Fault early warning method and device of vehicle-mounted power system and vehicle-mounted computing power platform

Abstract

The invention discloses a fault early warning method and device of a vehicle-mounted power system and a vehicle-mounted computing power platform, and relates to the technical field of vehicle-mounted power systems. Vibration data are divided into multiple groups of sub vibration data; determining an optimal decomposition parameter according to the first group of sub-vibration data; according to the method, the parameters are optimally decomposed, the low-resonance components corresponding to each group of sub-vibration data are obtained, the low-resonance components often contain fault-related feature information, the fault feature frequency can be extracted in the early stage, whether the vehicle-mounted power system breaks down or not is judged according to the low-resonance components, and the timeliness of fault early warning is improved. In addition, for different decomposition parameters, low resonance components obtained from each group of sub-vibration data are also different, so that proper decomposition parameters need to be found. And the optimal decomposition parameter is determined according to the first group of sub-vibration data, so that the low-resonance component is accurately obtained according to the optimal decomposition parameter, and the timeliness of fault early warning is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle-mounted power systems, and in particular to a fault warning method and device for a vehicle-mounted power system and a vehicle-mounted computing power platform. Background Art

[0002] With the increasing penetration rate of new energy vehicles in the market, status monitoring of vehicle power systems has become the key to the development of vehicle intelligence.

[0003] Currently, related technologies perform fault analysis based on data collected from acoustics and temperature. However, under complex operating conditions, the collected data is easily affected by interference from background noise and shaft frequency harmonics, making it difficult to extract early fault characteristics. As a result, faults cannot be diagnosed until they have developed to a significant stage, reducing the timeliness of fault warnings. Summary of the Invention

[0004] This application provides a fault warning method, device and vehicle-mounted computing power platform for a vehicle-mounted power system to at least solve the problem of timeliness of fault warning in related technologies.

[0005] This application provides a fault warning method for a vehicle power system, comprising:

[0006] Receive vibration data for the vehicle power system sent by the data terminal;

[0007] Dividing the vibration data into multiple groups of sub-vibration data;

[0008] determining optimal decomposition parameters according to the first group of sub-vibration data;

[0009] According to the optimal decomposition parameters, the low resonance components corresponding to each group of sub-vibration data are obtained;

[0010] Based on the low resonance component, determine whether the vehicle power system has a fault;

[0011] If it is determined that the vehicle's power system has a fault, an early warning will be issued.

[0012] The present application also provides a fault warning device for a vehicle-mounted power system, comprising:

[0013] A receiving module, used to receive vibration data of the vehicle power system sent by the data terminal;

[0014] A division module, used for dividing the vibration data into multiple groups of sub-vibration data;

[0015] a determination module, configured to determine an optimal decomposition parameter based on the first group of sub-vibration data;

[0016] An acquisition module, used for acquiring low resonance components corresponding to each group of sub-vibration data according to the optimal decomposition parameters;

[0017] A judgment module, used to judge whether a vehicle power system has a fault based on the low resonance component;

[0018] The determination module is used to issue an early warning if it determines that a fault occurs in the vehicle power system.

[0019] The present application also provides a vehicle-mounted computing power platform, including: a memory for storing computer programs; a processor for implementing the steps of any of the above-mentioned vehicle-mounted power system fault warning methods when executing the computer program.

[0020] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned fault warning methods for the vehicle power system are implemented.

[0021] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned fault warning methods for a vehicle-mounted power system.

[0022] Through this application, the vibration data is divided into multiple groups of sub-vibration data; based on the first group of sub-vibration data, the optimal decomposition parameters are determined; the optimal decomposition parameters are used to obtain the low resonance components corresponding to each group of sub-vibration data. The low resonance components often contain characteristic information related to the fault, and can extract the fault characteristic frequency at an early stage, and then judge whether the vehicle power system has a fault based on the low resonance components, thereby improving the timeliness of the fault warning. In addition, different decomposition parameters will obtain different low resonance components from each group of sub-vibration data, so it is necessary to find suitable decomposition parameters. Based on the first group of sub-vibration data, the optimal decomposition parameters are determined, and then based on the optimal decomposition parameters, the low resonance components are accurately obtained, further improving the timeliness of the fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 A schematic diagram of the system structure of the vehicle-mounted computing power platform provided in an embodiment of the present application;

[0025] Figure 2 A flowchart of a fault warning method for a vehicle power system provided in an embodiment of the present application;

[0026] Figure 3 A simplified diagram of the drive axle structure provided in an embodiment of the present application;

[0027] Figure 4 This is the envelope demodulation result of the low resonance component of the 196th group of sub-vibration data provided in an embodiment of the present application;

[0028] Figure 5 This is the envelope demodulation result of the low resonance component of the 197th group of sub-vibration data provided in an embodiment of the present application;

[0029] Figure 6 A schematic diagram of the structure of a fault warning device for a vehicle power system provided in an embodiment of the present application;

[0030] Figure 7 Schematic diagram of the structure of the vehicle-mounted computing power platform provided for this application. DETAILED DESCRIPTION

[0031] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] It should be noted that, in the description of this application, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. The terms "first," "second," etc., in this application are used to distinguish similar objects, and are not used to describe a particular order or sequence.

[0033] With the increasing penetration of new energy vehicles in the market, monitoring the condition of onboard powertrains has become crucial for the development of intelligent vehicles. Currently, related technologies perform fault analysis based on data collected from acoustics and temperature. However, under complex operating conditions, the collected data is easily affected by interference from background noise and shaft frequency harmonics, making it difficult to extract early fault signatures. Consequently, faults cannot be diagnosed until they have developed to a significant stage, reducing the timeliness of fault warnings.

[0034] In order to solve the problem of timeliness of fault warning in the prior art, the embodiments of the present application propose the following technical concept: considering that the collected data is easily interfered by background noise and shaft frequency harmonics, it is difficult to extract early fault features. The inventors thought of extracting low-resonance components from vibration data. Low-resonance components often contain characteristic information related to faults, which can extract fault characteristic frequencies at an early stage, and then judge whether the vehicle power system has a fault based on the low-resonance components, thereby improving the timeliness of fault warning. In addition, different decomposition parameters will result in different low-resonance components obtained from each group of sub-vibration data, so it is necessary to find suitable decomposition parameters. Based on the first group of sub-vibration data, the optimal decomposition parameters are determined, and then based on the optimal decomposition parameters, the low-resonance components are accurately obtained, further improving the timeliness of fault warning.

[0035] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0036] In conjunction with the specific application environment architecture or specific hardware architecture on which the execution of the fault warning method for the vehicle power system depends, the specific application environment architecture or specific hardware architecture is described herein.

[0037] refer to Figure 1 , Figure 1 This is a schematic diagram of the system structure of the vehicle computing platform provided in the embodiment of this application. Figure 1 As shown, the vehicle-mounted computing platform includes: a receiving device 101, a processor 102 and a display device 103.

[0038] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the fault warning method for the vehicle power system. In other feasible implementations of this application, the above architecture may include more or fewer components than shown, or combine or split certain components, or arrange the components differently. The specific configuration can be determined based on the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0039] In a specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, and can obtain vibration data of the vehicle power system sent by the data terminal.

[0040] The processor 102 can determine whether a fault occurs in the vehicle power system based on the vibration data.

[0041] The display device 103 can be used to display faults of the vehicle power system.

[0042] The display device may also be a touch screen display, which is used to receive user instructions while displaying the above-mentioned content to achieve operational interaction with the user.

[0043] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0044] Figure 2 A flow chart of a fault warning method for a vehicle power system provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the embodiment of the present application provides a fault warning method for a vehicle power system, and the method is described in detail as follows:

[0045] S201: Receive vibration data for the vehicle power system sent by the data terminal.

[0046] In this embodiment, the vibration sensor is installed on the housing of the vehicle power system, and the data terminal is integrated into the carrier board of the vehicle computing power platform. The vibration data of the vibration sensor is collected through the data terminal, and the vibration data is transmitted to the on-chip system of the vehicle computing power platform for processing.

[0047] In this embodiment, integrating the data terminal into the carrier board of the vehicle-mounted computing platform has the following advantages:

[0048] 1) Improved system integration: On the one hand, integrating the data terminal into the vehicle computing platform's carrier board allows for the consolidation of multiple previously independent hardware modules. After integration, it becomes part of the carrier board, reducing the number of independent hardware components. Given the limited space in a vehicle, a large number of electronic devices need to be accommodated. This highly integrated design can make the entire system more compact, reduce the number of connecting lines and interfaces between devices, and reduce hardware complexity and cost. Furthermore, integrating the data terminal into the carrier board eliminates the need for separate space for the data terminal, thereby improving the space utilization of the entire vehicle computing platform.

[0049] 2) Optimize signal transmission performance: On the one hand, in traditional independent data terminal systems, signals need to be transmitted through longer cables, which increases the risk of external interference to the signal. Cables are susceptible to electromagnetic interference, radio frequency interference, etc. during transmission, resulting in signal distortion or noise. After the data terminal is integrated into the carrier board, the signal transmission distance is greatly shortened, reducing the chance of the signal coming into contact with external interference sources during transmission and reducing signal interference; on the other hand, the integrated design makes communication between the data terminal and the on-board computing power platform more direct and efficient. Signals can be transmitted quickly through the internal bus on the carrier board, avoiding delays and data loss that may occur when communicating between independent devices, and improving signal transmission efficiency.

[0050] 3) Software and Function Integration: On the one hand, after the data terminal is integrated into the vehicle computing platform board, a unified software architecture can be used to manage data acquisition and processing. This means that developers only need to develop and maintain on a single software platform, reducing the complexity and cost of software development. The unified software architecture can also improve the compatibility and maintainability of the software, enabling different functional modules to work better together. On the other hand, the integrated design provides greater flexibility for system functional expansion. Because the data terminal and the vehicle computing platform are tightly integrated, when new functions need to be added, only the corresponding hardware modules need to be added to the board and the functional development can be carried out under the unified software architecture, which allows for flexible functional expansion.

[0051] Optionally, the data terminal may be a data acquisition card.

[0052] Optionally, vibration sensors can be divided into vibration acceleration sensors, vibration velocity sensors and vibration displacement sensors according to cost from low to high. Piezoelectric vibration acceleration sensors can be used in general vehicle-mounted scenarios, which have the characteristics of wide frequency response and good dynamic performance.

[0053] S202: Divide the vibration data into multiple groups of sub-vibration data.

[0054] Optionally, the vibration data is grouped into ten minute buckets.

[0055] S203: Determine optimal decomposition parameters based on the first group of sub-vibration data.

[0056] Specifically, step S203 includes S2031 to S2035:

[0057] S2031: Determine the initial search position and search parameters of the longicorn in the first group of sub-vibration data using the longicorn whisker search algorithm.

[0058] In this embodiment, the search parameters include an initial orientation vector, an initial search perception distance, and an initial search step size.

[0059] In this embodiment, it can be set as is the initial search position, and the spatial dimension of the initial search position is 2. For example, Can be .

[0060] The initial heading vector determines the direction the beetle may move in during the search process. Optionally, the initial heading vector can be randomly generated; the initial search perception distance is the detection range of the beetle's left and right antennae; and the initial search step size is the step size of the beetle's movement.

[0061] S2032: Starting from the initial search position of the longicorn, the search position of the longicorn is iteratively updated according to the search parameters until the search iteration stop condition is satisfied; wherein different search positions correspond to different decomposition parameters.

[0062] Specifically, step S2032 includes Sa~Si:

[0063] Sa: Determine the position of the longhorn beetle's left antenna based on the initial search position, initial orientation vector, and initial search perception distance.

[0064] Alternatively, the position of the left antenna of the longicorn can be determined by the following formula:

[0065]

[0066] Where, Indicates the position of the longicorn's left antennae. Indicates the initial search position, represents the initial search perception distance, Represents the initial heading vector.

[0067] Sb: Determine the position of the longicorn's right antenna based on the initial search position, initial orientation vector, and initial search perception distance.

[0068] Alternatively, the position of the right antenna of the longicorn can be determined by the following formula:

[0069]

[0070] Where, Indicates the position of the right antenna of the longicorn. Indicates the initial search position, represents the initial search perception distance, Represents the initial heading vector.

[0071] Sc: Calculate the fitness function value of the left tentacle position.

[0072] Specifically, the calculation formula of the fitness function value is:

[0073]

[0074] Where, represents the fitness function value, represents the kurtosis function of the low resonance component, represents the kurtosis constraint of each subband of the low resonance component, represents the kurtosis function of each subband of the low resonance component, Represents an operator.

[0075] Sd: Calculate the fitness function value of the right tentacle position.

[0076] Se: Determine the search direction for the first update of the search position based on the fitness function value of the left tentacle position and the fitness function value of the right tentacle position.

[0077] In this embodiment, if the fitness function of the left tentacle position is less than the fitness function value of the right tentacle position, the longhorn beetle believes that the target is in the direction of the left tentacle position, and the search direction of the first updated search position is to move toward the left tentacle; if the fitness function of the right tentacle position is less than the fitness function value of the left tentacle position, the longhorn beetle believes that the target is in the direction of the right tentacle position, and the search direction of the first updated search position is to move toward the right tentacle.

[0078] Sf: Determine the search perception distance for the first updated search position based on the initial search perception distance.

[0079] In this embodiment, the initial search perception distance is set to ; The search perception distance is dynamically adjusted according to the formula, which is as follows:

[0080]

[0081] The calculation formula for the search perception distance of the first updated search position is:

[0082]

[0083] Where, Indicates the search perception distance for the first update of the search position. Indicates the initial search perception distance.

[0084] Sg: Determine the search step size for the first update of the search position based on the initial search step size.

[0085] In this embodiment, the initial search step size is set to ; The search step length is dynamically adjusted according to the formula, which is as follows:

[0086]

[0087] The calculation formula for the search perception distance of the first updated search position is:

[0088]

[0089] Where, Indicates the search step length for the first update of the search position, Indicates the initial search step size.

[0090] Sh: Determine the first updated search position of the longicorn based on the initial search position, the search direction of the first updated search position, the search perception distance of the first updated search position, and the search step size of the first updated search position.

[0091] In this embodiment, at the initial search position, movement is performed according to the search direction of the first updated search position, the search perception distance of the first updated search position, and the search step size of the first updated search position to determine the first updated search position of the longicorn.

[0092] In this embodiment, after moving according to the search direction of the first updated search position, the orientation vector after the first updated position is obtained as the initial orientation vector for the second updated search position.

[0093] Si: During the iterative update of the longhorn beetle's search position, the next updated search position of the longhorn beetle is determined according to the current search position, the search direction of the next updated search position, the search perception distance of the next updated search position, and the search step size of the next updated search position, until the search iteration stop condition is met.

[0094] In this embodiment, the search parameters also include a time step, which is the number of search iterations. When the number of iterations reaches the time step, the updating of the longhorn beetle's search position is stopped. Optionally, the time step can be set to 0 to 100.

[0095] Exemplarily, when determining the second updated search position of the longhorn beetle, the position of the longhorn beetle's left tentacle is determined based on the search position, heading vector, and search perception distance after the first updated search position; the position of the longhorn beetle's right tentacle is determined based on the search position, heading vector, and search perception distance after the first updated search position. Calculate the fitness function value of the left tentacle position. Calculate the fitness function value of the right tentacle position. Determine the search direction of the second updated search position based on the fitness function value of the left tentacle position and the fitness function value of the right tentacle position. Determine the search perception distance of the second updated search position based on the search perception distance. Determine the search step length of the second updated search position based on the search step length. Determine the second updated search position of the longhorn beetle based on the search position, search direction, search perception distance, and search step length. And so on, until the search iteration stop condition is met.

[0096] In the present embodiment, the direction of the search position is determined according to the size of the fitness function values of the left and right tentacles. If the fitness function value detected by the left tentacles is less than that of the right tentacles, it is considered that the target is on the left, and the longhorn beetle will advance in the direction of the left tentacles according to the search perception distance and search step size; otherwise, it will advance in the direction of the right tentacles. This process is constantly repeated, and the longhorn beetle will gradually move in the direction that makes the fitness function value smaller, thereby realizing the search for the optimal solution. Compared to some complex optimization algorithms, the computational complexity is small, the parameters involved are fewer, and it is possible to complete iterative updates faster.

[0097] S2033: Record the search position during the iterative update process.

[0098] In this embodiment, the search position is recorded each time the search position is updated.

[0099] S2034: Calculate the fitness function values of different search positions.

[0100] S2035: Determine the decomposition parameter corresponding to the search position with the smallest fitness function value as the optimal decomposition parameter.

[0101] In this embodiment, different search positions correspond to one decomposition parameter.

[0102] S204: Obtaining low resonance components corresponding to each group of sub-vibration data according to the optimal decomposition parameters.

[0103] In this embodiment, each group of sub-vibration data is decomposed according to the optimal decomposition parameter to obtain the low resonance component corresponding to each group of sub-vibration data.

[0104] In this embodiment, according to the optimal decomposition parameters, a wavelet transform method with adjustable quality factor can be used to obtain the low resonance components corresponding to each group of sub-vibration data.

[0105] The quality factor-adjustable wavelet transform is a time-frequency analysis method that can decompose vibration data into different components based on given decomposition parameters, from which low-resonance components are obtained. These low-resonance components often contain characteristic information related to faults.

[0106] S205: Determine whether a vehicle power system fails based on the low resonance component.

[0107] In this embodiment, the faults include but are not limited to the outer ring, inner ring and cage of the rolling bearing. Different faults correspond to different fault characteristic frequencies.

[0108] Specifically, envelope demodulation analysis is performed on the low-resonance component to obtain an envelope demodulation result; it is determined whether the envelope demodulation result contains a fault characteristic frequency; if the envelope demodulation result contains a fault characteristic frequency, it is determined that a fault has occurred in the vehicle power system; if the envelope demodulation result does not contain a fault characteristic frequency, it is determined that no fault has occurred in the vehicle power system.

[0109] In this embodiment, since the fault signal often exists in a modulated form, the fault characteristic frequency can be highlighted through envelope demodulation.

[0110] Envelope demodulation analysis involves performing a Hilbert transform on the low-resonance components to generate an envelope signal. Spectral analysis of the envelope signal typically uses a Fast Fourier Transform to convert the time-domain signal into a frequency-domain signal, generating an envelope spectrum. If these fault characteristic frequencies appear in the envelope demodulation analysis results, a fault in the vehicle's powertrain is identified.

[0111] Optionally, the root mean square value of the low resonance component can be calculated to further verify whether the vehicle power system has a fault.

[0112] In this embodiment, the RMS value reflects the signal energy of the low-resonance component; a larger RMS value indicates a stronger signal energy. When a malfunction occurs in the vehicle's powertrain, vibration and shock intensify, significantly increasing the signal energy of the low-resonance component and correspondingly increasing the RMS value. Therefore, the RMS value can be used as a quantitative indicator to measure changes in signal energy. If the RMS value exceeds a preset threshold, it indicates an abnormal increase in the energy of the low-resonance component, possibly due to a malfunction, thus confirming a malfunction in the vehicle's powertrain.

[0113] In this embodiment, the abstract signal energy is converted into a specific numerical value by calculating the root mean square value of the low resonance component, thereby verifying whether the vehicle power system has a fault, thereby improving the accuracy of the fault warning.

[0114] S206: If it is determined that the vehicle power system fails, a warning is issued.

[0115] For example, taking the drive axle of car A as an example, Figure 3 The schematic diagram of the drive axle structure provided in the embodiment of the present application has an input shaft rotation frequency of 5Hz and an inner ring fault characteristic frequency of 47.2Hz. The vibration sensor is installed on the housing of the vehicle power system, and three sensors need to be installed in the three coordinate axis directions of the three-dimensional coordinate system; the vibration data is transmitted to the on-chip system of the vehicle computing power platform through the data terminal, and the sampling frequency is 5120Hz. The vibration data is divided into sub-vibration data, and the optimal decomposition parameters of the first group of sub-vibration data are determined. The optimal decomposition parameters are (11.3, 1.7). According to the optimal decomposition parameters, the low resonance components corresponding to each group of sub-vibration data are obtained; according to the low resonance components, it is judged whether the vehicle power system has a fault; the low resonance components are subjected to envelope demodulation analysis to obtain the envelope demodulation results; and it is judged whether the envelope demodulation results contain the fault characteristic frequency. Figure 4 The envelope demodulation result of the low resonance component of the 196th group of sub-vibration data provided in the embodiment of the present application is as follows: Figure 4 As shown, no fault frequency characteristics appear. Figure 5 The envelope demodulation result of the low resonance component of the 197th group of sub-vibration data provided in the embodiment of the present application is as follows: Figure 5 As shown in the figure, the fault frequency characteristic is 47.2Hz, so it is determined that the inner race is faulty.

[0116] In summary, the vibration data is divided into multiple groups of sub-vibration data; the optimal decomposition parameters are determined based on the first group of sub-vibration data; the optimal decomposition parameters are used to obtain the low-resonance components corresponding to each group of sub-vibration data. Low-resonance components often contain characteristic information related to faults, which can be used to extract fault characteristic frequencies at an early stage. Based on the low-resonance components, the presence of a fault in the vehicle's powertrain can be determined, thus improving the timeliness of fault warnings. Furthermore, different decomposition parameters will result in different low-resonance components obtained from each group of sub-vibration data, necessitating the identification of appropriate decomposition parameters. The optimal decomposition parameters are determined based on the first group of sub-vibration data, and the low-resonance components can then be accurately obtained based on the optimal decomposition parameters, further improving the timeliness of fault warnings.

[0117] In this embodiment, based on the above embodiment, the formula for calculating the fitness function value is introduced, which is detailed as follows:

[0118] In this embodiment, the objective function is determined according to the Karush-Kuhn-Tucker (KKT) optimization method; and the fitness function value is calculated using the objective function.

[0119] In step S204 of the above embodiment, based on the optimal decomposition parameters, a wavelet transform method with adjustable quality factor can be used to obtain the low resonance components corresponding to each group of sub-vibration data. In the wavelet transform method with adjustable quality factor, different quality factors, i.e., decomposition parameters, will affect the low resonance components obtained. The wavelet transform method with adjustable quality factor controls the sub-band bandwidth after the low resonance component is decomposed by the quality factor. The low resonance component usually contains low-frequency information related to the fault, so it is important to correctly decompose the low resonance component. In step S203, in the process of updating the search position, the fitness function values of different search positions are calculated. The decomposition parameter corresponding to the search position with the smallest fitness function value is determined as the optimal decomposition parameter, so it is important to determine the most effective decomposition parameter.

[0120] Among them, the KKT optimization method is a widely used technology in optimization theory, which is used to solve nonlinear programming problems with constraints. The original formula is:

[0121]

[0122] Where, and Both represent variables, called KKT operators; The equality of is an equality constraint, which is 0 in this scenario, that is, ; The inequalities between are called inequality constraints. is the kurtosis function of the low resonance component, As the kurtosis constraint of each subband of the low resonance component, is the kurtosis function of each subband of the low resonance component, so The minimum value is 3, that is .

[0123] According to the duality theory, the final objective function is determined as:

[0124]

[0125] In this embodiment, , which reflects the double-layer optimization strategy. The outer layer seeks the minimum value, and the inner layer Find the maximum value under the conditions. Maximize the inner layer , in satisfying Under the conditions of Get the maximum value. This step is to balance the relationship between the objective function and the constraints while considering the constraints; the outer layer minimizes , which minimizes the value of x that maximizes the inner layer.

[0126] In this embodiment, the final objective function combines the kurtosis function of the low resonance component of the objective function and the kurtosis constraints of each subband of the low resonance component of the inequality constraint condition. Through a two-layer optimization method, the optimal decomposition parameters can be found by calculating the fitness function value during the continuous updating of the search position, providing data support for the correct decomposition of the low resonance component.

[0127] On the basis of the above embodiment, in this embodiment, if it is determined that the vehicle-mounted power system fails, a warning signal is sent to the operation and maintenance terminal, so that the operation and maintenance terminal issues a warning through the human-computer interaction interface.

[0128] In this embodiment, when the fault characteristic frequency appears and it is determined that the vehicle power system has a fault, the driver is warned through the human-computer interaction interface of the operation and maintenance terminal, and the fault situation can be synchronized to the driver in time, warning that the rolling bearing at the corresponding position may have a problem and recommending timely maintenance.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0130] Figure 6 This is a schematic diagram of the structure of the fault warning device of the vehicle power system provided in the embodiment of the present application. Figure 6 As shown, an embodiment of the present application also provides a fault warning device for a vehicle-mounted power system, including: a receiving module 601, a dividing module 602, a determining module 603, an acquiring module 604, a judging module 605 and a determining module 606.

[0131] The receiving module 601 is used to receive vibration data of the vehicle power system sent by the data terminal;

[0132] A division module 602 is used to divide the vibration data into multiple groups of sub-vibration data;

[0133] A determination module 603 is configured to determine an optimal decomposition parameter based on the first set of sub-vibration data;

[0134] An acquisition module 604 is configured to acquire low resonance components corresponding to each group of sub-vibration data according to the optimal decomposition parameters;

[0135] A judgment module 605 is used to judge whether a vehicle power system fails based on the low resonance component;

[0136] The determination module 606 is configured to issue an early warning if it is determined that a fault occurs in the vehicle power system.

[0137] In a possible implementation, the determining module 603 includes:

[0138] The first determining unit is configured to determine an initial search position and search parameters of the longicorn in the first group of sub-vibration data by using a longicorn whisker search algorithm.

[0139] An iterative unit is used to iteratively update the search position of the longicorn beetle starting from an initial search position of the longicorn beetle according to a search parameter until a search iteration stop condition is satisfied; wherein different search positions correspond to different decomposition parameters;

[0140] A recording unit, used to record the search position during the iterative update process;

[0141] A calculation unit, used to calculate the fitness function values of different search positions;

[0142] The second determining unit is configured to determine the decomposition parameter corresponding to the search position with the smallest fitness function value as the optimal decomposition parameter.

[0143] In one possible implementation, the search parameters include an initial orientation vector, an initial search perception distance, and an initial search step size; and the iteration unit includes:

[0144] The first determining subunit is used to determine the position of the longicorn's left antennae according to the initial search position, the initial orientation vector, and the initial search perception distance.

[0145] The second determining subunit is used to determine the position of the right antenna of the longicorn according to the initial search position, the initial orientation vector, and the initial search perception distance.

[0146] The first calculation subunit is used to calculate the fitness function value of the left tentacle position.

[0147] The second subunit is used to calculate the fitness function value of the right tentacle position.

[0148] The third determining subunit is used to determine the search direction of the first updated search position according to the fitness function value of the left tentacle position and the fitness function value of the right tentacle position.

[0149] The fourth determining subunit is configured to determine a search perception distance for updating the search position for the first time according to the initial search perception distance.

[0150] The fifth determining subunit is configured to determine a search step length for updating the search position for the first time according to the initial search step length.

[0151] The sixth determining subunit is used to determine the first updated search position of the longicorn based on the initial search position, the search direction of the first updated search position, the search perception distance of the first updated search position, and the search step size of the first updated search position.

[0152] The seventh determination subunit is used to determine the next updated search position of the longhorn beetle according to the current search position, the search direction of the next updated search position, the search perception distance of the next updated search position and the search step size of the next updated search position during the iterative update of the longhorn beetle's search position, until the search iteration stop condition is met.

[0153] In a possible implementation, the fitness function value , is calculated as follows:

[0154]

[0155] Where, represents the fitness function value, represents the kurtosis function of the low resonance component, represents the kurtosis constraint of each subband of the low resonance component, represents the kurtosis function of each subband of the low resonance component, Represents an operator.

[0156] In a possible implementation, the acquisition module 604 is specifically configured to decompose each group of sub-vibration data according to the optimal decomposition parameter, and acquire a low resonance component corresponding to each group of sub-vibration data.

[0157] In a possible implementation, the determination module 605 includes:

[0158] An analysis unit, used for performing envelope demodulation analysis on the low resonance component to obtain an envelope demodulation result;

[0159] The judging unit is used to judge whether the envelope demodulation result contains a fault characteristic frequency.

[0160] The first determination unit is configured to determine that a fault occurs in the vehicle power system if the envelope demodulation result includes a fault characteristic frequency.

[0161] The second determination unit is configured to determine that no fault occurs in the vehicle power system if the envelope demodulation result does not include a fault characteristic frequency.

[0162] In one possible embodiment, the vehicle power system fault warning device further includes a sending module. The sending module is specifically configured to send a warning signal to an operation and maintenance terminal if a fault is determined in the vehicle power system, so that the operation and maintenance terminal issues a warning via a human-computer interaction interface.

[0163] For the description of the features in the embodiment corresponding to the fault warning device of the vehicle power system, please refer to the relevant description of the embodiment corresponding to the fault warning method of the vehicle power system, and no further details will be given here.

[0164] Figure 7This is a schematic diagram of the structure of the vehicle computing platform provided by this application. Figure 7 As shown, the vehicle-mounted computing platform provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the vehicle-mounted computing platform also includes a communication component 703. The processor 701, the memory 702, and the communication component 703 are connected via a bus.

[0165] During the specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that the at least one processor 701 executes the above-mentioned embodiment of the fault warning method for the vehicle power system.

[0166] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0167] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the application may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0168] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0169] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0170] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, wherein the computer program is configured to execute the steps of any of the above-mentioned embodiments of the fault warning method for the vehicle power system when running.

[0171] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0172] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned embodiments of the fault warning method for a vehicle-mounted power system are implemented.

[0173] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps in any of the above-mentioned embodiments of the fault warning method for the vehicle power system.

[0174] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0175] The above is a detailed introduction to the fault warning method, device and vehicle-mounted computing power platform of a vehicle-mounted power system provided by this application. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method of this application and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A fault warning method for a vehicle-mounted power system, characterized in that: include: Receive vibration data for the vehicle power system sent by the data terminal; dividing the vibration data into a plurality of groups of sub-vibration data; determining optimal decomposition parameters according to the first group of sub-vibration data; According to the optimal decomposition parameters, obtaining low resonance components corresponding to each group of sub-vibration data; determining, based on the low resonance component, whether a fault occurs in the vehicle power system; If it is determined that the vehicle-mounted power system fails, an early warning is issued.

2. The method according to claim 1, characterized in that Determining the optimal decomposition parameters based on the first group of sub-vibration data includes: Determine the initial search position and search parameters of the longicorn beetle of the first group of sub-vibration data by using the longicorn beetle whisker search algorithm; Starting from the initial search position of the longicorn, the search position of the longicorn is iteratively updated according to the search parameters until a search iteration stop condition is satisfied; wherein different search positions correspond to different decomposition parameters; Record the search position during the iterative update process; Calculate the fitness function values of different search positions; The decomposition parameter corresponding to the search position with the smallest fitness function value is determined as the optimal decomposition parameter.

3. The method according to claim 2, characterized in that The search parameters include an initial heading vector, an initial search perception distance, and an initial search step size; Accordingly, starting from the initial search position of the longicorn, the search position of the longicorn is iteratively updated according to the search parameters until the search iteration stop condition is met, including: Determining the position of the left antenna of the longicorn according to the initial search position, the initial orientation vector, and the initial search perception distance; Determining the position of the right antenna of the longicorn according to the initial search position, the initial orientation vector, and the initial search perception distance; Calculating the fitness function value of the left tentacle position; Calculating the fitness function value of the right tentacle position; determining a search direction for a first update of the search position according to the fitness function value of the left tentacle position and the fitness function value of the right tentacle position; Determining a search perception distance for a first updated search position based on the initial search perception distance; Determining a search step length for updating the search position for the first time according to the initial search step length; Determining a first updated search position of the longicorn according to the initial search position, the search direction of the first updated search position, the search perception distance of the first updated search position, and the search step size of the first updated search position; During the iterative update of the longhorn beetle's search position, the next updated search position of the longhorn beetle is determined based on the current search position, the search direction of the next updated search position, the search perception distance of the next updated search position, and the search step size of the next updated search position until the search iteration stop condition is met.

4. The method according to claim 3, characterized in that The calculation formula of the fitness function value is: Where, represents the fitness function value, represents the kurtosis function of the low resonance component, represents the kurtosis constraint of each subband of the low resonance component, represents the kurtosis function of each subband of the low resonance component, Represents an operator.

5. The method according to claim 1, wherein The step of obtaining the low resonance component corresponding to each group of sub-vibration data according to the optimal decomposition parameter includes: Each group of sub-vibration data is decomposed according to the optimal decomposition parameter to obtain a low resonance component corresponding to each group of sub-vibration data.

6. The method according to claim 1, characterized in that The determining, based on the low resonance component, whether a fault occurs in the vehicle-mounted power system includes: Performing envelope demodulation analysis on the low resonance component to obtain an envelope demodulation result; Determining whether the envelope demodulation result contains a fault characteristic frequency; If the envelope demodulation result contains a fault characteristic frequency, it is determined that the vehicle power system has a fault; If the envelope demodulation result does not include the fault characteristic frequency, it is determined that the vehicle power system has no fault.

7. The method according to any one of claims 1 to 6, characterized in that Also includes: If it is determined that the vehicle-mounted power system fails, a warning signal is sent to the operation and maintenance terminal, so that the operation and maintenance terminal issues a warning through a human-computer interaction interface.

8. A fault warning device for a vehicle-mounted power system, characterized in that: include: A receiving module, used to receive vibration data of the vehicle power system sent by the data terminal; a division module, configured to divide the vibration data into a plurality of groups of sub-vibration data; a determination module, configured to determine an optimal decomposition parameter based on the first group of sub-vibration data; an acquisition module, configured to acquire, based on the optimal decomposition parameters, low resonance components corresponding to each group of sub-vibration data; a judgment module, configured to judge whether a fault occurs in the vehicle power system based on the low resonance component; The determination module is used to issue an early warning if it is determined that the vehicle-mounted power system has a fault.

9. A vehicle-mounted computing platform, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the fault warning method for the vehicle power system as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the fault warning method for the vehicle-mounted power system according to any one of claims 1 to 7 are implemented.

Images