Armored vehicle engine fault identification system based on vibration characteristics

Abstract

The invention provides a system for recognizing faults of an armored vehicle engine based on vibration characteristics, and relates to the field of electric digital data processing, the system comprises a data acquisition module, a signal processing module, a characteristic analysis module and a fault detection module, the data acquisition module is used for acquiring vibration signals of a transmitter in a running state, and the signal processing module is used for processing the vibration signals; the signal processing module is used for cleaning the signals, the feature analysis module is used for extracting key features in the vibration signals and analyzing the key features, and the fault detection module judges faults existing in an engine based on feature analysis information; the system can judge the existing fault information according to the vibration information of the engine, can predict the fault which may occur in the future and the corresponding time, and makes a reasonable plan for the maintenance of the engine.

Description

Technical Field

[0001] The invention relates to the field of electrical digital data processing, and in particular to a system for identifying engine faults of armored vehicles based on vibration characteristics. Background Art

[0002] With the development of modern armored vehicle engine technology, its complexity and operating performance have been greatly improved. However, this also makes engine maintenance and fault diagnosis more difficult. Once an engine fails, it may not only cause vehicle performance to decline, but also have a serious impact on mission execution and personnel safety. Traditional engine fault diagnosis methods mainly rely on manual experience and regular maintenance. This method is not only inefficient, but also difficult to detect potential fault hazards in a timely manner. Therefore, how to quickly and accurately diagnose engine faults and predict their development trends has become an important research direction in the field of armored vehicle maintenance.

[0003] Now many fault detection systems have been developed. After a lot of searching and reference, it is found that the existing fault detection systems are such as the system disclosed in the publication number CN117009791B. These system methods generally include: dividing the flight conditions and constructing a granular condition set; extracting the engine signal feature data, generating a basic feature data set, and constructing a smoothing mark; obtaining the recognition precision factor, generating the demand constraint, and synchronously sending the demand constraint and the sub-network to the encryption unit for network optimization to complete the construction of the granular recognition sub-network; extracting the vibration characteristics, sound characteristics and temperature characteristic signals of the engine, and constructing an abnormal recognition database according to the extraction results; performing engine fault recognition through the granular recognition sub-network and the abnormal recognition database, and generating fault recognition results. However, this system only extracts features and then performs fault recognition, and can only detect some common faults, and at the same time, it cannot predict faults in advance. Summary of the invention

[0004] The purpose of the present invention is to propose a system for identifying engine faults of armored vehicles based on vibration characteristics in response to the existing deficiencies.

[0005] The present invention adopts the following technical solution:

[0006] A system for identifying engine faults of armored vehicles based on vibration characteristics, comprising a data acquisition module, a signal processing module, a characteristic analysis module and a fault detection module;

[0007] The data acquisition module is used to collect the vibration signal of the transmitter in the running state, the signal processing module is used to clean the signal, the feature analysis module is used to extract the key features in the vibration signal and analyze it, and the fault detection module determines the fault of the engine based on the feature analysis information;

[0008] The data acquisition module includes a vibration sensing unit, a data transmission unit and an environment monitoring unit. The vibration sensing unit is used to collect vibration data of the engine, the data transmission unit is used to output the collected data information, and the environment monitoring unit is used to monitor the environment data where the armored vehicle is located;

[0009] The signal processing module includes a signal filtering unit, a data cleaning unit and a frequency domain conversion unit, wherein the signal filtering unit is used to filter the signal, the data cleaning unit is used to delete redundant and abnormal data, and the frequency domain conversion unit is used to convert the time domain signal into a frequency domain signal;

[0010] The feature analysis module includes a feature extraction unit, a feature selection unit and a feature processing unit, wherein the feature extraction unit is used to extract feature information from the signal, the feature selection unit is used to select feature information for analysis, and the feature processing unit is used to calculate and process the feature information to obtain feature parameters;

[0011] The fault detection module includes a fault model storage unit, a comparison diagnosis unit and a trend prediction unit. The fault model storage unit is used to store vibration characteristic model information of engine faults, the comparison diagnosis unit is used to detect faults by comparing characteristic parameters with model information, and the trend prediction unit is used to predict possible future fault developments.

[0012] Furthermore, the comparative diagnosis unit includes a fault retrieval processor, a deep diagnosis processor and a fault output processor. The fault retrieval processor determines the suspected fault based on parameter type retrieval, the deep diagnosis processor is used to compare the characteristic parameter standard value of the suspected fault with the characteristic parameter and determine the existing fault, and the fault output processor is used to output fault information and corresponding data information.

[0013] Furthermore, the process of comparing and judging the fault by the deep diagnosis processor includes the following steps:

[0014] S1. Select a suspected fault;

[0015] S2. Based on the environmental data, the characteristic parameters are corrected according to the following formula:

[0016] Cp(i)=Cp′(i)·(1+λ 1 ·(TT 0 )+λ 2 ·(HH 0 ));

[0017] Where T represents the current temperature, H represents the current humidity, and T 0 Indicates standard temperature, H 0 represents standard humidity, λ 1is the temperature influence coefficient of the suspected fault, λ 2 is the humidity influence coefficient of the suspected fault, Cp'(i) represents the i-th characteristic parameter before correction, and Cp(i) represents the i-th characteristic parameter after correction;

[0018] S3. Calculate the suspected fault occurrence index Q according to the following formula:

[0019]

[0020] Where n is the number of characteristic parameters of the suspected fault, Sp(i) represents the standard value of the i-th characteristic parameter;

[0021] S4. When the occurrence index is greater than the judgment threshold, it is judged that there is a suspected fault;

[0022] S5. Repeat steps S1 to S4 until all suspected faults are analyzed.

[0023] Furthermore, the trend prediction unit includes a historical parameter register, a change screening processor and a time prediction processor. The historical parameter register is used to store characteristic parameters of different periods, the change screening processor is used to screen out characteristic parameters that conform to the change law and determine delayed faults, and the time prediction processor is used to predict the time when delayed faults occur.

[0024] Furthermore, the time prediction processor calculates the occurrence time t of the delayed fault according to the following formula:

[0025]

[0026] Where Cg(i) represents the change index of the i-th characteristic parameter of delayed fault, t 0 is the time interval between two adjacent storage points, n 1 The number of characteristic parameters included for delayed faults.

[0027] The beneficial effects achieved by the present invention are:

[0028] After extracting the features of the vibration signal, this system combines the features to obtain feature parameters, and determines the fault type based on the comparison of the feature parameters. Compared with directly identifying faults through extracted features, it can detect a wider range of faults. At the same time, it analyzes the feature parameters to determine the types of faults that will exist in the future and predict the time of occurrence. This can provide more targeted reference information for engine maintenance and reduce the probability of temporary failures.

[0029] To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and description and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the overall structural framework of the present invention;

[0031] Figure 2 This is a schematic diagram of the data acquisition module of the present invention;

[0032] Figure 3 This is a schematic diagram of the signal processing module of the present invention;

[0033] Figure 4 This is a schematic diagram of the characteristic analysis module of the present invention;

[0034] Figure 5 This is a schematic diagram of the fault detection module of the present invention;

[0035] Figure 6 This is a comparison chart of the fault prediction application and the actual time of the present invention. DETAILED DESCRIPTION

[0036] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual sizes. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0037] Embodiment 1.

[0038] This embodiment provides a system for identifying armored vehicle engine failure based on vibration characteristics. Figure 1 , including data acquisition module, signal processing module, feature analysis module and fault detection module.

[0039] The data acquisition module is used to collect the vibration signal of the transmitter in the running state, the signal processing module is used to clean the signal, the feature analysis module is used to extract the key features in the vibration signal and analyze it, and the fault detection module determines the fault of the engine based on the feature analysis information.

[0040] The data acquisition module includes a vibration sensing unit, a data transmission unit and an environmental monitoring unit. The vibration sensing unit is used to collect vibration data of the engine, the data transmission unit is used to output the collected data information, and the environmental monitoring unit is used to monitor the environmental data of the armored vehicle.

[0041] The signal processing module includes a signal filtering unit, a data cleaning unit and a frequency domain transformation unit. The signal filtering unit is used to filter the signal, the data cleaning unit is used to delete redundant and abnormal data, and the frequency domain transformation unit is used to transform the time domain signal into a frequency domain signal.

[0042] The feature analysis module includes a feature extraction unit, a feature selection unit and a feature processing unit. The feature extraction unit is used to extract feature information from the signal, the feature selection unit is used to select feature information for analysis, and the feature processing unit is used to calculate and process the feature information to obtain feature parameters.

[0043] The fault detection module includes a fault model storage unit, a comparison diagnosis unit and a trend prediction unit. The fault model storage unit is used to store vibration characteristic model information of engine faults, the comparison diagnosis unit is used to detect faults by comparing characteristic parameters with model information, and the trend prediction unit is used to predict possible future fault developments.

[0044] The comparative diagnosis unit includes a fault retrieval processor, a deep diagnosis processor and a fault output processor. The fault retrieval processor determines the suspected fault based on parameter type retrieval, the deep diagnosis processor is used to compare the characteristic parameter standard value of the suspected fault with the characteristic parameter and determine the existing fault, and the fault output processor is used to output fault information and corresponding data information.

[0045] The process of comparing and judging the fault by the deep diagnosis processor comprises the following steps:

[0046] S1. Select a suspected fault.

[0047] S2. Based on the environmental data, the characteristic parameters are corrected according to the following formula:

[0048] Cp(i)=Cp′(i)·(1+λ 1 ·(TT 0 )+λ 2 ·(HH 0 )).

[0049] Where T represents the current temperature, H represents the current humidity, and T 0 Indicates standard temperature, H 0 represents standard humidity, λ 1 is the temperature influence coefficient of the suspected fault, λ 2 is the humidity influence coefficient of the suspected fault, Cp'(i) represents the i-th characteristic parameter before correction, and Cp(i) represents the i-th characteristic parameter after correction.

[0050] S3. Calculate the suspected fault occurrence index Q according to the following formula:

[0051]

[0052] Wherein, n is the number of the suspected fault characteristic parameters, and Sp(i) represents the standard value of the i-th characteristic parameter.

[0053] S4. When the occurrence index is greater than the judgment threshold, it is determined that there is a suspected fault.

[0054] S5. Repeat steps S1 to S4 until all suspected faults are analyzed.

[0055] The trend prediction unit includes a historical parameter register, a change screening processor and a time prediction processor. The historical parameter register is used to store characteristic parameters of different periods. The change screening processor is used to screen out characteristic parameters that conform to the change law and determine delayed faults. The time prediction processor is used to predict the time when delayed faults occur.

[0056] The time prediction processor calculates the occurrence time t of the delayed fault according to the following formula:

[0057]

[0058] Where Cg(i) represents the change index of the i-th characteristic parameter of delayed fault, t 0 is the time interval between two adjacent storage points, n 1 The number of characteristic parameters included for delayed faults.

[0059] Embodiment 2.

[0060] This embodiment includes all the contents of the first embodiment, and provides a system for identifying engine faults of armored vehicles based on vibration characteristics, including a data acquisition module, a signal processing module, a feature analysis module and a fault detection module.

[0061] The data acquisition module is used to collect the vibration signal of the transmitter in the running state, the signal processing module is used to clean the signal, the feature analysis module is used to extract the key features in the vibration signal and analyze it, and the fault detection module determines the fault of the engine based on the feature analysis information.

[0062] Combination Figure 2 The data acquisition module includes a vibration sensing unit, a data transmission unit and an environmental monitoring unit. The vibration sensing unit is used to collect vibration data of the engine, the data transmission unit is used to output the collected data information, and the environmental monitoring unit is used to monitor the environmental data of the armored vehicle.

[0063] Combination Figure 3 The signal processing module includes a signal filtering unit, a data cleaning unit and a frequency domain transformation unit. The signal filtering unit is used to filter the signal, the data cleaning unit is used to delete redundant and abnormal data, and the frequency domain transformation unit is used to transform the time domain signal into a frequency domain signal.

[0064] Combination Figure 4 The feature analysis module includes a feature extraction unit, a feature selection unit and a feature processing unit. The feature extraction unit is used to extract feature information from the signal, the feature selection unit is used to select feature information for analysis, and the feature processing unit is used to calculate and process the feature information to obtain feature parameters.

[0065] Combination Figure 5 The fault detection module includes a fault model storage unit, a comparison diagnosis unit and a trend prediction unit. The fault model storage unit is used to store the vibration characteristic model information of the engine fault. The comparison diagnosis unit is used to detect the fault by comparing the characteristic parameters with the model information. The trend prediction unit is used to predict the possible development of the fault in the future.

[0066] The vibration sensing unit includes a vibration detection processor, a threshold analysis processor and a reference information register. The vibration detection processor is used to collect vibration information, the threshold analysis processor is used to analyze the vibration information to determine whether the engine is working, and the reference information register is used to store vibration data when the engine is not working.

[0067] The data transmission processor unit includes a signal conversion processor, a vibration transmission processor and an environment transmission processor. The signal conversion processor is used to convert an analog signal into a digital signal. The vibration transmission processor is used to transmit the vibration digital signal to the signal processing module. The environment transmission processor is used to transmit the collected environment data to the fault detection module.

[0068] The environmental monitoring unit includes a temperature detection processor, a humidity detection processor and a detection control processor. The temperature detection processor is used to monitor temperature information, the humidity detection processor is used to detect humidity information, and the monitoring control processor is used to control the temperature and humidity detection switches.

[0069] The signal filtering unit includes a signal subtraction processor, a low-pass filter processor and a high-pass filter processor. The signal subtraction processor is used to subtract the vibration signal when the engine is working from the vibration signal when the engine is not working to obtain a pure vibration signal. The low-pass filter processor is used to filter the high-frequency signal in the pure vibration signal. The high-pass filter processor is used to filter the low-frequency signal in the pure vibration signal.

[0070] The data cleaning unit includes an anomaly detection processor, a data denoising processor and a redundancy removal processor. The anomaly detection processor is used to detect and clean the abnormal part of the signal, the data denoising processor is used to remove noise in the signal, and the redundancy removal processor is used to remove redundant information in the signal.

[0071] The frequency domain transformation unit includes a fast transformation processor, a short-time transformation processor and an envelope mediation processor. The fast transformation processor is used to perform frequency domain transformation on the signal when the engine is working stably to obtain spectrum information. The short-time transformation processor is used to slice the signal when the engine is just started and then perform frequency domain transformation to obtain time-frequency change information. The envelope mediation processor is used to obtain the envelope curve of the spectrum information.

[0072] The feature extraction unit includes a feature item register, a parsing and extraction processor, and a feature data register. The feature item register is used to store annotation information of the feature item. The parsing and extraction processor is used to parse the annotation information and read the corresponding feature data from the signal. The feature data register is used to save the feature data of each feature item.

[0073] The feature selection unit includes a feature combination processor, a conventional comparison processor and a combination output processor. The feature combination processor is used to combine different feature items to obtain a feature group. The conventional comparison processor is used to compare the feature group data with the conventional data and filter out consistent feature groups. The combination output processor is used to send the remaining feature group data to the feature processing unit.

[0074] The feature processing unit includes a combination recognition processor, a parameter calculation processor and a data guidance processor. The combination recognition processor is used to identify the type of feature items in the feature group. The parameter calculation processor is used to process the data in the feature group to obtain feature parameters. The data guidance processor guides the data in the feature group to the corresponding parameter calculation processor based on the recognized type.

[0075] Different parameter calculation processors are provided with different data processing formulas.

[0076] The fault model storage unit includes a fault information register, a standard parameter register and an environmental impact register. The fault information register is used to store fault type information, the standard parameter register is used to store the standard value of the characteristic parameter of each fault type, and the environmental impact register is used to store the influence relationship of the environmental item on each fault type.

[0077] The comparative diagnosis unit includes a fault retrieval processor, a deep diagnosis processor and a fault output processor. The fault retrieval processor determines the suspected fault based on parameter type retrieval, the deep diagnosis processor is used to compare the characteristic parameter standard value of the suspected fault with the characteristic parameter and determine the existing fault, and the fault output processor is used to output fault information and corresponding data information.

[0078] The set consisting of the characteristic parameter types output by the characteristic analysis module is set to B, and the set consisting of the characteristic parameter types included in the fault type is set to A. When set B includes set A, the corresponding fault type is a suspected fault.

[0079] The process of comparing and judging the fault by the deep diagnosis processor comprises the following steps:

[0080] S1. Select a suspected fault.

[0081] S2. Based on the environmental data, the characteristic parameters are corrected according to the following formula:

[0082] Cp(i)=Cp′(i)·(1+λ 1 ·(TT 0 )+λ 2 ·(HH 0 )).

[0083] Where T represents the current temperature, H represents the current humidity, and T 0 Indicates standard temperature, H 0 represents standard humidity, λ 1 is the temperature influence coefficient of the suspected fault, λ 2 is the humidity influence coefficient of the suspected fault, Cp'(i) represents the i-th characteristic parameter before correction, and Cp(i) represents the i-th characteristic parameter after correction.

[0084] S3. Calculate the suspected fault occurrence index Q according to the following formula:

[0085]

[0086] Wherein, n is the number of the suspected fault characteristic parameters, and Sp(i) represents the standard value of the i-th characteristic parameter.

[0087] S4. When the occurrence index is greater than the judgment threshold, it is determined that there is a suspected fault.

[0088] S5. Repeat steps S1 to S4 until all suspected faults are analyzed.

[0089] The trend prediction unit includes a historical parameter register, a change screening processor and a time prediction processor. The historical parameter register is used to store characteristic parameters of different periods. The change screening processor is used to screen out characteristic parameters that conform to the change law and determine delayed faults. The time prediction processor is used to predict the time when delayed faults occur.

[0090] Storage points are set in the historical parameter register, each storage point corresponds to a period, the time intervals between adjacent storage points are the same, and each type of characteristic parameter stores a value in each storage point.

[0091] The screening process of the change screening processor includes the following steps:

[0092] S21. Select a characteristic parameter and obtain the values ​​of the most recent m storage points.

[0093] S22. Calculate the variation index Cg of the characteristic parameter according to the following formula:

[0094]

[0095] Wherein, Vp(i) represents the characteristic parameter value of the i-th storage point.

[0096] S23. Mark the characteristic parameters whose absolute values ​​of the change index are greater than the prediction threshold.

[0097] S24, repeating steps S21 to S23 to count the characteristic parameters of the existence mark.

[0098] S25. Set the faults whose characteristic parameters are all marked as delayed faults.

[0099] The time prediction processor calculates the occurrence time t of the delayed fault according to the following formula:

[0100]

[0101] Where Cg(i) represents the change index of the i-th characteristic parameter of delayed fault, t 0 is the time interval between two adjacent storage points, n 1 The number of characteristic parameters included for delayed faults.

[0102] The i appearing in the above text is an ordinal number representing a sequence number and has no actual meaning.

[0103] Some of the code for this system is described below:

[0104]

[0105]

[0106]

[0107] The system is now used to predict engine failures. Without performing targeted maintenance on the engine, the actual time of the failure is compared with the predicted time, and the results are Figure 6 . .

[0108] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A system for identifying engine failures of armored vehicles based on vibration characteristics, characterized in that: It includes data acquisition module, signal processing module, feature analysis module and fault detection module; The data acquisition module is used to collect the vibration signal of the transmitter in the running state, the signal processing module is used to clean the signal, the feature analysis module is used to extract the key features in the vibration signal and analyze it, and the fault detection module determines the fault of the engine based on the feature analysis information; The data acquisition module includes a vibration sensing unit, a data transmission unit and an environment monitoring unit. The vibration sensing unit is used to collect vibration data of the engine, the data transmission unit is used to output the collected data information, and the environment monitoring unit is used to monitor the environment data where the armored vehicle is located; The signal processing module includes a signal filtering unit, a data cleaning unit and a frequency domain conversion unit, wherein the signal filtering unit is used to filter the signal, the data cleaning unit is used to delete redundant and abnormal data, and the frequency domain conversion unit is used to convert the time domain signal into a frequency domain signal; The feature analysis module includes a feature extraction unit, a feature selection unit and a feature processing unit, wherein the feature extraction unit is used to extract feature information from the signal, the feature selection unit is used to select feature information for analysis, and the feature processing unit is used to calculate and process the feature information to obtain feature parameters; The fault detection module includes a fault model storage unit, a comparison diagnosis unit and a trend prediction unit. The fault model storage unit is used to store vibration characteristic model information of engine faults, the comparison diagnosis unit is used to detect faults by comparing characteristic parameters with model information, and the trend prediction unit is used to predict possible future fault developments.

2. A system for identifying engine failure of an armored vehicle based on vibration characteristics as claimed in claim 1, characterized in that: The comparative diagnosis unit includes a fault retrieval processor, a deep diagnosis processor and a fault output processor. The fault retrieval processor determines the suspected fault based on parameter type retrieval, the deep diagnosis processor is used to compare the characteristic parameter standard value of the suspected fault with the characteristic parameter and determine the existing fault, and the fault output processor is used to output fault information and corresponding data information.

3. A system for identifying engine failure of an armored vehicle based on vibration characteristics as claimed in claim 2, characterized in that: The process of comparing and judging the fault by the deep diagnosis processor comprises the following steps: S1. Select a suspected fault; S2. Based on the environmental data, the characteristic parameters are corrected according to the following formula: Cp(i)=Cp′(i)·(1+λ1·(T-T0)+λ2·(H-H0)); Wherein, T represents the current temperature, H represents the current humidity, T0 represents the standard temperature, H0 represents the standard humidity, λ1 represents the temperature influence coefficient of the suspected fault, λ2 represents the humidity influence coefficient of the suspected fault, Cp'(i) represents the i-th characteristic parameter before correction, and Cp(i) represents the i-th characteristic parameter after correction; S3. Calculate the suspected fault occurrence index Q according to the following formula: Where n is the number of characteristic parameters of the suspected fault, Sp(i) represents the standard value of the i-th characteristic parameter; S4. When the occurrence index is greater than the judgment threshold, it is judged that there is a suspected fault; S5. Repeat steps S1 to S4 until all suspected faults are analyzed.

4. A system for identifying engine failure of an armored vehicle based on vibration characteristics as claimed in claim 3, characterized in that: The trend prediction unit includes a historical parameter register, a change screening processor and a time prediction processor. The historical parameter register is used to store characteristic parameters of different periods. The change screening processor is used to screen out characteristic parameters that conform to the change law and determine delayed faults. The time prediction processor is used to predict the time when delayed faults occur.

5. A system for identifying engine failure of an armored vehicle based on vibration characteristics as claimed in claim 4, characterized in that: The time prediction processor calculates the occurrence time t of the delayed fault according to the following formula: Wherein, Cg(i) represents the change index of the i-th characteristic parameter of the delay fault, t0 is the time interval between two adjacent storage points, and n1 is the number of characteristic parameters contained in the delay fault.

Images