Method, device and equipment for monitoring state of diesel engine injector for vehicle and storage medium

Abstract

The application discloses a kind of vehicle diesel engine injector state monitoring method, device, equipment and storage medium, the method obtains the sensitivity characteristic value corresponding to different sound sources by sensor in diesel engine cylinder, carries out sensitivity analysis of in-cylinder emission source according to sensitivity characteristic value, obtains sensitivity analysis data;From sensitivity analysis data, obtain the sampling sequence of preset sampling length, filter processing is carried out to sampling sequence, and the acoustic emission signal and instantaneous speed signal that meet the screening requirement are extracted;According to acoustic emission signal and instantaneous speed signal, the state of diesel engine injector is fault diagnosed, and obtains fault positioning result;Can be completed by acoustic emission technology and instantaneous speed method, the detection of the clogging state of vehicle diesel engine injector is guaranteed, the injector state monitoring precision is improved, the accuracy of fault diagnosis and health assessment is improved, the speed and efficiency of vehicle diesel engine injector state monitoring are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil extraction machine state monitoring, and particularly relates to a diesel engine injector state monitoring method, device, equipment and storage medium. BACKGROUND

[0002] When the diesel engine starts at low temperature, the injector is blocked due to the high viscosity of diesel oil, self-wear of the injector and other reasons, and the engine is difficult to start. However, it is difficult to determine the fault cause after the fault occurs, and the fault cause can only be determined by disassembling the cylinder cover and performing injector pump bench test.

[0003] The diesel engine is the power source of various machines, and its reliability directly affects the economy and reliability of related machines and systems. Especially, the marine diesel engine is the heart of the vehicle. If the vehicle fails during operation and is not repaired in time, it may cause economic loss, or even cause serious economic loss or even endanger the life safety of the driver and passenger. Therefore, the reliability requirement of the diesel engine for vehicles is higher.

[0004] The existing solution is to obtain the rail pressure drop value when the engine switches the cylinder; and determine whether the injector is blocked by judging whether the rail pressure drop value is greater than the preset pressure drop value. However, the rail pressure drop is caused by multiple factors, and is not necessarily caused by abnormal state of the injector. The state monitoring precision of the injector is low, and the accuracy of fault diagnosis and health assessment is low. SUMMARY

[0005] The main purpose of the present application is to provide a diesel engine injector state monitoring method, device, equipment and storage medium, which aims to solve the technical problems of low precision of the injector state monitoring, low accuracy of fault diagnosis and health assessment, and low reliability of the oil extraction engine in the prior art.

[0006] In a first aspect, the present application provides a diesel engine injector state monitoring method, which comprises the following steps:

[0007] Obtain the sensitivity characteristic value corresponding to different sound sources through the sensor in the diesel engine cylinder, and perform sensitivity analysis on the emission source in the cylinder according to the sensitivity characteristic value to obtain sensitivity analysis data;

[0008] Obtain the sampling sequence of the preset sampling length from the sensitivity analysis data, filter the sampling sequence, and extract the acoustic emission signal and the instantaneous speed signal meeting the screening requirements;

[0009] According to the acoustic emission signal and the instantaneous speed signal, the state of the diesel engine injector is diagnosed to obtain the fault positioning result.

[0010] Optionally, the sensitivity characteristic values corresponding to different sound sources are obtained by the sensor in the cylinder of the diesel engine, and sensitivity analysis of the sound emission source in the cylinder is performed according to the sensitivity characteristic values to obtain sensitivity analysis data, including:

[0011] The attenuation amount of the point energy with respect to the sound emission source corresponding to different sound sources is obtained by the sensor in the cylinder of the diesel engine, and the attenuation amount is taken as the sensitivity characteristic value.

[0012] The sensitivity analysis of the sound emission source in the cylinder is performed according to the sensitivity characteristic values by using an amplifier to obtain sensitivity analysis data.

[0013] Optionally, the attenuation amount of the point energy with respect to the sound emission source corresponding to different sound sources is obtained by the sensor in the cylinder of the diesel engine, and the attenuation amount is taken as the sensitivity characteristic value, including:

[0014] The corresponding relationship between the different point energies and the attenuation factors and the relative distances corresponding to different sound sources is obtained by the sensor in the cylinder of the diesel engine.

[0015] The attenuation amount of the different point energies with respect to the sound emission source is obtained according to the corresponding relationship by the following formula, and the attenuation amount is taken as the sensitivity characteristic value:

[0016]

[0017] kl = lnW0 - lnW(l)

[0018] Wherein, kl is the point sensitivity characteristic value, k is the attenuation factor, l is the distance between the point and the sound emission source, v(t) is the sound emission signal of the point, W is the sound emission signal energy from P0 to P t , W0 is the sound emission energy of the initial point, and W(l) is the sound emission energy of the calculation point.

[0019] Optionally, the sensitivity analysis of the sound emission source in the cylinder is performed according to the sensitivity characteristic values by using an amplifier to obtain sensitivity analysis data, including:

[0020] The gain of the collection signal corresponding to the sensitivity characteristic value collected by the sensor in the cylinder of the diesel engine is obtained by using an amplifier to obtain a gain signal.

[0021] The nozzle blockage amount of the fuel injector of the diesel engine is monitored in real time, and when the nozzle blockage amount is in a target blockage amount range, a target gain signal corresponding to the target blockage amount range is obtained.

[0022] The target gain signal is subjected to sensitivity analysis to obtain sensitivity analysis data of each point to each sound emission source.

[0023] Optionally, the method further comprises: obtaining a sampling sequence with a preset sampling length from the sensitivity analysis data; filtering the sampling sequence; and extracting acoustic emission signals and instantaneous speed signals that meet screening requirements.

[0024] According to a preset sampling length, a preset sampling point number, and a preset sampling rate, sampling data that meets a preset working cycle time is collected from the sensitivity analysis data; the sampling data is subjected to cycle averaging to obtain a sampling sequence.

[0025] A transfer function of a filter is obtained, and the sampling sequence is filtered according to the transfer function to obtain a filtering result.

[0026] The filtering result is converted from a time domain to an angle domain to obtain angle domain data, and acoustic emission signals and instantaneous speed signals are extracted from the angle domain data according to a preset crank angle value range.

[0027] Optionally, the method further comprises: diagnosing a state of a diesel engine injector according to the acoustic emission signals and the instantaneous speed signals to obtain a fault positioning result.

[0028] Sample data measured in the past is searched from a historical database, a fault feature vector is extracted from the acoustic emission signals, and the fault feature vector and the sample data are combined into a feature vector group.

[0029] The feature vector group is introduced into a preset membership matrix, and an evaluation function value of a cluster center of all groups in the acoustic emission signals is calculated.

[0030] When the evaluation function value is a minimum value or is lower than a preset function value threshold, a new preset membership matrix is used to calculate the evaluation function value of each cluster center.

[0031] When the evaluation function value is not a minimum value and is not lower than the preset function value threshold, a cluster result of a current cluster center is taken as a fault feature parameter.

[0032] A target instantaneous speed signal corresponding to the fault feature parameter is obtained from the instantaneous speed signals, a kurtosis maximum peak of the target instantaneous speed signal is determined, and the fault positioning result is determined according to the kurtosis maximum peak.

[0033] Optionally, the method further comprises: introducing the feature vector group into a preset membership matrix, and calculating an evaluation function value of a cluster center of all groups in the acoustic emission signals.

[0034] The feature vector group is introduced into a preset membership matrix, and an evaluation function value of a cluster center of all groups in the acoustic emission signals is calculated by the following formula.

[0035]

[0036] wherein J(U,V) is the evaluation function value, U is the membership matrix, V is the cluster center, c is the classification category, and n is the data sample size, is the optimal solution of clustering, is the minimum distance from the target to the cluster center.

[0037] The second aspect, to achieve the above object, the present application also proposes a diesel engine injector state monitoring device for vehicle, the diesel engine injector state monitoring device for vehicle includes:

[0038] The sensitivity analysis module is configured to obtain sensitivity characteristic values corresponding to different sound sources through sensors in the cylinder of the diesel engine, perform sensitivity analysis on the emission sources in the cylinder based on the sensitivity characteristic values, and obtain sensitivity analysis data.

[0039] The signal extraction module is configured to obtain a sampling sequence with a preset sampling length from the sensitivity analysis data, perform filtering processing on the sampling sequence, and extract acoustic emission signals and instantaneous speed signals that meet the screening requirements.

[0040] The fault diagnosis module is configured to perform fault diagnosis on the state of the diesel engine injector based on the acoustic emission signals and the instantaneous speed signals, and obtain a fault positioning result.

[0041] The third aspect, to achieve the above object, the present application also proposes a diesel engine injector state monitoring device for vehicle, the diesel engine injector state monitoring device for vehicle includes: a memory, a processor, and a diesel engine injector state monitoring program for vehicle stored on the memory and executable on the processor, the diesel engine injector state monitoring program for vehicle is configured to implement the steps of the diesel engine injector state monitoring method as described above.

[0042] The fourth aspect, to achieve the above object, the present application also proposes a storage medium, the storage medium has a diesel engine injector state monitoring program for vehicle stored thereon, the diesel engine injector state monitoring program for vehicle is executed by a processor to implement the steps of the diesel engine injector state monitoring method as described above.

[0043] The method for monitoring the state of the diesel engine injector for vehicles provided in the application obtains the sensitivity characteristic values corresponding to different sound sources through the sensor in the cylinder of the diesel engine, performs sensitivity analysis on the emission source in the cylinder according to the sensitivity characteristic values, and obtains the sensitivity analysis data; the sampling sequence of the preset sampling length is obtained from the sensitivity analysis data, the acoustic emission signal and the instantaneous speed signal meeting the screening requirements are extracted by performing filtering processing on the sampling sequence; the state of the diesel engine injector is diagnosed according to the acoustic emission signal and the instantaneous speed signal, and the fault positioning result is obtained; the acoustic emission technology and the instantaneous speed method are used to complete the detection of the blockage state of the diesel engine injector for vehicles, the comprehensive performance and the reliability of the diesel engine are improved, the overall technical level of the diesel engine for vehicles is improved, the wear of each cylinder of the diesel engine can be accurately identified, the state monitoring precision of the diesel engine injector is ensured, the accuracy of the fault diagnosis and the health evaluation is improved, and the speed and the efficiency of the state monitoring of the diesel engine injector for vehicles are improved. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The device structure schematic diagram of the hardware running environment involved in the embodiment scheme of the application;

[0045] Figure 2 The flowchart of the first embodiment of the method for monitoring the state of the diesel engine injector for vehicles;

[0046] Figure 3 The flowchart of the second embodiment of the method for monitoring the state of the diesel engine injector for vehicles;

[0047] Figure 4 The flowchart of the third embodiment of the method for monitoring the state of the diesel engine injector for vehicles;

[0048] Figure 5 The flowchart of the fourth embodiment of the method for monitoring the state of the diesel engine injector for vehicles;

[0049] Figure 6 The flowchart of the fifth embodiment of the method for monitoring the state of the diesel engine injector for vehicles;

[0050] Figure 7 The data mining schematic diagram based on the fuzzy C algorithm in the method for monitoring the state of the diesel engine injector for vehicles;

[0051] Figure 8 The function module diagram of the first embodiment of the device for monitoring the state of the diesel engine injector for vehicles.

[0052] The implementation, the functional features and the advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are merely illustrative of the present application and should not be used to limit the present application in any manner.

[0054] The solution of the embodiment of the present application is mainly: obtaining sensitivity characteristic values corresponding to different sound sources through a sensor in the cylinder of the diesel engine, performing sensitivity analysis on the emission source in the cylinder according to the sensitivity characteristic values to obtain sensitivity analysis data; obtaining a sampling sequence of a preset sampling length from the sensitivity analysis data, performing filtering processing on the sampling sequence, and extracting acoustic emission signals and instantaneous speed signals that meet the screening requirements; performing fault diagnosis on the state of the diesel engine injector according to the acoustic emission signals and the instantaneous speed signals to obtain a fault positioning result; the blockage state of the diesel engine injector for vehicles can be detected through acoustic emission technology and instantaneous speed method, the comprehensive performance and reliability of the diesel engine are improved, the overall technical level of the diesel engine for vehicles is improved, the wear of each cylinder of the diesel engine can be accurately identified, the accuracy of the injector state monitoring is ensured, the accuracy of the fault diagnosis and health evaluation is improved, the speed and efficiency of the injector state monitoring of the diesel engine for vehicles are improved, the reliability of the diesel engine is affected, and the technical problems of low accuracy of the injector state monitoring, low accuracy of the fault diagnosis and health evaluation, and affected reliability of the diesel engine in the prior art are solved.

[0055] Reference Figure 1 , Figure 1 The device structure diagram of the hardware running environment involved in the embodiment of the present application is shown.

[0056] As Figure 1 shown, the device can include a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 can include a display screen (Display) and an input unit such as a keyboard (Keyboard). The optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a Wi-Fi interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (Non-Volatile Memory), such as a magnetic disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0057] Those skilled in the art can understand that Figure 1 the device structure shown in the foregoing embodiments does not constitute a limitation on the device, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements.

[0058] As Figure 1As shown, the memory 1005 as a storage medium can include an operating device, a network communication module, a user interface module and a diesel engine injector state monitoring program.

[0059] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and performs the following operations:

[0060] Obtain the sensitivity characteristic value corresponding to different sound sources through the sensor in the cylinder of the diesel engine, and perform sensitivity analysis on the in-cylinder emission source according to the sensitivity characteristic value to obtain sensitivity analysis data;

[0061] Obtain a sampling sequence of a preset sampling length from the sensitivity analysis data, filter the sampling sequence, and extract acoustic emission signals and instantaneous speed signals that meet the screening requirements;

[0062] Diagnose the state of the diesel engine injector according to the acoustic emission signals and the instantaneous speed signals to obtain a fault positioning result.

[0063] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and performs the following operations:

[0064] Obtain the attenuation amount of the measuring point energy relative to the acoustic emission source corresponding to different sound sources through the sensor in the cylinder of the diesel engine, and take the attenuation amount as the sensitivity characteristic value;

[0065] Perform sensitivity analysis on the in-cylinder emission source according to the sensitivity characteristic value by using an amplifier to obtain sensitivity analysis data.

[0066] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and performs the following operations:

[0067] Obtain the corresponding relationship between different measuring point energies and attenuation factors and relative distances corresponding to different sound sources through the sensor in the cylinder of the diesel engine;

[0068] According to the corresponding relationship, the attenuation amount of the measuring point energy relative to the acoustic emission source is obtained by the following formula, and the attenuation amount is taken as the sensitivity characteristic value:

[0069]

[0070] kl=lnW0-lnW(l)

[0071] Wherein, kl is the measuring point sensitivity characteristic value, k is the attenuation factor, l is the distance between the measuring point and the acoustic emission source, v(t) is the acoustic emission signal of the measuring point, W is the acoustic emission signal from P0 point to P tThe acoustic emission signal energy of the initial point is W0, and the acoustic emission energy of the calculation point is W(l).

[0072] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0073] The gain of the acquisition signal corresponding to the sensitive characteristic value collected by the sensor in the diesel engine cylinder is obtained by using an amplifier, and a gain signal is obtained.

[0074] The nozzle blockage amount of the diesel engine injector is monitored in real time, and when the nozzle blockage amount is in the target blockage amount range, a target gain signal corresponding to the target blockage amount range is obtained.

[0075] The target gain signal is subjected to sensitivity analysis to obtain sensitivity analysis data of each measuring point to each acoustic emission source.

[0076] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0077] According to the preset sampling length, the preset sampling point number and the preset sampling rate, the sampling data conforming to the preset working cycle time are collected from the sensitivity analysis data, the sampling data are subjected to periodic averaging to obtain a sampling sequence;

[0078] The transfer function of the filter is obtained, and the sampling sequence is subjected to filtering processing according to the transfer function to obtain a filtering result;

[0079] The filtering result is converted from the time domain to the angle domain to obtain angle domain data, and the acoustic emission signal and the instantaneous speed signal are extracted from the angle domain data according to a preset crank angle value range.

[0080] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and also performs the following operations:

[0081] The measured sample data are searched from a historical database, and a fault feature vector is extracted from the acoustic emission signal, and the fault feature vector and the sample data are combined into a feature vector group;

[0082] The feature vector group is introduced into a preset membership matrix, and the evaluation function value of the cluster center of all groups in the acoustic emission signal is calculated.

[0083] When the evaluation function value is the minimum value or lower than the preset function value threshold, the evaluation function value of each cluster center is calculated using a new preset membership matrix.

[0084] When the evaluation function value is not the minimum value and is not lower than a preset function value threshold, taking the clustering result of the current clustering center as the fault feature parameter;

[0085] From the instantaneous speed signal, a target instantaneous speed signal corresponding to the fault feature parameter is obtained, a kurtosis maximum peak of the target instantaneous speed signal is determined, and the fault positioning result is determined according to the kurtosis maximum peak.

[0086] The device of the application calls the diesel engine injector state monitoring program stored in the memory 1005 through the processor 1001, and further performs the following operations:

[0087] The feature vector group is imported into a preset membership matrix, and the evaluation function value of the clustering center of all groups in the acoustic emission signal is calculated by the following formula:

[0088]

[0089] Wherein, J(U,V) is the evaluation function value, U is the membership matrix, V is the clustering center, c is the classification category, n is the data sample size, is the optimal solution of clustering, is the minimum distance from the target to the clustering center.

[0090] The embodiment obtains the sensitivity feature values corresponding to different sound sources through the sensor in the diesel engine cylinder, performs sensitivity analysis on the in-cylinder emission source according to the sensitivity feature values, and obtains sensitivity analysis data; a sampling sequence of a preset sampling length is obtained from the sensitivity analysis data, the sampling sequence is filtered, and the acoustic emission signal and the instantaneous speed signal meeting the screening requirements are extracted; the state of the diesel engine injector is diagnosed according to the acoustic emission signal and the instantaneous speed signal, and a fault positioning result is obtained; the diesel engine injector blockage state can be detected through the acoustic emission technology and the instantaneous speed method, the comprehensive performance and reliability of the diesel engine are improved, the overall technical level of the diesel engine is improved, the wear of each cylinder of the diesel engine can be accurately identified, the accuracy of the injector state monitoring is ensured, the accuracy of fault diagnosis and health evaluation is improved, and the speed and efficiency of the diesel engine injector state monitoring are improved.

[0091] Based on the above hardware structure, the diesel engine injector state monitoring method embodiment of the application is proposed.

[0092] Referring to Figure 2 , Figure 2 is a flowchart of the first embodiment of the diesel engine injector state monitoring method of the application.

[0093] In the first embodiment, the diesel engine injector state monitoring method comprises the following steps:

[0094] Step S10, obtain the sensitivity characteristic value corresponding to different sound sources through the sensor in the cylinder of the diesel engine, and perform sensitivity analysis on the in-cylinder emission source according to the sensitivity characteristic value to obtain sensitivity analysis data.

[0095] It should be noted that the sensitivity characteristic value corresponding to different sound sources can be obtained through the sensor in the cylinder of the diesel engine, and then the sensitivity analysis on the in-cylinder emission source is performed according to the sensitivity characteristic value to obtain the sensitivity analysis data.

[0096] It should be understood that the injector is a key component responsible for fuel injection in the common rail system, and its working state greatly affects the working performance of the diesel engine. Due to the complex structure and operating environment of the injector, it is prone to failure and causes economic loss. When the injector fails, it will affect the injection quantity, injection timing and injection law, thereby causing changes in the fuel pressure waveform in the high-pressure oil pipe. Since the fuel pressure in the system is directly related to the working state of the injector, the fuel pressure signal has obvious advantages in fault diagnosis and health assessment of the injector relative to other signals. However, there are many excitations that cause pressure fluctuations in the system. How to extract features from the signal components closely related to the injector failure is the key to reducing feature information redundancy and improving the accuracy of fault diagnosis and health assessment.

[0097] In a specific implementation, when the acoustic emission waves excited by the acoustic emission sources in the cylinder of the diesel engine propagate to the outer surface through the complex structure of the cylinder head, complex reflection, refraction, mode conversion and energy attenuation phenomena occur. The acoustic emission signals obtained by the sensor on the cylinder head have great changes relative to the original acoustic emission source signals, and the diagnosis effect is also different. Therefore, when applying acoustic emission technology to the monitoring and diagnosis process of the diesel engine, it is necessary to consider whether the acoustic emission source signal can be captured by the sensor or the signal-to-noise ratio of the captured signal is high, that is, it is necessary to study the sensitivity of the measuring point (sensor installation position) to different acoustic emission sources. The smaller the energy attenuation of the acoustic emission signal captured by the sensor relative to the energy of the acoustic emission source, the higher the sensitivity of the measuring point. The greater the attenuation, the lower the sensitivity of the measuring point. In order to ensure accurate identification of the wear of each cylinder by the acoustic emission signal, sensitivity analysis is needed.

[0098] Step S20, obtaining a sampling sequence of a preset sampling length from the sensitivity analysis data, and performing filtering processing on the sampling sequence to extract acoustic emission signals and instantaneous speed signals that meet the screening requirements.

[0099] It can be understood that a sampling sequence of a preset sampling length can be obtained from the sensitivity analysis data, and then the sampling sequence can be filtered to extract signals, i.e. acoustic emission signals and instantaneous speed signals, that meet the screening requirements.

[0100] Step S30, diagnosing the state of the diesel engine injector according to the acoustic emission signal and the instantaneous speed signal to obtain a fault positioning result.

[0101] It should be understood that the state of the diesel engine injector can be diagnosed according to the acoustic emission signal and the instantaneous speed signal, so as to obtain a fault positioning result of the corresponding fault.

[0102] The embodiment obtains the sensitivity characteristic values corresponding to different sound sources through the sensor in the diesel engine cylinder, performs sensitivity analysis on the emission source in the cylinder according to the sensitivity characteristic values, and obtains sensitivity analysis data; a sampling sequence of a preset sampling length is obtained from the sensitivity analysis data, the sampling sequence is filtered, and the acoustic emission signal and the instantaneous speed signal meeting the screening requirements are extracted; the state of the diesel engine injector is diagnosed according to the acoustic emission signal and the instantaneous speed signal to obtain a fault positioning result; the blockage state of the diesel engine injector for vehicles can be detected through the acoustic emission technology and the instantaneous speed method, the comprehensive performance and reliability of the diesel engine are improved, the overall technical level of the diesel engine for vehicles is improved, the wear of each cylinder of the diesel engine can be accurately identified, the accuracy of the injector state monitoring is ensured, the accuracy of fault diagnosis and health evaluation is improved, and the speed and efficiency of the injector state monitoring of the diesel engine for vehicles are improved.

[0103] Further, Figure 3 The flowchart of the second embodiment of the diesel engine injector state monitoring method for vehicles of the present application is shown in Figure 3 The second embodiment of the diesel engine injector state monitoring method for vehicles of the present application is proposed based on the first embodiment, and in the embodiment, the step S10 specifically includes the following steps:

[0104] Step S11, obtaining the attenuation amount of the measuring point energy relative to the acoustic emission source corresponding to different sound sources through the sensor in the diesel engine cylinder, and taking the attenuation amount as a sensitivity characteristic value.

[0105] It should be understood that the attenuation amount of the measuring point energy relative to the acoustic emission source corresponding to different sound sources can be obtained through the sensor in the diesel engine cylinder, and the attenuation amount is taken as a sensitivity characteristic value.

[0106] Further, the step S11 includes the following steps:

[0107] The corresponding relationship between different measuring point energies and attenuation factors and relative distances corresponding to different sound sources is obtained through the sensor in the diesel engine cylinder;

[0108] The attenuation amount of different measuring point energies relative to the acoustic emission source is obtained according to the corresponding relationship by the following formula, and the attenuation amount is taken as a sensitivity characteristic value:

[0109]

[0110] kl=lnW0-lnW(l)

[0111] Where kl is the sensitivity characteristic value of the measuring point, k is the attenuation factor, l is the distance between the measuring point and the acoustic emission source, v(t) is the acoustic emission signal at the measuring point, and W is the distance from point P0 to P... t The acoustic emission signal energy is W0, which is the acoustic emission energy at the initial point, and W(l) is the acoustic emission energy at the calculation point.

[0112] It should be understood that the above formula can represent the energy attenuation between the measuring point and the acoustic emission source. Since the attenuation factor k of different measuring points relative to the same acoustic emission source is different for a complex medium such as the cylinder head, the magnitude of energy attenuation at different measuring points is related to both the attenuation factor k and the distance x. The product of the two, kx, can be used as a parameter to measure the energy attenuation (measuring point sensitivity) between the measuring point and the acoustic emission source.

[0113] Therefore, kx can characterize the amount of energy attenuation at the measuring point relative to the acoustic emission source. A smaller kx value indicates less energy attenuation and higher sensitivity at the measuring point; a larger kx value indicates greater energy attenuation and lower sensitivity at the measuring point. By using sensors and acquisition equipment to obtain acoustic emission signals from the acoustic emission source and different measuring points, the kx value between different measuring points and the acoustic emission source can be calculated using the above formula, thus obtaining the sensitivity characteristics of each measuring point in the diesel engine cylinder head to the in-cylinder acoustic emission source.

[0114] Step S12: Use an amplifier to perform sensitivity analysis of the in-cylinder emission source based on the sensitivity characteristic values ​​to obtain sensitivity analysis data.

[0115] It is understandable that the sensitivity analysis data of the in-cylinder emission source can be obtained by using an amplifier based on the aforementioned sensitivity characteristic values.

[0116] This embodiment uses the above-described scheme to obtain the attenuation of the energy at the measuring point corresponding to different sound sources relative to the sound emission source through sensors inside the diesel engine cylinder. The attenuation is used as a sensitivity feature value. An amplifier is used to perform sensitivity analysis of the in-cylinder emission source based on the sensitivity feature value to obtain sensitivity analysis data. This allows for accurate identification of wear in each cylinder of the diesel engine through sensors, ensuring the accuracy of injector condition monitoring.

[0117] Furthermore, Figure 4 This is a flowchart illustrating the third embodiment of the method for monitoring the condition of fuel injectors in automotive diesel engines according to the present invention. Figure 4 As shown, based on the second embodiment, a third embodiment of the method for monitoring the condition of automotive diesel engine injectors of the present invention is proposed. In this embodiment, step S12 specifically includes the following steps:

[0118] Step S121, using an amplifier to gain the acquisition signal corresponding to the sensitive characteristic value collected by the sensor in the cylinder of the diesel engine, to obtain a gain signal.

[0119] It should be noted that the acquisition signal corresponding to the sensitive characteristic value collected by the sensor in the cylinder of the diesel engine can be gained by using an amplifier, and then the gain signal after gain can be obtained.

[0120] Step S122, real-time monitoring of the nozzle blockage amount of the fuel injector of the diesel engine, and when the nozzle blockage amount is in a target blockage amount range, a target gain signal corresponding to the target blockage amount range is obtained.

[0121] It should be understood that different combustion sections of different nozzle amounts correspond to different acoustic emission signals, and the nozzle blockage amount of the fuel injector of the diesel engine is monitored in real time, and then when the nozzle blockage amount is in a target blockage amount range, a target gain signal corresponding to the target blockage amount range can be obtained.

[0122] Step S123, sensitive analysis of the target gain signal, to obtain sensitive analysis data of each measuring point to each acoustic emission source.

[0123] It can be understood that the sensitive analysis of the target gain signal can obtain the sensitive analysis data of each measuring point to each acoustic emission source.

[0124] The above-mentioned scheme is used to gain the acquisition signal corresponding to the sensitive characteristic value collected by the sensor in the cylinder of the diesel engine by using an amplifier, to obtain a gain signal; the nozzle blockage amount of the fuel injector of the diesel engine is monitored in real time, and when the nozzle blockage amount is in a target blockage amount range, a target gain signal corresponding to the target blockage amount range is obtained; the sensitive analysis of the target gain signal obtains sensitive analysis data of each measuring point to each acoustic emission source, which can accurately identify the wear of each cylinder of the diesel engine through the sensor, and ensures the state monitoring precision of the fuel injector.

[0125] Further, Figure 5 The flowchart of the fourth embodiment of the method for monitoring the state of the diesel engine fuel injector of the vehicle is shown in Figure 5 The fourth embodiment of the method for monitoring the state of the diesel engine fuel injector of the vehicle is proposed based on the first embodiment, and in the embodiment, the step S20 specifically includes the following steps:

[0126] Step S21, according to the preset sampling length, the preset sampling point number and the preset sampling rate, the sampling data conforming to the preset working cycle time is collected from the sensitive analysis data, the sampling data is periodically averaged, and a sampling sequence is obtained.

[0127] It should be noted that by pre-setting the sampling length, the pre-set number of sampling points and the pre-set sampling rate, the sampling data conforming to the preset working cycle time can be collected from the sensitivity analysis data, and then the sampling data is periodically averaged to obtain the sampling sequence.

[0128] In a specific implementation, sampling: extracts a sampling sequence of a specific length from signals such as acoustic emission, top dead center and instantaneous speed, takes 240K sampling points, and when the sampling rate is 60KHz, the interception time is 4s, and when the diesel engine speed is 1500r / min, the sampling length is about 50 working cycles of the diesel engine. This process can be represented as:

[0129]

[0130] In the formula, x s (t) is the sequence after sampling, x(t) is the thermal δ(t-nT s ) electric signal before sampling, δ(t-nT s ) is the sampling pulse sequence; T s is the sampling time interval.

[0131] Working cycle time: 1 working cycle of the diesel engine is intercepted from each zero crossing of the top dead center signal every 2 revolutions to determine the sampling sequence number, and its working cycle time can be represented as:

[0132] T η =(j-i)T s

[0133] In the formula, T η is the working cycle time; j, i are the sampling sequence numbers separated by 2 top dead centers;

[0134] Periodic average: due to the characteristics of random factors such as fuel injection and non-continuous working cycle during the operation of the diesel engine, the instantaneous speed fluctuates. In order to improve the analysis reliability, the average value of the thermal electric signal is calculated with a proper number of working cycles. This process can be represented as:

[0135]

[0136] In the formula, (X i1 , X i2 ,...X im ) is the sampling sequence after the average of the i th working cycle; (X n1 , X n2 ,...X nm ) is the sampling sequence of the i+N-1 th working cycle; N is the periodic average number.

[0137] Step S22, obtaining a transfer function of the filter, and filtering the sampling sequence according to the transfer function to obtain a filtering result.

[0138] It can be understood that the transfer function of the filter is obtained, and then the sampling sequence is filtered according to the transfer function to obtain the corresponding filtering result.

[0139] In a specific implementation, the signal filtering: analyzing the thermoelectric signal and the operation characteristics of the diesel engine, and selecting a 6-order Butterworth IIR low-pass filter according to the actual filtering effect, and the transfer function of the filter is:

[0140]

[0141] In the formula, θ i =(zi-1)π / 2N(i=1,2,...,2N), Z is a complex variable of the digital filter; ω is a digital domain frequency; N is the number of transfer function roots; N1 is the nearest integer of N / 2, and the larger N is, the closer the passband and the stopband are to the ideal.

[0142] Step S23, converting the filtering result from the time domain to the angle domain to obtain angle domain data, and extracting the acoustic emission signal and the instantaneous speed signal from the angle domain data according to a preset crank angle value range.

[0143] It should be understood that the filtering result is converted from the time domain to the angle domain, and then the angle domain data is obtained, and then the corresponding data, i.e., the acoustic emission signal and the instantaneous speed signal, is extracted from the angle domain data according to the pre-set crank angle value range.

[0144] In a specific implementation, the waveform of the corresponding tooth on the flywheel obtained by the magneto speed sensor is an approximate sine wave, and the corresponding sampling time is the sampling time interval of the fixed angle (360° / Z, Z is the number of flywheel teeth) corresponding to one flywheel tooth. By capturing the start and end points of the sine wave, the fixed angle signal sequence index corresponding to one flywheel tooth can be obtained, and the corresponding points in the thermoelectric data sequence are selected to form a new thermoelectric data sequence. The data sequence length is interpolated to 720 points (determined according to the resolution of the angle), and the equal crank angle of the thermoelectric signal is completed, and the calculation formula is as follows:

[0145]

[0146] In the formula, a n+x is the crank angle corresponding to the nth+x sampling point; n is the ordinal number of the tooth where the sampling point is located; N is the number of flywheel teeth; p x is the point ordinal number in the nth tooth; j-i is the total number of sampling points in the nth tooth.

[0147] Feature signal extraction: extract the acoustic emission signal and instantaneous speed signal of 430-520°CA (crank angle) after the top dead center for analysis.

[0148] Correspondingly, the acoustic emission signal power feature extraction: in addition to selecting the acoustic emission signal in a certain crank angle for time domain analysis, the time domain waveform corresponding to a certain working process can also be transformed into the frequency domain for analysis. The area surrounded by the signal PSD spectrum amplitude and the frequency axis can represent the power of the signal. The signal power is the average of the signal energy in time, which can represent the average intensity of the acoustic emission excitation in the window.

[0149] The definition of signal power P is as follows:

[0150]

[0151] Where P is the power of the acoustic emission signal (V 2 ), which is also equal to the square of the RMS value of the time domain signal; b and a are the upper and lower limits of the frequency band (Hz) respectively; P(i) is the amplitude of the PSD spectrum (V 2 ·Hz -1 ); and Δf is the frequency interval (Hz).

[0152] In a specific implementation, the instantaneous speed feature value extraction can correspond the 6 peaks of the instantaneous speed curve to 6 cylinders according to the crank angle of the engine ignition, and calculate the kurtosis of the 6 peaks as the feature values of the 6 cylinders.

[0153] The embodiment extracts the sampling data conforming to the preset working cycle time from the sensitivity analysis data according to the preset sampling length, the preset sampling point number and the preset sampling rate, performs periodic averaging on the sampling data to obtain a sampling sequence, obtains a transfer function of a filter, performs filter processing on the sampling sequence according to the transfer function to obtain a filter result, converts the filter result from the time domain to the angle domain to obtain angle domain data, extracts acoustic emission signals and instantaneous speed signals from the angle domain data according to a preset crank angle value range, and completes the detection of the clogging state of the fuel injector of the diesel engine for vehicles through the acoustic emission technology and the instantaneous speed method, thereby improving the comprehensive performance and reliability of the diesel engine and improving the overall technical level of the diesel engine for vehicles.

[0154] Further, Figure 6 The flowchart of the fifth embodiment of the diesel engine for vehicles is shown in FIG. 5. Figure 6 The fifth embodiment of the diesel engine for vehicles is based on the first embodiment. In the embodiment, the step S30 specifically includes the following steps.

[0155] Step S31: Search for measured sample data from the historical database, extract fault feature vectors from the acoustic emission signals, and combine the fault feature vectors and the sample data into a feature vector group.

[0156] It should be noted that measured sample data can be retrieved from historical databases, and fault feature vectors can be extracted from the acoustic emission signals. Then, the fault feature vectors and the sample data can be combined into a feature vector group.

[0157] Step S32: Import the feature vector group into a preset membership matrix and calculate the evaluation function value of the cluster center of all groups in the acoustic emission signal.

[0158] It is understandable that the feature vector group is imported into a pre-set membership matrix, and then the evaluation function value of the cluster center of all groups in the acoustic emission signal is calculated.

[0159] Furthermore, step S32 specifically includes the following steps:

[0160] The feature vector group is imported into a preset membership matrix, and the evaluation function value of the cluster centers of all groups in the acoustic emission signal is calculated using the following formula:

[0161]

[0162] Where J(U,V) is the evaluation function value, U is the membership matrix, V is the cluster center, c is the classification category, and n is the data sample size. The optimal solution for clustering. The minimum distance from the target to the cluster center.

[0163] In specific implementations, such as Figure 7 As shown, Figure 7 This is a schematic diagram of data mining based on the fuzzy C algorithm in the fuel injector condition monitoring method for automotive diesel engines of the present invention. See [link / reference] Figure 7 By extracting fault feature vectors, combining sample data, and importing the membership matrix, cluster centers are calculated, and the centers of all groups are solved to determine the group to which various sample data belong, ultimately achieving the goal of automatically classifying sample data.

[0164] The basic process of data mining is as follows:

[0165] (1) Select a suitable signal to extract feature values; (2) Calculate the cluster center V; (3) Calculate the membership degree U = [u ji (4) Calculate the new cluster centers V = [v ji(5) find the objective function value, if the objective function is compared with the function after solving and iteration, if the difference is small, the algorithm ends, if the difference is large, it will return to the flow (3) to re-perform data mining.

[0166] If the evaluation function J(U, V) is less than a certain threshold, the algorithm is restarted, and a new matrix U is calculated, and finally, until the difference between the new clustering center and the last obtained clustering center is within the allowable error range.

[0167] Step S33, when the evaluation function value is the minimum value or lower than the preset function value threshold, the evaluation function value of each clustering center is calculated using the new preset membership matrix.

[0168] It should be understood that the evaluation function value can be determined by comparing the evaluation function value with the preset function value threshold, that is, when the evaluation function value is the minimum value or lower than the preset function value threshold, the evaluation function value of each clustering center is calculated using the new preset membership matrix.

[0169] Step S34, when the evaluation function value is not the minimum value and not lower than the preset function value threshold, the clustering result of the current clustering center is taken as the fault feature parameter.

[0170] It can be understood that when the evaluation function value is not the minimum value and not lower than the preset function value threshold, the clustering result of the current clustering center is taken as the fault feature parameter.

[0171] Step S35, obtaining a target instantaneous speed signal corresponding to the fault feature parameter from the instantaneous speed signal, determining the kurtosis maximum peak of the target instantaneous speed signal, and determining the fault positioning result according to the kurtosis maximum peak.

[0172] It should be understood that the target instantaneous speed signal corresponding to the fault feature parameter is obtained from the instantaneous speed signal, and then the kurtosis maximum peak corresponding to the target instantaneous speed signal can be determined, and the fault positioning result is determined according to the kurtosis maximum peak.

[0173] In specific implementation, fault judgment can be realized through acoustic emission signals, and it is difficult to perform fault positioning although there is a fault in the judgment period (0-720°CA). Therefore, the kurtosis of each cylinder instantaneous speed is used for positioning, and it is further verified through experiments that the kurtosis maximum peak corresponds to the fault position.

[0174] The embodiment finds the measured sample data from the historical database, extracts a fault feature vector from the acoustic emission signal, combines the fault feature vector and the sample data into a feature vector group, imports the feature vector group into a preset membership matrix, calculates the evaluation function value of the cluster center of all groups in the acoustic emission signal, uses a new preset membership matrix to calculate the evaluation function value of each cluster center when the evaluation function value is the minimum value or lower than the preset function value threshold, takes the clustering result of the current cluster center as the fault feature parameter when the evaluation function value is not the minimum value and is not lower than the preset function value threshold, obtains the target instantaneous speed signal corresponding to the fault feature parameter from the instantaneous speed signal, determines the kurtosis maximum peak of the target instantaneous speed signal, and determines the fault positioning result according to the kurtosis maximum peak. The detection of the clogging state of the diesel engine injector of the vehicle can be completed through the acoustic emission technology and the instantaneous speed method, the comprehensive performance and reliability of the diesel engine are improved, the overall technical level of the diesel engine of the vehicle is improved, the wear of each cylinder of the diesel engine can be accurately identified, the state monitoring precision of the diesel engine injector is ensured, the accuracy of fault diagnosis and health evaluation is improved, and the speed and efficiency of state monitoring of the diesel engine injector of the vehicle are improved.

[0175] Correspondingly, the application further provides a diesel engine injector state monitoring device for vehicle.

[0176] Referring to Figure 8 Figure 8 It is a functional module diagram of the first embodiment of the diesel engine injector state monitoring device for vehicle.

[0177] In the first embodiment of the diesel engine injector state monitoring device for vehicle, the diesel engine injector state monitoring device for vehicle comprises:

[0178] The sensitivity analysis module 10 is used for obtaining the sensitivity characteristic value corresponding to different sound sources through the sensor in the diesel engine cylinder, performing sensitivity analysis on the in-cylinder emission source according to the sensitivity characteristic value, and obtaining sensitivity analysis data.

[0179] The signal extraction module 20 is used for obtaining a sampling sequence with a preset sampling length from the sensitivity analysis data, performing filtering processing on the sampling sequence, and extracting the acoustic emission signal and the instantaneous speed signal meeting the screening requirements.

[0180] The fault diagnosis module 30 is used for performing fault diagnosis on the state of the diesel engine injector according to the acoustic emission signal and the instantaneous speed signal, and obtaining a fault positioning result.

[0181] ​​​​​​​​​The sensitivity analysis module 10 is also used to obtain the attenuation of the energy at the measurement point corresponding to different sound sources relative to the sound emission source through the sensor in the diesel engine cylinder, and use the attenuation as the sensitivity feature value; and use an amplifier to perform sensitivity analysis of the in-cylinder emission source based on the sensitivity feature value to obtain sensitivity analysis data.

[0182] The sensitivity analysis module 10 is also used to obtain the correspondence between the energy, attenuation factor and relative distance of different measuring points corresponding to different sound sources through the sensors in the diesel engine cylinder;

[0183] Based on the aforementioned correspondence, the attenuation of energy at different measurement points relative to the acoustic emission source is obtained using the following formula, and this attenuation is used as a sensitivity characteristic value:

[0184]

[0185] kl=lnW0-lnW(l)

[0186] Where kl is the sensitivity characteristic value of the measuring point, k is the attenuation factor, l is the distance between the measuring point and the acoustic emission source, v(t) is the acoustic emission signal at the measuring point, and W is the distance from point P0 to P... t The acoustic emission signal energy is W0, which is the acoustic emission energy at the initial point, and W(l) is the acoustic emission energy at the calculation point.

[0187] The sensitivity analysis module 10 is further configured to use an amplifier to amplify the acquisition signal corresponding to the sensitivity feature value collected by the sensor in the diesel engine cylinder to obtain a gain signal; monitor the nozzle blockage of the diesel engine injector in real time, and when the nozzle blockage is within the target blockage range, obtain a target gain signal corresponding to the target blockage range; perform sensitivity analysis on the target gain signal to obtain sensitivity analysis data of each measuring point to each acoustic emission source.

[0188] The signal extraction module 20 is further configured to: collect sampling data conforming to a preset working cycle time from the sensitivity analysis data according to a preset sampling length, a preset number of sampling points, and a preset sampling rate; perform periodic averaging on the sampling data to obtain a sampling sequence; obtain the transfer function of the filter; perform filtering processing on the sampling sequence according to the transfer function to obtain a filtering result; convert the filtering result from the time domain to the angle domain to obtain angle domain data; and extract acoustic emission signals and instantaneous rotational speed signals from the angle domain data according to a preset crank angle range.

[0189] The fault diagnosis module 30 is further configured to: search for measured sample data from a historical database, extract a fault feature vector from the acoustic emission signal, combine the fault feature vector and the sample data into a feature vector group; introduce the feature vector group into a preset membership matrix, calculate evaluation function values of clustering centers of all groups in the acoustic emission signal; when the evaluation function values are minimum values or lower than a preset function value threshold, calculate evaluation function values of the clustering centers using a new preset membership matrix; when the evaluation function values are not minimum values and are not lower than the preset function value threshold, take a clustering result of a current clustering center as a fault feature parameter; obtain a target instantaneous speed signal corresponding to the fault feature parameter from the instantaneous speed signal, determine a kurtosis maximum peak of the target instantaneous speed signal, and determine a fault positioning result according to the kurtosis maximum peak.

[0190] The fault diagnosis module 30 is further configured to: introduce the feature vector group into a preset membership matrix, and calculate evaluation function values of clustering centers of all groups in the acoustic emission signal by the following formula:

[0191]

[0192] wherein J(U, V) is an evaluation function value, U is a membership matrix, V is a clustering center, c is a classification category, and n is a data sample amount, is an optimal solution of clustering, is a minimum distance from a target to a clustering center.

[0193] The steps implemented by each functional module of the diesel engine injector state monitoring device can refer to the steps of each embodiment of the diesel engine injector state monitoring method, and will not be described here again.

[0194] In addition, the embodiment of the present application further provides a storage medium, and the storage medium stores a diesel engine injector state monitoring program.

[0195] Obtain sensitivity characteristic values corresponding to different sound sources through a sensor in a cylinder of the diesel engine, perform sensitivity analysis on the in-cylinder emission source according to the sensitivity characteristic values, and obtain sensitivity analysis data;

[0196] Obtain a sampling sequence of a preset sampling length from the sensitivity analysis data, perform filtering processing on the sampling sequence, and extract acoustic emission signals and instantaneous speed signals meeting screening requirements;

[0197] Perform fault diagnosis on the state of the diesel engine injector according to the acoustic emission signals and the instantaneous speed signals, and obtain a fault positioning result.

[0198] Further, the vehicle diesel engine injector state monitoring program, when executed by the processor, further implements the following operations:

[0199] Obtaining, by a sensor in the diesel engine cylinder, an attenuation amount of different measuring point energy corresponding to different sound sources relative to a sound emission source, taking the attenuation amount as a sensitivity characteristic value;

[0200] Performing sensitivity analysis of the in-cylinder emission source according to the sensitivity characteristic value by using an amplifier to obtain sensitivity analysis data.

[0201] Further, the vehicle diesel engine injector state monitoring program, when executed by the processor, further implements the following operations:

[0202] Obtaining, by a sensor in the diesel engine cylinder, a corresponding relationship between different measuring point energy corresponding to different sound sources and an attenuation factor and a relative distance;

[0203] According to the corresponding relationship, the attenuation amount of different measuring point energy relative to the sound emission source is obtained by the following formula, and the attenuation amount is taken as a sensitivity characteristic value:

[0204]

[0205] kl = lnW0-lnW(l)

[0206] Wherein, kl is the measuring point sensitivity characteristic value, k is the attenuation factor, l is the distance between the measuring point and the sound emission source, v(t) is the sound emission signal of the measuring point, W is the sound emission signal energy from P0 point to P t , W0 is the sound emission energy of the initial point, and W(l) is the sound emission energy of the calculation point.

[0207] Further, the vehicle diesel engine injector state monitoring program, when executed by the processor, further implements the following operations:

[0208] Using an amplifier to perform gain on the acquisition signal corresponding to the sensitivity characteristic value collected by the sensor in the diesel engine cylinder to obtain a gain signal;

[0209] Real-time monitoring of the nozzle blockage amount of the diesel engine injector, when the nozzle blockage amount is in a target blockage amount range, obtaining a target gain signal corresponding to the target blockage amount range;

[0210] Performing sensitivity analysis on the target gain signal to obtain sensitivity analysis data of each measuring point to each sound emission source.

[0211] Further, the vehicle diesel engine injector state monitoring program, when executed by the processor, further implements the following operations:

[0212] According to a preset sampling length, a preset sampling point number and a preset sampling rate, sample data conforming to a preset working cycle time is collected from the sensitivity analysis data, the sample data is periodically averaged to obtain a sample sequence;

[0213] A transfer function of a filter is obtained, the sample sequence is filtered according to the transfer function to obtain a filtering result;

[0214] The filtering result is converted from a time domain to an angle domain to obtain angle domain data, and an acoustic emission signal and an instantaneous rotating speed signal are extracted from the angle domain data according to a preset crank angle value range.

[0215] Further, the vehicle diesel engine injector state monitoring program further implements the following operations when executed by the processor:

[0216] Sample data measured from a historical database is searched, a fault feature vector is extracted from the acoustic emission signal, and the fault feature vector and the sample data are combined into a feature vector group;

[0217] The feature vector group is introduced into a preset membership matrix, and an evaluation function value of a cluster center of all groups in the acoustic emission signal is calculated;

[0218] When the evaluation function value is a minimum value or lower than a preset function value threshold, a new preset membership matrix is used to calculate the evaluation function value of each cluster center;

[0219] When the evaluation function value is not a minimum value and is not lower than the preset function value threshold, a clustering result of the current cluster center is taken as a fault feature parameter;

[0220] A target instantaneous rotating speed signal corresponding to the fault feature parameter is obtained from the instantaneous rotating speed signal, a kurtosis maximum peak of the target instantaneous rotating speed signal is determined, and a fault positioning result is determined according to the kurtosis maximum peak.

[0221] Further, the vehicle diesel engine injector state monitoring program further implements the following operations when executed by the processor:

[0222] The feature vector group is introduced into a preset membership matrix, and an evaluation function value of a cluster center of all groups in the acoustic emission signal is calculated by the following formula:

[0223]

[0224] Wherein, J(U, V) is an evaluation function value, U is a membership matrix, V is a cluster center, c is a classification category, and n is a data sample amount, is a clustering optimal solution, is a minimum distance from a target to a cluster center.

[0225] Those skilled in the art can understand that all or part of the steps of the methods in the above embodiments can be completed by instructing the relevant hardware through a program stored in a storage medium, including a plurality of instructions for causing an apparatus (which can be a single-chip microcomputer, a chip, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present application; and the aforementioned storage medium includes various media capable of storing program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0226] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, method, article or apparatus including the element.

[0227] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0228] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for monitoring the condition of fuel injectors in automotive diesel engines, characterized in that, The method for monitoring the condition of automotive diesel engine injectors includes: Sensitivity characteristic values ​​corresponding to different sound sources are obtained by sensors inside the diesel engine cylinder. Sensitivity analysis of the in-cylinder emission source is performed based on the sensitivity characteristic values ​​to obtain sensitivity analysis data. A sampling sequence with a preset sampling length is obtained from the sensitivity analysis data, and the sampling sequence is filtered to extract the acoustic emission signal and instantaneous rotation speed signal that meet the screening requirements. Based on the acoustic emission signal and the instantaneous speed signal, the state of the diesel engine injector is diagnosed to obtain the fault location result; The step of diagnosing the state of the diesel engine injector based on the acoustic emission signal and the instantaneous speed signal to obtain fault location results includes: Search for measured sample data from the historical database, extract fault feature vectors from the acoustic emission signals, and combine the fault feature vectors and the sample data into a feature vector group; The feature vector group is imported into a preset membership matrix, and the evaluation function value of the cluster center of all groups in the acoustic emission signal is calculated. When the evaluation function value is at its minimum or below a preset function value threshold, a new preset membership matrix is ​​used to calculate the evaluation function value of each cluster center. When the evaluation function value is not the minimum value and is not lower than the preset function value threshold, the clustering result of the current cluster center is used as the fault feature parameter; Obtain the target instantaneous speed signal corresponding to the fault characteristic parameters from the instantaneous speed signal, determine the maximum kurtosis peak of the target instantaneous speed signal, and determine the fault location result based on the maximum kurtosis peak; The step of importing the feature vector group into a preset membership matrix and calculating the evaluation function value of the cluster centers of all groups in the acoustic emission signal includes: The feature vector group is imported into a preset membership matrix, and the evaluation function value of the cluster centers of all groups in the acoustic emission signal is calculated using the following formula: in, To evaluate the function value, The membership matrix, As cluster center, For classification categories, For the data sample size, The optimal solution for clustering. The minimum distance from the target to the cluster center.

2. The method for monitoring the condition of automotive diesel engine injectors as described in claim 1, characterized in that, The process involves obtaining sensitivity characteristic values ​​corresponding to different sound sources through sensors within the diesel engine cylinder, performing sensitivity analysis on the in-cylinder emission sources based on these sensitivity characteristic values, and obtaining sensitivity analysis data, including: The attenuation of energy at measurement points corresponding to different sound sources relative to the sound emission source is obtained by sensors inside the diesel engine cylinder, and the attenuation is used as a sensitivity feature value. Sensitivity analysis of the in-cylinder emission source is performed using an amplifier based on the aforementioned sensitivity characteristic values ​​to obtain sensitivity analysis data.

3. The method for monitoring the condition of automotive diesel engine injectors as described in claim 2, characterized in that, The method of obtaining the attenuation of energy at measurement points corresponding to different sound sources relative to the sound emission source through sensors inside the diesel engine cylinder, and using the attenuation as a sensitivity feature value, includes: The relationship between energy, attenuation factor, and relative distance at different measuring points corresponding to different sound sources is obtained by using sensors inside the diesel engine cylinder. Based on the aforementioned correspondence, the attenuation of energy at different measurement points relative to the acoustic emission source is obtained using the following formula, and this attenuation is used as a sensitivity characteristic value: Where kl is the sensitivity characteristic value of the measurement point. Let P0 be the attenuation factor, l be the distance between the measuring point and the acoustic emission source, v(t) be the acoustic emission signal at the measuring point, and W be the distance from point P0 to point P1. t The acoustic emission signal energy is W0, where W0 is the acoustic emission energy at the initial point. Let be the acoustic emission energy at the calculation point.

4. The method for monitoring the condition of automotive diesel engine injectors as described in claim 2, characterized in that, The process of using an amplifier to perform sensitivity analysis on the in-cylinder emission source based on the sensitivity characteristic values, and obtaining sensitivity analysis data, includes: An amplifier is used to amplify the acquired signal corresponding to the sensitivity feature value collected by the sensor inside the diesel engine cylinder to obtain a gain signal; The amount of nozzle blockage in the fuel injector of the diesel engine is monitored in real time, and when the amount of nozzle blockage is within the target blockage range, a target gain signal corresponding to the target blockage range is obtained; Sensitivity analysis is performed on the target gain signal to obtain sensitivity analysis data of each measurement point to each acoustic emission source.

5. The method for monitoring the condition of automotive diesel engine injectors as described in claim 1, characterized in that, The step of obtaining a sampling sequence of a preset sampling length from the sensitivity analysis data, filtering the sampling sequence, and extracting acoustic emission signals and instantaneous rotation speed signals that meet the screening requirements includes: Based on the preset sampling length, preset number of sampling points and preset sampling rate, sampling data that meets the preset working cycle time is collected from the sensitivity analysis data, and the sampling data is periodically averaged to obtain a sampling sequence; Obtain the transfer function of the filter, and perform filtering processing on the sampled sequence according to the transfer function to obtain the filtering result; The filtering result is converted from the time domain to the angle domain to obtain angle domain data. The acoustic emission signal and instantaneous rotation speed signal are extracted from the angle domain data according to the preset crank angle value range.

6. A device for monitoring the condition of fuel injectors for automotive diesel engines, characterized in that, The vehicle diesel engine injector condition monitoring device includes: The sensitivity analysis module is used to obtain sensitivity characteristic values ​​corresponding to different sound sources through sensors inside the diesel engine cylinder, and to perform sensitivity analysis of the in-cylinder emission sources based on the sensitivity characteristic values ​​to obtain sensitivity analysis data. The signal extraction module is used to obtain a sampling sequence of a preset sampling length from the sensitivity analysis data, filter the sampling sequence, and extract acoustic emission signals and instantaneous rotation speed signals that meet the screening requirements. The fault diagnosis module is used to diagnose the state of the diesel engine injector based on the acoustic emission signal and the instantaneous speed signal, and obtain the fault location result. The fault diagnosis module is further configured to: search for measured sample data from a historical database; extract fault feature vectors from the acoustic emission signal; combine the fault feature vectors and the sample data into a feature vector group; import the feature vector group into a preset membership matrix; calculate the evaluation function value of the cluster centers of all groups in the acoustic emission signal; when the evaluation function value is the minimum value or lower than a preset function value threshold, use a new preset membership matrix to calculate the evaluation function value of each cluster center; when the evaluation function value is not the minimum value and is not lower than the preset function value threshold, use the clustering result of the current cluster center as the fault feature parameter; obtain the target instantaneous speed signal corresponding to the fault feature parameter from the instantaneous speed signal; determine the maximum kurtosis peak of the target instantaneous speed signal; and determine the fault location result based on the maximum kurtosis peak. The fault diagnosis module is further configured to import the feature vector group into a preset membership matrix and calculate the evaluation function value of the cluster centers of all groups in the acoustic emission signal using the following formula: in, To evaluate the function value, The membership matrix, As cluster center, For classification categories, For the data sample size, The optimal solution for clustering. The minimum distance from the target to the cluster center.

7. A condition monitoring device for automotive diesel engine injectors, characterized in that, The vehicle diesel engine injector condition monitoring device includes: a memory, a processor, and a vehicle diesel engine injector condition monitoring program stored in the memory and executable on the processor, wherein the vehicle diesel engine injector condition monitoring program is configured to implement the steps of the vehicle diesel engine injector condition monitoring method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a vehicle diesel engine injector condition monitoring program, which, when executed by a processor, implements the steps of the vehicle diesel engine injector condition monitoring method as described in any one of claims 1 to 5.

Images