Unmanned mine card fault diagnosis method and device based on data driving

Abstract

The embodiment of the invention provides an unmanned mine card fault diagnosis method and device based on data driving, and the method comprises the steps: comparing a course angle associated with an unmanned mine card in a rotation process with an actual steering angle, and determining whether the steering process is consistent or not according to an actual comparison process; under the condition that it is confirmed that the steering processes are inconsistent, an outer ring steering arc and an inner ring steering arc of the unmanned mine truck in the steering process at the corresponding moment are confirmed, the confirmed outer ring steering arc and the inner ring steering arc are compared and verified, and a fault signal is generated according to the comparison and verification processes; and determining a group of monitoring periods based on the fault signals, comparing and verifying fault related data in the monitoring periods, and diagnosing real faults of the unmanned mine card according to a comparison and verification process.

Description

Technical Field

[0001] This document relates to the field of equipment fault diagnosis technology, and in particular to a data-driven method and device for diagnosing faults in unmanned mining trucks. Background Technology

[0002] In the process of intelligent transformation of mining production, unmanned mining trucks, as the core equipment for open-pit mine transportation, are directly related to the safety, continuity, and economic benefits of mine production due to their operational stability and fault diagnosis efficiency. However, unmanned mining trucks operate in complex and harsh environments, facing severe conditions such as bumpy roads, heavy loads, and frequent turns, which makes their key components, such as steering systems and hydraulic systems, prone to failure. If these failures are not diagnosed and addressed in a timely manner, they may lead to loss of vehicle control, transportation disruptions, or even safety accidents.

[0003] Traditional fault diagnosis methods for unmanned mining trucks often rely on preset threshold judgments or single sensor data monitoring, which has obvious limitations: on the one hand, judging faults based on a single parameter (such as the absolute value of steering angle deviation) makes it difficult to distinguish whether the fault originates from vehicle control system errors, external road surface anomalies (such as potholes), or hydraulic component failures, which can easily lead to misjudgments; on the other hand, the identification of faults in key components such as hydraulic systems lacks dynamic data comparison and feature analysis, and often only responds passively after a fault occurs, making it difficult to achieve early warning and accurate positioning.

[0004] Therefore, how to construct a fault diagnosis mechanism based on multi-dimensional data correlation analysis to quickly identify, differentiate, and accurately trace the steering anomalies and potential faults of unmanned mining trucks has become a key technical requirement for improving the operation and maintenance level of unmanned mining trucks and ensuring efficient mine production. It is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a data-driven method and apparatus for diagnosing faults in unmanned mining trucks, aiming to solve the aforementioned problems in the prior art.

[0006] This invention provides a data-driven fault diagnosis method for unmanned mining trucks, comprising: The heading angle associated with the unmanned mining truck during rotation is compared with the actual turning angle, and the turning process is confirmed to be consistent based on the actual comparison process. If the turning process is confirmed to be inconsistent, the outer and inner turning arcs of the unmanned mining truck at the corresponding moment are confirmed, and the confirmed outer and inner turning arcs are compared and verified. Based on the comparison and verification process, a fault signal is generated. Based on the fault signal, a set of monitoring cycles is identified, and the fault-related data within the monitoring cycle is compared and verified. The actual fault of the unmanned mining truck is diagnosed according to the comparison and verification process.

[0007] This invention provides a data-driven unmanned mining truck fault diagnosis device, comprising: The comparison module is used to compare the heading angle associated with the unmanned mining truck during rotation with the actual turning angle, and to confirm whether the turning process is consistent based on the actual comparison process. The verification module is used to confirm the outer and inner turning arcs of the unmanned mining truck at the corresponding moment during the turning process when the turning process is inconsistent. It then compares and verifies the confirmed outer and inner turning arcs and generates a fault signal based on the comparison and verification process. The diagnostic module is used to confirm a set of monitoring cycles based on the fault signal, compare and verify the fault-related data within the monitoring cycle, and diagnose the actual fault of the unmanned mining truck according to the comparison and verification process.

[0008] This invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the above-described data-driven unmanned mining truck fault diagnosis method.

[0009] This invention also provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, implements the steps of the above-described data-driven unmanned mining truck fault diagnosis method.

[0010] By employing the embodiments of this invention, a preliminary comparison between the heading angle and the actual steering angle can quickly capture potential signs of steering anomalies. Further, a refined comparison and verification of the outer and inner steering arcs can distinguish fault types, such as control faults, external environmental interference like dents, or suspected hydraulic faults. This avoids the limitations of relying on a single indicator and makes fault location more accurate. By relying on actual data from the unmanned mining truck's operation (such as heading angle, steering angle, radian data, and hydraulic data), rather than subjective experience, errors in human judgment are reduced, making fault diagnosis results more reliable and convincing. Through multi-step verification and analysis, control faults, external environmental (dent) influences, and hydraulic system faults can be effectively distinguished. In particular, further verification of suspected hydraulic faults ensures the accuracy of fault type judgment and provides a clear direction for subsequent maintenance. From initial angle comparison to characteristic analysis of the steering arc, and then to periodic monitoring and variance verification of hydraulic data, a complete diagnostic process is formed, covering multiple dimensions that may involve steering anomalies, such as equipment control, external environment, and key components (hydraulic system), avoiding any omissions of faults. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a data-driven unmanned mining truck fault diagnosis method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a data-driven unmanned mining truck fault diagnosis device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0014] Method Implementation Examples According to embodiments of the present invention, a data-driven fault diagnosis method for unmanned mining trucks is provided. Figure 1 This is a flowchart of a data-driven fault diagnosis method for unmanned mining trucks according to an embodiment of the present invention, such as... Figure 1 As shown, the data-driven fault diagnosis method for unmanned mining trucks according to an embodiment of the present invention specifically includes: Step S101: Compare the heading angle associated with the unmanned mining truck during the rotation process with the actual turning angle, and confirm whether the turning process is consistent based on the actual comparison process. Specifically, during autonomous operation, unmanned mining trucks have associated heading angles and corresponding turning angles during actual operation. During normal operation, their heading angles should be consistent with their turning angles. If they are inconsistent, it means that there is a turning error during actual operation. In this case, it is necessary to generate corresponding error signals in real time for display and perform subsequent steps to verify features and identify specific abnormal signals. The specific method for confirming the steering process and assessing consistency is as follows: Confirm the heading angle associated with the unmanned mining truck during actual operation. The heading angle is determined by the unmanned mining truck itself based on the front-end material conditions and the actual route. The associated heading angle is denoted as Hi, where i represents different times. The actual turning angle associated with the unmanned mining truck at the corresponding time is then denoted as Ji. The confirmed heading angle is compared with the actual turning angle: if Hi=Ji, no processing is performed; if Hi≠Ji, an error confirmation signal is generated. Specifically, when there is a deviation between the corresponding heading angle and the associated turning angle, it means that there is a related difference between the corresponding angles. In actual operation, this indicates that there is a specific angle error. When an angle error exists, it is necessary to confirm the anomaly and identify the associated abnormal signal. By comparing the heading angle with the actual steering angle, potential signs of steering abnormalities can be quickly captured. Then, by combining the fine comparison and verification of the outer and inner steering arcs, the fault types can be further distinguished, such as control faults, external environmental interference such as dents, or suspected hydraulic faults. This avoids the one-sidedness of judging by a single indicator and makes fault location more accurate. Step S102: If the turning process is confirmed to be inconsistent, the outer and inner turning arcs of the unmanned mining truck at the corresponding moment are confirmed during the turning process. The confirmed outer and inner turning arcs are compared and verified. A fault signal is generated based on the comparison and verification process. Specifically, if the turning characteristics associated with the inner and outer turning arcs are relatively consistent during the comparison and verification process, it means that there is a turning error in the actual turning process. Therefore, in order to effectively confirm the actual fault of the unmanned mining truck, it is necessary to confirm the characteristics and lock the corresponding fault signal. The specific method for confirming the verification signal is as follows: Based on the generated error confirmation signal, the specific time associated with the corresponding error confirmation signal is confirmed, and the turning process associated with the specific time is recorded as the process to be verified. The corresponding turning angle exists in the turning process. That is, the specific process that has a turning angle in the time period before and after the corresponding time belongs to the corresponding turning process. The two sets of arc circles associated with the steering process are compared and verified to lock the outer and inner steering arcs (if the corresponding steering angle is inward, then the arc associated with the inner tire belongs to the inner steering arc; when the corresponding steering angle is to the other side, then the arc associated with the other side also belongs to the inner steering arc). The arc data of adjacent circle points within the outer steering arc are confirmed, and the confirmed arc data is labeled as Hk, where k represents the arc segment between different adjacent circle points. Arc segments with the same arc data Hk are recorded as the same arc segment, and the total number of the same arc segments G is confirmed. From several different values ​​G, the arc segment with Gmax is selected as the feature arc segment. Based on the confirmed feature arc segment, a set of built-in circle centers is locked (the arc segment belongs to a part of a circle, so the associated circle can be confirmed based on the corresponding arc segment, and the corresponding circle center can be locked based on the associated circle. The confirmed circle center is the built-in circle center associated with the corresponding feature arc segment). Connect the inner center of the circle to different circle points within the outer turning arc to identify several feature lines. Record the intersections of these feature lines with the inner turning arc as the corresponding auxiliary points of the circle points. Perform feature verification on the identified circle points and their associated auxiliary points: confirm the external tangent lines to the circle points within the outer turning arc, and simultaneously confirm the external tangent lines to the corresponding auxiliary points of the inner turning arc. Identify whether the two sets of confirmed tangent lines are parallel. If they are parallel, no processing is required. If they are not parallel, identify whether the corresponding circle point or auxiliary point belongs to the same arc segment as the feature arc segment. If it belongs, no processing is required. If it does not belong, mark the corresponding point as an abnormal point. After analyzing the entire steering process, identify any anomalies: If it does not exist, it means that there is a control fault in the current unmanned mining truck, and a control fault signal will be generated and displayed directly. This will cause a large error between the required heading angle and the actual controlled steering angle, which will not achieve a good control effect and is prone to control deviation. If present: Confirm the number of abnormal points K1 on the corresponding arc, then confirm the total number of all circle points Z1 on the corresponding arc. Use: K1÷Z1=Zb to confirm the proportion of abnormal points Zb. From the two sets of proportion values ​​Zb confirmed in the two arcs, select the maximum value Zbmax and confirm whether Zbmax satisfies: Zbmax≤Y1. If satisfied, generate a pit presence signal for display (when the characteristics of other arc segments on the corresponding two arcs are relatively consistent, and only a small part is abnormal, it is very likely caused by the corresponding road segment pit, so directly generate a pit presence signal for display). Y1 is a preset value, and its specific value is determined by the operator based on experience. If not satisfied, generate a suspected hydraulic fault signal. After the suspected hydraulic fault signal is generated, it needs to undergo further processing and analysis to identify whether the hydraulic components associated with the left and right tires have changed abnormally, and to make a comprehensive assessment of the abnormality based on the specific identification process. By relying on actual data from the operation of unmanned mining trucks (such as heading angle, turning angle, radian data, hydraulic data, etc.) rather than subjective experience, the error of human judgment is reduced, making the fault diagnosis results more reliable and convincing. Step S103: Based on the fault signal, a set of monitoring periods is confirmed, and the fault-related data within the monitoring periods are compared and verified. The actual fault of the unmanned mining truck is diagnosed according to the comparison and verification process. Specifically, the method for comprehensively verifying the changing characteristics is as follows: Based on the confirmed suspected hydraulic fault signals, a set of monitoring cycles is determined. The monitoring cycle is a preset cycle, which is determined in advance by the operator based on experience. The time when there is no steering angle within the monitoring cycle is recorded as the verification time, and the hydraulic data associated with the verification time is recorded as YZq-o, where q represents different tires and o represents different verification times. The hydraulic data YZq-o associated with the same verification time are confirmed sequentially. From the confirmed hydraulic data YZq-o, the change characteristics associated with adjacent hydraulic data YZq-o are confirmed. Then, from the change characteristics associated with several sets of the same period, the feature difference between adjacent change characteristics is confirmed. Where: feature difference = |B1-B2|, where B1 and B2 represent different change characteristics within adjacent change characteristics. The variance of the confirmed set of characteristic differences is processed to confirm the standard variance. The confirmed standard variance is then compared with a preset threshold for verification. If the standard variance is less than or equal to the preset threshold, it means that the hydraulic error associated with the two tires is small, and it may not be a fault caused by a hydraulic fault. In this case, a maintenance signal is generated and displayed. If the standard variance is greater than the preset threshold, a hydraulic fault signal is generated and displayed. Specifically, during the comprehensive evaluation process, it is necessary to conduct a comprehensive evaluation based on the specific hydraulic change process, identify the specific changes between the data, and then quickly confirm the specific change process between the corresponding two tires based on the specific change process, in order to confirm the difference in the actual error processing process, and comprehensively evaluate whether there is a related fault in the hydraulic system. From initial angle comparison to feature analysis of the steering arc, and then to periodic monitoring and variance verification of hydraulic data, a complete diagnostic process has been formed, covering multiple dimensions such as equipment control, external environment, and key components (hydraulic system) that may be involved in steering anomalies, thus avoiding the omission of faults.

[0015] The technical solution of this invention distinguishes fault types, such as control faults, external environmental interference such as dents, or suspected hydraulic faults, avoiding the one-sidedness of judging by a single indicator and making fault location more accurate; it forms a complete diagnostic process that covers multiple dimensions such as equipment control, external environment, and key components (hydraulic system) that may be involved in steering abnormalities, avoiding the omission of faults.

[0016] Device Example 1 According to embodiments of the present invention, a data-driven fault diagnosis device for unmanned mining trucks is provided. Figure 2 This is a schematic diagram of a data-driven unmanned mining truck fault diagnosis device according to an embodiment of the present invention, as shown below. Figure 2 As shown, the data-driven unmanned mining truck fault diagnosis device according to an embodiment of the present invention specifically includes: The comparison module 20 is used to compare the heading angle associated with the unmanned mining truck during rotation with the actual turning angle, and to confirm whether the turning process is consistent based on the actual comparison process; specifically used for: Confirm the heading angle associated with the unmanned mining truck during actual operation. This heading angle is determined automatically by the unmanned mining truck based on the front-end material conditions and the actual route, and is calibrated as H. i Where i represents different times, and the actual turning angle associated with the unmanned mining truck at the corresponding time is calibrated as J. i Compare the confirmed heading angle with the actual turning angle: If H i =J i If H, then no processing is performed. i ≠J i Then an error confirmation signal is generated.

[0017] Verification module 22 is used to confirm the outer and inner turning arcs of the unmanned mining truck during the turning process at the corresponding moment when the turning process is inconsistent, and to compare and verify the confirmed outer and inner turning arcs. Based on the comparison and verification process, a fault signal is generated; specifically used for: Based on the generated error confirmation signal, the specific time associated with the corresponding error confirmation signal is confirmed, and the turning process associated with the specific time is recorded as the process to be verified. In this process, the corresponding turning angle exists. That is, the specific process that has a turning angle in the time period before and after the corresponding time belongs to the corresponding turning process. The two sets of arc circles associated with the steering process are compared and verified to lock the outer and inner steering arcs. The arc data of adjacent circle points within the outer steering arc are confirmed, and the confirmed arc data is calibrated as H. k Where k represents the arc segment between different adjacent circle points, and the radian data H k Identical arc segments are denoted as common arc segments, and the total number of common arc segments G is determined. Then, G is selected from several different values ​​of G. max The arc segment is denoted as the characteristic arc segment, and a set of built-in center points are locked based on the confirmed characteristic arc segment; Connect the inner center of the circle to different circle points within the outer turning arc to identify several feature lines. Record the intersection points of these feature lines with the inner turning arc as the corresponding auxiliary points of the circle points. Perform feature verification on the identified circle points and their associated auxiliary points: confirm the external tangent lines to the circle points within the outer turning arc, and simultaneously confirm the external tangent lines to the corresponding auxiliary points of the inner turning arc. Identify whether the two sets of confirmed tangent lines are parallel. If they are parallel, no processing is required. If they are not parallel, identify whether the corresponding circle point or auxiliary point belongs to the same arc segment as the feature arc segment. If it belongs, no processing is required. If it does not belong, mark the corresponding point as an abnormal point. After analyzing the entire turning process, identify whether any anomalies exist: if none exist, it indicates a control fault in the current unmanned mining truck, and a fault signal is generated and displayed directly; if any exist, confirm the number of anomalies K1 on the corresponding arc, and then confirm the total number of all circle points Z1 on the corresponding arc, using: K1 ÷ Z1 = Z b Confirmed outlier percentage Z b And the two sets of proportion values ​​Z confirmed from the two arcs b In the middle, select the maximum value Z bmax And confirm Z bmax If Zbmax ≤ Y1, a pit presence signal is generated and displayed, where Y1 is a preset value. If not, a suspected hydraulic fault signal is generated, and further processing and analysis are performed to identify whether the hydraulic components associated with the left and right tires have changed abnormally. Based on the specific identification process, a comprehensive assessment of the abnormality is made.

[0018] The diagnostic module 24 is used to confirm a set of monitoring cycles based on the fault signal, compare and verify the fault-related data within the monitoring cycles, and diagnose the actual fault of the unmanned mining truck according to the comparison and verification process. Specifically, it is used for: Based on the confirmed suspected hydraulic fault signals, a set of monitoring cycles is established, which is a preset cycle. The time within the monitoring cycle when there is no steering angle is recorded as the verification time, and the hydraulic data associated with the verification time is recorded as YZ. q-o , where q represents different tires and o represents different calibration times; Hydraulic data YZ associated with the same verification time q-o Confirm sequentially, and from the confirmed sets of hydraulic data YZ q-o In the middle, confirm the adjacent hydraulic data YZ q-o The associated change features are then identified from several sets of associated change features in the same period, and the feature difference between adjacent change features is confirmed, where: feature difference = |B1-B2|, where B1 and B2 represent different change features within adjacent change features respectively; The variance of the confirmed set of characteristic differences is processed to confirm the standard variance. The confirmed standard variance is then compared with a preset threshold for verification. If the standard variance is less than or equal to the preset threshold, it means that the hydraulic error associated with the two tires is small. Therefore, it is determined that the fault is not caused by a hydraulic fault. In this case, a maintenance signal is generated and displayed. If the standard variance is greater than the preset threshold, a hydraulic fault signal is generated and displayed. Based on the specific hydraulic change process, a comprehensive evaluation is conducted to identify the specific changes between the data. Then, based on the specific change processing process, the specific change process between the corresponding two tires is confirmed. Further confirmation is made of the differences in the actual error processing process, and a comprehensive evaluation is conducted to determine whether there are any related hydraulic faults.

[0019] The embodiments of the present invention are device embodiments corresponding to the above method embodiments. The specific operation of each module can be understood with reference to the description of the method embodiments, and will not be repeated here.

[0020] Device Example 2 This invention provides an electronic device, such as... Figure 3 As shown, it includes: a memory 30, a processor 32, and a computer program stored in the memory 30 and executable on the processor 32, wherein the computer program, when executed by the processor 32, performs the steps as described in the method embodiment.

[0021] Device Example 3 This invention provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor 32, performs the steps described in the method embodiment.

[0022] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0023] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data-driven based fault diagnosis method for unmanned mine truck, characterized in that, The method comprises the following steps: comparing the heading angle associated with the turning process of the unmanned mine car and the actual turning angle, and confirming whether the turning process is consistent according to the actual comparison process; in the case where the turning process is inconsistent, confirming the outer turning arc and the inner turning arc of the unmanned mine car in the turning process at the corresponding time, and comparing and verifying the confirmed outer turning arc and inner turning arc, and generating a fault signal according to the comparison and verification process; based on the fault signal, confirming a group of monitoring periods, comparing and verifying the fault related data in the monitoring period, and diagnosing the real fault of the unmanned mine car according to the comparison and verification process.

2. The method of claim 1, wherein, The method comprises the following steps: Confirm the heading angle associated with the unmanned mine car in actual operation, which is the heading angle confirmed by the unmanned mine car according to the front-end conditions and the actual route, and is marked as H i , where i represents different time points, and the actual turning angle associated with the unmanned mine car at the corresponding time point is marked as J i ; compare the confirmed heading angle with the actual turning angle: if H i =J i , no processing is performed, and if H i ≠J i , an error confirmation signal is generated.

3. The method of claim 2, wherein, in the case where the turning process is inconsistent, confirming the outer turning arc and the inner turning arc of the unmanned mine car in the turning process at the corresponding time, and comparing and verifying the confirmed outer turning arc and inner turning arc, and generating a fault signal according to the comparison and verification process. According to the generated error confirmation signal, the specific time corresponding to the error confirmation signal is confirmed, and the turning process associated with the specific time is recorded as the process to be verified, wherein the corresponding turning angles in the turning process all exist, that is, the specific process in which the turning angle exists all the time before and after the corresponding time belongs to the corresponding turning process. The two groups of radian circles associated with the turning process are compared and verified, the outer turning arc and the inner turning arc are locked, the radian data of the adjacent circle points in the outer turning arc are confirmed, and the confirmed radian data is marked as H k , wherein k represents the arc segment between different adjacent circle points, the radian data H k The same arc segment is recorded as a same arc segment, the total number of same arc segments G is confirmed, and G max The arc segment is recorded as a characteristic arc segment, and a group of built-in circle centers is locked according to the confirmed characteristic arc segment. connecting the built-in center with different circle points in the outer turning arc, confirming a plurality of characteristic lines, recording the intersection points associated with the circle points as the auxiliary points corresponding to the circle points, and performing feature verification on the confirmed circle points and the associated auxiliary points: confirming the external tangent line of the circle point in the outer turning arc, synchronously confirming the external tangent line of the auxiliary point corresponding to the inner turning arc, identifying whether the two confirmed tangent lines are parallel, if they are parallel, no further processing is needed, if they are not parallel, identifying whether the corresponding circle point or auxiliary point belongs to the same arc segment with the same feature arc segment, if it does, no further processing is needed, if it does not, the corresponding point is marked as an abnormal point; After the whole steering process is analyzed, it is identified whether the abnormal point exists: if not, it represents that there is no control failure of the current unmanned mine card, and a fault signal is directly generated for display; if so, the number K1 of abnormal points on the corresponding arc is confirmed, and the total number Z1 of all circle points on the corresponding arc is confirmed, and K1 ÷ Z1 = Z is used b Confirm the abnormal point proportion value Z b , and select the maximum value Z b from the two groups of proportion values Z bmax confirmed in the two arcs, and confirm whether Z bmax satisfies Zbmax≤Y1, if so, a pit existence signal is generated for display, wherein Y1 is a preset value; if not, a suspected hydraulic fault signal is generated, and a further processing and analysis process is performed to identify whether the hydraulic components associated with the left and right tires are abnormal, and based on the specific identification process, an abnormal comprehensive evaluation is performed.

4. The method of claim 3, wherein, based on the fault signal, confirming a group of monitoring periods, comparing and verifying the fault related data in the monitoring period, and diagnosing the real fault of the unmanned mine car according to the comparison and verification process. According to the confirmed suspected hydraulic fault signal, a set of monitoring periods is confirmed, the monitoring period is a preset period, a time point without steering angle in the monitoring period is recorded as a verification time point, and the hydraulic data associated with the verification time point is recorded as YZ q-o , wherein q represents different tires, and o represents different verification time points. Hydraulic data YZ associated with the same check time q-o Confirm in sequence, and from the several groups of hydraulic data YZ q-o confirmed, confirm the adjacent hydraulic data YZ q-o associated with the change characteristics, and from the several groups of change characteristics associated with the same period, confirm the feature difference between the adjacent change characteristics, wherein: feature difference = |B1-B2|, wherein B1 and B2 represent different change characteristics in the adjacent change characteristics respectively; The method comprises the following steps: performing variance processing on the confirmed several groups of feature differences, confirming the standard deviation, and comparing and verifying the confirmed standard deviation with the preset threshold: if the standard deviation is less than or equal to the preset threshold, it means that the hydraulic error associated with the two side tires is small, so it is determined that it is not a fault caused by hydraulic failure, and a maintenance signal is generated for display, if the standard deviation is greater than the preset threshold, a hydraulic failure signal is generated for display; 5. A data-driven based unmanned mine truck fault diagnosis device, characterized in that, according to the specific hydraulic change process, the specific change between the data is identified, and then according to the specific change processing process, the specific change process between the two side tires is confirmed, the difference in the error actual processing process is further confirmed, and whether the hydraulic pressure exists related fault is comprehensively evaluated. The method comprises the following steps: The comparison module is configured to compare the heading angle associated with the unmanned mine car during rotation with the actual turning angle, and determine whether the turning process is consistent according to the actual comparison process. The verification module is configured to, in the case where the turning process is inconsistent, determine the outer turning arc and the inner turning arc of the unmanned mine car during the turning process at the corresponding time, compare and verify the determined outer turning arc and inner turning arc, and generate a fault signal according to the comparison and verification process. The diagnosis module is configured to, based on the fault signal, determine a set of monitoring periods, compare and verify the fault-related data in the monitoring periods, and diagnose the actual fault of the unmanned mine car according to the comparison and verification process.

6. The apparatus of claim 5, wherein, The comparison module is specifically configured to: Confirm the heading angle associated with the unmanned mine car in actual operation, which is the heading angle confirmed by the unmanned mine car according to the front-end conditions and the actual route, and is marked as H i , where i represents different time points, and the actual turning angle associated with the unmanned mine car at the corresponding time point is marked as J i ; compare the confirmed heading angle with the actual turning angle: if H i =J i , no processing is performed, and if H i ≠J i , an error confirmation signal is generated.

7. The apparatus of claim 6, wherein, The verification module is specifically configured to: According to the generated error confirmation signal, the specific time corresponding to the error confirmation signal is determined, and the turning process associated with the specific time is recorded as a process to be verified, wherein the corresponding turning angles in the turning process all exist, that is, the specific process in which the turning angle exists continuously before and after the corresponding time belongs to the corresponding turning process. The two groups of radian circles associated with the turning process are compared and verified, the outer turning arc and the inner turning arc are locked, the radian data of the adjacent circle points in the outer turning arc are confirmed, and the confirmed radian data is marked as H k wherein k represents the arc segment between different adjacent circle points, the radian data H k The same arc segment is recorded as a same arc segment, the total number of same arc segments G is confirmed, and G max The arc segment is recorded as a characteristic arc segment, and a group of built-in circle centers is locked according to the confirmed characteristic arc segment. The feature verification is performed on the determined circle points and the associated auxiliary points: the outer tangent lines of the circle points in the outer turning arc are determined, the outer tangent lines of the corresponding auxiliary points in the inner turning arc are determined synchronously, it is identified whether the two groups of tangent lines determined are parallel, if yes, no further processing is needed, if no, it is identified whether the corresponding circle points or auxiliary points belong to the same arc segment of the feature arc segment, if yes, no further processing is needed, if no, the corresponding points are marked as abnormal points. After the whole steering process is analyzed, it is identified whether the abnormal point exists: if not, it represents that there is no control failure of the current unmanned mine card, and a fault signal is directly generated for display; if so, the number K1 of abnormal points on the corresponding arc is confirmed, and the total number Z1 of all circle points on the corresponding arc is confirmed, and K1 ÷ Z1 = Z is used b Confirm the proportion of abnormal points Z b , and select the maximum value Z bmax from the two groups of proportion values Z b confirmed in the two arcs bmax , and confirm whether Z bmax satisfies Zbmax≤Y1: if so, a pit existence signal is generated for display, wherein Y1 is a preset value; if not, a suspected hydraulic fault signal is generated, and a further processing and analysis process is performed to identify whether the hydraulic components associated with the left and right tires are abnormal, and based on the specific identification process, an abnormal comprehensive evaluation is performed.

8. The apparatus of claim 7, wherein, The diagnosis module is specifically configured to: According to the confirmed suspected hydraulic fault signal, a set of monitoring periods is confirmed, the monitoring period is a preset period, a time point without steering angle in the monitoring period is recorded as a verification time point, and the hydraulic data associated with the verification time point is recorded as YZ q-o wherein q represents different tires, and o represents different verification time points. Hydraulic data YZ associated with the same verification time q-o Confirm sequentially, and from the confirmed sets of hydraulic data YZ q-o In the middle, confirm the adjacent hydraulic data YZ q-o The associated change features are then identified from several sets of associated change features in the same period, and the feature difference between adjacent change features is confirmed, where: feature difference = |B1-B2|, where B1 and B2 represent different change features within adjacent change features respectively; The standard deviation is determined by performing variance processing on the determined several groups of feature differences, and the determined standard deviation is compared and verified with a preset threshold: if the standard deviation is less than or equal to the preset threshold, it means that the hydraulic error associated with the two-side tires is small, and it is determined that the fault condition is not caused by hydraulic failure, and a maintenance signal to be generated is displayed, if the standard deviation is greater than the preset threshold, a hydraulic failure signal is generated and displayed. According to the specific hydraulic change process, the specific change between the data is identified, and according to the specific change processing process, the specific change process between the two-side tires is determined, the difference in the error actual processing process is further determined, and whether the hydraulic system has a related fault is comprehensively evaluated.

9. An electronic device, comprising: The computer program stored in the memory and executable on the processor implements the steps of the data-driven unmanned mine car fault diagnosis method according to any one of claims 1 to 4. The computer readable storage medium stores an implementation program of information transmission, and the program is executed by the processor to implement the steps of the data-driven unmanned mine car fault diagnosis method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, ​

Images