Special vehicle health management method and device
By constructing representative matrix and weighted correction data, and using functional data analysis methods, data fluctuations caused by special vehicle vibration are solved, health management accuracy and fault prediction capabilities are improved, equipment life is extended, and maintenance costs are reduced.
Patent Information
- Application Number
- CN202410878867.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-07-02
AI Technical Summary
Vibration of special vehicles during startup and operation causes sensor data to fluctuate, affecting the accuracy of health management and trend prediction.
By configuring the sensor to collect data, using normal distribution probability values to build a representative matrix, generating a correction coefficient matrix, weighted correction of the data, and using a functional data analysis method to establish the damage of each component over time.
The precise description of the functional curve of equipment status and parameters improves the accuracy of health management, realizes timely detection and prediction of equipment failures in special vehicle, extends the service life of the equipment and reduces maintenance costs.
Smart Images

Figure CN119004245A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle fault diagnosis, and in particular to a method and device for special vehicle health management. Background Art
[0002] Special vehicles have irreplaceable advantages in engineering construction, disaster relief and other operations. However, when special vehicles are started and running, the operation of the engine, transmission and other equipment will cause great vibrations in the entire vehicle, resulting in large fluctuations in data collected by certain equipment sensors (such as vibration, speed and other sensors), further affecting the accuracy of subsequent health management and trend prediction of various equipment. Summary of the invention
[0003] In view of this, the present invention provides a method and device for special vehicle health management, which can solve the technical problem of low accuracy of special vehicle health management.
[0004] In order to solve the above technical problems, the present invention is implemented as follows.
[0005] A method for special vehicle health management, the method comprising:
[0006] Step S1: The various sensors configured on the special vehicle collect data of the corresponding components of the various sensors; the collected data are sent to the data bus; the data acquisition device obtains the collected data of the corresponding components of the various sensors from the data bus periodically, and stores it in the data processing and analysis device. The collected data stored in the data processing and analysis device obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation;
[0007] Step S2: Select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix;
[0008] Step S3: Correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, and use a functional data analysis method to establish a functional relationship of the corrected data over time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0009] Preferably, the correction coefficient matrix of each representative matrix mapped to the standard matrix is solved by partial least squares algorithm (PLS), and 5 correction coefficient matrices S are obtained: μ-2σ , S μ-σ , S μ , S μ+σ and S μ+2σ .
[0010] Preferably, a standard matrix is generated based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix, including:
[0011] All data in the data processing and analysis device are classified by component type, and the average of each data of the same type of components is calculated as an element in the standard matrix to generate a standard matrix Establish the functional relationship between each representative matrix and the standard matrix respectively to form five functions, and solve the five functions to obtain five correction coefficient matrices
[0012]
[0013] Determining a weighted correction coefficient matrix based on each correction coefficient matrix includes:
[0014] The correction coefficient matrices corresponding to the five representative matrices are weighted to obtain the weighted correction coefficient matrix M corresponding to the standard matrix, M = α1S μ-2σ +α2S μ-σ +α3S μ +α4S μ+σ +α5S μ+2σ , where the values of α1, α2, α3, α4, and α5 are calculated based on the probability of the standard normal distribution as follows:
[0015] According to N(μ,σ 2 ) corresponding to the normal distribution function, and calculate the probabilities corresponding to the probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ, respectively, denoted as P μ-2σ , P μ-σ , P μ , P μ+σ , P μ+2σ ,in:
[0016]
[0017] Preferably, the step S3 comprises:
[0018] Obtain the standard correction coefficient M, multiply the data stored in the data processing and analysis equipment by the coefficient M one by one to obtain the corrected data; store the corrected data in a database, select the corrected data within a preset time range from the database, and use a functional data analysis method to establish a functional relationship of the corrected data within the preset time range that changes with time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0019] Preferably, the method for special vehicle health management further includes:
[0020] Step S4: Send the damage status of each component of the special vehicle over time to the display layer for visual display.
[0021] The present invention provides a device for special vehicle health management, the device comprising:
[0022] Acquisition module: various sensors configured for the special vehicle collect data of the corresponding components of the various sensors; the collected data are sent to the data bus; the data acquisition device obtains the collected data of the corresponding components of the various sensors from the data bus periodically, and stores it in the data processing and analysis equipment. The collected data stored in the data processing and analysis equipment obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation;
[0023] Correction module: It is configured to select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix;
[0024] Analysis module: configured to correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, use a functional data analysis method to establish a functional relationship of the corrected data over time; and determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0025] The present invention provides a computer-readable storage medium, wherein a plurality of instructions are stored in the storage medium; the plurality of instructions are used for a processor to load and execute the method as described above.
[0026] An electronic device provided by the present invention is characterized in that the electronic device comprises:
[0027] A processor, which is used to execute multiple instructions;
[0028] A memory for storing a plurality of instructions;
[0029] The plurality of instructions are used to be stored by the memory and loaded and executed by the processor to implement the method as described above.
[0030] Beneficial technical effects brought by the present invention:
[0031] (1) The present invention can correct the data volatility caused by vibration and accurately depict the function curve of the continuous change of parameters such as the status and characteristics of each device over time, thereby improving the accuracy of health management of each device. The present invention realizes accurate health management of each device under data fluctuation conditions.
[0032] (2) In the data collection of the present invention, the minimum data collection period is 5 ms, which can more accurately characterize the trend of continuous changes of each device over time; in the data correction, 5 representative values that can characterize the data fluctuations are selected in a probabilistic manner, thereby increasing the reliability of the representative value selection; in the establishment of the functional relationship, the basis function can be flexibly selected according to the data type to be applicable to data with periodic or non-periodic changes.
[0033] (3) The present invention can accurately manage the health of each device, thereby realizing timely detection of special vehicle equipment failures, accurately predicting equipment operation trends, etc., thereby extending the service life of the equipment and reducing equipment maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 This is a flow chart of a method for special vehicle health management according to the present invention;
[0035] Figure 2 An equipment layout diagram of the method for health management of special vehicle equipment provided by the present invention;
[0036] Figure 3 A schematic diagram of data correction in a method for special vehicle equipment health management provided by an embodiment of the present invention;
[0037] Figure 4 A schematic diagram of the functional relationship established in the method for special vehicle equipment health management provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0038] The present invention is described in detail below in conjunction with the accompanying drawings and embodiments.
[0039] like Figure 1-Figure 2As shown, the present invention proposes a method for special vehicle health management, the method comprising:
[0040] Step S1: The various sensors configured on the special vehicle collect data of the corresponding components of the various sensors; the collected data are sent to the data bus; the data acquisition device obtains the collected data of the corresponding components of the various sensors from the data bus periodically, and stores it in the data processing and analysis device. The collected data stored in the data processing and analysis device obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation;
[0041] Step S2: Select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix;
[0042] Step S3: Correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, and use a functional data analysis method to establish a functional relationship of the corrected data over time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0043] Furthermore, the components corresponding to the various sensors include special vehicle brake controllers, generator controllers, engine controllers, various types of equipment and various types of equipment controllers.
[0044] In the step S1, the data of the component includes operating status and characteristic parameters.
[0045] The acquisition software in the data acquisition device periodically acquires the number of components corresponding to each type of sensor from the data bus and sends it to the data processing and analysis equipment for storage.
[0046] Furthermore, in step S2, the correction coefficient matrix of each representative matrix mapped to the standard matrix is solved by partial least squares algorithm (PLS) to obtain 5 correction coefficient matrices S μ-2σ , S μ-σ , S μ , S μ+σ and S μ+2σ .
[0047] The method generates a standard matrix based on all the data in the data processing and analysis device. Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix, including:
[0048] All data in the data processing and analysis device are classified by component type, and the average of each data of the same type of components is calculated as an element in the standard matrix to generate a standard matrix The functional relationship between each representative matrix and the standard matrix is established respectively to form five functions, and five correction coefficient matrices are obtained by solving the five functions.
[0049]
[0050] Determining a weighted correction coefficient matrix based on each correction coefficient matrix includes:
[0051] The correction coefficient matrices corresponding to the five representative matrices are weighted to obtain the weighted correction coefficient matrix M corresponding to the standard matrix, M = α1S μ-2σ +α2S μ-σ +α3S μ +α4S μ+σ +α5S μ+2σ , where the values of α1, α2, α3, α4, and α5 are calculated based on the probability of the standard normal distribution as follows:
[0052] According to N(μ,σ 2 ) corresponding to the normal distribution function, and calculate the probabilities corresponding to the probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ, respectively, denoted as P μ-2σ , P μ-σ , P μ , P μ+σ , P μ+2σ ,in:
[0053]
[0054] For example, the probability at point μ is: P μ =0.0080, the probability at points μ-σ and μ+σ: P μ-σ =P μ+σ =0.0049; Probability at points μ-2σ and μ+2σ: P μ-2σ =P μ+2σ =0.0011, then:
[0055]
[0056] The step S3 comprises:
[0057] Obtain the standard correction coefficient M, multiply the data stored in the data processing and analysis equipment by the coefficient M one by one to obtain the corrected data; store the corrected data in a database, select the corrected data within a preset time range from the database, and use a functional data analysis method to establish a functional relationship of the corrected data within the preset time range that changes with time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0058] In the present invention, data of parameters such as the status and characteristics of each device within a certain time range are taken out from the database as needed (the data are corrected data), and a functional data analysis algorithm is used to establish a functional relationship that changes continuously over time, thereby realizing the changing trend of the health status of each device of the special vehicle and achieving the purpose of implementing health management of each device.
[0059] In the present invention, the basis function type of the functional data analysis method is a B-spline basis, and the number of basis functions is set to 4th order.
[0060] Furthermore, the method for special vehicle health management also includes:
[0061] Step S4: Send the damage status of each component of the special vehicle over time to the display layer for visual display.
[0062] In the present invention, the health management results of each device and the original parameters, status and other data are sent to the display layer for visual display.
[0063] The present invention provides an embodiment of a method for special vehicle health management.
[0064] like Figure 2 As shown, the acquisition and analysis system includes a device layer, a data acquisition layer, a data processing and analysis layer, and a display layer; after each device is running, it will send its own status, characteristics and other parameters to the data bus. The acquisition software in the data acquisition layer collects the vibration, speed and control signals of equipment such as engines and generators from the data bus at a cycle of 5ms and sends them to the data processing and analysis equipment for storage.
[0065] like Figure 3 As shown, the correction of the collected data is realized. The data processing and analysis module first reads 1000 times of collected data of signal 1, signal 2, ..., signal 10 from the database. It is known that the 1000 times collected data of each signal obeys the normal distribution N(μ,σ 2 )(σ is the standard deviation, μ is the expectation). In the 10 signals, the data with probability μ-2σ, μ-σ, μ, μ+σ and μ+2σ are selected from 1000 data as the representative values of the randomly collected data to form 5 matrices D μ-2σ, D μ-σ , D μ , D μ+σ and D μ+2σ , the average of 1000 collected data of 10 signals is used as the standard value to form a matrix Establish the functional relationship between the representative matrix and the standard matrix respectively and After solving by PLS (partial least squares algorithm), we get 5 coefficient matrices S μ-2σ , S μ-σ , S μ , S μ+σ and S μ+2σ ; Weighted integration of the five coefficient matrices to obtain the final correction coefficient M = α1S μ-2σ +α2S μ-σ +α3S μ +α4S μ+σ +α5S μ+2σ , where the values of α1, α2, α3, α4 and α5 can be calculated based on the probability of the standard normal distribution, which are 0.055, 0.245, 0.4, 0.245 and 0.055 respectively; when M is established, the data D collected at any time is multiplied by the coefficient M to obtain the corrected data, and the corrected data is stored in the database.
[0066] like Figure 4 As shown, the functional relationship of the corrected data of each device over time is established. The vibration signal data of the engine and generator and other equipment within half a year are taken from the database (the vibration signal is used in the example, and other signal analysis can be selected according to the actual situation according to the analysis needs), and the functional data analysis algorithm is used to establish the functional relationship of its continuous change over time. For each signal, Where: φ n (t),n∈{1,2,...,N}, c is the basis function coefficient, To fit the function curve, the basis function type is B-spline basis, and the number of basis functions is set to 4th order. After the functional relationship is established for each signal, the changing trend of the health status of each device of the special vehicle can be characterized, so as to achieve the purpose of implementing health management for each device. Finally, the health management results of each device and the original parameters, status and other data (the collected data in other formats is converted into Ethernet data through the data conversion module) are stored in the database on the one hand, and sent to the display layer for visual display on the other hand.
[0067] Embodiments General Description
[0068] The equipment in the equipment layer transmits the speed, vibration and other data it generates to the data bus; the data acquisition device collects the speed, vibration and other data on the data bus at a period of 5ms and sends them to the data processing and analysis equipment; the data processing and analysis equipment first corrects the equipment data using a probability distribution data correction method and stores it in the database, thereby reducing data fluctuations caused by the strong vibration of special vehicles; then the data processing and analysis module retrieves the vibration signal data of equipment such as engines and generators within half a year from the database, and uses functional data analysis algorithms to establish their functional relationships that continuously change over time; finally, the health management results and original parameters, status and other data of each device are stored in the database on the one hand, and sent to the display layer for visual display on the other hand.
[0069] The present invention provides a device for special vehicle health management, the device comprising:
[0070] Acquisition module: various sensors configured for the special vehicle collect data of the corresponding components of the various sensors; the collected data are sent to the data bus; the data acquisition device obtains the collected data of the corresponding components of the various sensors from the data bus periodically, and stores it in the data processing and analysis equipment. The collected data stored in the data processing and analysis equipment obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation;
[0071] Correction module: It is configured to select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix;
[0072] Analysis module: configured to correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, use a functional data analysis method to establish a functional relationship of the corrected data over time; and determine the damage status of each component of the special vehicle over time based on the functional relationship.
[0073] The present invention provides a computer-readable storage medium, wherein a plurality of instructions are stored in the storage medium; the plurality of instructions are used for a processor to load and execute the method as described above.
[0074] An electronic device provided by the present invention is characterized in that the electronic device comprises:
[0075] A processor, which is used to execute multiple instructions;
[0076] A memory for storing a plurality of instructions;
[0077] The plurality of instructions are used to be stored by the memory and loaded and executed by the processor to implement the method as described above.
[0078] The above specific embodiments only describe the design principle of the present invention. The shapes and names of the components in the description may be different and are not limited. Therefore, those skilled in the art in the field of the present invention may modify or replace the technical solutions recorded in the above embodiments; and these modifications and replacements do not deviate from the creative purpose and technical solutions of the present invention and should all fall within the protection scope of the present invention.
Claims
1. A method for special vehicle health management, characterized in that: include: Step S1: various sensors configured on the special vehicle collect data of components corresponding to the various sensors; Send the collected data to the data bus; The data acquisition device periodically obtains the collected data of the corresponding components of the various sensors from the data bus and stores it in the data processing and analysis device. The collected data stored in the data processing and analysis device obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation; Step S2: Select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix; Step S3: Correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, and use a functional data analysis method to establish a functional relationship of the corrected data over time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
2. The method according to claim 1, characterized in that In step S2, the correction coefficient matrix of each representative matrix mapped to the standard matrix is solved by partial least squares algorithm (PLS) to obtain 5 correction coefficient matrices S μ-2σ , S μ-σ , S μ , S μ+σ and S μ+2σ .
3. The method according to claim 2, characterized in that The method generates a standard matrix based on all the data in the data processing and analysis device. Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix, including: All data in the data processing and analysis device are classified by component type, and the average of each data of the same type of components is calculated as an element in the standard matrix to generate a standard matrix Establish the functional relationship between each representative matrix and the standard matrix respectively to form five functions, and solve the five functions to obtain five correction coefficient matrices Determining a weighted correction coefficient matrix based on each correction coefficient matrix includes: The correction coefficient matrices corresponding to the five representative matrices are weighted to obtain the weighted correction coefficient matrix M corresponding to the standard matrix, M = α1S μ-2σ +α2S μ-σ +α3S μ +α4S μ+σ +α5S μ+2σ , where the values of α1, α2, α3, α4, and α5 are calculated based on the probability of the standard normal distribution as follows: According to N(μ,σ 2 ) corresponding to the normal distribution function, and calculate the probabilities corresponding to the probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ, respectively, denoted as P μ-2σ , P μ-σ , P μ , P μ+σ , P μ+2σ ,in:
4. The method according to claim 3, characterized in that The step S3 comprises: Obtain the standard correction coefficient M, multiply the data stored in the data processing and analysis equipment by the coefficient M one by one to obtain the corrected data; store the corrected data in a database, select the corrected data within a preset time range from the database, and use a functional data analysis method to establish a functional relationship of the corrected data within the preset time range that changes with time; determine the damage status of each component of the special vehicle over time based on the functional relationship.
5. The method according to any one of claims 1 to 4, characterized in that The method for special vehicle health management also includes: Step S4: Send the damage status of each component of the special vehicle over time to the display layer for visual display.
6. A device for special vehicle health management, characterized in that: include: Acquisition module: configured to collect data of components corresponding to various sensors configured for the special vehicle itself; Send the collected data to the data bus; The data acquisition device periodically obtains the collected data of the corresponding components of the various sensors from the data bus and stores it in the data processing and analysis device. The collected data stored in the data processing and analysis device obeys the normal distribution N(μ,σ 2 ), σ is the standard deviation, μ is the expectation; Correction module: It is configured to select the collected data with probability values of μ-2σ, μ-σ, μ, μ+σ and μ+2σ in the normal distribution in turn, and construct a representative matrix for the collected data corresponding to each probability value to obtain the representative matrix D μ-2σ , D μ-σ , D μ , D μ+σ and D μ+2σ ; Generate a standard matrix based on all the data in the data processing and analysis device Determine a correction coefficient matrix for mapping each representative matrix to a standard matrix, and determine a weighted correction coefficient matrix based on each correction coefficient matrix; Analysis module: configured to correct the data stored in the data processing and analysis device based on the weighted correction coefficient matrix, use a functional data analysis method to establish a functional relationship of the corrected data over time; and determine the damage status of each component of the special vehicle over time based on the functional relationship.
7. A computer-readable storage medium, wherein a plurality of instructions are stored in the storage medium; the plurality of instructions are used for a processor to load and execute the method as claimed in any one of claims 1 to 5.
8. An electronic device, characterized in that: The electronic device comprises: A processor, which is used to execute multiple instructions; A memory for storing a plurality of instructions; The plurality of instructions are used to be stored in the memory and loaded and executed by the processor according to any one of claims 1 to 5.
Citation Information
Patent Citations
Terminal device and information acquisition method and device
CN104156715A
Method, device and system for correcting automobile power battery
CN108508369A
Industrial equipment health state monitoring system and method based on side cloud cooperative computing
CN115186883A
Iterative optimization multi-scale fusion speed prediction algorithm for intelligent connected vehicle
WO2022206079A1
