Diesel generating set fault prediction method, model and storage medium

Abstract

The invention discloses a diesel generating set fault prediction method and model, and a storage medium, and the method comprises the steps: obtaining operation data, and processing the operation data to obtain a data sample set; mapping the data sample set to obtain an extended data sample set; performing calculation according to the extended data sample set to obtain an Euclidean distance; extracting according to the Euclidean distance and the correlation function to obtain local features; obtaining a first category and a first possibility according to the local feature output; obtaining a second fault category and a second fault occurrence possibility according to conversion between the first category and the first possibility; according to the second fault category and the second fault occurrence possibility output, obtaining a prediction value; analyzing according to the predicted value and the expected value to obtain a first parameter; performing calculation optimization according to the first parameter to obtain a second parameter; and optimizing the prediction model according to the second fault parameter, and outputting to obtain a fault prediction result. According to the method, the optimal parameters can be obtained through model iteration updating, and the accuracy of fault prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault prediction, and in particular to a diesel generator set fault prediction method, model, and storage medium. Background Art

[0002] Diesel generator sets have been widely used in various industries such as communications and industry due to their good adaptability and economy. They can provide reliable power support when the city power is unstable or unavailable, ensuring the normal operation of the enterprise. However, diesel generator sets will inevitably encounter various faults during operation, such as lubrication system problems, supercharger failures, fuel system abnormalities, etc. These faults will not only affect the production process of the enterprise, but may even cause significant economic losses. Therefore, it is of great significance to predict the faults of diesel generator sets, which can help maintenance personnel take measures in advance to reduce the losses caused by faults and extend the service life of equipment.

[0003] In one existing technology, the specific implementation includes: sensors are placed at key locations of the unit to collect multi-dimensional operating data such as temperature and pressure, and after being aggregated into a data set, machine learning (such as decision tree algorithms that build tree structures based on data features to determine fault branches) and deep learning (neural networks that convert input and hidden layer calculations to obtain results at the output layer, CNNs that process vibration image data to extract features, and RNNs and their variants that capture time series data trends) algorithms are introduced. A large amount of historical data is used to train the model and adjust parameters to identify fault modes. The trained model receives new collected data, analyzes and judges, and outputs the fault type and possibility, providing a reference for maintenance personnel to prevent faults.

[0004] However, the prediction results obtained in the prior art are only the types of faults, and the output results are not further iteratively optimized, resulting in poor accuracy of the obtained prediction results. Summary of the invention

[0005] The present invention provides a diesel generator set fault prediction method, model, and storage medium to solve the problem that the prediction result obtained in the prior art is only the type of fault, and the output result is not further iteratively optimized, resulting in poor accuracy of the obtained prediction result.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for predicting faults of a diesel generator set, comprising: Obtain diesel generator set operation data; Performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; Performing high-dimensional mapping on the diesel generator set operation data sample set to obtain an extended operation data sample set; Performing distance calculation based on the extended running data sample set to obtain a Euclidean distance; Extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; Outputting the local features through a model to obtain a first fault category and a first fault occurrence probability; Converting the first fault category and the first fault occurrence probability to obtain a second fault category and a second fault occurrence probability; Performing a collective output according to the second fault category and the second fault occurrence probability to obtain a predicted output value; Performing error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; Performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters; The pre-stored fault prediction model is adjusted and optimized according to the second fault prediction model parameters and then output to obtain a fault prediction result.

[0007] In an implementable manner of the first aspect, performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set includes: Perform feature extraction based on the diesel generator set operation data to obtain attribute values ​​and feature vectors; Calculate the mean and variance of the attribute value to obtain the attribute value mean and the attribute value standard deviation; Performing integrated calculation based on the attribute value and the feature vector to obtain an operation data sample; Normalization processing is performed according to the operation data samples, the mean value of the attribute values ​​and the standard deviation of the attribute values ​​to obtain a set of operation data samples of the diesel generator set.

[0008] In an implementation manner of the first aspect, performing integrated calculation according to the attribute value and the feature vector to obtain the operation data sample includes: The running data sample is calculated by the following formula: in, Indicates the running data sample, Indicates the number of samples in the diesel generator set operation data set. The data sample attribute values, Indicates The feature vector of attribute values, Indicates The feature vector of attribute values, To control the neighborhood influence range parameters, The number of neighboring nodes with the highest similarity selected for the data samples in the diesel generator set operation data sample set, Represents the Euclidean distance between feature vectors.

[0009] In an implementable manner of the first aspect, extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features includes: The local features are calculated by the following formula: in, Represents local features, Samples in the extended run data sample set With sample The Euclidean distance, Samples in the extended run data sample set The extended run data sample set Samples corresponding to the location where the class fault occurs The Euclidean distance, Indicates the pre-stored fault location function, For the Fault categories of extended operation data samples, is the number of pre-stored fault categories, The index of the sample set of data for the extended run, is the weight coefficient.

[0010] In an implementable manner of the first aspect, converting according to the first fault category and the first fault occurrence probability to obtain a second fault category and a second fault occurrence probability includes: The second fault category and the second fault occurrence probability are calculated using the following formula: C Where C represents the second fault category, Indicates the possibility of the second fault occurring. Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Indicates The extended operation data sample corresponds to The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the number of pre-stored fault categories, Indicates The extended run data sample occurs The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the fault category number, Indicates the extended running data sample number.

[0011] In an implementable manner of the first aspect, performing error analysis based on the predicted output value and a pre-stored expected output value to obtain a first fault prediction model parameter includes: The first fault prediction model parameters are calculated by the following formula: in, represents the first fault prediction model parameter, Indicates the number of pre-stored fault categories, Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Represents the predicted output value, Indicates the expected output value stored in advance, Indicates the fault category number, Indicates the extended running data sample number.

[0012] In an implementable manner of the first aspect, performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters includes: Iterate using the gradient descent method according to the first fault prediction model parameters to obtain updated fault prediction model parameters; until the error between the predicted output value and the pre-stored expected output value is less than a preset threshold, terminate the iteration, and output the updated fault prediction model parameters at this time as the second fault prediction model parameters.

[0013] In a second aspect, the present invention provides a diesel generator set fault prediction model, comprising: A data acquisition module is used to acquire the operating data of the diesel generator set; A data processing module, used for performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; A high-dimensional mapping module, used for performing high-dimensional mapping according to the diesel generator set operation data sample set to obtain an extended operation data sample set; A distance calculation module, used for performing distance calculation according to the extended running data sample set to obtain a Euclidean distance; A feature extraction module, used for extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; A feature analysis module, configured to obtain a first fault category and a possibility of occurrence of a first fault by outputting the local features through a model; A data conversion module, configured to convert the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; A data output module, configured to perform a collective output according to the second fault category and the probability of occurrence of the second fault to obtain a predicted output value; an error analysis module, used to perform error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; A parameter iteration module, used to perform algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters; The result output module is used to adjust and optimize the pre-stored fault prediction model according to the second fault prediction model parameters and then output the result to obtain the fault prediction result.

[0014] In an implementable manner of the second aspect, performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set includes: Perform feature extraction based on the diesel generator set operation data to obtain attribute values ​​and feature vectors; Calculate the mean and variance of the attribute value to obtain the attribute value mean and the attribute value standard deviation; Performing integrated calculation based on the attribute value and the feature vector to obtain an operation data sample; Normalization processing is performed according to the operation data samples, the mean value of the attribute values ​​and the standard deviation of the attribute values ​​to obtain a set of operation data samples of the diesel generator set.

[0015] In an implementation manner of the second aspect, performing integrated calculation according to the attribute value and the feature vector to obtain the operation data sample includes: The running data sample is calculated by the following formula: in, Indicates the running data sample, Indicates the number of samples in the diesel generator set operation data set. The data sample attribute values, Indicates The feature vector of attribute values, Indicates The feature vector of attribute values, To control the neighborhood influence range parameters, The number of neighboring nodes with the highest similarity selected for the data samples in the diesel generator set operation data sample set, Represents the Euclidean distance between feature vectors.

[0016] In an implementable manner of the second aspect, extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features includes: The local features are calculated by the following formula: in, Represents local features, Samples in the extended run data sample set With sample The Euclidean distance, Samples in the extended run data sample set The extended run data sample set Samples corresponding to the location where the class fault occurs The Euclidean distance, Indicates the pre-stored fault location function, For the Fault categories of extended operation data samples, is the number of pre-stored fault categories, The index of the sample set of data for the extended run, is the weight coefficient.

[0017] In an implementable manner of the second aspect, converting according to the first fault category and the first fault occurrence probability to obtain a second fault category and a second fault occurrence probability includes: The second fault category and the second fault occurrence probability are calculated using the following formula: C Where C represents the second fault category, Indicates the possibility of the second fault occurring. Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Indicates The extended operation data sample corresponds to The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the number of pre-stored fault categories, Indicates The extended run data sample occurs The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the fault category number, Indicates the extended running data sample number.

[0018] In an implementable manner of the second aspect, performing error analysis based on the predicted output value and a pre-stored expected output value to obtain a first fault prediction model parameter includes: The first fault prediction model parameters are calculated by the following formula: in, represents the first fault prediction model parameter, Indicates the number of pre-stored fault categories, Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Represents the predicted output value, Indicates the expected output value stored in advance, Indicates the fault category number, Indicates the extended running data sample number.

[0019] In an implementable manner of the second aspect, performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters includes: Iterate using the gradient descent method according to the first fault prediction model parameters to obtain updated fault prediction model parameters; until the error between the predicted output value and the pre-stored expected output value is less than a preset threshold, terminate the iteration, and output the updated fault prediction model parameters at this time as the second fault prediction model parameters.

[0020] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the diesel generator set fault prediction method described in any one of the above is implemented.

[0021] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the diesel generator set fault prediction methods described above.

[0022] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for predicting faults of a diesel generator set, comprising: acquiring operating data of a diesel generator set; performing normalization processing on the operating data of the diesel generator set to obtain a sample set of operating data of the diesel generator set; performing high-dimensional mapping on the sample set of operating data of the diesel generator set to obtain an extended operating data sample set; performing distance calculation on the extended operating data sample set to obtain Euclidean distance; performing feature extraction on the basis of the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; performing output through a model on the basis of the local features to obtain a first fault category and a first fault occurrence possibility; performing conversion on the basis of the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; performing set output on the basis of the second fault category and the second fault occurrence possibility to obtain a predicted output value; performing error analysis on the basis of the predicted output value and a pre-stored expected output value to obtain a first fault prediction model parameter; performing algorithm iterative optimization on the basis of the first fault prediction model parameter to obtain a second fault prediction model parameter. The present invention obtains various operating data of a diesel generator set (such as load data, fuel flow, compressor air flow, diesel engine speed, diesel engine operating condition, and ambient temperature) through an information acquisition system; maps these original operating data samples to a higher-dimensional feature space to obtain an extended operating data sample set, and extracts local features based on the extended set; constructs a fault prediction model based on the local features, and the model outputs the fault category, the possibility of fault occurrence, and the corresponding local features of each extended operating data sample; adopts a stochastic gradient descent method to minimize the sum of squares of errors between the actual output and the expected output of the fault prediction model, optimizes the model parameters, and further improves the prediction accuracy by iteratively updating the parameters of the fault prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flow chart of a diesel generator set fault prediction method provided by the first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of a diesel generator set fault prediction model provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Reference Figure 1 The first embodiment of the present invention provides a method for predicting faults of a diesel generator set, comprising the following steps: S1, obtain the operating data of the diesel generator set; S2, performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; S3, performing high-dimensional mapping according to the diesel generator set operation data sample set to obtain an extended operation data sample set; S4, performing distance calculation according to the extended running data sample set to obtain a Euclidean distance; S5, extracting features according to the Euclidean distance and the pre-stored fault location occurrence function to obtain local features; S6, outputting the local features through a model to obtain a first fault category and a first fault occurrence probability; S7, converting according to the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; S8, performing a set output according to the second fault category and the second fault occurrence possibility to obtain a predicted output value; S9, performing error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; S10, performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters; S11, adjusting and optimizing the pre-stored fault prediction model according to the second fault prediction model parameters and outputting the result to obtain a fault prediction result.

[0026] In step S1, it is necessary to obtain the operating data of the diesel generator set.

[0027] Exemplarily, the diesel generator set operation data includes: generator voltage, generator frequency, and power output data of the set. Generator parameters include: rated generator voltage, rated power generation frequency, rated power, etc. The acquisition method is to track the diesel generator set for a long time through sensors, collect and store relevant data during the operation process.

[0028] In step S2, normalization processing is performed on the diesel generator set operation data to obtain a diesel generator set operation data sample set.

[0029] In the above step S2, the normalization process is performed on the diesel generator set operation data to obtain a diesel generator set operation data sample set, which specifically includes the following steps: S21, extracting features based on the diesel generator set operation data to obtain attribute values ​​and feature vectors.

[0030] In one feasible manner, feature extraction is performed based on the diesel generator set operating data to obtain attribute values ​​and feature vectors, including: for each operating data sample in the diesel generator set operating data, starting from its high-dimensional feature projection point, according to the feature dimension form and mapping function of the sample, constructing approximate projection points mapped to the low-dimensional space, and calculating the distances from these approximate projection points to several cycles before the failure; by calculating the Euclidean distance and sorting it, selecting the failure cycles corresponding to the first certain number of minimum distances as local features, these local features and the original features of the sample together constitute a feature vector, and the specific numerical value on each feature dimension is the attribute value.

[0031] S22, calculating the mean and variance according to the attribute value to obtain the attribute value mean and the attribute value standard deviation.

[0032] Exemplarily, the attribute value mean is obtained by summing the attribute values ​​of each sample and dividing the sum by the number of samples; the attribute value standard deviation is obtained by summing the difference between the attribute value of each sample and the attribute value mean.

[0033] S23, performing integration calculation based on the attribute value and the feature vector to obtain an operation data sample.

[0034] It should be noted that the running data sample is calculated by the following formula: in, Indicates the running data sample, Indicates the number of samples in the diesel generator set operation data set. The data sample attribute values, Indicates The feature vector of attribute values, Indicates The feature vector of attribute values, To control the neighborhood influence range parameters, The number of neighboring nodes with the highest similarity selected for the data samples in the diesel generator set operation data sample set, Represents the Euclidean distance between feature vectors.

[0035] The formula used in this embodiment is a data expansion method based on local information. By using neighborhood information and distance weighting, the data expression ability can be enhanced to a certain extent. For data processing of complex systems (such as diesel generator sets), it helps to improve the accuracy and reliability of subsequent data analysis and fault prediction. By expanding the original data using neighborhood information, the local structure and characteristics of the data can be better captured. When calculating the running data sample, the formula will find the first The original sample The most similar neighboring nodes. For example, for the original sample set , when calculating a sample When the extended data is Find the Most similar These neighboring nodes will participate in the subsequent weighted calculation to generate running data samples.

[0036] In this embodiment, the parameters in the control neighborhood influence range parameters need to be adjusted through experiments (such as cross-validation) to find the most suitable values ​​for the specific data set and task, so as to optimize the performance of the algorithm. For example, in fault prediction, by adjusting this parameter, the model can better utilize local sample information when predicting diesel generator set faults, thereby improving the prediction accuracy.

[0037] In an achievable manner, the process of obtaining the number of neighboring nodes with the highest similarity selected from the data sample set of the diesel generator set operation data sample comprises: calculating a The matrix ,in Representation sample and The similarity (or distance) between them; Calculate the matrix based on the selected similarity measure For each element in ,right No. Line (or Sort by similarity (or distance) from large to small (or small to large), and select the first The sample indices corresponding to the elements are of The neighboring nodes with the highest similarity.

[0038] S24, performing normalization processing according to the operation data sample, the mean value of the attribute value and the standard deviation of the attribute value to obtain a set of operation data samples of the diesel generator set.

[0039] It should be noted that the diesel generator set operation data sample set is calculated by the following formula: in, represents the diesel generator set operation data sample set, is the running data sample, It is The average value of the attribute, It is The standard deviation of the attribute values.

[0040] In step S3, high-dimensional mapping is performed based on the diesel generator set operation data sample set to obtain an extended operation data sample set.

[0041] In one achievable manner, high-dimensional mapping is performed on the diesel generator set operating data sample set to obtain an extended operating data sample set, including: preprocessing the diesel generator set operating data sample set, including normalization processing and building a fault model to obtain a sample set; selecting a suitable mapping function, such as using a specific formula to calculate the projection point and determine the mapping function coefficient, and iterative optimization through the Lagrange multiplier method; mapping the diesel generator set operating data sample set according to the mapping function, thereby obtaining an extended operating data sample set.

[0042] Exemplarily, a normalization function is used to normalize the operating data of the diesel generator set to avoid the interference of abnormal points on the entire parameter space training process. For example, the data can be normalized to a specific interval, such as [0,1] or [-1,1], etc. The specific normalization method can be selected according to the characteristics of the data and the requirements of the model. After obtaining the normalized operating data, a fault model is constructed using expert experience for all possible faults. The fault model includes the fault state and several cycles before the fault, and the corresponding fault cycle characteristics are the original operating data samples. The diesel generator set operating data sample set is: in, Representative Failure cycle characteristics, Represents the fault type corresponding to the fault cycle characteristics given by expert experience, and classifies them according to The vector expression is in the form of represents the number of features of the diesel generator set operation data sample set, Indicates The first extended run data sample The original features, , Represents the number of extended running data samples. The extended running data samples are mapped from the low-dimensional parameter set space to the higher-dimensional feature space to obtain projection points using a mapping function. The specific form of the mapping function to achieve the above mapping is as follows: express The projection points after mapping to high dimensions, is the mapping function coefficient, The calculation method is: in, After conversion The same dimension The original running data sample features, After conversion The same dimension The original running data sample features are determined by calculating the formula related to the cosine similarity .

[0043] According to the determined mapping function , for each sample in the diesel generator set running data sample set Mapping is performed to transform it from a low-dimensional space to a higher-dimensional feature space, thereby obtaining an extended running data sample set.

[0044] In step S4, distance calculation is performed based on the extended running data sample set to obtain the Euclidean distance.

[0045] In this embodiment, the Euclidean distance is used to measure the straight-line distance between two points in Euclidean space. and , the Euclidean distance between them The calculation formula is: For example, there are two two-dimensional vectors and , then the Euclidean distance between them is: In step S5, feature extraction is performed based on the Euclidean distance and the pre-stored fault location occurrence function to obtain local features.

[0046] It should be noted that the local features are calculated by the following formula: in, Represents local features, Samples in the extended run data sample set With sample The Euclidean distance, Samples in the extended run data sample set The extended run data sample set Samples corresponding to the location where the class fault occurs The Euclidean distance, Indicates the pre-stored fault location function, For the Fault categories of extended operation data samples, is the number of pre-stored fault categories, The index of the sample set of data for the extended run, is the weight coefficient.

[0047] In this embodiment, the pre-stored fault location function refers to a function used to determine the correlation between the sample and the fault location. For example, if the data contains the operating data of different components, the fault location function is a function that determines the component or operating status of the sample based on the characteristics of the sample data. If the predicted fault type If it is a "generator stator winding fault", then It may be possible to determine whether the sample comes from a monitoring point or operating state related to the generator stator winding based on the voltage, current, temperature and other characteristics in the sample. If so, , the sample is considered when calculating the local characteristics of this fault type; if not, , the sample is excluded from this calculation.

[0048] In step S6, the local features are outputted through the model to obtain the first fault category and the possibility of the first fault occurring.

[0049] In one feasible manner, the output is performed through a model according to the local features to obtain a first fault category and a possibility of a first fault occurrence, including: inputting the extracted local features into a pre-built fault prediction model, and continuously adjusting its internal parameters through optimization algorithms such as stochastic gradient descent to adapt to the characteristic patterns and fault laws of the data; after inputting the local features, the model performs calculations and inferences based on the mapping relationship between the learned features and the faults; for the output results obtained, the first fault category is determined through a specific conversion method, and the probability values ​​corresponding to different fault categories in the output are sorted, and the category with the largest probability is selected as the first fault category; and the possibility of the first fault occurrence corresponds to the probability value of the category in the model output.

[0050] In step S7, conversion is performed according to the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility.

[0051] It should be noted that the second fault category and the possibility of the second fault are calculated by the following formula: C Where C represents the second fault category, Indicates the possibility of the second fault occurring. Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Indicates The extended operation data sample corresponds to The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the number of pre-stored fault categories, Indicates The extended run data sample occurs The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the fault category number, Indicates the extended running data sample number.

[0052] In this embodiment, the second fault category and the second fault occurrence possibility refer to numerical values ​​obtained by converting the fault category and the fault occurrence possibility directly output by the model in a certain form.

[0053] In step S8, a set output is performed according to the second fault category and the second fault occurrence possibility to obtain a predicted output value.

[0054] For example, the second fault category and the second fault are processed through a series of data processing, model calculation and analysis to obtain a fault type identification with a higher probability. The probability of the second fault occurrence is expressed in the form of probability to indicate the degree of occurrence of the fault. When performing the set output, these two pieces of information are integrated to form a predicted output value.

[0055] In step S9, an error analysis is performed based on the predicted output value and the pre-stored expected output value to obtain the first fault prediction model parameter.

[0056] It should be noted that the first fault prediction model parameters are calculated by the following formula: in, represents the first fault prediction model parameter, Indicates the number of pre-stored fault categories, Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Represents the predicted output value, Indicates the expected output value stored in advance, Indicates the fault category number, Indicates the extended running data sample number.

[0057] In this embodiment, the first fault prediction model parameter refers to the preliminary fault prediction model parameter obtained by analyzing the predicted output value and the pre-stored expected output value by the preset model without iterative update. The pre-stored expected output value refers to the relatively ideal output value output by the fault model constructed by expert experience.

[0058] S10, performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters.

[0059] Exemplarily, according to the first fault prediction model parameters, the gradient of the model parameters is calculated using the stochastic gradient descent method. The stochastic gradient descent method randomly selects a small batch of samples in each iteration, calculates the gradients of these samples, and updates the model parameters. The specific update formula is: in are model parameters, is the learning rate, is the error function, For model parameters In the present invention, the first The number of sample failures, the optimal solution of the mapping function iteration and the historical sample The fault type of each fault is input into the logistic regression model, the output of the logistic regression model is calculated, and the gradient descent parameters are obtained based on the output and the number of historical sample faults, and then the model parameters are updated. The above process is repeated continuously, and the parameters of the fault prediction model are iteratively updated in each training cycle until the model converges. Convergence can be judged by monitoring indicators such as the loss function value or accuracy on the validation set. When these indicators no longer change significantly, the model is considered to have converged, thereby obtaining the second fault prediction model parameters.

[0060] In step S11, the pre-stored fault prediction model is adjusted and optimized according to the second fault prediction model parameters and then output to obtain a fault prediction result.

[0061] In a specific embodiment, the weights, biases or other key structures within the model are adjusted according to the second fault prediction model parameters. Exemplarily, for a neural network-based model, the weight values ​​of the connections between neurons are updated; the input data is processed and analyzed using the adjusted fault prediction model, and the input data is the operating data of the diesel generator set after preprocessing and feature extraction; the model will calculate the probability of occurrence of each fault category and related feature information based on its internal algorithm and new parameter settings. Finally, according to specific rules or thresholds, the most likely fault category is selected from the output of the model as the predicted fault type, and the final fault prediction result is determined by giving the corresponding confidence or other relevant information.

[0062] In summary, the present invention discloses a method for predicting faults of a diesel generator set, comprising: acquiring operating data of a diesel generator set; performing normalization processing on the operating data of the diesel generator set to obtain a sample set of operating data of the diesel generator set; performing high-dimensional mapping on the sample set of operating data of the diesel generator set to obtain an extended operating data sample set; performing distance calculation on the extended operating data sample set to obtain Euclidean distance; performing feature extraction on the basis of the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; performing output through a model based on the local features to obtain a first fault category and a first fault occurrence possibility; performing conversion based on the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; performing set output based on the second fault category and the second fault occurrence possibility to obtain a predicted output value; performing error analysis on the predicted output value and a pre-stored expected output value to obtain a first fault prediction model parameter; performing algorithm iterative optimization based on the first fault prediction model parameter to obtain a second fault prediction model parameter. The present invention obtains various operating data of a diesel generator set (such as load data, fuel flow, compressor air flow, diesel engine speed, diesel engine operating condition, and ambient temperature) through an information acquisition system; maps these original operating data samples to a higher-dimensional feature space to obtain an extended operating data sample set, and extracts local features based on the extended set; constructs a fault prediction model based on the local features, and the model outputs the fault category, the possibility of fault occurrence, and the corresponding local features of each extended operating data sample; adopts a stochastic gradient descent method to minimize the sum of squares of errors between the actual output and the expected output of the fault prediction model, optimizes the model parameters, and further improves the prediction accuracy by iteratively updating the parameters of the fault prediction model.

[0063] Reference Figure 2 The second embodiment of the present invention provides a diesel generator set fault prediction model, including: The data acquisition module 101 is used to acquire the operating data of the diesel generator set; The data processing module 102 is used to perform normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; A high-dimensional mapping module 103 is used to perform high-dimensional mapping according to the diesel generator set operation data sample set to obtain an extended operation data sample set; A distance calculation module 104 is used to perform distance calculation according to the extended operation data sample set to obtain a Euclidean distance; A feature extraction module 105 is used to extract features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; A feature analysis module 106, configured to obtain a first fault category and a first fault occurrence probability by outputting the local features through a model; A data conversion module 107, configured to convert the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; A data output module 108, configured to perform a collective output according to the second fault category and the second fault occurrence probability to obtain a predicted output value; An error analysis module 109 is used to perform error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; The parameter iteration module 110 is used to perform algorithm iteration optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters.

[0064] The result output module 111 is used to adjust and optimize the pre-stored fault prediction model according to the second fault prediction model parameters and then output the result to obtain a fault prediction result.

[0065] It should be noted that the diesel generator set fault prediction model provided in the embodiment of the present invention is used to execute all the process steps of the diesel generator set fault prediction method in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0066] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a diesel generator set fault prediction program. When the processor executes the computer program, the steps in the above-mentioned diesel generator set fault prediction method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0067] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0068] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0069] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0070] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0071] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0072] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0073] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A diesel generator set fault prediction method, characterized in that: Executed by a computer, including: Obtain diesel generator set operation data; Performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; Performing high-dimensional mapping on the diesel generator set operation data sample set to obtain an extended operation data sample set; Performing distance calculation based on the extended running data sample set to obtain a Euclidean distance; Extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; Outputting the local features through a model to obtain a first fault category and a first fault occurrence probability; Converting the first fault category and the first fault occurrence probability to obtain a second fault category and a second fault occurrence probability; Performing a collective output according to the second fault category and the second fault occurrence probability to obtain a predicted output value; Performing error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; Performing algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters; The pre-stored fault prediction model is adjusted and optimized according to the second fault prediction model parameters and then output to obtain a fault prediction result.

2. The diesel generator set fault prediction method according to claim 1, characterized in that: The normalization process is performed on the diesel generator set operation data to obtain a diesel generator set operation data sample set, including: Perform feature extraction based on the diesel generator set operation data to obtain attribute values ​​and feature vectors; Calculate the mean and variance of the attribute value to obtain the attribute value mean and the attribute value standard deviation; Performing integrated calculation based on the attribute value and the feature vector to obtain an operation data sample; Normalization processing is performed according to the operation data samples, the mean value of the attribute values ​​and the standard deviation of the attribute values ​​to obtain a set of operation data samples of the diesel generator set.

3. The diesel generator set fault prediction method according to claim 2, characterized in that: The step of performing integrated calculation based on the attribute value and the feature vector to obtain the operation data sample includes: The running data sample is calculated by the following formula: in, Indicates the running data sample, Indicates the number of samples in the diesel generator set operation data set. The data sample attribute values, Indicates The feature vector of attribute values, Indicates The feature vector of attribute values, To control the neighborhood influence range parameters, The number of neighboring nodes with the highest similarity selected for the data samples in the diesel generator set operation data sample set, Represents the Euclidean distance between feature vectors.

4. The diesel generator set fault prediction method according to claim 1, characterized in that: The extracting features according to the Euclidean distance and the pre-stored fault location occurrence function to obtain local features includes: The local features are calculated by the following formula: in, Represents local features, Samples in the extended run data sample set With sample The Euclidean distance, Samples in the extended run data sample set The extended run data sample set Samples corresponding to the location where the class fault occurs The Euclidean distance, Indicates the pre-stored fault location function, For the Fault categories of extended operation data samples, is the number of pre-stored fault categories, The index of the sample set of data for the extended run, is the weight coefficient.

5. The diesel generator set fault prediction method according to claim 1, characterized in that: The converting according to the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility includes: The second fault category and the second fault occurrence probability are calculated using the following formula: C Where C represents the second fault category, Indicates the possibility of the second fault occurring. Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Indicates The extended operation data sample corresponds to The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the number of pre-stored fault categories, Indicates The extended run data sample occurs The probability of the first fault of the type of fault, Indicates The extended operation data sample corresponds to The first fault category of the class fault, Indicates the fault category number, Indicates the extended running data sample number.

6. The diesel generator set fault prediction method according to claim 1, characterized in that: The performing error analysis based on the predicted output value and the pre-stored expected output value to obtain the first fault prediction model parameter includes: The first fault prediction model parameters are calculated by the following formula: in, represents the first fault prediction model parameter, Indicates the number of pre-stored fault categories, Indicates the number of extended operation data samples in the pre-stored extended operation data sample set, Represents the predicted output value, Indicates the expected output value stored in advance, Indicates the fault category number, Indicates the extended running data sample number.

7. The diesel generator set fault prediction method according to claim 1, characterized in that: The iterative optimization of the algorithm according to the first fault prediction model parameters to obtain the second fault prediction model parameters includes: Iterate using the gradient descent method according to the first fault prediction model parameters to obtain updated fault prediction model parameters; until the error between the predicted output value and the pre-stored expected output value is less than a preset threshold, terminate the iteration, and output the updated fault prediction model parameters at this time as the second fault prediction model parameters.

8. A diesel generator set fault prediction model, characterized in that: include: A data acquisition module is used to acquire the operating data of the diesel generator set; A data processing module, used for performing normalization processing on the diesel generator set operation data to obtain a diesel generator set operation data sample set; A high-dimensional mapping module, used for performing high-dimensional mapping according to the diesel generator set operation data sample set to obtain an extended operation data sample set; A distance calculation module, used for performing distance calculation according to the extended running data sample set to obtain a Euclidean distance; A feature extraction module, used for extracting features according to the Euclidean distance and a pre-stored fault location occurrence function to obtain local features; A feature analysis module, configured to obtain a first fault category and a possibility of occurrence of a first fault by outputting the local features through a model; A data conversion module, configured to convert the first fault category and the first fault occurrence possibility to obtain a second fault category and a second fault occurrence possibility; A data output module, configured to perform a collective output according to the second fault category and the probability of occurrence of the second fault to obtain a predicted output value; an error analysis module, used to perform error analysis based on the predicted output value and the pre-stored expected output value to obtain a first fault prediction model parameter; A parameter iteration module, used to perform algorithm iterative optimization according to the first fault prediction model parameters to obtain second fault prediction model parameters; The result output module is used to adjust and optimize the pre-stored fault prediction model according to the second fault prediction model parameters and then output the result to obtain the fault prediction result.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for predicting faults of a diesel generator set as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the diesel generator set fault prediction method according to any one of claims 1 to 7.

Images