based on the above method, the stability of the extreme point can be obtained based on the first stability index and the second stability index.

[0063] S3: The modulus of the vector composed of the first stability index and the second stability index is used as the rate of change of the extreme point to obtain the stability of the initial window.

[0064] It should be noted that the change rate of the extreme point is obtained by obtaining the first stability index and the second stability index of the extreme point, which takes into account the comprehensive influence of the first stability index and the second stability index, and can more comprehensively reflect the dynamic change characteristics of the extreme point.

[0065] By way of example, in an embodiment of the present invention, when determining the stability of the initial window, the modulus of the vector composed of the first stability index and the second stability index is used as the rate of change of the extreme points, and then the stability of the initial window is obtained based on the rate of change of each extreme point in the initial window; wherein, the stability of the initial window is negatively correlated with the rate of change of the extreme points.

[0066] Among them, the change rate of the extreme point can be determined by referring to the following relationship:

[0067] ;

[0068] In the formula, represents the rate of change of the i-th extreme point, represents the first stability index of the i-th extreme point, represents the second stability index of the i-th extreme point, represents the 2-norm of the vector, that is, the modulus of the vector, A vector representing the rate of change of the i-th extreme point.

[0069] After obtaining the rate of change of the extreme point, the stability of the initial window can be determined based on the variance of the rate of change of the extreme point. For details, see the following relationship:

[0070] ;

[0071] In the formula, represents the stability of the initial window, represents the number of extreme points in the initial window, represents the rate of change of the i-th extreme point, represents the mean value of the rate of change of all extreme points in the initial window, Represents an exponential function with base e.

[0072] In the above formula, It represents the variance of the rate of change of the extreme points in the initial window. The larger the variance, the worse the stability of the initial window. Conversely, the smaller the variance, the better the stability of the initial window.

[0073] Based on the above steps, by analyzing the data changes of the speed itself in the initial window, the stability of the initial window can be obtained. However, in addition to its own normal data fluctuations, the speed may also be affected by the load of the mine car, so the relationship between speed and load also needs to be considered.

[0074] S4: Obtain the area enclosed by the mine car speed curve and the mine car load curve corresponding to the data points in the initial window, and determine the correlation between the mine car speed and the mine car load in the initial window.

[0075] It should be noted that the load of the mine car affects the power demand of the mine car. As the load increases, the mine car needs a larger drive to maintain stable operation, which in turn causes the running speed of the mine car to change. When the load changes rapidly, the speed of the mine car may also change significantly in a short period of time. Therefore, the higher the correlation between the speeds of the mine cars, the higher the possibility that the load affects the speed. In order to accurately adjust the initial window and accurately obtain the operating status monitoring results of the mine car, it is also necessary to obtain the correlation between the mine car speed and the mine car load in the initial window.

[0076] Specifically, the gravity sensor can be placed inside the mine car, with the same collection frequency as the speed collection setting, to obtain the mine car load data in real time. The obtained data points of the mine car speed and the mine car load correspond one by one, that is, at the same sampling moment, each corresponding mine car speed and mine car load has a data point.

[0077] For example, when determining the correlation between the mine car speed and the mine car load in the initial window, the mine car speed curve / mine car load curve can be constructed by first taking the collection time corresponding to the data point as the horizontal coordinate and the speed value / load value corresponding to the data point as the vertical coordinate; determining the collection time corresponding to the first speed value and the collection time corresponding to the last speed value among the speed values ​​corresponding to all the data points in the initial window; obtaining the area enclosed by the mine car speed curve and the mine car load curve corresponding to the data points in the initial window, thereby determining the similarity between the mine car speed curve and the mine car load curve, the smaller the area, the higher the similarity; obtaining the cosine similarity of the mine car speed curve and the mine car load curve as the credibility of the similarity, thereby obtaining the correlation between the mine car speed and the mine car load in the initial window, the higher the cosine similarity, the higher the credibility of the similarity between the mine car speed curve and the mine car load curve, and the correlation between the mine car speed curve and the mine car load curve is negatively correlated with the area enclosed by the mine car speed curve and the mine car load curve.

[0078] Specifically, in the embodiment of the present invention, the correlation between the mine car speed and the mine car load in the initial window is determined, and the following relationship can be referred to:

[0079] ;

[0080] In the formula, represents the correlation between the minecart speed and the minecart load in the initial window, Indicates the acquisition time corresponding to the first velocity value in the initial window, Indicates the acquisition time corresponding to the last velocity value in the initial window, The expression representing the minecart speed curve in the initial window, The expression representing the minecart load curve for the initial window, represents the absolute value symbol, represents the integral symbol, Represents the integral variable The differential of Represents the cosine similarity function.

[0081] In the above formula, Indicates that the mine car speed curve and the mine car load curve are in the integral interval [ ] The smaller the area is, the closer the two curves are in the integration interval and the higher their similarity is.

[0082] It is understandable that the step of obtaining expressions of the mine car speed curve and the mine car load curve through the collected data can be implemented through existing solutions, and the embodiments of the present invention will not be described in detail here.

[0083] After respectively obtaining the stability of the initial window and the correlation between the mine car speed and the mine car load based on the above steps, the initial window can be adjusted based on the stability of the initial window and the correlation between the mine car speed and the mine car load to adapt to the changes in the speed data in the initial window.

[0084] S5: Based on the ratio of correlation to stability, the length of the initial window is adjusted to obtain the target window, and the data points in the target window are processed by the RRCF algorithm to obtain the monitoring results of the mine car.

[0085] It should be noted that when the running speed of the mine cart in the initial window is more unstable and the correlation between the mine cart speed and the mine cart load is higher, a smaller window is needed to improve the response speed of the algorithm to changes, and the corresponding initial window adjustment degree is greater.

[0086] For example, when the length of the initial window is adjusted based on the ratio of correlation to stability, the length of the target window can be obtained based on the ratio of correlation to stability, and then the initial window is adjusted according to the length of the target window.

[0087] Specifically, to determine the length of the target window, refer to the following relationship:

[0088] ;

[0089] In the formula, Indicates the length of the target window, represents the length of the initial window, represents the logarithmic function with base 2, represents the correlation between the minecart speed and the minecart load in the initial window, Indicates the stability of the initial window.

[0090] In the above formula, Indicates the adjustment degree of the initial window. The adjustment degree has both positive and negative values. A positive value indicates that the speed in the window changes quickly and the initial window needs to be increased; a negative value indicates that the speed in the window changes slowly and the initial window needs to be reduced. Specifically, it includes the following three situations:

[0091] when hour, , indicating that the stability of the initial window is low and the correlation between the mine car speed and the mine car load is high, and the adjustment degree is also large. In this case, the initial window needs to be reduced, and the greater the adjustment degree, the greater the degree of reduction of the initial window.

[0092] when , it means that the stability of the initial window is high and the correlation between the mine cart speed and the mine cart load is low. In this case, it is necessary to expand the initial window.

[0093] when , it indicates that the adjustment degree is a negative value and exceeds the length of the initial window. In this case, in order to avoid the initial window being adjusted to 0 or a negative value, the initial window is directly reduced by half.

[0094] Based on the above steps, the length of the target window can be obtained. It can be understood that the length of the target window is the number of data points contained in the target window. After obtaining the length of the target window, the target window can be constructed with the target data point as the end, and the initial window can be adjusted to the length of the target window to obtain the target window; the window sliding step of the target window can be the same as the length of the target window, which can be set according to actual needs.

[0095] For example, when the data points in the target window are processed by the RRCF algorithm to obtain the monitoring results of the mine car, the RRCF forest can be constructed first, and for each data point in the window, it is inserted into each tree in the RRCF forest in turn; for each newly inserted data point, the change in tree complexity caused by it is calculated, and the anomaly score is calculated according to the change in tree complexity after the data point is inserted, wherein the greater the complexity change of the data point, the higher its anomaly score, indicating that the data point is more likely to be an anomaly point; the calculated anomaly score is compared with the preset threshold to determine whether the data point is an anomaly point, and the monitoring result is output.

[0096] It is understandable that the step of obtaining the abnormal score of the data point based on the RRCF algorithm is a prior art and will not be described in detail in the embodiment of the present invention.

[0097] After obtaining the monitoring results of the target window based on the above steps, the target can be slid to a new position based on the window sliding step of the target window, and the target window at the new position is used as the new initial window, and the above steps are continued to be adjusted and the monitoring results are obtained. In this way, as new data points arrive, the window slides forward, and the old data points are removed from the window, and the monitoring results of all data points in the speed data time series can be obtained.

[0098] For example, after obtaining the monitoring results of the mine car, it also includes: issuing an early warning for abnormal monitoring results. In this way, by issuing an early warning, the staff can be reminded to deal with the abnormal monitoring results in time, effectively reducing safety hazards.

[0099] It can be seen that in the embodiment of the present invention, a plurality of data points in the speed data time series of the mine car are obtained; the length of the initial window is preset, any data point is taken as the target data point, the initial window is constructed with the target data point as the end, the extreme point in the initial window is obtained, the slope of the line between the extreme point and the next extreme point is taken as the first stability index of the extreme point, the absolute value of the speed difference between each data point on the line and the next data point is obtained, and the second stability index of the extreme point is determined, and the second stability index is positively correlated with the absolute value of the speed difference; the modulus of the vector composed of the first stability index and the second stability index is taken as the rate change rate of the extreme point, and the stability of the initial window is obtained, and the stability is negatively correlated with the rate change rate; the area enclosed by the mine car speed curve and the mine car load curve corresponding to the data point in the initial window is obtained, and the correlation between the mine car speed and the mine car load in the initial window is determined, and the correlation is negatively correlated with the area; the length of the initial window is adjusted based on the ratio of the correlation to the stability to obtain the target window, and the data points in the window after the target window is adjusted are processed by the RRCF algorithm to obtain the monitoring result of the mine car.

[0100] In this way, the embodiment of the present invention can accurately obtain the stability of the initial window by analyzing the changes in speed data and slope in the initial window, and realize accurate adjustment of the initial window through the correlation between the mine car speed and the mine car load, thereby effectively avoiding the influence of speed data fluctuations on the monitoring results of the tram. The monitoring results are obtained based on the target window obtained after adjustment, which can effectively improve the accuracy of the operating status monitoring results of the underground rail mine car.

[0101] An embodiment of the present invention further discloses an operating status monitoring system for an underground rail mining vehicle, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an operating status monitoring method for an underground rail mining vehicle according to the present invention is implemented.

[0102] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0103] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, 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.

[0104] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0105] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the running status of an underground railcar, characterized in that: include: Get multiple data points in the time series of the mine car's speed data; Preset the length of the initial window, take any data point as the target data point, construct the initial window with the target data point as the end, obtain the extreme point in the initial window, take the slope of the line between the extreme point and the next extreme point as the first stability index of the extreme point, obtain the absolute value of the speed difference between each data point on the line and the next data point, determine the second stability index of the extreme point, and the second stability index is positively correlated with the absolute value of the speed difference; The modulus of the vector composed of the first stability index and the second stability index is used as the change rate of the extreme point to obtain the stability of the initial window. The stability is negatively correlated with the change rate, and the stability of the initial window satisfies the relationship: ； In the formula, represents the stability of the initial window, represents the number of extreme points in the initial window, represents the rate of change of the i-th extreme point, represents the mean value of the rate of change of all extreme points in the initial window, represents an exponential function with base e; The area enclosed by the mine car speed curve and the mine car load curve corresponding to the data point in the initial window is obtained, and the correlation between the mine car speed and the mine car load in the initial window is determined. The correlation is negatively correlated with the area, and the correlation between the mine car speed and the mine car load in the initial window satisfies the relationship: ； In the formula, represents the correlation between the minecart speed and the minecart load in the initial window, Indicates the acquisition time corresponding to the first velocity value in the initial window, Indicates the acquisition time corresponding to the last velocity value in the initial window, The expression representing the minecart speed curve in the initial window, The expression representing the minecart load curve for the initial window, represents the absolute value symbol, represents the integral symbol, Represents the integral variable The differential of represents the cosine similarity function, represents the area enclosed by the mine car speed curve and the mine car load curve; adjusting the length of the initial window based on the ratio of the correlation to the stability to obtain a target window, and processing the data points in the target window by the RRCF algorithm to obtain the monitoring result of the mine car; The adjusting the length of the initial window based on the ratio of the correlation to the stability to obtain the target window includes: The length of the target window is obtained based on the ratio of the correlation to the stability: ； In the formula, Indicates the length of the target window, represents the length of the initial window, represents the logarithmic function with base 2, represents the correlation between the minecart speed and the minecart load in the initial window, Indicates the stability of the initial window; The length of the initial window is adjusted based on the length of the target window to obtain the target window.

2. The method for monitoring the running status of an underground railcar according to claim 1, characterized in that: The method of obtaining a plurality of data points in a time series of speed data of the mine car comprises: The original speed data generated during the operation of the mine car is collected, the original speed data is preprocessed to obtain a speed data time series sequence of the mine car, and a plurality of data points in the speed data time series sequence are obtained.

3. The method for monitoring the running status of an underground railcar according to claim 1, characterized in that: The second stability index of the extreme point satisfies the relationship: ； In the formula, represents the second stability index of the i-th extreme point, represents the number of data points on the line connecting the ith extreme point and the i+1th extreme point, represents the velocity value of the jth data point on the line, Represents the velocity value of the j+1th data point on the line, Represents the absolute value symbol.

4. The method for monitoring the running status of an underground railcar according to claim 1, characterized in that: The step of obtaining the monitoring result of the mine car further includes: Issue early warnings for abnormal monitoring results.

5. An underground railcar operation status monitoring system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for monitoring the operating status of an underground railcar according to any one of claims 1 to 4 is implemented.

Images