Method for monitoring wear state of piston ring of vehicle diesel engine, storage medium and device

Abstract

The application discloses a kind of vehicle diesel engine piston ring wear state monitoring method, storage medium and device, it is related to diesel engine state monitoring field, the method includes defining the measured point sensitivity characteristic value for representing the attenuation amount of measured point energy relative to acoustic emission source energy, and determining multiple acoustic emission source positions and measured point positions for installing acoustic emission sensor on cylinder cover;Drive acoustic emission sensor at acoustic emission source to produce excitation, the measured point sensitivity characteristic value between each measured point and acoustic emission source is calculated, determine the measured point for carrying out fault identification among all measured points, as detection measured point;Acoustic emission signal of detection measured point is obtained when piston is located in set position during diesel engine operation, the PSD spectral amplitude of acoustic emission signal is calculated, and compared with the fault threshold under different fault states of piston ring, realize piston ring fault determination.The application can realize the accuracy and effectiveness of piston ring fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of diesel engine condition monitoring, and specifically to a method, storage medium, and device for monitoring the wear condition of piston rings in automotive diesel engines. Background Technology

[0002] As the power source for various machines, the reliability of diesel engines directly affects the economy and reliability of related machinery and systems. In particular, marine diesel engines, which are the heart of vehicles, can cause economic losses if they malfunction during operation and are not repaired in a timely and effective manner. In severe cases, they can lead to serious economic losses or even endanger the lives of drivers and passengers. Therefore, the reliability requirements for automotive diesel engines are even higher.

[0003] Piston rings, as a key component of the combustion chamber in automotive diesel engines, primarily function to seal the piston and cylinder liner, conduct heat, scrape oil, and distribute oil. Piston rings operate under harsh conditions; the average effective pressure in low-speed diesel engines can exceed 2 MPa, and the maximum combustion pressure can exceed 25 MPa, making them highly susceptible to friction, wear, and breakage. Studies show that power loss due to friction between the piston rings and cylinder liner accounts for approximately 20% of the total mechanical friction loss in an engine. Poor lubrication of the friction pair between the piston rings and cylinder liner easily leads to excessive piston ring wear. Once the wear limit is exceeded, the seal between the piston and cylinder decreases, allowing high-temperature, high-pressure combustion gases to leak into the crankcase. Excessive oil mist concentration in the crankcase can also cause serious malfunctions such as crankcase explosion. Furthermore, in-cylinder gas leakage and reduced combustion pressure decrease the diesel engine's output power and increase fuel consumption. Real-time monitoring of the wear condition of diesel engine piston rings and determining the amount of wear is of significant research importance and practical engineering value for improving the reliability of automotive diesel engines.

[0004] Currently, many scholars have conducted research on wear monitoring of the piston-piston ring-cylinder liner friction pair and have achieved some research results. The main methods that can be used directly or indirectly to monitor piston ring wear include instantaneous speed monitoring, oil monitoring, thin-layer activation, and vibration monitoring.

[0005] While instantaneous engine speed monitoring can reflect the working status of each cylinder, there are many factors that can cause fluctuations in instantaneous speed, such as cylinder scoring, misfire, and fuel cut-off. Furthermore, when piston ring wear is small, it has little impact on cylinder pressure. Therefore, fluctuations in instantaneous speed can only indicate that the engine piston rings may have experienced excessive wear, and cannot quantitatively analyze the wear condition of the piston rings.

[0006] The oil monitoring method can only make an overall judgment on the wear of piston rings in all cylinders of a diesel engine. It cannot quantitatively analyze the wear condition of a specific cylinder or piston ring, nor can it locate the faulty cylinder or the worn piston ring.

[0007] Thin-layer activation method utilizes charged particles to bombard the material under test, forming a layer of radioactive material of the required thickness on the material surface. Based on the relationship between radioactivity and depth, the change in radioactivity activity can be converted into the wear amount of the material under test. It is a non-destructive method for online monitoring of the wear degree of components. However, for diesel engines, thin-layer activation method can monitor the wear state of a single cylinder and a single ring. But for multi-cylinder and multi-ring systems, if all rings are activated, the location of the faulty cylinder and faulty ring cannot be located. Therefore, it is not suitable for online monitoring of the wear state of each cylinder and each ring of a diesel engine.

[0008] Vibration monitoring is primarily used to monitor and analyze the wear condition between the piston and cylinder liner in diesel engines. However, the vibration signals from different components influence each other, making it difficult to quantitatively analyze the piston-cylinder liner wear condition. Its main application is in diagnosing severe wear between the piston and cylinder liner or between the piston rings and cylinder liner. Marine low-speed diesel engines employ a crosshead slider structure, where the lateral thrust of the piston and piston rings on the cylinder liner is borne by the crosshead slider. Therefore, using vibration monitoring to monitor piston ring wear has certain limitations.

[0009] Therefore, there is an urgent need for a method that can effectively monitor the wear condition of piston rings in automotive diesel engines. Summary of the Invention

[0010] In view of the deficiencies in the existing technology, the purpose of this invention is to provide a method, storage medium and device for monitoring the wear condition of piston rings in automotive diesel engines, which can achieve accurate and effective piston ring fault diagnosis.

[0011] To achieve the above objectives, the present invention provides a method for monitoring the wear condition of piston rings in automotive diesel engines, specifically including the following steps:

[0012] Define a measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors;

[0013] The acoustic emission sensor at the acoustic emission source is driven to generate excitation, and the signals between each measuring point and the acoustic emission source are collected. The sensitivity characteristic value of each measuring point and the acoustic emission source is calculated. Based on the sum of the sensitivity characteristic values ​​of the current measuring point and all acoustic emission sources, the measuring point used for fault identification is determined from all measuring points and used as the detection measuring point.

[0014] Acoustic emission signals from the detection point are collected when the piston is in a set position during diesel engine operation. The PSD spectrum amplitude of the acoustic emission signal is calculated and compared with the fault threshold under different piston ring fault conditions to determine piston ring faults.

[0015] Based on the above technical solution, the calculation method for the sensitivity characteristic value of the measuring point is as follows:

[0016]

[0017] kl=lnW0-lnW(l)

[0018] Where kl represents the sensitivity characteristic value of the measuring point, k represents the attenuation factor, l represents the distance between the measuring point and the acoustic emission source, V(t) represents the acoustic emission signal at the measuring point, and W represents the distance from point P0 to point P... t The acoustic emission signal energy is W0 and W(l), which represent the acoustic emission energy at the initial point and the calculation point, respectively.

[0019] Based on the above technical solutions,

[0020] Specifically, the center position of the intake and exhaust sides of each cylinder of the diesel engine is selected as the measurement point position;

[0021] Specifically, the location of the acoustic emission source is selected as the center of the bottom of each cylinder head of the diesel engine.

[0022] Based on the above technical solutions,

[0023] Signals are acquired through an acquisition system to calculate the sensitivity characteristic values ​​of the measurement points.

[0024] The acquisition system includes two acoustic emission sensors and an acquisition card connected to both acoustic emission sensors for acquiring their signals. An amplifier is provided between each acoustic emission sensor and the acquisition card.

[0025] The two acoustic emission sensors are a first acoustic emission sensor and a second acoustic emission sensor, where the first acoustic emission sensor is used to locate the acoustic emission source and the second acoustic emission sensor is used to locate the measuring point.

[0026] Based on the above technical solution, the acoustic emission sensor at the acoustic emission source is excited to collect signals between each measuring point and the acoustic emission source, and the measuring point sensitivity characteristic value between each measuring point and the acoustic emission source is calculated. Specifically, the calculation of the measuring point sensitivity characteristic value for the current measuring point includes the following steps:

[0027] The second acoustic emission sensor is placed at the current measurement point, and the first acoustic emission sensor is placed sequentially at each acoustic emission source position. When it is at each acoustic emission source position, it is excited by a standard Hsu–Neilson acoustic emission source.

[0028] The signals from the first acoustic emission sensor and the second acoustic emission sensor are acquired by the acquisition card when the first acoustic emission sensor is located at each acoustic emission source position. Based on the acquired signals, the sensitivity characteristic value of the current measurement point and each acoustic emission source is calculated.

[0029] Based on the above technical solution, the step of determining the measurement point for fault identification from all measurement points according to the sum of the sensitivity characteristic values ​​of the current measurement point and all acoustic emission sources includes:

[0030] Obtain the sensitivity feature values ​​of the current measurement point and each acoustic emission source, and obtain multiple sensitivity feature values ​​of the measurement point. Sum the multiple sensitivity feature values ​​of the measurement point to obtain the total sensitivity feature value of the measurement point and match it with the current measurement point.

[0031] The sum of the sensitivity feature values ​​of each measuring point is obtained and compared. The measuring point corresponding to the minimum sum of the sensitivity feature values ​​is determined as the measuring point for fault identification.

[0032] Based on the above technical solution, the specific steps for acquiring the acoustic emission signal from the detection point when the piston is in a set position during diesel engine operation and calculating the PSD spectral amplitude of the acoustic emission signal include:

[0033] Extracting a sampling sequence of a specific length from the acoustic emission signal, top dead center signal, and instantaneous rotational speed signal, specifically:

[0034]

[0035] Where, x s (t) represents the sampled sequence, x(t) represents the thermoelectric signal before sampling, δ(t-nT) represents the sampled pulse sequence, and T s This represents the sampling time interval, and n represents the number of measurement cycles.

[0036] By capturing one working cycle of the diesel engine every two times the top dead center signal crosses zero, the sampling sequence number is determined. The working cycle time is expressed as:

[0037] T η =(ji)T s

[0038] Among them, T η This represents the work cycle time, where j and i are the sampling sequence numbers separated by two top dead ends;

[0039] The average value of the thermoelectric signal is calculated based on the number of working cycles. Specifically:

[0040]

[0041] Among them, (x i1 ,x i2 …x im (x) represents the sampling sequence after the i-th working cycle. n1 ,x n2 …x nm ) represents the sampling sequence of the (i+N-1)th work cycle, where N represents the average number of cycles;

[0042] A 6th-order Butterworth IIR low-pass filter is selected for signal filtering, where the transfer function is:

[0043]

[0044] Where H(z) represents the transfer function, θ i Indicates intermediate quantity. z represents the complex variables of the digital filter, ω represents the digital domain frequency, N represents the number of roots of the transfer function, and N1 is... The nearest integer is used for rounding, and e represents the natural constant;

[0045] The waveform of the corresponding tooth on the flywheel is obtained by a magnetoelectric speed sensor, resulting in a sine wave. The sampling time is the sampling time interval corresponding to the fixed angle of 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 is obtained. The corresponding points are selected in the thermoelectric data sequence to form a new thermoelectric data sequence. The length of this thermoelectric data sequence is interpolated to 720 points to complete the equal crank angle conversion of the thermoelectric signal. Specifically:

[0046]

[0047] Where, α n+x The crankshaft angle corresponding to the (n+x)th sampling point is represented by q, the ordinal number of the tooth containing the sampling point is represented by M, and the number of flywheel teeth is represented by p. x Let f represent the point sequence number within the q-th tooth, ef represent the total number of sampling points within the q-th tooth, and x represent the number of teeth;

[0048] The acoustic emission signal at the measurement point was selected 20°CA after the top dead center, and the PSD spectral amplitude was calculated. Specifically:

[0049]

[0050] Where P represents the power of the acoustic emission signal, P(k) represents the PSD spectral amplitude, Δf represents the frequency interval, b represents the upper frequency limit of the frequency band, and a represents the lower frequency limit of the frequency band.

[0051] Based on the above technical solution, the comparison of fault thresholds under different fault states of the piston ring to determine the piston ring fault includes the following specific steps:

[0052] A fault simulation test was conducted on the oil extraction machine, and the PSD spectral amplitude of the acoustic emission signal at the detection point under different fault conditions of the diesel engine was calculated as a dataset.

[0053] The dataset is divided into training and testing datasets according to a set ratio to train the support vector machine and obtain the fault thresholds of piston rings under different fault states. The training and testing datasets communicate with the cloud platform for real-time updates.

[0054] Based on the PSD spectral amplitude of the acoustic emission signal at the detection point, a piston ring fault can be determined by training a support vector machine.

[0055] The present invention provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method for monitoring the wear condition of piston rings in automotive diesel engines.

[0056] This invention provides a device for monitoring the wear condition of piston rings in automotive diesel engines, comprising:

[0057] The module is used to define the measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and to determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors.

[0058] The calculation module is used to drive the acoustic emission sensor at the acoustic emission source to generate excitation, collect signals between each measurement point and the acoustic emission source, calculate the measurement point sensitivity characteristic value between each measurement point and the acoustic emission source, and determine the measurement point used for fault identification as the detection measurement point based on the sum of the measurement point sensitivity characteristic values ​​between the current measurement point and all acoustic emission sources.

[0059] The execution module is used to acquire the acoustic emission signal of the detection point when the piston is in a set position during the operation of the diesel engine, calculate the PSD spectrum amplitude of the acoustic emission signal, and compare it with the fault threshold under different fault conditions of the piston ring to determine the piston ring fault.

[0060] Compared with existing technologies, the advantages of this invention are as follows: By defining a sensitivity characteristic value for measuring point to characterize the attenuation of energy at the measuring point relative to the energy of the acoustic emission source, a measuring point for fault identification is determined as a detection measuring point. Then, the acoustic emission signal of the detection measuring point is collected when the piston is in a set position during diesel engine operation. The PSD spectrum amplitude of the acoustic emission signal is calculated and compared with the fault threshold under different fault states of the piston ring to achieve piston ring fault determination. That is, the acoustic emission technology is used to monitor and diagnose the diesel engine, thereby improving the overall performance of the diesel engine. The wear state of the diesel engine piston ring is monitored in real time, the wear amount of the piston ring is determined, the accuracy and effectiveness of piston ring fault diagnosis are achieved, and the overall technical level of automotive diesel engines is improved. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart of a method for monitoring the wear condition of piston rings in a vehicle diesel engine according to an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram showing the location of the measuring points;

[0064] Figure 3 A schematic diagram showing the location of the acoustic emission source;

[0065] Figure 4 This is a schematic diagram of the data acquisition system.

[0066] Figure 5 A schematic diagram showing the sum of the sensitivity characteristic values ​​of each measuring point;

[0067] Figure 6 This is a schematic diagram illustrating the training of a support vector machine.

[0068] Figure 7 This is a schematic diagram of a piston ring wear monitoring system;

[0069] Figure 8 This is a schematic diagram of the machine-side control box. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0071] Acoustic emission (AE) technology, as a non-destructive monitoring technology, has a wide applicable frequency range and high signal-to-noise ratio compared to other monitoring methods. It can effectively reduce the damage to diesel engines caused by sensor installation. Therefore, AE technology can monitor different parts of diesel engines and is less restricted by field applications. Compared with general cylinder pressure and fuel injection pressure monitoring methods, AE monitoring technology has higher sensitivity to faults and is easier to assemble later.

[0072] See Figure 1 As shown in the figure, an embodiment of the present invention provides a method for monitoring the wear condition of piston rings in a vehicle diesel engine, which specifically includes the following steps:

[0073] S101: Define the measurement point sensitivity characteristic value used to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors;

[0074] When acoustic emission waves excited by the acoustic emission source inside the diesel engine cylinder propagate through the complex cylinder head to the outer surface, they undergo complex reflections, refractions, mode conversions, and energy attenuation. The acoustic emission signal acquired by the sensor in the cylinder head differs significantly from the original acoustic emission source signal, resulting in different diagnostic effects. Therefore, when applying acoustic emission technology to diesel engine monitoring and diagnosis, it is necessary to first consider whether the acoustic emission source signal can be captured by the sensor or whether the signal-to-noise ratio of the captured signal is high. In other words, it is necessary to first study the sensitivity of the measurement point (sensor installation location) to different acoustic emission sources. If the energy of the acoustic emission signal captured by the sensor is less attenuated relative to the energy of the acoustic emission source, the measurement point is more sensitive; if the attenuation is greater, the measurement point is less sensitive. To ensure accurate identification of wear in each cylinder by the acoustic emission signal, sensitivity analysis is required.

[0075] In this invention, the method for calculating the sensitivity characteristic value of the measuring point is as follows:

[0076]

[0077] kl=lnW0-lnW(l)

[0078] Where kl represents the sensitivity characteristic value of the measuring point, k represents the attenuation factor, l represents the distance between the measuring point and the acoustic emission source, V(t) represents the acoustic emission signal at the measuring point, and W represents the distance from point P0 to point P... t The acoustic emission signal energy is W0 and W(l), which represent the acoustic emission energy at the initial point and the calculation point, respectively.

[0079] The above formula can be used to represent the energy attenuation between the measuring point and the acoustic emission source. However, the attenuation characteristics of the medium need to be obtained through experiments. Since the attenuation factor k of different measuring points relative to the same acoustic emission source is different for complex media such as cylinder heads, the magnitude of energy attenuation at different measuring points is related to both the attenuation factor k and the distance l. The product of the two, kl, can be used as a parameter to measure the energy attenuation between the measuring point and the acoustic emission source (measuring point sensitivity).

[0080] In this invention, kl characterizes the attenuation of energy at the measuring point relative to the acoustic emission source. A smaller kl value indicates less energy attenuation and higher sensitivity at the measuring point; a larger kl value indicates greater energy attenuation and lower sensitivity at the measuring point. By acquiring acoustic emission signals from the acoustic emission source and different measuring points using sensors and acquisition equipment, and calculating the kx values ​​between different measuring points and the acoustic emission source using the above formula, the sensitivity characteristics of each measuring point in the diesel engine cylinder head to the in-cylinder acoustic emission source can be obtained.

[0081] In this invention, the measuring point location is specifically selected as the center position of the intake and exhaust sides of each cylinder of the diesel engine; the acoustic emission source location is specifically selected as the center position of the bottom of each cylinder head of the diesel engine.

[0082] See Figure 2 As shown, Figure 2 The large black dots in the diagram represent the locations of the measuring points. A total of 12 measuring point locations can be selected, denoted as P1-P12; see [link to documentation]. Figure 3 As shown, Figure 3 The large black dot in the diagram represents the location of the acoustic emission source. A total of eight acoustic emission source locations can be selected, denoted as S1-S8. Considering the randomness of the excitation generated by in-cylinder combustion, the center position can reflect the average level. Therefore, the center position of the intake and exhaust sides of each cylinder is selected as the measuring point position, and the center position of the bottom of the cylinder head (the center of the combustion chamber) is selected as the excitation point, i.e., the acoustic emission source location.

[0083] S201: Drive the acoustic emission sensor at the acoustic emission source to generate excitation, collect signals between each measuring point and the acoustic emission source, calculate the measuring point sensitivity characteristic value between each measuring point and the acoustic emission source, and determine the measuring point used for fault identification from all measuring points based on the sum of the measuring point sensitivity characteristic values ​​between the current measuring point and all acoustic emission sources, and use it as the detection measuring point.

[0084] In this invention, a signal acquisition system is used to acquire signals in order to calculate the sensitivity characteristic value of the measurement point. The acquisition system includes two acoustic emission sensors and an acquisition card connected to both acoustic emission sensors for acquiring the signals from the acoustic emission sensors. An amplifier is provided between each acoustic emission sensor and the acquisition card. The two acoustic emission sensors are a first acoustic emission sensor and a second acoustic emission sensor, wherein the first acoustic emission sensor is used to place the acoustic emission source position and the second acoustic emission sensor is used to place the measurement point position.

[0085] The acquisition system used for sensitivity testing, such as Figure 4 As shown, the two acoustic emission sensors are PAC Micro80D type acoustic emission sensors, and the two preamplifiers are PAC 2 / 4 / 6C type amplifiers with a gain coefficient set to 40dB. The signal is acquired by a NIPCI-6115 acquisition card with a sampling rate set to 1MHz. The NIPCI-6115 acquisition card is a PCI (Peripheral Component Interconnect, a standard for defining local buses) type data acquisition card with a total of 4 analog voltage input channels. The maximum sampling rate of a single channel can reach 10MHz, and the voltage signal measurement range is ±42V. It is suitable for high-speed acquisition of radar, sonar, and ultrasonic signals. During the experiment, the first acoustic emission sensor was fixed sequentially at the bottom of the cylinder head near 8 acoustic emission sources. A standard Hsu-Neilson acoustic emission source (broken pencil lead) was used to excite the sensor at the acoustic emission source location. The second acoustic emission sensor was installed at 12 different sensor mounting positions on the upper part of the cylinder head, and the signals from both sensors were acquired simultaneously. Since the first acoustic emission sensor is very close to the acoustic emission source, its signal can be considered the original acoustic emission wave signal. The signal from the second acoustic emission sensor is the signal from the original acoustic emission wave propagating to measurement points P1-P12. By selecting signals from both sensors within a certain time window, the kx value between each acoustic emission source and measurement point can be obtained using the formula for calculating the sensitivity characteristic value of the measurement point. Using all kx values, the sensitivity pattern of each measurement point on the cylinder head to the main acoustic emission sources in the cylinder can be obtained. The final value of each kx is the average of five acquisitions.

[0086] In this invention, an excitation is generated at the acoustic emission sensor at the acoustic emission source to collect signals between each measuring point and the acoustic emission source, and the measuring point sensitivity characteristic value between each measuring point and the acoustic emission source is calculated. Specifically, the calculation of the measuring point sensitivity characteristic value for the current measuring point includes the following steps:

[0087] S2011: Place the second acoustic emission sensor at the current measurement point, and place the first acoustic emission sensor at each acoustic emission source location in sequence. When the sensor is at each acoustic emission source location, it generates excitation through a standard Hsu–Neilson acoustic emission source.

[0088] S2022: The first acoustic emission sensor and the second acoustic emission sensor are acquired by the acquisition card when the first acoustic emission sensor is located at each acoustic emission source position. Based on the acquired signals, the sensitivity characteristic value of the current measurement point and each acoustic emission source is calculated.

[0089] In this invention, based on the sum of the sensitivity characteristic values ​​of the current measuring point and all acoustic emission sources, the measuring point used for fault identification is determined from all measuring points. Specific steps include:

[0090] S2111: Obtain the sensitivity feature values ​​of the current measuring point and each acoustic emission source, obtain multiple sensitivity feature values ​​of the measuring point, sum the multiple sensitivity feature values ​​of the measuring point to obtain the total sensitivity feature value of the measuring point and match it with the current measuring point;

[0091] S2112: Obtain the sum of the sensitivity feature values ​​of each measuring point and compare them. The measuring point corresponding to the minimum sum of the sensitivity feature values ​​of the measuring points is determined as the measuring point used for fault identification.

[0092] In one possible implementation, for 12 measuring points, the sum of the measuring point sensitivity eigenvalues ​​corresponding to each measuring point is as follows: Figure 5 As shown, Figure 5 In the diagram, each bar represents the sum of the sensitivity characteristic values ​​of a measurement point. It can be seen that the sum of the sensitivity characteristic values ​​of measurement point 5 is the smallest. Therefore, measurement point 5 is the determined measurement point used for fault identification, i.e., the detection measurement point.

[0093] S301: Acquires the acoustic emission signal of the detection point when the piston is in the set position during the operation of the diesel engine, calculates the PSD spectrum amplitude of the acoustic emission signal, and compares it with the fault threshold under different fault conditions of the piston ring to determine the piston ring fault.

[0094] In the actual test process, since the piston ring friction power consumption and knocking force are mainly concentrated at the top dead center of combustion, when a wear failure occurs, the second-order motion of the piston ring and piston will lead to an increase in acoustic emission excitation. Therefore, the signal 20°CA (crank angle) after the top dead center of combustion is selected as the analysis time period.

[0095] In this invention, the acoustic emission signal of the detection point is acquired when the piston of the diesel engine is in a set position during operation, and the PSD spectral amplitude of the acoustic emission signal is calculated. The specific steps include:

[0096] S3011: Extracts a sampling sequence of a specific length from the acoustic emission signal, top dead center signal, and instantaneous rotational speed signal. Specifically:

[0097]

[0098] Where, x s (t) represents the sampled sequence, x(t) represents the thermoelectric signal before sampling, δ(t-nT) represents the sampled pulse sequence, and T s This represents the sampling time interval, and n represents the number of measurement cycles.

[0099] This involves extracting a sampling sequence of a specific length from signals such as acoustic emission, top dead center, and instantaneous rotational speed. Using 240K sampling points at a sampling rate of 60kHz, the truncation time is 4 seconds. When the diesel engine speed is 1500r / min, the sampling length is approximately 50 diesel engine working cycles.

[0100] S3012: One working cycle of the diesel engine is captured every two times the top dead center signal crosses zero, and the sampling sequence number is determined. The working cycle time is expressed as:

[0101] T η =(ji)T s

[0102] Among them, T η This represents the work cycle time, where j and i are the sampling sequence numbers separated by two top dead ends;

[0103] S3013: The average value of the thermoelectric signal is calculated based on the number of working cycles. Specifically:

[0104]

[0105] Among them, (x i1 ,x i2 …x im (x) represents the sampling sequence after the i-th working cycle. n1 ,x n2 …x nm ) represents the sampling sequence of the (i+N-1)th work cycle, where N represents the average number of cycles;

[0106] Due to random factors such as fuel injection and the characteristics of discontinuous working cycles during diesel engine operation, its instantaneous speed fluctuates. To improve the reliability of the analysis, the average value of the thermoelectric signal is calculated with an appropriate number of working cycles.

[0107] S3014: Analyze the thermoelectric signal and the operating characteristics of the diesel engine, and based on the actual filtering effect, select a 6th-order Butterworth IIR low-pass filter for signal filtering, where the transfer function is:

[0108]

[0109] Where H(z) represents the transfer function, θ i Indicates intermediate quantity. z represents the complex variables of the digital filter, ω represents the digital domain frequency, N represents the number of roots of the transfer function, and N1 is... The nearest integer is used for rounding, and e represents the natural constant;

[0110] S3015: The waveform of the corresponding tooth on the flywheel is acquired through a magnetoelectric speed sensor to obtain a sine wave. The corresponding sampling time is the sampling time interval of the fixed angle corresponding to the flywheel rotating through 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 is obtained. Corresponding points are selected in the thermoelectric data sequence to form a new thermoelectric data sequence. The length of this thermoelectric data sequence is interpolated to 720 points (depending on the rotation angle resolution) to complete the equal crank angle conversion of the thermoelectric signal. Specifically:

[0111]

[0112] Where, α n+x The crankshaft angle corresponding to the (n+x)th sampling point is represented by q, the ordinal number of the tooth containing the sampling point is represented by M, and the number of flywheel teeth is represented by p. x Let f represent the point sequence number within the q-th tooth, ef represent the total number of sampling points within the q-th tooth, and x represent the number of teeth;

[0113] S3016: Select the acoustic emission signal at the measurement point 20°CA after the top dead center, and calculate the PSD (Power Spectral Density) spectral amplitude. Specifically:

[0114]

[0115] Where P represents the power of the acoustic emission signal, P(k) represents the PSD spectral amplitude, Δf represents the frequency interval, b represents the upper frequency limit of the frequency band, and a represents the lower frequency limit of the frequency band. The area enclosed by the signal PSD spectral amplitude and the frequency axis can characterize the signal power. The signal power is the time average of the signal energy and can characterize the average intensity of the acoustic emission excitation within the window.

[0116] In actual operation, in addition to selecting acoustic emission signals within a specific 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.

[0117] In this invention, the piston ring fault is determined by comparing the fault thresholds under different fault states of the piston ring. Specific steps include:

[0118] S3111: Conduct a fault simulation test on the oil extraction machine and calculate the PSD spectrum amplitude of the acoustic emission signal at the detection point under different fault conditions of the diesel engine, which will be used as a dataset;

[0119] S3112: Divide the dataset into a training dataset and a test dataset according to a set ratio to train the support vector machine, obtain the fault threshold under different fault states of the piston ring, and communicate between the training dataset and the test dataset with the cloud platform for real-time updates.

[0120] S3113: Based on the PSD spectral amplitude of the acoustic emission signal at the detection point, the piston ring fault is determined by training a support vector machine.

[0121] This means that a fault simulation experiment needs to be conducted first to serve as a sample for training the support vector machine to obtain the judgment threshold, i.e., the fault threshold. The specific training process is as follows: Figure 6 As shown, the training and test datasets communicate with the cloud platform to achieve real-time updates.

[0122] Support Vector Machines (SVMs) were first applied to binary classification problems. Their principle is to find the optimal classification hyperplane. For each hyperplane, the distances to all samples need to be calculated, and the minimum distance is chosen as the minimum distance d for each hyperplane. min Select all d min The hyperplane corresponding to the largest hyperplane in the dataset is the optimal hyperplane, and the corresponding sample data is the support vector. After determining the optimal hyperplane, the test samples are input, and the test samples are classified according to the regions defined by the optimal hyperplane. The hyperplane determined by the maximum hyperplane principle can achieve optimal classification.

[0123] In fault diagnosis algorithm research, all datasets are typically divided into training and testing sets according to a certain ratio. Each test condition of the diesel engine is considered a working state, and P(k) is extracted as data. The state division of the diesel engine is shown in Table 1 below. That is, the training and testing sets are distinguished according to the degree of fault. The specific dataset division is shown in Table 2 below.

[0124] Table 1 Diesel Engine Status Classification

[0125]

[0126]

[0127] Table 2. Division of Training and Test Sets

[0128]

[0129] The obtained partial PSD spectral amplitude data are shown in Table 3 below.

[0130] Table 3

[0131]

[0132]

[0133] Currently, the accuracy after training and testing is only 98.8%. If a cloud platform is used, the accuracy can be further improved by training with a large amount of data.

[0134] The method for monitoring the wear condition of piston rings in automotive diesel engines according to this invention defines a sensitivity feature value for measuring the attenuation of energy at a measuring point relative to the energy of an acoustic emission source. This determines the measuring points used for fault identification, which are then used as detection measuring points. The acoustic emission signal from the detection measuring points is acquired when the piston is in a set position during diesel engine operation. The PSD spectral amplitude of the acoustic emission signal is calculated and compared with the fault threshold under different piston ring fault states to determine the piston ring fault. This method utilizes acoustic emission technology to monitor and diagnose diesel engines, thereby improving their overall performance. It monitors the wear condition of diesel engine piston rings in real time, determines the amount of piston ring wear, and achieves accurate and effective piston ring fault diagnosis, ultimately improving the overall technical level of automotive diesel engines.

[0135] In one possible implementation, the present invention also provides a non-transitory computer-readable storage medium located in a PLC (Programmable Logic Controller) controller. The storage medium stores a computer program that, when executed by a processor, implements the steps of the method for monitoring the wear condition of piston rings in automotive diesel engines as described below:

[0136] Define a measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors;

[0137] The acoustic emission sensor at the acoustic emission source is driven to generate excitation, and the signals between each measuring point and the acoustic emission source are collected. The sensitivity characteristic value of each measuring point and the acoustic emission source is calculated. Based on the sum of the sensitivity characteristic values ​​of the current measuring point and all acoustic emission sources, the measuring point used for fault identification is determined from all measuring points and used as the detection measuring point.

[0138] Acoustic emission signals from the detection point are collected when the piston is in a set position during diesel engine operation. The PSD spectrum amplitude of the acoustic emission signal is calculated and compared with the fault threshold under different piston ring fault conditions to determine piston ring faults.

[0139] Storage media may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0140] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0141] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0142] The present invention provides a device for monitoring the wear condition of piston rings in a vehicle diesel engine, comprising a determination module, a calculation module, and an execution module.

[0143] The module is used to define the measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and to determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors.

[0144] The calculation module is used to drive the acoustic emission sensor at the acoustic emission source to generate excitation, collect signals between each measuring point and the acoustic emission source, calculate the measurement point sensitivity characteristic value between each measuring point and the acoustic emission source, and determine the measuring point for fault identification from all measuring points based on the sum of the measurement point sensitivity characteristic values ​​between the current measuring point and all acoustic emission sources, and use it as the detection measuring point; the execution module is used to collect the acoustic emission signal of the detection measuring point when the piston is in the set position during the operation of the diesel engine, calculate the PSD spectrum amplitude of the acoustic emission signal, and compare it with the fault threshold under different fault states of the piston ring to realize the piston ring fault determination.

[0145] Specifically, for the piston ring wear monitoring system structure corresponding to the piston ring wear condition monitoring device for automotive diesel engines of the present invention, please refer to... Figure 7 As shown, the piston ring wear monitoring system adopts a modular design to improve the system's replaceability and versatility. It includes online monitoring sensors, a local control box, a vehicle diesel engine piston ring wear monitoring system, a cloud platform, and a vehicle diesel engine piston ring wear intelligent diagnostic system.

[0146] In this invention, the machine-side control box includes an explosion-proof enclosure, a power supply, and heat dissipation equipment. The online monitoring sensors include an acoustic emission sensor, a top dead center sensor, a crankshaft angle sensor, a signal amplifier, and an anti-interference cable.

[0147] The automotive diesel engine piston ring wear monitoring system includes a CAN (Controller Area Network) communication card, a dedicated acquisition card, a C-QAD controller, and automotive diesel engine piston ring wear monitoring system software. Its main function is to perform preliminary signal analysis, extract feature values, and send them to the cloud platform. The automotive diesel engine piston ring wear intelligent diagnostic system includes a database, SVM (Support Vector Machine) algorithm, and SVM-based intelligent diagnostic software.

[0148] For the machine-side control box, the specific results are as follows: Figure 8 As shown, the local control box provides power to the acquisition system, acoustic emission sensors, and other equipment in this invention. To ensure thermal balance, a fan is required for heat dissipation.

[0149] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0150] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A method for monitoring the wear condition of piston rings in a vehicle diesel engine, characterized in that, Specifically, the following steps are included: Define a measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors; The acoustic emission sensor at the acoustic emission source is driven to generate excitation, and the signals between each measuring point and the acoustic emission source are collected. The sensitivity characteristic value of each measuring point and the acoustic emission source is calculated. Based on the sum of the sensitivity characteristic values ​​of the current measuring point and all acoustic emission sources, the measuring point used for fault identification is determined from all measuring points and used as the detection measuring point. Acoustic emission signals from the detection point are collected when the piston is in a set position during diesel engine operation. The PSD spectrum amplitude of the acoustic emission signal is calculated and compared with the fault threshold under different piston ring fault conditions to determine piston ring faults. Specifically, the center position of the intake and exhaust sides of each cylinder of the diesel engine is selected as the measurement point position. Specifically, the location of the acoustic emission source is selected as the center of the bottom of each cylinder head of the diesel engine. Among them, the acquisition system is used to acquire signals in order to calculate the sensitivity characteristic values ​​of the measurement points; The acquisition system includes two acoustic emission sensors and an acquisition card connected to both acoustic emission sensors for acquiring the acoustic emission sensor signals, and an amplifier is provided between each acoustic emission sensor and the acquisition card; The two acoustic emission sensors are a first acoustic emission sensor and a second acoustic emission sensor, where the first acoustic emission sensor is used to locate the acoustic emission source and the second acoustic emission sensor is used to locate the measuring point.

2. The method for monitoring the wear condition of piston rings in a vehicle diesel engine as described in claim 1, characterized in that, The method for calculating the sensitivity feature value of the measurement point is as follows: in, This represents the sensitivity characteristic value of the measuring point. Indicates the attenuation factor. Indicates the distance between the measuring point and the acoustic emission source. This represents the acoustic emission signal at the measuring point. Indicates from point Time The acoustic emission signal energy, , These represent the acoustic emission energy at the initial point and the calculation point, respectively.

3. The method for monitoring the wear condition of piston rings in a vehicle diesel engine as described in claim 1, characterized in that, The process involves driving the acoustic emission sensor at the acoustic emission source to generate excitation, acquiring signals between each measuring point and the acoustic emission source, and calculating the measuring point sensitivity characteristic value between each measuring point and the acoustic emission source. Specifically, the calculation of the measuring point sensitivity characteristic value for the current measuring point includes the following steps: The second acoustic emission sensor is placed at the current measurement point, and the first acoustic emission sensor is placed sequentially at each acoustic emission source position. When it is at each acoustic emission source position, it is excited by a standard Hsu–Neilson acoustic emission source. The signals from the first acoustic emission sensor and the second acoustic emission sensor are acquired by the acquisition card when the first acoustic emission sensor is located at each acoustic emission source position. Based on the acquired signals, the sensitivity characteristic value of the current measurement point and each acoustic emission source is calculated.

4. The method for monitoring the wear condition of piston rings in a vehicle diesel engine as described in claim 3, characterized in that, The step of determining the measurement point for fault identification from all measurement points based on the sum of the sensitivity characteristic values ​​between the current measurement point and all acoustic emission sources includes: Obtain the sensitivity feature values ​​of the current measurement point and each acoustic emission source, and obtain multiple sensitivity feature values ​​of the measurement point. Sum the multiple sensitivity feature values ​​of the measurement point to obtain the total sensitivity feature value of the measurement point and match it with the current measurement point. The sum of the sensitivity feature values ​​of each measuring point is obtained and compared. The measuring point corresponding to the minimum sum of the sensitivity feature values ​​is determined as the measuring point for fault identification.

5. The method for monitoring the wear condition of piston rings in a vehicle diesel engine as described in claim 1, characterized in that, The acoustic emission signal is acquired at the detection point when the piston is in a set position during diesel engine operation, and the PSD spectral amplitude of the acoustic emission signal is calculated. The specific steps include: Extracting a sampling sequence of a specific length from the acoustic emission signal, top dead center signal, and instantaneous rotational speed signal, specifically: in, Represents the sampled sequence. This indicates the thermoelectric signal before sampling. Represents the sampling pulse sequence. Indicates the sampling time interval. Indicates the number of measurement cycles; By capturing one working cycle of the diesel engine every two times the top dead center signal crosses zero, the sampling sequence number is determined. The working cycle time is expressed as: in, Indicates the work cycle time. , This is the sampling sequence number separated by two top endpoints; The average value of the thermoelectric signal is calculated based on the number of working cycles. Specifically: in, For the first The sampling sequence after one working cycle For the first A sampling sequence for each work cycle. Indicates the average number of cycles; A 6th-order Butterworth IIR low-pass filter is selected for signal filtering, where the transfer function is: in, Represents the transfer function. Indicates intermediate quantity. , Represents the complex variables of a digital filter. Represents frequency in the digital domain. This indicates the number of roots of the transfer function. for Round down to the nearest whole number. Represents the natural constant; The waveform of the corresponding tooth on the flywheel is obtained by a magnetoelectric speed sensor, resulting in a sine wave. The sampling time is the sampling time interval corresponding to the fixed angle of 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 is obtained. The corresponding points are selected in the thermoelectric data sequence to form a new thermoelectric data sequence. The length of this thermoelectric data sequence is interpolated to 720 points to complete the equal crank angle conversion of the thermoelectric signal. Specifically: in, Indicates the first The crankshaft rotation angle corresponding to each sampling point Indicates the ordinal number of the tooth where the sampling point is located. Indicates the number of teeth on the flywheel. Indicates the first The number of points within each tooth. Indicates the first Total number of sampling points within each tooth, Indicates the number of teeth; The acoustic emission signal at the measurement point was selected 20°CA after the top dead center, and the PSD spectral amplitude was calculated. Specifically: in, Indicates the power of the acoustic emission signal. Indicates the PSD spectral amplitude. Indicates frequency interval, Indicates the upper frequency limit of the frequency band. This indicates the lower limit of the frequency band.

6. The method for monitoring the wear condition of piston rings in a vehicle diesel engine as described in claim 1, characterized in that, The comparison of fault thresholds under different fault states of the piston rings enables the determination of piston ring faults. Specific steps include: A fault simulation test was conducted on the oil extraction machine, and the PSD spectral amplitude of the acoustic emission signal at the detection point under different fault conditions of the diesel engine was calculated as a dataset. The dataset is divided into training and testing datasets according to a set ratio to train the support vector machine and obtain the fault thresholds of piston rings under different fault states. The training and testing datasets communicate with the cloud platform for real-time updates. Based on the PSD spectral amplitude of the acoustic emission signal at the detection point, a piston ring fault can be determined by training a support vector machine.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for monitoring the wear condition of piston rings of a vehicle diesel engine as described in any one of claims 1 to 6.

8. A device for monitoring the wear condition of piston rings in a vehicle diesel engine, characterized in that, include: The module is used to define the measurement point sensitivity characteristic value to characterize the attenuation of the measurement point energy relative to the acoustic emission source energy, and to determine multiple acoustic emission source positions and measurement point positions on the cylinder head for mounting acoustic emission sensors. The calculation module is used to drive the acoustic emission sensor at the acoustic emission source to generate excitation, collect signals between each measurement point and the acoustic emission source, calculate the measurement point sensitivity characteristic value between each measurement point and the acoustic emission source, and determine the measurement point used for fault identification as the detection measurement point based on the sum of the measurement point sensitivity characteristic values ​​between the current measurement point and all acoustic emission sources. The execution module is used to acquire the acoustic emission signal of the detection point when the piston is in a set position during the operation of the diesel engine, calculate the PSD spectrum amplitude of the acoustic emission signal, and compare it with the fault threshold under different fault conditions of the piston ring to determine the piston ring fault. Specifically, the center position of the intake and exhaust sides of each cylinder of the diesel engine is selected as the measurement point position. Specifically, the location of the acoustic emission source is selected as the center of the bottom of each cylinder head of the diesel engine. Among them, the acquisition system is used to acquire signals in order to calculate the sensitivity characteristic values ​​of the measurement points; The acquisition system includes two acoustic emission sensors and an acquisition card connected to both acoustic emission sensors for acquiring their signals. An amplifier is provided between each acoustic emission sensor and the acquisition card. The two acoustic emission sensors are a first acoustic emission sensor and a second acoustic emission sensor, where the first acoustic emission sensor is used to locate the acoustic emission source and the second acoustic emission sensor is used to locate the measuring point.

Images