A state predictive system for electric wheel reducer of mine car

Abstract

This invention provides a condition prediction system for a mine car electric wheel reducer, comprising an online monitoring system for collecting and processing condition data of the mine car electric wheel reducer, and a decision-making system for analyzing and predictively processing the mine car electric wheel reducer based on the processing results of the condition data. This condition prediction system for a mine car electric wheel reducer, through comprehensive analysis of different data, can promptly detect and prevent malfunctions during equipment operation, reduce serious mechanical accidents such as bearing damage or gear breakage, and effectively schedule major overhauls.

Description

Technical Field

[0001] The invention relates to the technical field of electric wheel reducer state diagnosis, and in particular to a state predictive system for an electric wheel reducer of a mine car. Background Art

[0002] As one of the most important assemblies of a mine car, the electric wheel has a high cost and a high cost for major repairs. The electric wheel reducer is currently monitored by offline regular testing, which has a large gap period. If the major repair is not timely, it is easy to cause serious mechanical accidents such as bearing damage and tooth breaking, resulting in large losses. For safety reasons, the major repair cycle is shortened, which increases costs.

[0003] Fault diagnosis is to collect the on-site equipment operation data from the inspection system and the online system, and establish an equipment diagnosis model based on the on-site equipment data, and use technical means such as mechanism-based diagnosis and regression algorithms to analyze the degree of degradation of the production equipment under condition monitoring. It automatically gives the cause of the unit's failure, the hazard of the failure and maintenance suggestions, and finally forms a diagnosis report.

[0004] Application number CN202010662489.4 discloses a method, device and computer program product for generating a travel reducer fault model. The method for generating a travel reducer fault model includes: obtaining vibration signals of the travel reducer under various fault states; decomposing the vibration signals of various fault states using a preset algorithm to obtain corresponding fault characteristic parameters; using the fault characteristic parameters of various fault states and a preset modeling algorithm to establish fault diagnosis models corresponding to various fault states, and generate a fault model library. Summary of the invention

[0005] The present invention aims to overcome the technical problem in the prior art that the electric wheel reducer is monitored by an offline periodic test method, which makes it difficult to detect equipment failure in time. A state predictive system for the electric wheel reducer of a mine car is provided. Through comprehensive analysis of different data, failures in equipment operation can be detected and prevented in time, serious mechanical accidents such as bearing damage or tooth breaking can be reduced, and overhaul sequencing can be effectively performed.

[0006] The present invention provides a state predictive system for an electric wheel reducer of a mine car, comprising an online monitoring system for collecting and processing state data of the electric wheel reducer of the mine car and a decision system for analyzing and predicting the electric wheel reducer of the mine car according to the processing result of the state data;

[0007] The online monitoring system includes:

[0008] Data acquisition system: installed on the electric wheel of the mine car, used to collect status data and transmit the status data to the data collector; the status data includes vibration data, speed data and temperature data;

[0009] Data collector: used to receive status data transmitted by the data acquisition system, and to summarize the status data and transmit it to the online monitoring platform through the network cable;

[0010] Online monitoring platform: used to receive status data transmitted by the data collector, to process the status data and generate diagnostic results, to transmit the diagnostic results to the display system, and to transmit the status data and diagnostic results to the decision-making system;

[0011] The data processing process of the online monitoring platform includes: dividing the state data into vibration data set A according to different data types 0 and speed data set B 0 And assign temperature effects to them to get vibration data set A 1 and speed data set B 1 , and then obtain the vibration data feature vector M and the speed data feature vector N through feature vector extraction, substitute the vibration data feature vector M and the speed data feature vector N into the fault diagnosis model to obtain the fault prediction value Z and generate the diagnosis result;

[0012] The fault prediction value Z:

[0013]

[0014] Where: 0≤Z≤1; p, q, f are constants, 0≤p≤1, 0≤q≤1, 0≤f≤1; M i is the value of the vibration characteristic vector at time t = i, N i is the value of the speed characteristic vector at time t = i, t is the data acquisition time;

[0015] Display system: used to receive the diagnostic results transmitted by the online monitoring platform and display the processing results to the user;

[0016] The decision-making system includes:

[0017] Data analysis device: used to receive the status data and diagnosis results transmitted by the online monitoring platform, used to retrieve the data analysis model from the data storage device according to the diagnosis results, used to analyze the status data according to the data analysis model to obtain the analysis results, used to transmit the analysis results to the decision report generation device, used to transmit the status data, diagnosis results and analysis results to the data storage device;

[0018] Data storage device: used for storing data analysis models, for receiving status data, diagnosis results and analysis results transmitted by the data analysis device, and for receiving decision reports transmitted by the decision report generation device;

[0019] Decision report generating device: used for receiving the analysis results transmitted by the data analyzing device, for generating a decision report according to the analysis results, and for transmitting the decision report to the data storage device.

[0020] The state predictive system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the decision system further includes:

[0021] Data analysis model updating system: used to update the data analysis model according to the status data, diagnosis results and analysis results, and to transmit the updated data analysis model to the data storage device.

[0022] The state predictive system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the data processing process of the online monitoring platform includes the following steps:

[0023] S1. Data classification: The state data is divided into vibration data set A according to different data types. 0 , Speed ​​dataset B 0 and temperature data set T;

[0024] S2. Data temperature effect optimization: The vibration data set A 0 The vibration data in a 0 The optimized vibration data set A after adding temperature effect 1 , the speed data set B 0 Speed ​​data in b 0 The optimized speed data set B after giving temperature effect 1 ;

[0025] S3. Feature vector extraction: Based on the vibration data set A 1 Extract the vibration feature vector M according to the speed data set B 1 Extract the speed feature vector N;

[0026] S4. Generate diagnostic results: Substitute the vibration feature vector M and the speed feature vector N into the fault diagnosis model to obtain the fault prediction value Z:

[0027]

[0028] Where: Z is the fault prediction value, 0≤Z≤1; p, q, f are constants, 0≤p≤1, 0≤q≤1, 0≤f≤1; M i is the value of the vibration characteristic vector at time t = i, N i is the value of the speed characteristic vector at time t = i, t is the data acquisition time;

[0029] A diagnosis result is generated according to the fault prediction value Z.

[0030] The state predictive system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, step S2 further includes the following steps:

[0031] S21. Optimization of temperature effect of vibration dataset:

[0032] A 1 =f(T,t)×A 0

[0033] Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10;

[0034] S22, Optimization of temperature effect of speed data set:

[0035] B 1 =g(T,t)×B 0

[0036] Wherein: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10.

[0037] The state predictability system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, the value of the function f(T, t):

[0038] Below the critical temperature T 0 When , it decreases with the increase of temperature T;

[0039] Above the critical temperature T 0 When , it increases with the increase of temperature T;

[0040] It increases with the increase of time t.

[0041] The state predictive system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, the value of the function g(T, t):

[0042] Below the critical temperature T 1 When , it decreases with the increase of temperature T;

[0043] Above the critical temperature T 1 When , it increases with the increase of temperature T;

[0044] It increases with the increase of time t.

[0045] The state predictive system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, step S3 further includes the following steps:

[0046] S31, vibration feature vector M acquisition: vibration data set A 1 Data in 1Input the fault analysis model vibration feature vector M:

[0047]

[0048] Among them, m is the vibration impact factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and a 1ij The vibration data set A of sensor number j at time t=i 1 The data in a j is the standard vibration data of sensor number j;

[0049] S32, speed feature vector N acquisition: the speed data set B 1 Medium Data 1 Input the speed feature vector N of the fault analysis model:

[0050]

[0051] Among them, n is the speed influence factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and b 1ij The speed data set B of sensor number j at time t=i 1 The data in b j This is the standard speed data of sensor number j.

[0052] The state predictive system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, generating a diagnosis result according to the fault prediction value Z in step S4 as follows:

[0053] When the fault prediction value Z is less than the warning threshold, the diagnosis result is normal operation;

[0054] When the fault prediction value Z is greater than the warning threshold and less than the alarm threshold, the diagnosis result is equipment warning;

[0055] When the fault prediction value Z is greater than the alarm threshold, the diagnosis result is equipment failure.

[0056] The state predictive system for the electric wheel reducer of a mine car described in the present invention is preferably a data analysis model as follows:

[0057] H=max{H 1 , H 2 , H 3}

[0058] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0059]

[0060] In the formula, H is the value of the analysis data, H 1 is the first analysis data value, H 2 is the second analysis data value, H 3 is the third analysis data value, x is the number of electric wheel reducers of the mine car, and Zi is the fault prediction value of the electric wheel reducer of the mine car numbered i;

[0061] The analysis results based on the analysis value H are as follows:

[0062] When the analysis value H is less than the warning threshold, the analysis result is normal operation;

[0063] When the analysis value H is greater than the warning threshold and less than the alarm threshold, the analysis result is a device warning;

[0064] When the analysis value H is greater than the alarm threshold, the analysis result is equipment failure.

[0065] In the state predictive system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the updating of the data analysis model includes:

[0066] When the analysis value H is greater than the warning threshold, the data analysis model is updated to

[0067] H=d×max{H 1 , H 2 , H 3}

[0068] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0069]

[0070]

[0071] Wherein, d is a constant, 1.0015<d<1.0031;

[0072] When the analysis value H is greater than the alarm threshold, the data analysis model is updated to

[0073] H=e×max{H 1 , H 2 , H 3}

[0074] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0075]

[0076] Among them, e is a constant, 1.0086<e<1.0108.

[0077] The advantages of the present invention compared with the prior art are:

[0078] (1) The present invention establishes a state predictive system for the motor reducer of a mine car, processes the state data of the electric wheel reducer and extracts feature vectors, integrates and summarizes pattern recognition and fault diagnosis, and performs predictive monitoring of the equipment state. It can timely discover and prevent faults in the operation of the equipment based on the monitoring data, thereby increasing the service life of the equipment.

[0079] (2) The present invention conducts a comprehensive analysis of the data collected by different data collectors, thereby improving the timeliness and accuracy of the system's monitoring of equipment.

[0080] (3) The present invention further improves the accuracy of the system's equipment monitoring results by correcting the data analysis model with actual operating data. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a state predictive system composition diagram for a mine car motor reducer;

[0082] Figure 2 A schematic diagram of the position of the sensor installed on the outer side of the electric wheel of a state prediction system for a mine car motor reducer;

[0083] Figure 3 A schematic diagram of the position of the sensor installed on the inner side of the electric wheel of a state prediction system for a mine car motor reducer;

[0084] Figure 4 A schematic diagram of the sensor location for the main generator of a state predictive system for a mine car motor reducer;

[0085] Figure 5 The present invention is a data processing flow chart of an online monitoring platform for a state predictive system of a mine car motor reducer.

[0086] Reference numerals:

[0087] 100. Data acquisition system; 200. Data collector; 300. Online monitoring platform; 400. Display system; 500. Data analysis device; 600. Data storage device; 700. Decision report generation device; 800. Data analysis model update system. DETAILED DESCRIPTION

[0088] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0089] Example 1

[0090] like Figure 1 As shown, a state predictive system for an electric wheel reducer of a mine car comprises an online monitoring system for collecting and processing state data of the electric wheel reducer of the mine car and a decision system for analyzing and predicting the electric wheel reducer of the mine car according to the processing result of the state data;

[0091] The online monitoring system includes:

[0092] Data acquisition system 100: is set on the electric wheel of the mining car, used to collect status data and transmit the status data to the data collector 200; the status data includes vibration data, speed data and temperature data; Figures 3 to 5 As shown, each mining car includes at least 3 collection points, which are respectively arranged on the outside of the motor, the inside of the motor (on the gear box) and the main generator;

[0093] Data collector 200: used to receive status data transmitted by the data collection system 100, and to aggregate the status data and transmit it to the online monitoring platform 300 via a network cable;

[0094] Online monitoring platform 300: used to receive the status data transmitted by the data collector 200, used to process the status data and generate a diagnosis result, used to transmit the diagnosis result to the display system 400, used to transmit the status data and the diagnosis result to the decision-making system;

[0095] The data processing process of the online monitoring platform 300 includes: dividing the state data into vibration data sets A and B according to different data types. 0 and speed data set B 0 And assign temperature effects to them to get vibration data set A 1 and speed data set B 1 , and then extract the vibration data feature vector M and the speed data feature vector N through feature vector extraction, substitute the vibration data feature vector M and the speed data feature vector N into the fault diagnosis model to obtain the fault prediction value Z and generate the diagnosis result; Figure 5 As shown, the data processing process of the online monitoring platform 300 includes the following steps:

[0096] S1. Data classification: The state data is divided into vibration data set A according to different data types. 0 , Speed ​​dataset B 0 and temperature data set T;

[0097] S2. Data temperature effect optimization: The vibration data set A 0 The vibration data in a 0 The optimized vibration data set A after adding temperature effect 1 , the speed data set B 0 Speed ​​data in b 0 The optimized speed data set B after giving temperature effect 1 ; Step S2 further comprises the following steps:

[0098] S21. Optimization of temperature effect of vibration dataset:

[0099] A 1 =f(T,t)×A 0

[0100] Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10;

[0101] The value of the function f(T,t):

[0102] Below the critical temperature T 0 When , it decreases with the increase of temperature T;

[0103] Above the critical temperature T 0 When , it increases with the increase of temperature T;

[0104] Increases with the increase of time t;

[0105] The critical temperature of the motor is T 0 ≈32.2℃, the critical temperature of the main generator T 0 ≈38.5℃;

[0106] S22, Optimization of temperature effect of speed data set:

[0107] B 1 =g(T,t)×B 0

[0108] Where: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10;

[0109] The value of the function g(T,t):

[0110] Below the critical temperature T 1 When , it decreases with the increase of temperature T;

[0111] Above the critical temperature T 1 When , it increases with the increase of temperature T;

[0112] Increases with the increase of time t;

[0113] The critical temperature of the motor is T 1 ≈28.3℃, the critical temperature of the main generator T 1 ≈36.7℃;

[0114] S3. Feature vector extraction: Based on the vibration data set A 1 Extract the vibration feature vector M according to the speed data set B 1 Extracting the speed feature vector N; Step S3 further comprises the following steps:

[0115] S31, vibration feature vector M acquisition: vibration data set A 1 Data in 1 Input the fault analysis model vibration feature vector M:

[0116]

[0117] Among them, m is the vibration impact factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and a 1ij The vibration data set A of sensor number j at time t=i 1 The data in a j is the standard vibration data of sensor number j;

[0118] S32, speed feature vector N acquisition: the speed data set B 1 Medium Data 1 Input the speed feature vector N of the fault analysis model:

[0119]

[0120] Among them, n is the speed influence factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and b 1ij The speed data set B of sensor number j at time t=i 1 The data in b j The standard speed data of sensor number j;

[0121] S4. Generate diagnostic results: Substitute the vibration feature vector M and the speed feature vector N into the fault diagnosis model to obtain the fault prediction value Z:

[0122]

[0123] Where: Z is the fault prediction value, 0≤Z≤1; p, q, f are constants, 0≤p≤1, 0≤q≤1, 0≤f≤1; Mi is the value of the vibration characteristic vector at time t=i, Ni is the value of the speed characteristic vector at time t=i, and t is the data acquisition time;

[0124] Generate the diagnosis result according to the fault prediction value Z as follows:

[0125] When the fault prediction value Z is less than the warning threshold, the diagnosis result is normal operation;

[0126] When the fault prediction value Z is greater than the warning threshold and less than the alarm threshold, the diagnosis result is equipment warning;

[0127] When the fault prediction value Z is greater than the alarm threshold, the diagnosis result is equipment failure;

[0128] Display system 400: used to receive the diagnosis results transmitted by the online monitoring platform 300 and display the processing results to the user;

[0129] The decision-making system includes:

[0130] Data analysis device 500: used to receive the status data and diagnosis results transmitted by the online monitoring platform 300, to retrieve the data analysis model from the data storage device 600 according to the diagnosis results, to analyze the status data according to the data analysis model 600 to obtain the analysis results, and to transmit the analysis results to the decision report generation device 700, which is used to transmit the status data, diagnosis results and analysis results to the data storage device 600;

[0131] The data analysis model is as follows:

[0132] H=max{H 1 , H 2 , H 3}

[0133] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0134]

[0135] In the formula, H is the value of the analysis data, H 1 is the first analysis data value, H 2 is the second analysis data value, H 3 is the third analysis data value, x is the number of electric wheel reducers of the mine car, Z i is the fault prediction value of the electric wheel reducer of the mine car numbered i;

[0136] The analysis results based on the analysis value H are as follows:

[0137] When the analysis value H is less than the warning threshold, the analysis result is normal operation;

[0138] When the analysis value H is greater than the warning threshold and less than the alarm threshold, the analysis result is a device warning;

[0139] When the analysis value H is greater than the alarm threshold, the analysis result is equipment failure;

[0140] Data storage device 600: used for storing data analysis models, for receiving status data, diagnosis results and analysis results transmitted by data analysis device 500, and for receiving decision reports transmitted by decision report generation device 700;

[0141] Decision report generating device 700: used for receiving the analysis result transmitted by the data analyzing device 500, for generating a decision report according to the analysis result, and for transmitting the decision report to the data storage device 600;

[0142] The data analysis model updating system 800 is used to update the data analysis model according to the status data, the diagnosis results and the analysis results, and to transmit the updated data analysis model to the data storage device 600; the updating of the data analysis model includes:

[0143] When the analysis value H is greater than the warning threshold, the data analysis model is updated to

[0144] H=d×max{H 1 , H 2 , H 3}

[0145] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0146]

[0147] Wherein, d is a constant, 1.0015<d<1.0031;

[0148] When the analysis value H is greater than the alarm threshold, the data analysis model is updated to

[0149] H=e×max{H 1 , H 2 , H 3}

[0150] H 1 =max{Z 1 , Z 2 , ..., Z x}

[0151]

[0152] Among them, e is a constant, 1.0086<e<1.0108.

[0153] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A state predictive system for a mine car electric wheel reducer, characterized in that: It includes an online monitoring system for collecting and processing the state data of the electric wheel reducer of the mine car and a decision system for analyzing and predicting the electric wheel reducer of the mine car according to the processing results of the state data; The online monitoring system comprises: A data acquisition system (100) is arranged on the electric wheel of the mining vehicle and is used to collect the state data and transmit the state data to a data acquisition device (200); the state data includes vibration data, rotation speed data and temperature data; A data collector (200): used for receiving the status data transmitted by the data collection system (100), and for aggregating the status data and transmitting it to an online monitoring platform (300) via a network cable; An online monitoring platform (300) is used to receive the state data transmitted by the data collector (200), to process the state data and generate a diagnosis result, to transmit the diagnosis result to a display system (400), and to transmit the state data and the diagnosis result to the decision-making system; The data processing process of the online monitoring platform (300) comprises: dividing the state data into a vibration data set A0 and a rotation speed data set B0 according to different data types and respectively assigning temperature effects to obtain a vibration data set A1 and a rotation speed data set B1, then extracting feature vectors to obtain a vibration data feature vector M and a rotation speed data feature vector N, substituting the vibration data feature vector M and the rotation speed data feature vector N into a fault diagnosis model to obtain a fault prediction value Z and generate the diagnosis result; The fault prediction value Z: Where: 0≤Z≤1; p, q, f are constants, 0≤p≤1, 0≤q≤1, 0≤f≤1; M i is the value of the vibration characteristic vector at time t = i, N i is the value of the speed characteristic vector at time t = i, t is the data acquisition time; Display system (400): used for receiving the diagnosis result transmitted by the online monitoring platform (300) and displaying the processing result to the user; The decision-making system comprises: A data analysis device (500): used for receiving the state data and the diagnosis result transmitted by the online monitoring platform (300), for retrieving a data analysis model from a data storage device (600) according to the diagnosis result, for analyzing the state data according to the data analysis model to obtain an analysis result, and for transmitting the analysis result to a decision report generation device (700), for transmitting the state data, the diagnosis result and the analysis result to the data storage device; Data storage device (600): used for storing the data analysis model, for receiving the status data, the diagnosis result and the analysis result transmitted by the data analysis device (500), and for receiving the decision report transmitted by the decision report generation device (700); Decision report generating device (700): used for receiving the analysis result transmitted by the data analyzing device (500), for generating a decision report according to the analysis result, and for transmitting the decision report to the data storage device (600).

2. A state predictive system for a mine car electric wheel reducer according to claim 1, characterized in that: The decision-making system also includes: A data analysis model updating system (800) is used to update the data analysis model according to the status data, the diagnosis result and the analysis result, and to transmit the updated data analysis model to the data storage device (600).

3. A state predictive system for a mine car electric wheel reducer according to claim 1, characterized in that: The data processing process of the online monitoring platform (300) comprises the following steps: S1. Data classification: the state data is classified into a vibration data set A0, a rotation speed data set B0 and a temperature data set T according to different data types; S2, data temperature effect optimization: the vibration data a0 in the vibration data set A0 is given a temperature effect to obtain an optimized vibration data set A1, and the speed data b0 in the speed data set B0 is given a temperature effect to obtain an optimized speed data set B1; S3, feature vector extraction: extracting a vibration feature vector M according to the vibration data set A1, and extracting a rotation speed feature vector N according to the rotation speed data set B1; S4, generating diagnostic results: Substitute the vibration characteristic vector M and the rotation speed characteristic vector N into the fault diagnosis model to obtain the fault prediction value Z: Where: Z is the fault prediction value, 0≤Z≤1; p, q, f are constants, 0≤p≤1, 0≤q≤1, 0≤f≤1; M i is the value of the vibration characteristic vector at time t = i, N i is the value of the speed characteristic vector at time t = i, t is the data acquisition time; A diagnosis result is generated according to the fault prediction value Z.

4. A state predictive system for a mine car electric wheel reducer according to claim 3, characterized in that: Step S2 further comprises the following steps: S21. Optimization of temperature effect of vibration dataset: A1=f(T,t)×A0 Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10; S22, Optimization of temperature effect of speed data set: B1=g(T,t)×B0 Wherein: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10.

5. A state predictive system for a mine car electric wheel reducer according to claim 4, characterized in that: The value of the function f(T,t) is: When it is lower than the critical temperature T0, it decreases with the increase of temperature T; When the temperature is greater than the critical temperature T0, it increases with the increase of temperature T; It increases with the increase of time t.

6. A state predictive system for a mine car electric wheel reducer according to claim 4, characterized in that: The value of the function g(T,t) is: When the temperature is lower than the critical temperature T1, it decreases with the increase of temperature T; When it is greater than the critical temperature T1, it increases with the increase of temperature T; It increases with the increase of time t.

7. A state predictive system for a mine car electric wheel reducer according to claim 3, characterized in that: Step S3 further comprises the following steps: S31, obtaining vibration feature vector M: inputting data a1 in the vibration data set A1 into the vibration feature vector M of the fault analysis model: Wherein, m is the vibration influence factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and a 1ij is the data of the vibration data set A1 of sensor number j at time t=i, a j is the standard vibration data of sensor number j; S32, obtaining the speed characteristic vector N: inputting the data b1 in the speed data set B1 into the speed characteristic vector N of the fault analysis model: Where n is the speed influence factor, k is the number of sensors in the data acquisition system, j is the sensor number of the data acquisition system, and b 1ij is the data of the speed data set B1 of sensor number j at time t=i, b j This is the standard speed data of sensor number j.

8. A state predictive system for a mine car electric wheel reducer according to claim 3, characterized in that: In step S4, the diagnosis result is generated according to the fault prediction value Z as follows: When the fault prediction value Z is less than the warning threshold, the diagnosis result is normal operation; When the fault prediction value Z is greater than the warning threshold and less than the alarm threshold, the diagnosis result is equipment warning; When the fault prediction value Z is greater than the alarm threshold, the diagnosis result is equipment failure.

9. A state predictive system for a mine car electric wheel reducer according to claim 2, characterized in that: The data analysis model is as follows H=max{H1,H2,H3} H1=max{Z1,Z2,......,Z x } Wherein, H is the analysis data value, H1 is the first analysis data value, H2 is the second analysis data value, H3 is the third analysis data value, x is the number of electric wheel reducers of the mine car, Z is i is the fault prediction value of the electric wheel reducer of the mine car numbered i; The analysis results according to the analysis value H are as follows: When the analysis value H is less than the warning threshold, the analysis result is normal operation; When the analysis value H is greater than the warning threshold and less than the alarm threshold, the analysis result is a device warning; When the analysis value H is greater than the alarm threshold, the analysis result is equipment failure.

10. A state predictive system for a mine car electric wheel reducer according to claim 9, characterized in that: The updating of the data analysis model includes: When the analysis value H is greater than the warning threshold, the data analysis model is updated to H=d×max{H1,H2,H3} H1=max{Z1,Z2,......,Z x } Wherein, d is a constant, 1.0015<d<1.0031; When the analysis value H is greater than the alarm threshold, the data analysis model is updated as H=e×max{H1,H2,H3} H1=max{Z1,Z2,......,Z x } Among them, e is a constant, 1.0086<e<1.0108.

Images