Intelligent monitoring system for mine car electric wheel speed reducer

Abstract

The invention provides an intelligent monitoring system for an electric wheel speed reducer of a mine car, which comprises front-section acquisition hardware for acquiring operation data A and ambient temperature data T of the electric wheel speed reducer according to a data acquisition instruction, and a full-information intelligent data processor for classifying and optimizing the operation data A and extracting a feature vector M, the fault intelligent diagnosis system is used for generating a fault prediction value Z according to the feature vector M and generating a fault diagnosis result according to the fault prediction value Z; and the cloud intelligent monitoring service system is used for comprehensively managing related data of each monitoring device and interacting with a user. According to the intelligent monitoring system for the speed reducer of the electric wheel of the mine car, the internet remote monitoring and diagnosis technology is applied, the states of bearings and gear grinds of the electric wheel of the mine car are monitored in real time, intelligent analysis software is applied to analyze and judge the running state and fault positions of the electric wheel, precise maintenance is achieved, large mechanical accidents are prevented, and the safety of the mine car is improved. The maintenance cost is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of electric wheel reducers, and in particular to an intelligent monitoring system for electric wheel reducers of mining vehicles. 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] Application number CN202111134185.1 discloses a rail transit health intelligent monitoring system and monitoring method, which relates to the field of rail monitoring. The system includes a first vibration sensor for collecting the first vibration data of each position of the track during the operation of the train; a second vibration sensor for collecting the re-inspection vibration data of each position of the track during the operation of the train; a camera unit for photographing the track surface; a diagnostic control module for judging whether each position of the track is a suspected fault position with corrugation according to the first vibration data, if so, turning on the camera unit, and then determining whether the suspected fault position is a corrugation position according to the re-inspection vibration data of the suspected fault position, if so, photographing the corrugation position, if not, turning off the camera unit.

[0004] Application number CN202310968006.7 discloses an intelligent monitoring system for transmission equipment based on noise feature analysis and its method. Through this method, experts can input the sound evaluation information they hear from the console. The expert's sound evaluation value corresponds to the specific state of the reduction mechanism. The loudness output by the spectrum analyzer and the frequency characteristics of the noise signal are used as the input layer, and the expert's sound evaluation value is used as the output layer. Through data accumulation and neural network algorithms, a mapping relationship between the two is established. Using the abnormal noise expert database as a benchmark, similar abnormal noise data is found through comparison to provide early warnings to ensure that the noise meets the standard. After the expert's noise evaluation and neural network algorithm, the timbre can be evaluated, and then the specific type of fault can be determined. Summary of the invention

[0005] The present invention aims to overcome the technical problem in the prior art that the fault diagnosis process of the electric wheel reducer is highly dependent on the subjective judgment of the operation and maintenance personnel. An intelligent monitoring system for the electric wheel reducer of a mine car is provided. The system uses the Internet remote monitoring and diagnosis technology to monitor the bearing and gear grinding status of the mine car electric wheel in real time, and uses intelligent analysis software to analyze and judge the running status of the electric wheel and the fault location to achieve accurate maintenance, prevent major mechanical accidents, and save maintenance costs.

[0006] The present invention provides an intelligent monitoring system for a mine car electric wheel reducer, comprising:

[0007] Front-end acquisition hardware: It is installed on the electric wheel of the mine car, and is used to receive the data acquisition instructions issued by the cloud intelligent monitoring service system, and is used to collect the operation data A of the electric wheel reducer and the ambient temperature data T according to the data acquisition instructions, and is used to transmit the operation data A and temperature data T to the full-information intelligent data processor;

[0008] Full-information intelligent data processor: It is installed on the distribution box of the mine car, and is used to receive the operation data A and temperature data T transmitted by the front-end acquisition hardware, and is used to classify and optimize the operation data A, and extract the feature vector M, and is used to transmit the operation data A and the feature vector M to the fault diagnosis system, and is used to transmit the operation data A to the cloud intelligent monitoring service system;

[0009] Fault intelligent diagnosis system: used to receive the operation data A and the feature vector M transmitted by the full-information intelligent data processor, and to generate a fault prediction value Z according to the feature vector M:

[0010]

[0011] 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 1i is the value of the state eigenvector at time t=i, M 1i ∈M,M 2i is the value of the time-dependent characteristic vector at time t = i, M 2i ∈M, t is the data collection time;

[0012] Used to generate fault diagnosis results based on the fault prediction value Z,

[0013] When the fault prediction value Z is less than the fault threshold, it is judged to be normal;

[0014] When the fault prediction value Z is greater than the fault threshold, a warning is issued;

[0015] Used to transmit fault diagnosis results to the cloud intelligent monitoring service system;

[0016] Cloud intelligent monitoring service system: used to generate data collection instructions according to user needs, used to transmit data collection instructions to the front-end collection hardware, used to receive operation data A transmitted by the full-information intelligent data processor, used to receive fault diagnosis results transmitted by the fault intelligent diagnosis system, and used to transmit operation data A and fault diagnosis results to users;

[0017] Users can use the cloud intelligent monitoring service system to uniformly manage the point-by-point reduction wheels of mining car motors. When users have doubts about the fault diagnosis results, they can send a review instruction to the cloud intelligent monitoring service system. The cloud intelligent monitoring service system will retrieve data related to the fault diagnosis process or equipment according to the review instruction to verify the fault, and optimize the fault diagnosis model based on the verification results.

[0018] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the cloud intelligent monitoring service system includes:

[0019] Intelligent operation and maintenance big data cloud platform: used to receive the operation data A transmitted by the full-information intelligent data processor, used to generate the equipment operation status display interface according to the operation data A, used to transmit the equipment operation status display interface to the enterprise remote monitoring center; used to receive the fault diagnosis results transmitted by the fault intelligent diagnosis system, used to generate the operation and maintenance report based on the diagnosis, used to transmit the fault diagnosis results and the operation and maintenance report to the enterprise client; used to receive the data collection instructions transmitted by the enterprise client, used to transmit the data collection instructions to the front-end collection hardware;

[0020] Enterprise remote monitoring center: used to receive the equipment operation status display interface transmitted by the intelligent operation and maintenance big data cloud platform and display the operation status display interface to the user;

[0021] Enterprise client: used by users to generate the data collection instructions, used to transmit the data collection instructions to the intelligent operation and maintenance big data cloud platform, and used to receive fault diagnosis results and operation and maintenance reports transmitted by the intelligent operation and maintenance big data cloud platform.

[0022] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, the enterprise client includes an enterprise PC terminal and a mobile terminal.

[0023] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, the front-end acquisition hardware includes an electric wheel temperature and vibration integrated sensor and a main generator temperature and vibration integrated sensor arranged on the mine car.

[0024] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is preferably a full-information intelligent data processor that classifies the operation data A as follows:

[0025] According to the time effect, the operating status data A is divided into operating data A1 which is independent of the time t change and time-dependent data A2.

[0026] Assign the questionable value S1 to the operation data A1 to generate the processing data B.

[0027] The operation data A2 is assigned with the questionable value S2 to generate the processed data C.

[0028] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the optimization of the processing data B and the processing data C by the full-information intelligent data processor includes:

[0029] The temperature effect of processing data B is optimized to obtain the optimized processing data B1:

[0030] B1=f(T,t)×B

[0031] Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10;

[0032] The value of the function f(T,t):

[0033] When it is lower than the critical temperature T0, it decreases with the increase of temperature T;

[0034] When the temperature is greater than the critical temperature T0, it increases with the increase of temperature T;

[0035] Increases with the increase of time t;

[0036] The temperature effect of processing data C is optimized to obtain the optimized processing data C1:

[0037] C1=g(T,t)×C

[0038] Where: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10;

[0039] The value of the function g(T,t):

[0040] When the temperature is lower than the critical temperature T1, it decreases with the increase of temperature T;

[0041] When it is greater than the critical temperature T1, it increases with the increase of temperature T;

[0042] It increases with the increase of time t.

[0043] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, the feature vector M extraction of the processing data B1 and the processing data C1 by the full-information intelligent data processor includes:

[0044] M=M1∪M2

[0045]

[0046] Among them, M1 is the state feature vector, m is the state data influencing factor, M2 is the time-sensitive feature vector, n is the time-sensitive data influencing factor, k is the number of sensors, j is the sensor number, and b 1ijis the data of sensor number j in running data A1 at time t=i, b j is the standard operating data of sensor number j, c 1ij is the data of sensor number j in time t=i in time-sensitive data A2, c j This is the standard time-effectiveness data of sensor number j.

[0047] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is, as a preferred mode, capable of reviewing the fault diagnosis result when the user has doubts about the fault diagnosis result; the review process includes:

[0048] Retrieve relevant data for calculating the fault prediction value Z, and arrange the relevant data in descending order according to the size of the doubt value S of the relevant data to generate a sequence Q;

[0049] From the historical data of the device, number sequences similar to number sequence Q are retrieved to form a number sequence set M, and from the data of other identical devices, number sequences similar to number sequence Q are retrieved to form a number sequence set N. The data of number sequence sets M and N are substituted into the fault diagnosis model to regenerate the fault diagnosis result;

[0050] If the fault diagnosis result shows that the fault risk increases, the doubt value S of the data in the sequence Q is increased;

[0051] If the fault diagnosis result shows that the fault risk is reduced, the fault diagnosis model is optimized using the sequence Q.

[0052] The intelligent monitoring system for the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, when a device fails, a characteristic vector M of the fault point is extracted and substituted into the fault diagnosis model to optimize the parameters p, q, and f.

[0053] The advantages of the present invention compared with the prior art are:

[0054] (1) The present invention manages discrete devices in a unified manner through an intelligent monitoring system, which can detect potential faults in a timely manner and improve management effects.

[0055] (2) The present invention combines similar historical data with similar collected data from different collection points to perform secondary judgment on fault diagnosis, thereby improving the accuracy of fault diagnosis.

[0056] (3) The present invention conducts a comprehensive analysis of the data collected by different sensors, thereby improving the timeliness and accuracy of the system's monitoring of equipment faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a composition diagram of an intelligent monitoring system for electric wheel reducers of mine vehicles;

[0058] Figure 2A schematic diagram of an intelligent monitoring system for electric wheel reducers of mine vehicles;

[0059] Figure 3 This is a schematic diagram of the location of the sensor installed on the outer side of the electric wheel of an intelligent monitoring system for the electric wheel reducer of a mine car;

[0060] Figure 4 This is a schematic diagram of the position of the sensor installed on the inner side of the electric wheel of an intelligent monitoring system for the electric wheel reducer of a mine car;

[0061] Figure 5 A schematic diagram of the sensor location for the main generator of an intelligent monitoring system for electric wheel reducers of mine vehicles;

[0062] Figure 6 The present invention is a schematic diagram of storing standard data on an intelligent operation and maintenance big data cloud platform for an intelligent monitoring system of an electric wheel reducer for a mine car.

[0063] Reference numerals:

[0064] 100. Front-end acquisition hardware; 200. Full-information intelligent data processor; 300. Intelligent fault diagnosis system; 400. Cloud intelligent monitoring service system; 410. Intelligent operation and maintenance big data cloud platform; 420. Enterprise remote monitoring center; 430. Enterprise client 430. DETAILED DESCRIPTION

[0065] 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.

[0066] Example 1

[0067] like Figures 1-2 As shown, an intelligent monitoring system for an electric wheel reducer of a mine car comprises:

[0068] The front-end acquisition hardware 100 is arranged on the electric wheel of the mine car, and is used to receive the data acquisition instruction issued by the cloud intelligent monitoring service system 400, and is used to collect the operation data A of the electric wheel reducer and the ambient temperature data T according to the data acquisition instruction, and is used to transmit the operation data A and the temperature data T to the full-information intelligent data processor 200; the front-end acquisition hardware 100 includes an electric wheel temperature-vibration integrated sensor and a main generator temperature-vibration integrated sensor arranged on the mine car, such as 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;

[0069] Full information intelligent data processor 200: set on the mine car distribution box, used to receive the operation data A and temperature data T transmitted by the front-end acquisition hardware 100, used to classify and optimize the operation data A, and extract the feature vector M, used to transmit the operation data A and the feature vector M to the fault diagnosis system 300, and used to transmit the operation data A to the cloud intelligent monitoring service system 400;

[0070] The classification of the operation data A by the full information intelligent data processor 200 includes:

[0071] According to the time effect, the operating status data A is divided into operating data A1 which is independent of the time t change and time-dependent data A2.

[0072] Assign the questionable value S1 to the operation data A1 to generate the processing data B.

[0073] Assign the doubtful value S2 to the operation data A2 to generate the processing data C;

[0074] The optimization of the processing of data B and data C by the full information intelligent data processor 200 includes:

[0075] The temperature effect of processing data B is optimized to obtain the optimized processing data B1:

[0076] B1=f(T,t)×B

[0077] Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10;

[0078] The value of the function f(T,t) is:

[0079] When it is lower than the critical temperature T0, it decreases with the increase of temperature T;

[0080] When the temperature is greater than the critical temperature T0, it increases with the increase of temperature T;

[0081] Increases with the increase of time t;

[0082] The temperature effect of processing data C is optimized to obtain the optimized processing data C1:

[0083] C1=g(T,t)×C

[0084] Where: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10;

[0085] The value of the function g(T,t):

[0086] When the temperature is lower than the critical temperature T1, it decreases with the increase of temperature T;

[0087] When it is greater than the critical temperature T1, it increases with the increase of temperature T;

[0088] Increases with the increase of time t;

[0089] The extraction of the feature vector M of the data B1 and the data C1 processed by the full information intelligent data processor 200 includes:

[0090] M=M1∪M2

[0091]

[0092] Among them, M1 is the state feature vector, m is the state data influencing factor, M2 is the time-sensitive feature vector, n is the time-sensitive data influencing factor, k is the number of sensors, j is the sensor number, and b 1ij is the data of sensor number j in running data A1 at time t=i, b j is the standard operating data of sensor number j, c 1ij is the data of sensor number j in time t=i in time-sensitive data A2, c j is the standard time-effectiveness data of the sensor numbered j; the standard data is stored in the intelligent operation and maintenance big data cloud platform 410 schematic diagram, such as Figure 6 Shown

[0093] The fault intelligent diagnosis system 300 is used to receive the operation data A and the feature vector M transmitted by the full information intelligent data processor 200, and to generate a fault prediction value Z according to the feature vector M:

[0094]

[0095] 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 1i is the value of the state eigenvector at time t=i, M 1i ∈M,M 2i is the value of the time-dependent characteristic vector at time t = i, M 2i ∈M, t is the data collection time;

[0096] Used to generate fault diagnosis results based on the fault prediction value Z,

[0097] When the fault prediction value Z is less than the fault threshold, it is judged to be normal;

[0098] When the fault prediction value Z is greater than the fault threshold, a warning is issued;

[0099] Used to transmit the fault diagnosis result to the cloud intelligence monitoring service system 400;

[0100] The cloud intelligent monitoring service system 400 is used to generate data collection instructions according to user needs, to transmit the data collection instructions to the front-end collection hardware 100, to receive the operation data A transmitted by the full information intelligent data processor 200, to receive the fault diagnosis results transmitted by the fault intelligent diagnosis system 300, and to transmit the operation data A and the fault diagnosis results to the user; the cloud intelligent monitoring service system 400 includes:

[0101] Intelligent operation and maintenance big data cloud platform 410: used to receive the operation data A transmitted by the full-information intelligent data processor 200, used to generate a device operation status display interface according to the operation data A, and used to transmit the device operation status display interface to the enterprise remote monitoring center 420; used to receive the fault diagnosis result transmitted by the fault intelligent diagnosis system 300, used to generate an operation and maintenance report based on the diagnosis, and used to transmit the fault diagnosis result and the operation and maintenance report to the enterprise client 430; used to receive the data collection instruction transmitted by the enterprise client 430, and used to transmit the data collection instruction to the front-end collection hardware;

[0102] Enterprise remote monitoring center 420: used to receive the equipment operation status display interface transmitted by the intelligent operation and maintenance big data cloud platform 410 and display the operation status display interface to the user;

[0103] Enterprise client 430: used for users to generate data collection instructions, used for transmitting the data collection instructions to the intelligent operation and maintenance big data cloud platform 410, and used for receiving fault diagnosis results and operation and maintenance reports transmitted by the intelligent operation and maintenance big data cloud platform 410; the enterprise client 430 includes an enterprise PC terminal and a mobile terminal;

[0104] The user can use the cloud intelligent monitoring service system 400 to uniformly manage the point-like motor reduction wheels of the mine car. When the user has doubts about the fault diagnosis results, he can send a review instruction to the cloud intelligent monitoring service system 400. The cloud intelligent monitoring service system 400 retrieves data related to the fault diagnosis process or equipment according to the review instruction to verify the fault, and optimizes the fault diagnosis model according to the verification results. The review process includes:

[0105] Retrieve relevant data for calculating the fault prediction value Z, and arrange the relevant data in descending order according to the size of the doubt value S of the relevant data to generate a sequence Q;

[0106] From the historical data of the device, number sequences similar to number sequence Q are retrieved to form a number sequence set M, and from the data of other identical devices, number sequences similar to number sequence Q are retrieved to form a number sequence set N. The data of number sequence sets M and N are substituted into the fault diagnosis model to regenerate the fault diagnosis result;

[0107] If the fault diagnosis result shows that the fault risk increases, the doubt value S of the data in the sequence Q is increased;

[0108] If the fault diagnosis result shows that the fault risk is reduced, the fault diagnosis model is optimized using the sequence Q;

[0109] When a device fails, the feature vector M of the fault point is extracted and substituted into the fault diagnosis model to optimize the parameters p, q, and f.

[0110] 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. An intelligent monitoring system for a mine car electric wheel reducer, characterized in that: include: Front-end acquisition hardware (100): arranged on the electric wheel of the mining vehicle, used for receiving a data acquisition instruction issued by the cloud intelligent monitoring service system (400), used for collecting the operation data A of the electric wheel reducer and the ambient temperature data T according to the data acquisition instruction, and used for transmitting the operation data A and the temperature data T to the full-information intelligent data processor (200); A full-information intelligent data processor (200): arranged on the mine car distribution box, used for receiving the operation data A and the temperature data T transmitted by the front-end acquisition hardware (100), used for classifying and optimizing the operation data A, and extracting the feature vector M, used for transmitting the operation data A and the feature vector M to the fault diagnosis system, and used for transmitting the operation data A to the cloud intelligent monitoring service system; A fault intelligent diagnosis system (300): used for receiving the operation data A and the feature vector M transmitted by the full information intelligent data processor (200), and for generating a fault prediction value Z according to the feature vector M: 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 1i is the value of the state eigenvector at time t=i, M 1i ∈M,M 2i is the value of the time-dependent characteristic vector at time t = i, M 2i ∈M, t is the data collection time; used to generate a fault diagnosis result according to the fault prediction value Z, When the fault prediction value Z is less than the fault threshold, it is judged to be normal; When the fault prediction value Z is greater than the fault threshold, a warning is issued; Used to transmit the fault diagnosis result to the cloud intelligence monitoring service system (400); A cloud intelligent monitoring service system (400): used to generate the data collection instruction according to user needs, used to transmit the data collection instruction to the front-end collection hardware (100), used to receive the operation data A transmitted by the full information intelligent data processor (200), used to receive the fault diagnosis result transmitted by the fault intelligent diagnosis system (300), and used to transmit the operation data A and the fault diagnosis result to the user; The user can use the cloud intelligent monitoring service system (400) to uniformly manage the dotted mine car motor reduction wheels. When the user has doubts about the fault diagnosis result, the user can send a review instruction to the cloud intelligent monitoring service system (400). The cloud intelligent monitoring service system (400) retrieves data related to the fault diagnosis process or equipment according to the review instruction to verify the fault, and optimizes the fault diagnosis model according to the verification result.

2. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 1, characterized in that: The cloud intelligence monitoring service system (400) comprises: An intelligent operation and maintenance big data cloud platform (410): used for receiving the operation data A transmitted by the full-information intelligent data processor (200), for generating a device operation status display interface according to the operation data A, and for transmitting the device operation status display interface to an enterprise remote monitoring center (420); used for receiving the fault diagnosis result transmitted by the fault intelligent diagnosis system (300), for generating an operation and maintenance report from the diagnosis, and for transmitting the fault diagnosis result and the operation and maintenance report to an enterprise client (430); used for receiving the data collection instruction transmitted by the enterprise client (430), and for transmitting the data collection instruction to the front-end collection hardware (100); An enterprise remote monitoring center (420): used for receiving the device operation status display interface transmitted by the intelligent operation and maintenance big data cloud platform (410) and displaying the operation status display interface to a user; Enterprise client (430): used for a user to generate the data collection instruction, used for transmitting the data collection instruction to the intelligent operation and maintenance big data cloud platform (410), and used for receiving the fault diagnosis result and the operation and maintenance report transmitted by the intelligent operation and maintenance big data cloud platform (410).

3. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 2 is characterized in that: The enterprise client (430) includes an enterprise PC terminal and a mobile terminal.

4. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 1, characterized in that: The front-end acquisition hardware (100) comprises an electric wheel temperature-vibration integrated sensor and a main generator temperature-vibration integrated sensor arranged on the mining vehicle.

5. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 1, characterized in that: The full information intelligent data processor (200) classifies the operation data A in the following ways: According to the time effect, the operating status data A is divided into operating data A1 which is independent of the time t change and time-dependent data A2 which is related to the time t. The operation data A1 is assigned with the questionable value S1 to generate the processing data B, The operation data A2 is assigned a questionable value S2 to generate processing data C.

6. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 5, characterized in that: The optimization of the processed data B and the processed data C of the full information intelligent data processor (200) includes: The temperature effect of the processing data B is optimized to obtain the optimized processing data B1: B1=f(T,t)×B Where: function f(T, t) is a constant related to temperature T and time t, 1≤f(T, t)≤10; 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; Increases with the increase of time t; The temperature effect of the processing data C is optimized to obtain optimized processing data C1: C1=g(T,t)×C Where: function g(T,t) is a constant related to temperature T and time t, 1≤g(T,t)≤10; 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. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 6, characterized in that: The full information intelligent data processor (200) extracts the feature vector M of the processed data B1 and the processed data C1 include: M=M1∪M2 Among them, M1 is the state feature vector, m is the state data influencing factor, M2 is the time-sensitive feature vector, n is the time-sensitive data influencing factor, k is the number of sensors, j is the sensor number, and b 1ij is the data of the sensor number j in the operation data A1 at time t=i, j is the standard operating data of sensor number j, c 1ij is the data of sensor number j in time t=i in time-sensitive data A2, c j This is the standard time-effectiveness data of sensor number j.

8. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 5, characterized in that: When the user has doubts about the fault diagnosis result, the user can review the fault result; the review process includes: Retrieving relevant data for calculating the fault prediction value Z, and arranging the relevant data in descending order according to the size of the doubtful value S of the relevant data to generate a sequence Q; Retrieving number sequences close to the number sequence Q from the historical data of the device to form a number sequence set M, retrieving number sequences close to the number sequence Q from the data of other identical devices to form a number sequence set N, substituting the data of the number sequence set M and the number sequence set N into the fault diagnosis model to regenerate the fault diagnosis result; If the fault diagnosis result shows that the fault risk increases, then the doubt value S of the data in the sequence Q is increased; If the fault diagnosis result shows that the fault risk is reduced, the number sequence Q is used to optimize the fault diagnosis model.

9. The intelligent monitoring system for the electric wheel reducer of a mine car according to claim 1, characterized in that: When a device fails, a feature vector M of the fault point is extracted and substituted into the optimized parameters p, q, and f of the fault diagnosis model.

Images