Early warning method, device, medium and product for fouling failure of centrifugal compressor

Abstract

The application discloses a kind of early warning methods, equipment, medium and product for centrifugal compressor fouling failure, involve fault detection technical field, the method includes obtaining the roughness of surface of parts in target centrifugal compressor and static pressure;Roughness of surface of parts includes impeller surface roughness and diffuser surface roughness;Roughness of surface of parts and static pressure are input to trained running state prediction model, and the degree of fouling failure of target centrifugal compressor is obtained;Trained running state prediction model is the prediction model based on new evaluation index of equipment running state;New evaluation index of equipment running state is the evaluation index constructed according to predicted flow field data and actual flow field data;Flow field data includes correction volume flow, pressure ratio and isentropic efficiency.The application can realize accurate early warning to centrifugal compressor fouling failure based on new evaluation index.

Description

Technical Field

[0001] This application relates to the field of fault detection technology, and in particular to a method, device, medium and product for early warning of fouling faults in centrifugal compressors. Background Technology

[0002] Engines, as common power units, are widely used in ships, automobiles, power generation, and other fields. With the increasing power output demands of marine engines, turbochargers have become a core component of diesel engines. However, during the operation of marine diesel engines, particles such as dust and salt spray from the atmosphere gradually adhere to the surface of the compressor blades, forming deposits that cause engine performance degradation. As one of the main components of a turbocharger, the centrifugal compressor is inevitably affected by these risks during operation, leading to performance degradation, increased fuel consumption, increased maintenance costs, and a reduced stable operating range.

[0003] Increased blade surface roughness has been shown to have a significant impact on compressor aerodynamic performance. Studies have shown that increased surface roughness of compressor blades, due to the ingestion of corrosive substances and foreign matter such as sand particles, affects blade geometry, leading to a reduction in the effective flow area of ​​the flow channel. This change causes the compressor to deviate from its design parameters, thereby reducing its overall performance. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium, and product for early warning of fouling faults in centrifugal compressors, which can achieve accurate early warning of fouling faults in centrifugal compressors.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] In a first aspect, this application provides a method for early warning of fouling failure in centrifugal compressors, comprising:

[0007] Obtain the surface roughness and static pressure of components in the target centrifugal compressor; the surface roughness of the components includes the impeller surface roughness and the diffuser surface roughness.

[0008] The surface roughness and static pressure of the components are input into the trained operating status prediction model to obtain the degree of fouling failure of the target centrifugal compressor. The trained operating status prediction model is a prediction model based on a new evaluation index of equipment operating status. The new evaluation index of equipment operating status is an evaluation index constructed based on the predicted flow field data and the actual flow field data. The flow field data includes corrected volumetric flow rate, pressure ratio and compression efficiency.

[0009] Optionally, the training process of the running state prediction model is as follows:

[0010] The surface roughness and static pressure of several sample components were designed using CFD simulation, and the sample flow field data corresponding to the surface roughness and static pressure of the sample components were obtained. The surface roughness of the sample components included the surface roughness of the sample impeller and the surface roughness of the sample diffuser. The sample flow field data included the sample corrected volumetric flow rate, the sample pressure ratio, and the sample isentropic efficiency.

[0011] Using the surface roughness and static pressure of the sample components as input, and the sample flow field data corresponding to the surface roughness and static pressure of the sample components as labels, the deep forest model is trained to obtain the trained optimal deep forest model; the trained optimal deep forest model is used to output the flow field data of the target centrifugal compressor.

[0012] The new evaluation index of equipment operating status and the preset fault threshold are imported into the trained optimal deep forest model to obtain the trained operating status prediction model. The trained operating status prediction model is used to: obtain the current operating status value of the target centrifugal compressor based on the flow field data of the target centrifugal compressor output by the trained optimal deep forest model and the new evaluation index of equipment operating status; and determine the degree of fouling fault of the equipment based on the current operating status value and the preset fault threshold. The current operating status value is represented by the area enclosed by the pressure ratio-corrected volumetric flow rate curve composed of pressure ratio, efficiency and corrected volumetric flow rate in the flow field data and the pressure ratio axis.

[0013] Optionally, the formula expression for the new evaluation index of the equipment operating status is:

[0014]

[0015] Where ΔS is a new evaluation index for equipment operating status, S 预测 The area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from the predicted flow field data and the pressure ratio axis; the S 实际 This represents the area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from actual flow field data and the pressure ratio axis.

[0016] Optionally, the S 实际 The solution expression is:

[0017]

[0018] Where n represents the number of vertices, x i y i Let x and y be the x and y coordinates of the i-th vertex. i+1 y i+1 Let x and y be the coordinates of the (i+1)th vertex. n y nLet x and y be the coordinates of the nth vertex.

[0019] Optionally, based on the current operating status values ​​of the device and a preset fault threshold, the degree of scale buildup fault of the device is determined, specifically including:

[0020] When the current operating status value of the equipment is greater than the first fault threshold, the target centrifugal compressor is determined to be in normal operating condition.

[0021] When the current operating status value of the equipment is greater than or equal to the second fault threshold and less than the first fault threshold, the target centrifugal compressor is judged to be in a minor fault state.

[0022] When the current operating status value of the equipment is greater than or equal to the third fault threshold and less than the second fault threshold, the target centrifugal compressor is judged to be in a normal fault state.

[0023] When the current operating status value of the equipment is less than the third fault threshold, the target centrifugal compressor is judged to be in a serious fault state.

[0024] Optionally, the pressure ratio is a total-total pressure ratio, which refers to the ratio of the total pressure at the equipment outlet to the total pressure at the equipment inlet.

[0025] Optionally, the roughness setting range of the sample impeller surface roughness among the several sample component surface roughnesses is 1 to 150 μm; the roughness setting range of the sample diffuser surface roughness is 1 to 150 μm.

[0026] In a second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for early warning of fouling faults in centrifugal compressors as described above.

[0027] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements one of the above-described methods for early warning of fouling faults in centrifugal compressors.

[0028] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements one of the above-described methods for early warning of fouling faults in centrifugal compressors.

[0029] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0030] This application provides a method, device, medium, and product for early warning of fouling failures in centrifugal compressors. The method involves acquiring the surface roughness and static pressure values ​​of components in the target centrifugal compressor; the surface roughness includes the surface condition of the impeller and diffuser. Subsequently, these surface roughness data and static pressure values ​​are input into a trained operational status prediction model to assess the degree of fouling failure in the target centrifugal compressor. This operational status prediction model is built based on new equipment operational status evaluation indicators, which are formed by comparing predicted flow field data with actual flow field data. The flow field data includes key parameters such as corrected volumetric flow rate, pressure ratio, and isentropic efficiency. This application utilizes these new evaluation indicators to achieve accurate early warning of fouling failures in centrifugal compressors. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is an application environment diagram of an early warning method for fouling faults in centrifugal compressors according to an embodiment of this application.

[0033] Figure 2 This is a flowchart illustrating an early warning method for fouling faults in centrifugal compressors, provided as an embodiment of this application.

[0034] Figure 3 A pressure ratio-corrected volumetric flow rate diagram provided in one embodiment of this application.

[0035] Figure 4 An efficiency-corrected volumetric flow rate diagram is provided for one embodiment of this application.

[0036] Figure 5 This is a schematic diagram illustrating the solution of a new evaluation index for equipment operating status provided in an embodiment of this application.

[0037] Figure 6 A flowchart illustrating the compressor fouling fault early warning process based on a method combining a deep forest model and a new evaluation index, provided in an embodiment of this application.

[0038] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] The purpose of this application is to provide a method, device, medium, and product for early warning of fouling faults in centrifugal compressors, which can achieve accurate early warning of fouling faults in centrifugal compressors.

[0041] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] The early warning method for centrifugal compressor fouling faults provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send the surface roughness and static pressure of the components to be processed to server 104. After receiving the surface roughness and static pressure, server 104 obtains the surface roughness and static pressure of the components in the target centrifugal compressor; the surface roughness includes the impeller surface roughness and diffuser surface roughness; the surface roughness and static pressure are input into a trained operating state prediction model to obtain the degree of fouling failure of the target centrifugal compressor; the trained operating state prediction model is a prediction model based on a new evaluation index of equipment operating state; the new evaluation index of equipment operating state is an evaluation index constructed based on predicted flow field data and actual flow field data; the flow field data includes corrected volumetric flow rate, pressure ratio, and isentropic efficiency. Server 104 can feed back the degree of fouling fault of the target centrifugal compressor to terminal 102. Furthermore, in some embodiments, the early warning method for centrifugal compressor fouling faults can also be implemented separately by server 104 or terminal 102. For example, terminal 102 can directly process the data on the surface roughness and static pressure of the component to be processed, or server 104 can obtain the surface roughness and static pressure of the component to be processed from the data storage system and process the data accordingly.

[0043] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0044] In one exemplary embodiment, such as Figure 2 As shown, a method for early warning of fouling faults in centrifugal compressors is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 202.

[0045] in:

[0046] Step 201: Obtain the surface roughness and static pressure of the components in the target centrifugal compressor; the surface roughness of the components includes the impeller surface roughness and the diffuser surface roughness.

[0047] Step 202: Input the surface roughness and static pressure of the components into the trained operating state prediction model to obtain the degree of fouling failure of the target centrifugal compressor; the trained operating state prediction model is a prediction model based on the new evaluation index of equipment operating state; the new evaluation index of equipment operating state is an evaluation index constructed based on the predicted flow field data and the actual flow field data; the flow field data includes corrected volumetric flow rate, pressure ratio and isentropic efficiency.

[0048] The training process of the running state prediction model is as follows:

[0049] Step 301: Design the surface roughness and static pressure of several sample components through CFD simulation, and obtain the sample flow field data corresponding to the surface roughness and static pressure of the sample components; the surface roughness of the sample components includes the surface roughness of the sample impeller and the surface roughness of the sample diffuser; the sample flow field data includes the sample corrected volumetric flow rate, the sample pressure ratio and the sample isentropic efficiency.

[0050] Step 302: Construct a deep forest model.

[0051] Step 303: Using the surface roughness and static pressure of the sample components as input, and the sample flow field data corresponding to the surface roughness and static pressure of the sample components as labels, train the deep forest model to obtain the trained optimal deep forest model; the trained optimal deep forest model is used to output the flow field data of the target centrifugal compressor.

[0052] Step 304: Import the new evaluation index of equipment operating status and the preset fault threshold into the trained optimal deep forest model to obtain the trained operating status prediction model; the trained operating status prediction model is used to: obtain the current operating status value of the target centrifugal compressor based on the flow field data of the target centrifugal compressor output by the trained optimal deep forest model and the new evaluation index of equipment operating status; and determine the degree of fouling fault of the equipment based on the current operating status value and the preset fault threshold; the current operating status value is represented by the area enclosed by the pressure ratio-corrected volumetric flow rate curve composed of pressure ratio, corrected volumetric flow rate and efficiency in the flow field data and the pressure ratio axis.

[0053] The formula for the new evaluation index of equipment operating status is as follows:

[0054]

[0055] Where ΔS is a new evaluation index for equipment operating status, S 预测 The area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from the predicted flow field data and the pressure ratio axis; the S 实际 This represents the area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from actual flow field data and the pressure ratio axis.

[0056] Specifically, the S 实际 The solution expression is:

[0057]

[0058] Where n represents the number of vertices, x i y i Let x and y be the x and y coordinates of the i-th vertex. i+1 y i+1 Let x and y be the coordinates of the (i+1)th vertex. n y n Let x and y be the coordinates of the nth vertex.

[0059] The process after step 301 includes:

[0060] Data preprocessing, including outlier detection, data normalization, and feature engineering, ensures data quality and the effectiveness of model training. The preprocessed data is then divided into training, validation, and test sets in an 8:2 ratio to facilitate subsequent model training and evaluation.

[0061] Specifically, different surface roughnesses and static pressures of the impeller and diffuser are used as input data (samples), and the corrected volumetric flow rate, pressure ratio, and isentropic efficiency of the samples are used as output data. The pressure ratio is the total-total pressure ratio, which refers to the ratio of the total pressure at the equipment outlet to the total pressure at the equipment inlet.

[0062] In the obtained samples, the roughness settings for both the impeller and diffuser ranged from 1 μm to 150 μm, totaling 100 sets of calculations. The specific roughness settings for the impeller were 1, 5, 10, 15, 25, 35, 50, 75, 100, and 150; the roughness settings for the diffuser were the same as for the impeller. Details are shown in the table below:

[0063] Table 1 Roughness Settings

[0064]

[0065]

[0066] Specifically, when executing step 302, the following can be done:

[0067] A deep forest model is constructed and trained using grid search and cross-validation. The model's hyperparameters are systematically tuned to obtain the model with the highest prediction accuracy. Grid search traverses a series of preset hyperparameter combinations, while cross-validation evaluates the performance of each parameter combination by repeatedly splitting the training and validation sets, ultimately selecting the optimal parameter settings.

[0068] Specifically, during model construction, the model structure and hyperparameter range are determined, a suitable deep forest model structure is selected, and the hyperparameters requiring optimization are identified. Data preprocessing involves standardizing or normalizing the data. A grid search is performed to traverse all preset hyperparameter combinations, the model is trained, and its performance is evaluated. Cross-validation is then performed, re-split the training and validation sets, and the average of multiple results is taken. The optimal parameter combination is selected, the final model is trained, and its generalization performance is evaluated using a test set.

[0069] When the model structure is determined, an adaptive deep forest model is chosen, specifying the appropriate number of layers in the cascade structure and the number of random forest trees in each layer. The maximum number of layers in the cascade structure is 2. The initial number of random forest layers is 130. After each subsequent layer, the number of trees increases by "2 * the number of layers," meaning that for every additional layer, the number of trees in the random forest increases by 2. For example, the first layer has 130 trees; the second layer has 130 + 2 * 1 = 132 trees, and so on.

[0070] After performing step 302, data preprocessing is also included, which can be as follows:

[0071] In data preprocessing, standardization is chosen to eliminate dimensional differences between different feature data. By adjusting the scale of the data, standardization makes each feature comparable in statistical processing, thus ensuring equal weighted contributions from different features in the model. Standardization not only helps optimize the numerical stability of the model during training but also accelerates model convergence. The standardization formula is as follows:

[0072] X` = (X - μ) / σ.

[0073] Where X represents the original data, X' represents the standardized data, μ is the mean of X, and σ is the standard deviation of X.

[0074] In step 303, the deep forest model was trained using grid search and cross-validation, as detailed below:

[0075] The hyperparameters are determined for each random forest: the number of trees, the maximum depth of each tree, the minimum number of samples per leaf node, and the number of forests in each cascaded layer. A reasonable search range is set for each hyperparameter. The mean squared error is used to evaluate the performance index corresponding to each parameter combination. The mean squared error formula is shown below:

[0076]

[0077] Where n is the number of samples; y i This represents the true value of the i-th sample; This represents the predicted value of the i-th sample.

[0078] When performing cross-validation, k-fold cross-validation is used, with k set to 5. The specific steps are as follows: the dataset is randomly divided into k equal-sized subsets; each time, one subset is selected as the validation set, and the remaining k-1 subsets are used as the training set. This is repeated k times, using a different subset as the validation set each time. The final performance evaluation result is the average of the k validation results.

[0079] The impeller roughness, diffuser roughness, and static pressure were selected as input data; the corrected volumetric flow rate, pressure ratio, and efficiency were selected as output data. The optimal model was validated using validation set data, and the accuracy of each output data was verified using mean square error.

[0080] The further construction of the validation set data is shown in Table 2 below:

[0081] Table 2 Validation Set Data Table

[0082]

[0083] Furthermore, the prediction results of the validation set data are as follows: Figure 3 and Figure 4 As shown:

[0084] Based on the comparison between the actual results and the predicted results of validation cases 1, 2, and 3, the predicted errors of the corrected volumetric flow rate, pressure ratio, and efficiency for the three validation cases are shown in Table 3 below:

[0085] Table 3 Corrected prediction errors for volumetric flow rate, pressure ratio, and efficiency.

[0086] MSE Corrected volumetric flow rate pressure ratio efficiency Verification Case 1 0.000588 3.0e-06 0.0115 Verification Case 2 0.000746 6.94e-06 0.0142 Verification Case 3 0.00143 2.46e-06 0.005

[0087] Among them, Figure 3 On the PV (pressure ratio-corrected volumetric flow rate) plot, select a point from which the efficiency is at least 60% to the point of maximum efficiency for the equipment to obtain the pressure ratio-corrected volumetric flow rate curve. The area enclosed by this curve and the Y-axis (representing the pressure ratio axis here) can be used to construct a new physical quantity S (the current operating value of the equipment). Figure 5 As shown, a common challenge in model evaluation is accurately assessing the overall predictive accuracy of a model from multiple output variables. For example, if a model predicts three different outputs, such as corrected volumetric flow rate, pressure ratio, and efficiency, each output will have its own mean squared error (MSE). These errors measure the difference between the model's predictions and the actual data, but considering these errors in isolation can complicate the evaluation process and lead to misunderstandings of model performance because the magnitude and importance of each metric may differ.

[0088] To address this issue, this embodiment employs a unified new evaluation metric, ΔS, which combines the prediction errors of multiple outputs into a single comprehensive index. The aim is to provide a more holistic perspective for evaluating the overall model performance, while reducing the interference and misleading potential of a single output error metric.

[0089]

[0090] Furthermore, since the actual pressure ratio-efficiency curve is not a complete circle but rather composed of individual coordinate points, this patent uses the Gaussian area formula to solve for S. The Gaussian area formula, commonly known as the shoelace formula, can be used to calculate the area of ​​a polygon. For example, given the vertex coordinates of a polygon (x0, y0), (x1, y2), ..., (x... n y n ),(x n+1 y n+1 Connecting these vertices in sequence forms an irregular closed polygon. The shoelace formula can be used to calculate the actual area S of this polygon.

[0091]

[0092] Where n represents the number of vertices, x i y i Let x and y be the x and y coordinates of the i-th vertex. i+1 y i+1 Let x and y be the coordinates of the (i+1)th vertex. n y n Let x and y be the coordinates of the nth vertex. The prediction results obtained based on the new evaluation index are shown in Table 4 below:

[0093] Table 4 Prediction Results

[0094] <![CDATA[S 实际 ]]> <![CDATA[S 预测 ]]> ΔS Verification Case 1 7.88 7.83 0.00635 Verification Case 2 8.77 8.83 0.00684 Verification Case 3 9.43 9.45 0.00212

[0095] Specifically, when performing step 304, based on the current operating status value of the device and a preset fault threshold, to determine the degree of scale buildup fault, the following steps are included:

[0096] When the current operating status value of the equipment is greater than the first fault threshold, the target centrifugal compressor is determined to be in normal operating condition.

[0097] When the current operating status value of the equipment is greater than or equal to the second fault threshold and less than the first fault threshold, the target centrifugal compressor is judged to be in a minor fault state.

[0098] When the current operating status value of the equipment is greater than or equal to the third fault threshold and less than the second fault threshold, the target centrifugal compressor is judged to be in a normal fault state.

[0099] When the current operating status value of the equipment is less than the third fault threshold, the target centrifugal compressor is judged to be in a serious fault state.

[0100] Specifically, when the roughness at the impeller is 15 μm and the roughness at the diffuser is 15 μm, S is 9.81;

[0101] When the roughness at the impeller is 50 μm and the roughness at the diffuser is 50 μm, S is 8.35;

[0102] When the roughness at the impeller is 75 μm and the roughness at the diffuser is 75 μm, S is 7.87.

[0103] Therefore, when S is set to greater than 9.81, the compressor is in normal condition.

[0104] When S is greater than or equal to 8.35 and less than 9.81: it indicates a minor fault.

[0105] When S is greater than or equal to 7.87 and less than 8.35: compressor malfunction.

[0106] When S is less than or equal to 7.87: indicates a serious fault.

[0107] Specifically, the new physical quantity S can be expressed as shown in Table 5 below:

[0108] Table 5 Fault Diagnosis Table

[0109]

[0110] By assessing the impact of roughness on the performance of compressor impellers and diffusers, different operating states can be classified according to preset roughness thresholds. Based on this framework, the roughness index of Validation Case 1 indicates a faulty state, defined by an S value exceeding 7.87 but not reaching 8.35. Meanwhile, the S values ​​of Validation Cases 2 and 3 fall within the range of 8.35 to 9.81, indicating that both cases are in a state of minor fault. This classification is consistent with actual observations, confirming the effectiveness of using the new evaluation index to determine the compressor's operating status.

[0111] In some exemplary embodiments, such as Figure 6 As shown, a method combining a deep forest model with a new evaluation index is provided to achieve early warning of compressor fouling faults. The specific steps are as follows:

[0112] A1. Input of raw data:

[0113] Load and read the raw data table. The input raw data D = [X, Y, Z] is a sequence of three data elements, representing impeller roughness, diffuser roughness, and static pressure, respectively. Ensure the data is loaded correctly, in preparation for subsequent analysis.

[0114] A2. Data Preprocessing:

[0115] Data cleaning of the original data D involves steps including removing duplicate rows, filling in missing values, and identifying and handling outliers. The purpose of data cleaning is to ensure the integrity and consistency of the data, providing high-quality data input for the model.

[0116] A3. Construction of the Deep Forest Model:

[0117] To construct an adaptive deep forest model based on the characteristics of the data, the first step is to determine the number of layers in the cascaded structure and the number of random forests contained in each layer. These structural parameters will determine the complexity and adaptability of the model.

[0118] A4. Grid search and cross-validation:

[0119] Select hyperparameters for the model, including the number of trees in each random forest, the maximum tree depth, the minimum number of samples in a leaf node, and the number of forests in each cascaded layer. Find the optimal combination of parameters within the defined parameter range using grid search, and evaluate the model performance using 5-fold cross-validation. The average of the cross-validation results will be used as the final performance metric for the model.

[0120] A5. Optimal Model Output:

[0121] The model is optimized and tuned based on the results of the validation set, and its performance is evaluated using the test set to ensure it meets the expected metrics. The final output model is the training result based on the optimal parameters and structure.

[0122] B1. Introduction of new evaluation indicators:

[0123] New evaluation metrics are introduced, taking into account modified volumetric flow rate, pressure ratio, and efficiency, to provide a more comprehensive assessment of system performance.

[0124] A6. Prediction Results Output:

[0125] Based on the new evaluation index, a new physical quantity S is output to evaluate the current operating status of the equipment.

[0126] B2. Importing fault thresholds:

[0127] The preset fault thresholds are imported into the model, and the prediction results S are matched with these thresholds to determine whether the equipment is in normal operating condition.

[0128] A7. Fault Warning:

[0129] The current operating status S of the device is compared with the set fault threshold. If it exceeds a certain fault range, the device outputs the current fault warning level, indicating the potential fault risk of the device.

[0130] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores fault diagnosis results. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an early warning method for centrifugal compressor fouling faults.

[0131] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0132] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0133] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0134] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0137] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0138] In summary, this application has the following technical effects:

[0139] 1) The fault early warning method provided in this application can objectively assess the operating status of the compressor by using quantified roughness values, reducing the interference of subjective judgment and improving the accuracy of assessment.

[0140] 2) The fault early warning method provided in this application can detect small changes or anomalies in system performance earlier, thereby helping to identify potential faults or performance degradation in advance.

[0141] 3) The new evaluation metrics provided in this application are based on specific physical or engineering principles, which can better explain the behavior of models or systems. Furthermore, they can integrate multiple factors to provide a more comprehensive assessment of system performance.

[0142] 4) The new evaluation metrics provided in this application can improve the accuracy of fault early warning, reduce false alarms and missed alarms, and help the maintenance team make more effective decisions.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for early warning of fouling failure in centrifugal compressors, characterized in that, The aforementioned early warning method for centrifugal compressor fouling faults includes: Obtain the surface roughness and static pressure of components in the target centrifugal compressor; the surface roughness of the components includes the impeller surface roughness and the diffuser surface roughness; The surface roughness and static pressure of the components are input into a trained operating state prediction model to obtain the degree of fouling failure of the target centrifugal compressor. The trained operating state prediction model is a prediction model based on a new evaluation index of equipment operating state. The new evaluation index of equipment operating state is an evaluation index constructed based on predicted flow field data and actual flow field data. The flow field data includes corrected volumetric flow rate, pressure ratio, and compression efficiency. The training process of the operational status prediction model is as follows: The surface roughness and static pressure of several sample components were designed using CFD simulation, and the corresponding sample flow field data were obtained. The surface roughness of the sample components included the surface roughness of the sample impeller and the surface roughness of the sample diffuser. The sample flow field data included the sample corrected volumetric flow rate, sample pressure ratio, and sample isentropic efficiency. Using the surface roughness and static pressure of the sample components as input, and the sample flow field data corresponding to the surface roughness and static pressure of the sample components as labels, the deep forest model is trained to obtain the trained optimal deep forest model; the trained optimal deep forest model is used to output the flow field data of the target centrifugal compressor. The new evaluation index of equipment operating status and the preset fault threshold are imported into the trained optimal deep forest model to obtain the trained operating status prediction model. The trained operating status prediction model is used to: obtain the current operating status value of the target centrifugal compressor based on the flow field data of the target centrifugal compressor output by the trained optimal deep forest model and the new evaluation index of equipment operating status; and determine the degree of fouling fault of the equipment based on the current operating status value and the preset fault threshold. The current operating status value is represented by the area enclosed by the pressure ratio-corrected volumetric flow rate curve composed of pressure ratio, efficiency and corrected volumetric flow rate in the flow field data and the pressure ratio axis.

2. The early warning method for fouling faults in centrifugal compressors according to claim 1, characterized in that, The formula for the new evaluation index of equipment operating status is as follows: Where ΔS is a new evaluation index for equipment operating status, S 预测 The area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from the predicted flow field data and the pressure ratio axis; the S 实际 This represents the area enclosed by the pressure ratio-corrected volumetric flow rate curve obtained from actual flow field data and the pressure ratio axis.

3. The early warning method for fouling faults in centrifugal compressors according to claim 2, characterized in that, Based on the current operating status values ​​of the equipment and a preset fault threshold, the degree of scale buildup fault of the equipment is determined, specifically including: When the current operating status value of the equipment is greater than the first fault threshold, the target centrifugal compressor is determined to be in normal operating condition. When the current operating status value of the equipment is greater than or equal to the second fault threshold and less than the first fault threshold, the target centrifugal compressor is judged to be in a minor fault state. When the current operating status value of the equipment is greater than or equal to the third fault threshold and less than the second fault threshold, the target centrifugal compressor is judged to be in a normal fault state. When the current operating status value of the equipment is less than the third fault threshold, the target centrifugal compressor is judged to be in a serious fault state.

4. The early warning method for fouling faults in centrifugal compressors according to claim 3, characterized in that, The pressure ratio is the total-total pressure ratio, which refers to the ratio of the total pressure at the equipment outlet to the total pressure at the equipment inlet.

5. The early warning method for fouling faults in centrifugal compressors according to claim 4, characterized in that, The surface roughness of the sample impeller is set in the range of 1 to 150 μm; the surface roughness of the sample diffuser is set in the range of 1 to 150 μm.

6. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement a method for early warning of fouling failure in a centrifugal compressor according to any one of claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements a method for early warning of fouling faults in centrifugal compressors as described in any one of claims 1-5.

8. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements a method for early warning of fouling faults in centrifugal compressors as described in any one of claims 1-5.

Images