Diesel engine state monitoring method and device and storage medium

Abstract

The application discloses a diesel engine state monitoring method and device and a storage medium, wherein the method comprises the following steps: acquiring multiple groups of vibration signals corresponding to multiple detection points of a diesel engine, and performing feature extraction to obtain multiple feature parameters; counting the number of abnormalities of each feature parameter exceeding a preset parameter range within a preset time; determining the power state of the diesel engine based on the power change rate of the diesel engine, determining the weight value corresponding to each feature parameter according to the sensitivity index of each feature parameter in the power state; and evaluating the health state of the multiple detection points according to the number of abnormalities and the weight value of each feature parameter corresponding to the multiple groups of vibration signals. The technical scheme provided by the application can solve the problem that the power of the diesel engine changes greatly in a complex environment, the vibration signal is easily affected by the power change, the traditional vibration signal state monitoring method produces more false alarm problems, and it is difficult to accurately evaluate the health state of the diesel engine.

Description

Technical Field

[0001] The present invention relates to the technical field of diesel engines, and in particular to a diesel engine state monitoring method, device and storage medium. Background Art

[0002] A diesel engine is an internal combustion engine that uses diesel fuel to generate energy. It primarily burns diesel fuel, converting heat energy into mechanical work to power the equipment. The operating process of a diesel engine is similar to that of a gasoline engine, with each cycle consisting of four strokes: intake, compression, power generation, and exhaust.

[0003] Diesel engine fault diagnosis technology is a technique for understanding and monitoring the state of a diesel engine during operation, determining whether it is functioning normally or abnormally, both overall and locally, enabling early detection of faults and their causes, and predicting their developmental trends. Diesel engine operating conditions are typically monitored by a monitoring and alarm system, providing real-time monitoring and understanding of the engine's operating status. This system includes several key diagnostic techniques, including oil monitoring, vibration monitoring, noise monitoring, performance trend analysis, and nondestructive testing. Vibration signal condition monitoring, as a form of nondestructive testing, is widely used in many aspects of industrial production.

[0004] In the prior art, vehicles or other machinery and equipment using diesel engines may operate in complex application environments. For example, the on-site environment in which mining trucks travel is a mining road, which is generally divided into flat sections and uphill sections. Faced with the more complex mining working environment, the diesel engine needs to constantly change its power. When traveling on a flat section, the mining truck generally travels at a constant power. When encountering uphill sections (especially uphill), the mining truck needs to increase or decrease the power accordingly. The change in power will affect the vibration condition of the equipment. For example, a sudden change in power will cause the vibration to become larger, causing the fault diagnosis under the constant power state to have false alarms or failures. Therefore, in the prior art, when the vehicle-carrying power changes greatly and the operation is more complex, the vibration signal is easily affected by the power change. There is a technical problem that the use of traditional vibration signal status monitoring methods will produce a large number of false alarms, making it difficult to accurately assess the health status of the diesel engine. Summary of the Invention

[0005] The present invention provides a diesel engine status monitoring method, device and storage medium, aiming to effectively solve the problem in the prior art that the power of the diesel engine varies greatly in complex environments, the vibration signal is easily affected by the power change, the traditional vibration signal status monitoring method will produce many false alarms, and it is difficult to accurately assess the health status of the diesel engine.

[0006] According to one aspect of the present invention, the present invention provides a diesel engine state monitoring method, the method comprising:

[0007] Acquire multiple groups of vibration signals corresponding to multiple detection points of the diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals;

[0008] Determine whether each characteristic parameter is within a normal range according to the preset parameter range corresponding to each characteristic parameter, and count the number of abnormal times that each characteristic parameter exceeds the corresponding preset parameter range within a preset time;

[0009] Obtaining a power change rate of the diesel engine in a current state, determining a power state of the diesel engine based on the power change rate, and determining a weight value corresponding to each characteristic parameter according to a sensitivity index of each characteristic parameter in the power state, wherein the power state includes a constant power state and a variable power state;

[0010] The health status of the multiple detection points is evaluated according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals.

[0011] Furthermore, the step of obtaining multiple groups of vibration signals corresponding to multiple detection points of the diesel engine includes:

[0012] The multiple groups of vibration signals are acquired by multiple vibration signal sensors arranged at the multiple detection points, wherein the multiple detection points at least include a cylinder, a shaft system, and a gear box.

[0013] Furthermore, the acquiring the power change rate of the diesel engine in the current state and determining the power state of the diesel engine based on the power change rate includes:

[0014] The power value of the diesel engine is obtained in real time, the power change rate is calculated based on the power value, and the power change rate is compared with a preset change rate threshold. If the power change rate is less than the change rate threshold, the power state is determined to be a constant power state; if the power change rate is not less than the change rate threshold, the power state is determined to be a variable power state.

[0015] Furthermore, the extracting features of the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals includes:

[0016] Signal processing is performed on the multiple groups of vibration signals to obtain spectral kurtosis and time domain characteristic parameters of each group of vibration signals, and Fourier transform is performed on each group of vibration signals to obtain spectrum characteristic parameters, wherein the time domain characteristic parameters include time domain root mean square and time domain peak-to-peak value, and the spectrum characteristic parameters include spectrum octaves, low frequency spectrum and high frequency spectrum.

[0017] Furthermore, the method further comprises:

[0018] Before obtaining the plurality of groups of vibration signals corresponding to the plurality of detection points of the diesel engine, when the power state is the constant power state, obtaining first test vibration signals corresponding to the plurality of detection points, and determining a first sensitivity index of each characteristic parameter based on the first test vibration signal;

[0019] When the power state is the variable power state, second test vibration signals corresponding to the multiple detection points are acquired, and a second sensitivity index of each characteristic parameter is determined based on the second test vibration signal.

[0020] Furthermore, determining the first sensitivity index of each characteristic parameter based on the first test vibration signal includes:

[0021] performing signal processing on the first test vibration signal to obtain a first test vibration parameter and a first test characteristic parameter, and determining a first sensitivity index of each characteristic parameter based on a numerical change relationship between the first test vibration parameter and the first test characteristic parameter;

[0022] Determining the second sensitivity index of each characteristic parameter based on the second test vibration signal includes:

[0023] The second test vibration signal is subjected to signal processing to obtain a second test vibration parameter and a second test characteristic parameter, and a second sensitivity index of each characteristic parameter is determined based on a numerical change relationship between the second test vibration parameter and the second test characteristic parameter.

[0024] Furthermore, the method further comprises:

[0025] After determining the first sensitivity index of each characteristic parameter based on the first test vibration signal and determining the second sensitivity index of each characteristic parameter based on the second test vibration signal, a first weight value of each characteristic parameter is set based on the first sensitivity index, and a second weight value of each characteristic parameter is set based on the second sensitivity index, wherein the weight value decreases as the sensitivity index increases.

[0026] Furthermore, evaluating the health status of the multiple detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals includes:

[0027] For each group of vibration signals within the preset time, the weighted abnormal number of the characteristic parameter of each group of vibration signals is calculated based on the abnormal number and weight value of the characteristic parameter of the group of vibration signals, the total number of abnormal numbers of the multiple weighted abnormal numbers of the multiple characteristic parameters corresponding to each group of vibration signals is counted, and the health status of the detection point corresponding to the group of vibration signals is evaluated based on the total number of abnormal numbers of each group of vibration signals.

[0028] Furthermore, the evaluating the health status of the detection point corresponding to each group of vibration signals based on the total number of abnormal times of the vibration signals includes:

[0029] For each group of vibration signals, determining a first evaluation threshold and a second evaluation threshold corresponding to the group of vibration signals;

[0030] When the total number of abnormalities of the group of vibration signals is less than the first evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a normal operating state;

[0031] When the total number of abnormal times of the group of vibration signals is not less than the first evaluation threshold and not greater than the second evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a sub-healthy state;

[0032] When the total number of abnormal times corresponding to the group of vibration signals is greater than the second evaluation threshold, it is determined that the health state of the detection point corresponding to the group of vibration signals is a fault state.

[0033] According to another aspect of the present invention, the present invention further provides a diesel engine state monitoring device, the device comprising:

[0034] A feature parameter extraction module is used to obtain multiple groups of vibration signals corresponding to multiple detection points of the diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals;

[0035] an abnormality number determination module, configured to determine whether each characteristic parameter is within a normal range based on a preset parameter range corresponding to each characteristic parameter, and to count the number of abnormalities in which each characteristic parameter exceeds the corresponding preset parameter range within a preset time;

[0036] a weight value determination module, configured to obtain a power change rate of the diesel engine in a current state, determine a power state of the diesel engine based on the power change rate, and determine a weight value corresponding to each characteristic parameter in the power state according to a sensitivity index of each characteristic parameter, wherein the power state includes a constant power state and a variable power state;

[0037] A health status evaluation module is used to evaluate the health status of the multiple detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals.

[0038] According to another aspect of the present invention, the present invention further provides a storage medium, wherein a plurality of instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute any of the diesel engine state monitoring methods described above.

[0039] Through one or more of the above embodiments of the present invention, at least the following technical effects can be achieved:

[0040] In the technical solution disclosed in this invention, the diesel engine is analyzed in different dimensions based on its constant power and variable power operating conditions. Vibration signal condition monitoring is applied to diesel engine monitoring. By selecting different characteristic parameters, a weight distribution scheme for rated operating conditions is used under stable power, while a weight distribution scheme for variable power is used under variable power. This scheme uses constant power condition assessment as the primary method and variable power condition assessment as the supplementary method to conduct a more comprehensive diesel engine condition assessment, thereby improving the effectiveness of diesel engine condition monitoring.

[0041] The present invention utilizes a method combining dynamic weighting and statistical analysis to realize analysis and processing of diesel engine vibration signals, avoiding the shortcomings of traditional vibration signal states such as frequent false alarms and difficulty in effective monitoring of diesel engines. It is a diesel engine monitoring system based on dynamic weighting and statistical analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The technical solutions and other beneficial effects of the present invention will be made apparent by describing in detail the specific embodiments of the present invention in conjunction with the accompanying drawings.

[0043] Figure 1 A flowchart of a diesel engine status monitoring method provided by an embodiment of the present invention;

[0044] Figure 2 This is a structural diagram of a diesel engine status monitoring device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] In the description of the present invention, it should be noted that, unless otherwise specified or limited, the term "and / or" herein is merely a description of an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " herein, unless otherwise specified, generally indicates that the associated objects are in an "or" relationship.

[0047] According to one aspect of the present invention, the present invention provides a diesel engine state monitoring method. Figure 1FIG2 is a flowchart of a diesel engine state monitoring method according to an embodiment of the present invention, wherein the method comprises:

[0048] Step 101: Acquire multiple groups of vibration signals corresponding to multiple detection points of a diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals;

[0049] Step 102: determining whether each characteristic parameter is within a normal range according to a preset parameter range corresponding to each characteristic parameter, and counting the number of abnormal times that each characteristic parameter exceeds the corresponding preset parameter range within a preset time;

[0050] Step 103: Obtaining a power change rate of the diesel engine in a current state, determining a power state of the diesel engine based on the power change rate, and determining a weight value corresponding to each characteristic parameter in the power state according to a sensitivity index of each characteristic parameter, wherein the power state includes a constant power state and a variable power state;

[0051] Step 104: Evaluate the health status of the multiple detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals.

[0052] In vehicle or marine systems, diesel engines have one of the highest failure rates. Fault diagnosis technology is used to monitor diesel engines in real time, performing status detection and fault diagnosis on their various structures and components. The proposed calculation scheme is a diesel engine monitoring and alarm system based on dynamic weighting and statistical analysis. This system includes data acquisition and analysis, status monitoring, and fault diagnosis, enabling diesel engine monitoring, protection, analysis, and diagnosis. First, information related to the diesel engine's operation is collected, followed by data analysis. Finally, the engine's operating status and health status are determined based on the analysis results.

[0053] The present invention is a truck diesel engine monitoring and alarm system based on dynamic weights and statistical analysis. It aims to monitor the vibration status of diesel engines under complex working conditions, solves the shortcomings of the current traditional vibration signal processing and analysis methods in the application of mining truck diesel engine status monitoring, and improves the effectiveness of mining truck diesel engine status monitoring. Specifically, according to the different working characteristics of the diesel engine under fixed power and variable power, vibration signal analysis and processing technology and dynamic weight matching technology are adopted. Specifically, by selecting different characteristic parameters, the weight distribution scheme of the rated working condition is used under stable power; in the case of variable power, the weight distribution scheme of variable power is used. A more comprehensive status assessment of the diesel engine is performed with a scheme that mainly uses fixed power status assessment and supplemented by variable power status assessment.

[0054] The present invention applies vibration signal status monitoring to diesel engines, analyzing and processing both stable power operating conditions and variable power operating conditions, thereby enabling vibration signal status monitoring and analysis of the mining truck diesel engine during operation. The following describes steps 101 to 105 in detail.

[0055] In step 101, a plurality of groups of vibration signals corresponding to a plurality of detection points of a diesel engine are obtained, and feature extraction is performed on the plurality of groups of vibration signals to obtain a plurality of feature parameters corresponding to each group of vibration signals;

[0056] For example, during diesel engine operation, various parameters reflect the operating status. Vibration signal status monitoring, as a nondestructive testing method, is widely used in diesel engine monitoring technology. Specifically, sensors are installed at multiple detection points on the diesel engine to obtain the corresponding vibration signal. For example, sensors can be attached or installed in appropriate locations on the diesel engine, such as the cylinder, shafting, gearbox, supercharger, casing, or housing.

[0057] The sensor acquires data from the detection points in real time. The data collection interval can be preset during information collection, for example, collecting data every 1m or 2m. Each time data is collected, each detection point can collect a set of vibration signals. Multiple detection points correspond to multiple sets of vibration signals.

[0058] The vibration signals at the test points on a diesel engine are non-stationary, exhibiting regular fluctuations. Extracting characteristic parameters from these non-stationary vibration signals is crucial for health assessment. For each set of vibration signals, feature extraction is performed through signal processing to obtain multiple characteristic parameters.

[0059] In step 102, whether each characteristic parameter is within a normal range is determined based on the preset parameter range corresponding to each characteristic parameter, and the number of abnormal times that each characteristic parameter exceeds the corresponding preset parameter range within a preset time is counted.

[0060] For example, when a diesel engine is stable, the vibration signal at a test point exhibits irregularities, with regular fluctuations. When a diesel engine malfunctions, the irregularities become more pronounced. After extracting characteristic parameters from the non-stationary vibration signal, determining the operating status of the test point based on these multiple characteristic parameters is crucial for health assessment.

[0061] Each characteristic parameter has a preset parameter range set in advance. For each vibration signal collected at each detection point, each parameter characteristic is compared with the corresponding preset parameter range to determine whether the parameter characteristic is within the normal range. Then, after the preset time, the number of abnormalities of each characteristic parameter within the preset time is counted. The preset time can be set according to the actual application. For example, if the frequency of collecting vibration signals is once per second, the preset time can be set to 1 minute. Among them, within the preset time, if the characteristic parameter is within the preset parameter range, it indicates that the characteristic parameter is in a normal state. If the characteristic parameter exceeds the corresponding preset parameter range, it is determined that the characteristic parameter is in an abnormal state.

[0062] Among them, the characteristic parameters are the performance parameter signals of the diesel engine, which are more intuitive and convenient. Once the measured or calculated value exceeds the preset alarm threshold, the diagnostic results will be sent and an alarm will be issued, and historical data will be formed to monitor and predict changes in the operating status of the diesel engine.

[0063] In step 103, the power change rate of the diesel engine in the current state is obtained, the power state of the diesel engine is determined based on the power change rate, and the weight value corresponding to each characteristic parameter is determined according to the sensitivity index of each characteristic parameter in the power state, wherein the power state includes a constant power state and a variable power state.

[0064] For example, the equipment using a diesel engine may operate in a complex environment, requiring the engine to continuously change power. When the environment changes, the power is increased or decreased accordingly, and the power change can affect the vibration of the equipment. In the present invention, the rated operating weight distribution scheme is used under stable power conditions, and the variable power weight distribution scheme is used under variable power conditions. Therefore, this solution requires determining the diesel engine's power change rate.

[0065] Specifically, the power change rate of the diesel engine at the current moment is obtained in real time, and then the power state of the diesel engine is determined based on the power change rate. The power state includes a constant power state and a variable power state. Regardless of whether the vehicle is operating at high power or low power, as long as the power change rate is small, it is a constant power state. During the switching process between high power and low power, it is a variable power state.

[0066] When the power state changes, the sensitivity index of each characteristic parameter also varies accordingly, and furthermore, the corresponding weight value of each characteristic parameter also varies. The characteristic parameters can be divided into Class I, Class II, and Class III according to their sensitivity to power changes. The dynamic weighting algorithm assigns different weight coefficients to the characteristic parameters of different classes based on power changes to generate weighted characteristic parameters. Through statistical analysis, corresponding thresholds are established and the diesel engine status is evaluated.

[0067] For example, a smaller weight is assigned to Class I characteristic parameters, a moderate weight is assigned to Class II characteristic parameters, and a larger weight is assigned to Class III characteristic parameters. For example, initially weights 1, 2, and 3 are set, and then adjusted when the diesel engine is in a healthy state so that the three weights keep the statistical quantity below the healthy threshold.

[0068] In step 104 , the health status of the multiple detection points is evaluated based on the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals.

[0069] For example, each detection point corresponds to a set of vibration signals. The number of anomalies and weight values ​​for each characteristic parameter of this set of vibration signals are determined. Based on the number of triggers exceeding a threshold within a certain period of time, the health status of multiple preset detection points is evaluated based on the number of anomalies and weight values ​​for each characteristic parameter corresponding to multiple sets of vibration signals. The collected vibration signals are analyzed and processed to evaluate the health status of the equipment. The evaluation results display information such as equipment failure, sub-health, and health.

[0070] Since different characteristic parameters have different sensitivities at different powers, the present invention determines the weight values ​​of the characteristic parameters based on the sensitivity when the diesel engine is in different power states, so as to reduce the influence of the characteristic parameters with higher sensitivity and prevent false alarms caused by a large number of abnormalities.

[0071] Furthermore, the step of obtaining multiple groups of vibration signals corresponding to multiple detection points of the diesel engine includes:

[0072] The multiple groups of vibration signals are acquired by multiple vibration signal sensors arranged at the multiple detection points, wherein the multiple detection points at least include a cylinder, a shaft system, and a gear box.

[0073] For example, during operation, various components of a diesel engine are subject to high-speed vibration. Sensors are installed at multiple detection points on the diesel engine to obtain vibration signals corresponding to each detection point. For example, sensors may be attached or installed at appropriate locations on the diesel engine, such as the cylinder, shafting, gearbox, supercharger, housing, or casing. These sensors can be various types of vibration sensors, including acceleration sensors and eddy current sensors.

[0074] The selection of detection points significantly impacts the state assessment results, so it is necessary to accurately select multiple detection points. These detection points must fully reflect the operating information of the measured object and should have characteristics such as stable signals, high signal-to-noise ratios, and sensitivity to faults. Furthermore, the selection of detection points must facilitate sensor installation and data transmission, minimize impact on the machine's operating status, and be practical in actual production. The present invention does not impose any restrictions on the selection of detection points and vibration signal sensors, and in actual applications, these can be determined based on specific needs.

[0075] Furthermore, the acquiring the power change rate of the diesel engine in the current state and determining the power state of the diesel engine based on the power change rate includes:

[0076] The power value of the diesel engine is obtained in real time, the power change rate is calculated based on the power value, and the power change rate is compared with a preset change rate threshold. If the power change rate is less than the change rate threshold, the power state is determined to be a constant power state; if the power change rate is not less than the change rate threshold, the power state is determined to be a variable power state.

[0077] For example, the present invention uses different statistical analyses according to different power changes of the diesel engine, so it is necessary to determine the power change rate of the diesel engine. Specifically, the power value of the diesel engine is obtained in real time, and then the power change rate of the diesel engine is calculated in real time based on the power value.

[0078] Generally speaking, no matter whether the vehicle is operating at high power or low power, as long as the power change rate is small, it is in a constant power state. During the switching process between high power and low power, it is in a variable power state. In the present invention, a change rate threshold value related to the power change rate is preset in advance according to the power change situation, and the power change rate obtained in real time is compared with the preset change rate threshold value. Among them, when the power change rate is less than the change rate threshold value, the power state is determined to be a constant power state, and when the power change rate is not less than the change rate threshold value, the power state is determined to be a variable power state. In the present invention, using different statistical analyses for different powers can improve the accuracy of diesel engine evaluation.

[0079] Furthermore, the extracting features of the plurality of groups of vibration signals to obtain a plurality of feature parameters corresponding to each group of vibration signals includes:

[0080] Signal processing is performed on the multiple groups of vibration signals to obtain spectral kurtosis and time domain characteristic parameters of each group of vibration signals, and Fourier transform is performed on each group of vibration signals to obtain spectrum characteristic parameters, wherein the time domain characteristic parameters include time domain root mean square and time domain peak-to-peak value, and the spectrum characteristic parameters include spectrum octaves, low frequency spectrum and high frequency spectrum.

[0081] For example, signal analysis and feature extraction are prerequisites for health assessment. Specifically, signal processing includes signal preprocessing, time domain signal analysis, frequency domain signal analysis, and wavelet analysis, which can form characteristic parameters for translating the operating status of the diesel engine.

[0082] Specifically, after processing multiple vibration signals, time-domain signal analysis can be performed to extract time-domain characteristic parameters. This yields the spectral kurtosis and multiple time-domain characteristic parameters for each vibration signal. These parameters include at least the time-domain root mean square (RMS) and peak-to-peak value. Each vibration signal is then Fourier transformed and subjected to frequency-domain signal analysis to obtain multiple spectral characteristic parameters. These parameters include at least the spectral octaves, low-frequency spectrum, and high-frequency spectrum.

[0083] The changes in characteristic parameters at different detection points of a diesel engine are different, and the importance and change patterns of the characteristic parameters are also different. Obtaining multiple characteristic parameters corresponding to each detection point can improve the accuracy of the health status assessment of the corresponding detection point.

[0084] Furthermore, the method further comprises:

[0085] Before obtaining the plurality of groups of vibration signals corresponding to the plurality of detection points of the diesel engine, when the power state is the constant power state, obtaining first test vibration signals corresponding to the plurality of detection points, and determining a first sensitivity index of each characteristic parameter based on the first test vibration signal;

[0086] When the power state is the variable power state, second test vibration signals corresponding to the multiple detection points are acquired, and a second sensitivity index of each characteristic parameter is determined based on the second test vibration signal.

[0087] For example, before evaluating a diesel engine, it is necessary to determine the sensitivity index corresponding to each characteristic parameter under different power states. Specifically, before evaluating the diesel engine, first and second test vibration signals corresponding to multiple preset detection points of the diesel engine are acquired while the diesel engine is in a constant power state and a variable power state, respectively. Based on the first and second test vibration signals, a first and second sensitivity index for each characteristic parameter are determined, respectively. This solution fully eliminates evaluation errors caused by different sensitivity indices, reduces the impact of more sensitive characteristic parameters on evaluation results, and reduces false alarms.

[0088] Furthermore, determining the first sensitivity index of each characteristic parameter based on the first test vibration signal includes:

[0089] performing signal processing on the first test vibration signal to obtain a first test vibration parameter and a first test characteristic parameter, and determining a first sensitivity index of each characteristic parameter based on a numerical change relationship between the first test vibration parameter and the first test characteristic parameter;

[0090] Determining the second sensitivity index of each characteristic parameter based on the second test vibration signal includes:

[0091] The second test vibration signal is subjected to signal processing to obtain a second test vibration parameter and a second test characteristic parameter, and a second sensitivity index of each characteristic parameter is determined based on a numerical change relationship between the second test vibration parameter and the second test characteristic parameter.

[0092] For example, when extracting characteristic parameters, the sensitivity information corresponding to different characteristic parameters can be determined. The extraction of characteristic parameters is essentially a mathematical transformation of the vibration signal, that is, different characteristic parameters correspond to different mathematical formulas. Different eigenvalues ​​have different sensitivities to changes in vibration parameters. For example, when the vibration parameter increases by Δx, some characteristic parameters have average sensitivity, and the corresponding change value of such characteristic values ​​will deviate less from Δx; some characteristic parameters have high sensitivity, and the change in characteristic value will be much greater than Δx; some characteristic parameters have low sensitivity, and the change in characteristic value will be significantly less than Δx.

[0093] This solution processes the test vibration signal to obtain vibration parameters and test characteristic parameters. The sensitivity index of each characteristic parameter is then determined based on the numerical change relationship between the test vibration parameters and the test characteristic parameters. Different characteristic parameters can also be classified based on their sensitivity to changes in vibration parameters. For example, multiple characteristic parameters can be classified into three categories based on their sensitivity to vibration changes: the most sensitive category is Class I characteristic parameters, the averagely sensitive category is Class II characteristic parameters, and the least sensitive category is Class III characteristic parameters. Class I characteristic parameters include time domain peak values, time domain peak-to-peak values, etc. Class II characteristic parameters include main characteristic frequencies and intensity, etc. Class III characteristic parameters include octave values ​​such as 0.5 octave, 1 octave, and 2 octave.

[0094] Furthermore, the method further comprises:

[0095] After determining the first sensitivity index of each characteristic parameter based on the first test vibration signal and determining the second sensitivity index of each characteristic parameter based on the second test vibration signal, a first weight value of each characteristic parameter is set based on the first sensitivity index, and a second weight value of each characteristic parameter is set based on the second sensitivity index, wherein the weight value decreases as the sensitivity index increases.

[0096] For example, since characteristic parameters with higher sensitivity have poor stability, when the power changes, the data fluctuates greatly, which can easily lead to misjudgments and false alarms. Therefore, in general, the higher the sensitivity of the characteristic parameter, the lower the corresponding weight value. For example, a smaller weight is assigned to the characteristic parameter of Class I with the highest sensitivity index, a medium weight is assigned to the characteristic parameter of Class II with a medium sensitivity index, and a larger weight is assigned to the characteristic parameter of Class III with a lower sensitivity index. The specific weight value can be set according to the different sensitivity indices, can be set according to the classification, or each weight value can be set separately.

[0097] Furthermore, evaluating the health status of the multiple detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals includes:

[0098] For each group of vibration signals within the preset time, the weighted abnormal number of the characteristic parameter of each group of vibration signals is calculated based on the abnormal number and weight value of the characteristic parameter of the group of vibration signals, the total number of abnormal numbers of the multiple weighted abnormal numbers of the multiple characteristic parameters corresponding to each group of vibration signals is counted, and the health status of the detection point corresponding to the group of vibration signals is evaluated based on the total number of abnormal numbers of each group of vibration signals.

[0099] For example, when the number of abnormalities of a key characteristic parameter exceeds a preset threshold, or the total number of abnormalities of several related characteristic parameters within a preset time exceeds the corresponding threshold, it indicates that there is a problem with the health status of the diesel engine.

[0100] Among them, when the detection points are different, the importance of each feature parameter in the multiple feature parameters is also different, so the judgment criteria are also different. It is necessary to process the number of abnormalities of each feature. Specifically, it is necessary to calculate the weighted number of abnormalities in combination with the weight value.

[0101] Then, the total number of abnormalities of multiple weighted abnormalities of multiple characteristic parameters corresponding to each group of vibration signals is counted. For each group of vibration signals, the corresponding total number of abnormalities is calculated, and finally the health status of the corresponding preset detection point is evaluated based on the total number of abnormalities.

[0102] Furthermore, the evaluating the health status of the detection point corresponding to each group of vibration signals based on the total number of abnormal times of the vibration signals includes:

[0103] For each group of vibration signals, determining a first evaluation threshold and a second evaluation threshold corresponding to the group of vibration signals;

[0104] When the total number of abnormalities of the group of vibration signals is less than the first evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a normal operating state;

[0105] When the total number of abnormal times of the group of vibration signals is not less than the first evaluation threshold and not greater than the second evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a sub-healthy state;

[0106] When the total number of abnormal times corresponding to the group of vibration signals is greater than the second evaluation threshold, it is determined that the health state of the detection point corresponding to the group of vibration signals is a fault state.

[0107] Exemplarily, the health status of a detection point is determined based on the total number of abnormalities and the associated evaluation threshold. Specifically, the evaluation results can be divided into three categories: when the total number of abnormalities is small and less than the first evaluation threshold, it indicates that the corresponding detection point is relatively stable and maintains normal operation at the current moment, and the health status is normal operation; when the total number of abnormalities is moderate, not less than the first evaluation threshold and not greater than the second evaluation threshold, some characteristic parameters are in an abnormal state, and the detection point is determined to be in a sub-healthy state; when the total number of abnormalities is large and greater than the second evaluation threshold, it indicates that multiple characteristic parameters are in an abnormal state, or at least one characteristic parameter is clearly in an abnormal state, and the health status of the detection point is determined to be a fault state.

[0108] Through one or more of the above embodiments of the present invention, at least the following technical effects can be achieved:

[0109] In the technical solution disclosed in this invention, the diesel engine is analyzed in different dimensions based on its constant power and variable power operating conditions. Vibration signal condition monitoring is applied to diesel engine monitoring. By selecting different characteristic parameters, a weight distribution scheme for rated operating conditions is used under stable power, while a weight distribution scheme for variable power is used under variable power. This scheme uses constant power condition assessment as the primary method and variable power condition assessment as the supplementary method to conduct a more comprehensive diesel engine condition assessment, thereby improving the effectiveness of diesel engine condition monitoring.

[0110] The present invention utilizes a method combining dynamic weighting and statistical analysis to realize analysis and processing of diesel engine vibration signals, avoiding the shortcomings of traditional vibration signal states such as frequent false alarms and difficulty in effective monitoring of diesel engines. It is a diesel engine monitoring system based on dynamic weighting and statistical analysis.

[0111] Based on the same inventive concept as the diesel engine state monitoring method of the embodiment of the present invention, the embodiment of the present invention provides a diesel engine state monitoring device, please refer to Figure 2 , the device comprises:

[0112] According to another aspect of the present invention, the present invention further provides a diesel engine state monitoring device, the device comprising:

[0113] A feature parameter extraction module 201 is used to obtain multiple groups of vibration signals corresponding to multiple detection points of the diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals;

[0114] The abnormality number determination module 202 is used to determine whether each parameter characteristic is within a normal range based on the preset parameter range corresponding to each characteristic parameter, and to count the number of abnormalities of each characteristic parameter exceeding the corresponding preset parameter range within a preset time;

[0115] a weight value determination module 203 configured to obtain a power change rate of the diesel engine in a current state, determine a power state of the diesel engine based on the power change rate, and determine a weight value corresponding to each characteristic parameter in the power state according to a sensitivity index of each characteristic parameter, wherein the power state includes a constant power state and a variable power state;

[0116] The health status evaluation module 204 is configured to evaluate the health status of the multiple detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the multiple groups of vibration signals.

[0117] Furthermore, the feature parameter extraction module 201 is further configured to:

[0118] The multiple groups of vibration signals are acquired by multiple vibration signal sensors arranged at the multiple detection points, wherein the multiple detection points at least include a cylinder, a shaft system, and a gear box.

[0119] Furthermore, the weight value determination module 203 is further configured to:

[0120] The power value of the diesel engine is obtained in real time, the power change rate is calculated based on the power value, and the power change rate is compared with a preset change rate threshold. If the power change rate is less than the change rate threshold, the power state is determined to be a constant power state; if the power change rate is not less than the change rate threshold, the power state is determined to be a variable power state.

[0121] Furthermore, the feature parameter extraction module 201 is further configured to:

[0122] Signal processing is performed on the multiple groups of vibration signals to obtain spectral kurtosis and time domain characteristic parameters of each group of vibration signals, and Fourier transform is performed on each group of vibration signals to obtain spectrum characteristic parameters, wherein the time domain characteristic parameters include time domain root mean square and time domain peak-to-peak value, and the spectrum characteristic parameters include spectrum octaves, low frequency spectrum and high frequency spectrum.

[0123] Furthermore, the device is also used for:

[0124] Before obtaining the plurality of groups of vibration signals corresponding to the plurality of detection points of the diesel engine, when the power state is the constant power state, obtaining first test vibration signals corresponding to the plurality of detection points, and determining a first sensitivity index of each characteristic parameter based on the first test vibration signal;

[0125] When the power state is the variable power state, second test vibration signals corresponding to the multiple detection points are acquired, and a second sensitivity index of each characteristic parameter is determined based on the second test vibration signal.

[0126] Furthermore, the device is also used for:

[0127] performing signal processing on the first test vibration signal to obtain a first test vibration parameter and a first test characteristic parameter, and determining a first sensitivity index of each characteristic parameter based on a numerical change relationship between the first test vibration parameter and the first test characteristic parameter;

[0128] The second test vibration signal is subjected to signal processing to obtain a second test vibration parameter and a second test characteristic parameter, and a second sensitivity index of each characteristic parameter is determined based on a numerical change relationship between the second test vibration parameter and the second test characteristic parameter.

[0129] Furthermore, the device is also used for:

[0130] After determining the first sensitivity index of each characteristic parameter based on the first test vibration signal and determining the second sensitivity index of each characteristic parameter based on the second test vibration signal, a first weight value of each characteristic parameter is set based on the first sensitivity index, and a second weight value of each characteristic parameter is set based on the second sensitivity index, wherein the weight value decreases as the sensitivity index increases.

[0131] Furthermore, the health status assessment module 204 is further configured to:

[0132] For each group of vibration signals within the preset time, the weighted abnormal number of the characteristic parameter of each group of vibration signals is calculated based on the abnormal number and weight value of the characteristic parameter of the group of vibration signals, the total number of abnormal numbers of the multiple weighted abnormal numbers of the multiple characteristic parameters corresponding to each group of vibration signals is counted, and the health status of the detection point corresponding to the group of vibration signals is evaluated based on the total number of abnormal numbers of each group of vibration signals.

[0133] Furthermore, the health status assessment module 204 is further configured to:

[0134] For each group of vibration signals, determining a first evaluation threshold and a second evaluation threshold corresponding to the group of vibration signals;

[0135] When the total number of abnormalities of the group of vibration signals is less than the first evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a normal operating state;

[0136] When the total number of abnormal times of the group of vibration signals is not less than the first evaluation threshold and not greater than the second evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a sub-healthy state;

[0137] When the total number of abnormal times corresponding to the group of vibration signals is greater than the second evaluation threshold, it is determined that the health state of the detection point corresponding to the group of vibration signals is a fault state.

[0138] Among them, other aspects and implementation details of the diesel engine state monitoring device are the same as or similar to the diesel engine state monitoring method described above, and are not repeated here.

[0139] According to another aspect of the present invention, the present invention further provides a storage medium, wherein a plurality of instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute any of the diesel engine state monitoring methods described above.

[0140] In summary, although the present invention has been disclosed above with reference to preferred embodiments, the above preferred embodiments are not intended to limit the present invention. A person skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be based on the scope defined in the claims.

Claims

1. A diesel engine state monitoring method, characterized in that: The method comprises: Acquire multiple groups of vibration signals corresponding to multiple detection points of the diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals; Determine whether each characteristic parameter is within a normal range according to the preset parameter range corresponding to each characteristic parameter, and count the number of abnormal times that each characteristic parameter exceeds the corresponding preset parameter range within a preset time; Obtaining a power change rate of the diesel engine in a current state, determining a power state of the diesel engine based on the power change rate, and determining a weight value corresponding to each characteristic parameter according to a sensitivity index of each characteristic parameter in the power state, wherein the power state includes a constant power state and a variable power state; evaluating the health status of the plurality of detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the plurality of groups of vibration signals; Before obtaining the plurality of groups of vibration signals corresponding to the plurality of detection points of the diesel engine, when the power state is the constant power state, obtaining first test vibration signals corresponding to the plurality of detection points, and determining a first sensitivity index of each characteristic parameter based on the first test vibration signal; When the power state is the variable power state, obtaining second test vibration signals corresponding to the multiple detection points, and determining a second sensitivity index of each characteristic parameter based on the second test vibration signal; Determining the first sensitivity index of each characteristic parameter based on the first test vibration signal includes: performing signal processing on the first test vibration signal to obtain a first test vibration parameter and a first test characteristic parameter, and determining a first sensitivity index of each characteristic parameter based on a numerical change relationship between the first test vibration parameter and the first test characteristic parameter; Determining the second sensitivity index of each characteristic parameter based on the second test vibration signal includes: performing signal processing on the second test vibration signal to obtain a second test vibration parameter and a second test characteristic parameter, and determining a second sensitivity index of each characteristic parameter based on a numerical change relationship between the second test vibration parameter and the second test characteristic parameter; After determining the first sensitivity index of each characteristic parameter based on the first test vibration signal and determining the second sensitivity index of each characteristic parameter based on the second test vibration signal, a first weight value of each characteristic parameter is set based on the first sensitivity index, and a second weight value of each characteristic parameter is set based on the second sensitivity index, wherein the weight value decreases as the sensitivity index increases.

2. The method according to claim 1, wherein The step of obtaining multiple groups of vibration signals corresponding to multiple detection points of the diesel engine includes: The multiple groups of vibration signals are acquired by multiple vibration signal sensors arranged at the multiple detection points, wherein the multiple detection points at least include a cylinder, a shaft system, and a gear box.

3. The method according to claim 1, wherein The acquiring the power change rate of the diesel engine in the current state and determining the power state of the diesel engine based on the power change rate includes: The power value of the diesel engine is obtained in real time, the power change rate is calculated based on the power value, and the power change rate is compared with a preset change rate threshold. If the power change rate is less than the change rate threshold, the power state is determined to be a constant power state; if the power change rate is not less than the change rate threshold, the power state is determined to be a variable power state.

4. The method according to claim 1, wherein The extracting features of the plurality of groups of vibration signals to obtain a plurality of feature parameters corresponding to each group of vibration signals includes: Signal processing is performed on the multiple groups of vibration signals to obtain spectral kurtosis and time domain characteristic parameters of each group of vibration signals, and Fourier transform is performed on each group of vibration signals to obtain spectrum characteristic parameters, wherein the time domain characteristic parameters include time domain root mean square and time domain peak-to-peak value, and the spectrum characteristic parameters include spectrum octaves, low frequency spectrum and high frequency spectrum.

5. The method according to claim 1, wherein The evaluating the health status of the plurality of detection points according to the number of abnormalities and the weight value of each characteristic parameter corresponding to the plurality of groups of vibration signals includes: For each group of vibration signals within the preset time, the weighted abnormal number of the characteristic parameter of each group of vibration signals is calculated based on the abnormal number and weight value of the characteristic parameter of the group of vibration signals, the total number of abnormal numbers of the multiple weighted abnormal numbers of the multiple characteristic parameters corresponding to each group of vibration signals is counted, and the health status of the detection point corresponding to the group of vibration signals is evaluated based on the total number of abnormal numbers of each group of vibration signals.

6. The method according to claim 5, wherein The step of evaluating the health status of the detection point corresponding to each group of vibration signals based on the total number of abnormal times of the vibration signals includes: For each group of vibration signals, determining a first evaluation threshold and a second evaluation threshold corresponding to the group of vibration signals; When the total number of abnormalities of the group of vibration signals is less than the first evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a normal operating state; When the total number of abnormal times of the group of vibration signals is not less than the first evaluation threshold and not greater than the second evaluation threshold, determining that the health status of the detection point corresponding to the group of vibration signals is a sub-healthy state; When the total number of abnormal times corresponding to the group of vibration signals is greater than the second evaluation threshold, it is determined that the health state of the detection point corresponding to the group of vibration signals is a fault state.

7. A diesel engine status monitoring device, characterized in that: The device comprises: A feature parameter extraction module is used to obtain multiple groups of vibration signals corresponding to multiple detection points of the diesel engine, and perform feature extraction on the multiple groups of vibration signals to obtain multiple feature parameters corresponding to each group of vibration signals; An abnormality number determination module is used to determine whether each parameter characteristic is within a normal range based on the preset parameter range corresponding to each characteristic parameter, and to count the number of abnormalities of each characteristic parameter exceeding the corresponding preset parameter range within a preset time; a weight value determination module, configured to obtain a power change rate of the diesel engine in a current state, determine a power state of the diesel engine based on the power change rate, and determine a weight value corresponding to each characteristic parameter in the power state according to a sensitivity index of each characteristic parameter, wherein the power state includes a constant power state and a variable power state; a health status evaluation module, configured to evaluate the health status of the plurality of detection points based on the number of abnormalities and the weight value of each characteristic parameter corresponding to the plurality of groups of vibration signals; The device is further configured to: before obtaining the multiple groups of vibration signals corresponding to the multiple detection points of the diesel engine, when the power state is the constant power state, obtain first test vibration signals corresponding to the multiple detection points, and determine a first sensitivity index of each characteristic parameter based on the first test vibration signal; When the power state is the variable power state, obtaining second test vibration signals corresponding to the multiple detection points, and determining a second sensitivity index of each characteristic parameter based on the second test vibration signal; performing signal processing on the first test vibration signal to obtain a first test vibration parameter and a first test characteristic parameter, and determining a first sensitivity index of each characteristic parameter based on a numerical change relationship between the first test vibration parameter and the first test characteristic parameter; performing signal processing on the second test vibration signal to obtain a second test vibration parameter and a second test characteristic parameter, and determining a second sensitivity index of each characteristic parameter based on a numerical change relationship between the second test vibration parameter and the second test characteristic parameter; After determining the first sensitivity index of each characteristic parameter based on the first test vibration signal and determining the second sensitivity index of each characteristic parameter based on the second test vibration signal, a first weight value of each characteristic parameter is set based on the first sensitivity index, and a second weight value of each characteristic parameter is set based on the second sensitivity index, wherein the weight value decreases as the sensitivity index increases.

8. A storage medium, characterized in that: The storage medium stores a plurality of instructions, which are suitable for being loaded by a processor to execute the method according to any one of claims 1 to 6.

Images