A method and system for detecting and processing a fault of a flue gas waste heat recovery device

Abstract

The present invention discloses a fault detection and processing method and system for a flue gas waste heat recovery device, comprising: obtaining operating data of the flue gas waste heat recovery device within a preset period; preprocessing the operating data; inputting the preprocessed operating data into a pre-trained fault detection model for detection to determine the detection result; obtaining a solution strategy corresponding to the detection result; processing the fault of the flue gas waste heat recovery device based on the solution strategy; being able to monitor the operating status of the equipment in real time, and compared with the lag of manual inspection, being able to capture early abnormal signals of the equipment in time, avoiding the subjectivity and inaccuracy of manual judgment, greatly improving the accuracy of fault detection, and being able to identify various types of fault hazards more quickly and accurately.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving equipment, and in particular to a fault detection and processing method and system for a flue gas waste heat recovery device. Background Art

[0002] With the continuous expansion of industrial production and increasing demands for energy efficiency and environmental protection, various energy-saving devices are playing a key role in various fields. In industrial production, energy-saving pumps, energy-saving gas compressors, and energy-saving hydraulic and pneumatic components, by optimizing their operating mechanisms, effectively reduce energy consumption during production and improve the overall energy efficiency of industrial systems. In daily life and commercial settings, energy-saving refrigeration and air-conditioning equipment, energy-saving refrigerators and freezers, energy-saving air conditioners, and dual-mode solar heat pump air-conditioning units, with their high efficiency and energy-saving properties, meet people's comfort needs while significantly reducing electricity and other energy use. Flue gas waste heat recovery devices, as a key component of industrial energy recovery and utilization, also play a vital role in many industrial fields. These devices effectively recover the large amounts of waste heat carried by flue gases during industrial production, converting it into usable energy. This significantly improves energy efficiency, reduces energy consumption and production costs for enterprises, and reduces the thermal pollution caused by the direct emission of high-temperature flue gases, thus aligning with the concept of sustainable development.

[0003] However, in actual operation, flue gas waste heat recovery units face numerous complex and challenging operating conditions. For one thing, the flue gas generated by industrial production has a complex composition, potentially containing corrosive gases and dust particles. These substances can continuously erode and wear the unit's internal structures and heat exchange components, leading to frequent equipment failures. For example, acidic gases can corrode metal components, reducing the strength and service life of the equipment; dust accumulation can also affect heat exchange efficiency, further degrading unit performance. Furthermore, the units are exposed to harsh, high-temperature, and high-pressure environments for extended periods, making mechanical components susceptible to fatigue damage and seal failure. Currently, traditional fault detection methods often rely on manual inspections, which are inefficient and subject to significant human influence, making it difficult to detect potential faults early and accurately. Once a fault occurs, the lack of effective fault diagnosis and treatment strategies often leads to prolonged downtime for maintenance. This not only severely impacts the continuity of industrial production and causes significant economic losses, but can also lead to more serious equipment damage due to delayed maintenance. Therefore, there is an urgent need for efficient and intelligent fault detection and treatment methods. Summary of the Invention

[0004] The present invention aims to at least partially address one of the technical problems encountered in the aforementioned technologies. To this end, the first aspect of the present invention is to provide a fault detection and processing method for a flue gas waste heat recovery device, which can monitor the operating status of the device in real time. Compared to the lag of manual inspections, this method can promptly capture early abnormal signals from the device, avoiding the subjectivity and inaccuracy of manual judgment. This method greatly improves the accuracy of fault detection and enables faster and more accurate identification of various potential fault hazards.

[0005] A second aspect of the present invention aims to provide a fault detection and processing system for a flue gas waste heat recovery device.

[0006] To achieve the above objectives, a first embodiment of the present invention provides a method for detecting and processing a fault in a flue gas waste heat recovery device, comprising:

[0007] Obtaining the operating data of the flue gas waste heat recovery device within a preset period;

[0008] Preprocessing the operating data;

[0009] Input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results;

[0010] Obtain the solution strategy corresponding to the test results;

[0011] The failure of the flue gas waste heat recovery device is handled based on the solution strategy.

[0012] Preferably, preprocessing the operating data includes:

[0013] Performing data cleaning on the operating data to obtain a data cleaning result;

[0014] The data cleaning results are used as the preprocessed running data.

[0015] Preferably, performing data cleaning on the operating data to obtain a data cleaning result includes:

[0016] Align the data of multiple dimensions in the running data based on time series;

[0017] Perform anomaly detection and labeling on the data points in each dimension of the aligned running data to obtain anomaly labels corresponding to the data points in each dimension;

[0018] Obtain the number of abnormal markers in the data of multiple dimensions corresponding to each time series point and the data type of the dimension where the abnormal markers are located;

[0019] The multiple dimensional data corresponding to each time series point are judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined;

[0020] Taking a plurality of first abnormal data points and a plurality of second abnormal data points as target data points to be cleaned; taking data corresponding to the target data points to be cleaned as target data to be cleaned;

[0021] Obtain the data type corresponding to the target data to be cleaned of the target data point to be cleaned;

[0022] Obtaining a target data cleaning method corresponding to the target data to be cleaned based on the data type;

[0023] Performing data cleaning on the target data to be cleaned based on the target data cleaning method;

[0024] Traverse the data of multiple dimensions corresponding to all time series points to obtain the data cleaning results.

[0025] Preferably, performing anomaly detection and marking on the data points in each dimension of the aligned running data to obtain an anomaly mark corresponding to the data point in each dimension includes:

[0026] Use the data of any dimension in the aligned running data as the target data set;

[0027] Divide the data in the target dataset into several target sub-datasets evenly;

[0028] Calculate the mean of the data values corresponding to each data point in each target sub-dataset to obtain several target means;

[0029] Randomly select a data point in the first sub-data set as the first target data point;

[0030] Calculate the difference between the data value of the first target data point and a plurality of target means to obtain a plurality of difference values;

[0031] Calculate the mean of several differences to obtain the abnormality value of the first target data point;

[0032] Comparing the abnormality level value with a preset abnormality level threshold, and marking the first target data point as abnormal when it is determined that the abnormality level value is greater than or equal to the preset abnormality level threshold;

[0033] Traverse all data points in the target data set, mark the data points as abnormal based on the abnormality value of each data point, and obtain several abnormal labels;

[0034] Traverse the running data of all dimensions and obtain the abnormal labels corresponding to the data points in each dimension data.

[0035] Preferably, judging the multiple dimensional data corresponding to each time series point based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and determining a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point, includes:

[0036] Take any multiple-dimensional data corresponding to a time series point;

[0037] If the number of abnormal markers in the data of multiple dimensions is 1, the data point in the dimension where the abnormal marker is located is used as the second target data point; a target area is determined with the second target data point as the center and a preset distance as the radius; the correlation coefficient between the second target data point and other data points in the target area is calculated; when the sum of the correlation coefficients is less than or equal to a preset correlation threshold, the second target data point is used as the first abnormal data point;

[0038] If the number of abnormal markers in the data of multiple dimensions is greater than 1, then determining an abnormality evaluation value of the combination of dimensions where the abnormal markers are located based on a first preset algorithm; comparing the abnormality evaluation value with a preset abnormality evaluation threshold; when it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the data point corresponding to the abnormal marker is used as a second abnormal data point;

[0039] Traverse each time series point to obtain several first abnormal data points and several second abnormal data points.

[0040] Preferably, the first preset algorithm includes:

[0041]

[0042] Among them, Y a,m It represents the abnormal evaluation value of the mth abnormal marking dimension combination corresponding to the ath time series point; M represents the total number of abnormal marking dimensions; It represents the mean of the data values of all data points within the preset range of the abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination, δ m,i,j It represents the fluctuation coefficient of the data value of the jth abnormal data point in the i-th abnormal mark dimension in the m-th abnormal mark dimension combination within the preset range, τ m,i,j represents the data value of the jth abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination; f i Represents the weight value of the data in the i-th abnormal marker dimension; exp() represents an exponential function with a natural constant as the base.

[0043] Preferably, the method for constructing a fault detection model includes:

[0044] Obtain a fault detection training dataset;

[0045] The neural network model is trained based on the acquired fault detection training data set to obtain an initial fault detection model;

[0046] Obtain a fault detection test dataset;

[0047] The fault detection test data set is input into the initial fault detection model for testing to obtain a trained fault detection model.

[0048] Preferably, after handling the failure of the flue gas waste heat recovery device based on the solution strategy, the method further includes:

[0049] Evaluate the flue gas waste heat recovery device after the fault processing is completed based on the second preset algorithm to obtain an evaluation value of the flue gas waste heat recovery device;

[0050] The evaluation value of the flue gas waste heat recovery device is compared with a preset evaluation threshold value, and when it is determined that the evaluation value of the flue gas waste heat recovery device is greater than or equal to the preset evaluation threshold value, the fault processing is completed.

[0051] Preferably, the second preset algorithm includes:

[0052]

[0053] Wherein, φ represents the evaluation value of the flue gas waste heat recovery device; U represents the voltage value at both ends of the flue gas waste heat recovery device when it is working; I represents the current value at both ends of the flue gas waste heat recovery device when it is working; R represents the internal resistance value of the flue gas waste heat recovery device; t1 represents the time value of the flue gas waste heat recovery device in use; t2 represents the ideal use time of the flue gas waste heat recovery device; μ represents the flow index of the flue gas waste heat recovery device; γ represents the heat exchange efficiency of the flue gas waste heat recovery device: It indicates the theoretical remaining service life of the flue gas waste heat recovery device; δ indicates the number of failures of the flue gas waste heat recovery device.

[0054] To achieve the above objectives, a second embodiment of the present invention provides a fault detection and processing system for a flue gas waste heat recovery device, comprising:

[0055] The first acquisition module is used to obtain the operating data of the flue gas waste heat recovery device within a preset period;

[0056] A preprocessing module, used for preprocessing the operation data;

[0057] The detection module is used to input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results;

[0058] The second acquisition module is used to obtain the solution strategy corresponding to the detection result;

[0059] The processing module is used to process the failure of the flue gas waste heat recovery device based on the solution strategy.

[0060] The present invention provides a fault detection and processing method and system for a flue gas waste heat recovery device. By acquiring operating data within a preset period, the operating status of the flue gas waste heat recovery device can be monitored in real time. Subtle changes in the operation of the device, such as abnormal fluctuations in parameters such as temperature, pressure, and flow, can be captured in a timely manner. Compared with traditional manual inspections, the timeliness of fault detection is greatly improved, and valuable time is gained for subsequent fault processing. At the same time, the data is input into a pre-trained fault detection model, and the model's powerful data processing and analysis capabilities are utilized to accurately identify the type of fault, avoid misjudgments or missed judgments due to manual errors, and improve the accuracy of fault detection. Pre-processing the operating data can screen, clean, and organize the data to make it more suitable for input into the fault detection model, thereby accelerating the detection speed of the model. Once the test results are determined, the corresponding solution strategy can be quickly obtained and implemented. Waste heat caused by insufficient heat exchange and subsequent environmental protection equipment operation problems can be avoided, effectively shortening the fault processing time and improving the overall operating efficiency of the device. Timely and accurate fault detection and efficient processing can effectively avoid the deterioration of equipment failures.

[0061] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0062] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0064] Figure 1 This is a flow chart of a method for detecting and processing a fault of a flue gas waste heat recovery device according to one embodiment of the present invention;

[0065] Figure 2 is a flow chart of operation data preprocessing according to one embodiment of the present invention;

[0066] Figure 3The present invention is a block diagram of a fault detection and processing system for a flue gas waste heat recovery device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0068] Example 1

[0069] like Figure 1 As shown, a method for detecting and processing a fault of a flue gas waste heat recovery device includes steps S1-S5:

[0070] S1: Obtaining the operating data of the flue gas waste heat recovery device within a preset period;

[0071] S2: Preprocessing the operation data;

[0072] S3: Input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results;

[0073] S4: Obtain the solution strategy corresponding to the detection results;

[0074] S5: Processing the failure of the flue gas waste heat recovery device based on the solution strategy.

[0075] In this embodiment, the operating data of the flue gas waste heat recovery device includes but is not limited to: temperature data: including flue gas inlet temperature, flue gas outlet temperature, inlet temperature and outlet temperature of the heated medium (such as water, air); pressure data: involving flue gas side pressure, heated medium side pressure; flow data: including flue gas flow, heated medium flow; equipment operating parameters: such as fan speed, pump head and flow, etc.; energy consumption data: mainly refers to electricity consumption and fuel consumption during the operation of the device; heat recovery data: that is, the value of heat recovered by the device per unit time.

[0076] In this embodiment, the detection results include: crystallization, low temperature of refrigerant, low temperature of heat source water, overtemperature of hot water, overtemperature of solution, abnormal solution level, abnormal refrigerant level, etc.

[0077] In this embodiment, the solution strategy is a specific solution and implementation steps set based on experience for each detection result.

[0078] The working principle of the above technical solution is as follows: Various sensors are used to comprehensively collect operating data from the flue gas heat recovery unit within a preset period. The collected raw operating data may contain noise, missing values, or inconsistent formats. The preprocessed operating data is then fed into a pre-trained fault detection model. This model is typically built based on machine learning or deep learning algorithms. During the training phase, the model learns a large amount of operating data features under normal and fault conditions, thereby establishing a mapping between data features and fault types. When new operating data is input, the model analyzes the data based on the learned feature patterns to determine whether the current unit is operating normally. If an anomaly is detected, the fault type and severity are determined. Once the fault detection model determines the detection result, the system retrieves a corresponding resolution strategy based on pre-set rules and a knowledge base. This knowledge base is compiled from the experience of domain experts and historical fault handling cases. Based on the obtained resolution strategy, the flue gas heat recovery unit fault is addressed through automated control systems or manual operation.

[0079] The beneficial effects of the above technical solution are: by obtaining operating data within a preset period, the operating status of the flue gas waste heat recovery device can be monitored in real time; subtle changes in the operation of the device, such as abnormal fluctuations in parameters such as temperature, pressure, and flow, can be captured in a timely manner; compared with traditional manual inspections, the timeliness of fault detection is greatly improved, and valuable time is gained for subsequent fault handling. At the same time, by inputting data into a pre-trained fault detection model and utilizing the model's powerful data processing and analysis capabilities, the fault type can be accurately identified, avoiding misjudgments or missed judgments due to manual errors, thereby improving the accuracy of fault detection; pre-processing the operating data can filter, clean, and organize the data to make it more suitable for input into the fault detection model, thereby speeding up the model's detection speed. Once the test results are determined, the corresponding solution strategy can be quickly obtained and implemented; waste of waste heat caused by insufficient heat exchange and subsequent environmental protection equipment operation problems can be avoided, effectively shortening the fault handling time and improving the overall operating efficiency of the device; timely, accurate fault detection and efficient handling can effectively avoid the deterioration of equipment failures.

[0080] Example 2

[0081] like Figure 2 As shown, the operation data is pre-processed, including steps S21-S22:

[0082] S21: performing data cleaning on the operation data to obtain a data cleaning result;

[0083] S22: The data cleaning result is used as the pre-processed running data.

[0084] Example 3

[0085] Performing data cleaning on the operating data to obtain data cleaning results includes:

[0086] Align the data of multiple dimensions in the running data based on time series;

[0087] Perform anomaly detection and labeling on the data points in each dimension of the aligned running data to obtain anomaly labels corresponding to the data points in each dimension;

[0088] Obtain the number of abnormal markers in the data of multiple dimensions corresponding to each time series point and the data type of the dimension where the abnormal markers are located;

[0089] The multiple dimensional data corresponding to each time series point are judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined;

[0090] Taking a plurality of first abnormal data points and a plurality of second abnormal data points as target data points to be cleaned; taking data corresponding to the target data points to be cleaned as target data to be cleaned;

[0091] Obtain the data type corresponding to the target data to be cleaned of the target data point to be cleaned;

[0092] Obtaining a target data cleaning method corresponding to the target data to be cleaned based on the data type;

[0093] Performing data cleaning on the target data to be cleaned based on the target data cleaning method;

[0094] Traverse the data of multiple dimensions corresponding to all time series points to obtain the data cleaning results.

[0095] In this embodiment, the first abnormal data point is when the number of abnormal marks in the data of multiple dimensions corresponding to the time series point is 1, and the sum of the correlations between the abnormally marked data point and other data points within a preset distance range in the dimension where the abnormally marked data point is located is less than or equal to a preset correlation threshold.

[0096] In this embodiment, when the number of abnormal marks in the data of multiple dimensions corresponding to the second abnormal data point, that is, the time series point, is greater than 1, and the abnormal evaluation value of the dimensional combination where the abnormal mark is located is greater than or equal to the preset abnormal evaluation value, the data point corresponding to the abnormal mark is taken as the second abnormal data point.

[0097] The working principle of the above technical solution is as follows: the operating data of the flue gas waste heat recovery device comes from multiple sensors, such as temperature, pressure, and flow sensors, and the frequency and start time of data collection of these sensors may differ. Time series alignment processing is to uniformly calibrate the data of different dimensions in chronological order, using time as the reference axis, so that the data of each dimension corresponds one-to-one at the same time point; for each dimension-aligned time series data, it is determined whether the data point deviates from the normal range. If a temperature data point is significantly higher or lower than the normal fluctuation range, the algorithm will identify it as an anomaly and mark it accordingly. Each data point in each dimension of data undergoes such a test; after completing the anomaly marking of each dimension data point, for each time series point, the number of anomaly marks in the corresponding multiple dimensions of data is counted, and the data type of the dimension data where the anomaly mark is located is recorded; based on the number of anomaly marks corresponding to each time series point, different judgment thresholds are set to determine the first anomaly data point and the second anomaly data point; the determined first anomaly data point and second anomaly data point are used as the target data points to be cleaned, and the data corresponding to these data points are extracted as the target data to be cleaned. At the same time, the data types corresponding to these target data points to be cleaned are obtained; based on the data type of the target data to be cleaned, the corresponding target data cleaning method is selected from the preset data cleaning method library. For example, for numerical data, if the abnormal data is a significant deviation caused by sensor failure, it can be repaired using mean filling, median filling, or model-based prediction methods; for Boolean data, if the abnormality manifests as a state reversal, it can be corrected after verification with the actual state of the device; according to the selected target data cleaning method, the target data to be cleaned is cleaned. After completing the traversal and cleaning of the multi-dimensional data corresponding to all time series points, the cleaned data set is obtained, that is, the data cleaning result.

[0098] Example 4

[0099] Anomaly detection and labeling are performed on the data points in each dimension of the aligned running data to obtain the anomaly labels corresponding to the data points in each dimension, including:

[0100] Use the data of any dimension in the aligned running data as the target data set;

[0101] Divide the data in the target dataset into several target sub-datasets evenly;

[0102] Calculate the mean of the data values corresponding to each data point in each target sub-dataset to obtain several target means;

[0103] Randomly select a data point in the first sub-data set as the first target data point;

[0104] Calculate the difference between the data value of the first target data point and a plurality of target means to obtain a plurality of difference values;

[0105] Calculate the mean of several differences to obtain the abnormality value of the first target data point;

[0106] Comparing the abnormality level value with a preset abnormality level threshold, and marking the first target data point as abnormal when it is determined that the abnormality level value is greater than or equal to the preset abnormality level threshold;

[0107] Traverse all data points in the target data set, mark the data points as abnormal based on the abnormality value of each data point, and obtain several abnormal labels;

[0108] Traverse the running data of all dimensions and obtain the abnormal labels corresponding to the data points in each dimension data.

[0109] The above technical solution has the following beneficial effects: the operating data of each dimension is refined into multiple target sub-datasets, the mean of the data in each sub-dataset is calculated, and the abnormality level value of each data point is calculated based on this. This refined calculation method can fully consider the characteristic changes of the data in different local intervals. By calculating the mean of each interval, compared with the overall mean calculation, it can more keenly capture the abnormal conditions of the data point within the local interval to which it belongs, avoiding the local anomalies masked by the overall characteristics, thereby significantly improving the accuracy of abnormal data identification and providing more reliable data basis for subsequent fault diagnosis. Such detailed abnormality detection and marking operations for the operating data of each dimension ensure all-round monitoring of the device operation status. Because data of different dimensions (such as temperature, pressure, flow, etc.) reflect the operation status of the device from different angles, an abnormality in any dimension may indicate a potential fault in the device. When calculating the abnormality level value of a single data point, it is compared with the preset abnormality level threshold in real time. Once the abnormality level value is determined to be greater than or equal to the threshold, the data point is immediately marked as abnormal. This real-time processing method can quickly capture abnormal changes in the data and detect abnormal conditions as soon as they occur.

[0110] Example 5

[0111] The multiple dimensional data corresponding to each time series point is judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined, including:

[0112] Take any multiple-dimensional data corresponding to a time series point;

[0113] If the number of abnormal markers in the data of multiple dimensions is 1, the data point in the dimension where the abnormal marker is located is used as the second target data point; a target area is determined with the second target data point as the center and a preset distance as the radius; the correlation coefficient between the second target data point and other data points in the target area is calculated; when the sum of the correlation coefficients is less than or equal to a preset correlation threshold, the second target data point is used as the first abnormal data point;

[0114] If the number of abnormal markers in the data of multiple dimensions is greater than 1, then determining an abnormality evaluation value of the combination of dimensions where the abnormal markers are located based on a first preset algorithm; comparing the abnormality evaluation value with a preset abnormality evaluation threshold; when it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the data point corresponding to the abnormal marker is used as a second abnormal data point;

[0115] Traverse each time series point to obtain several first abnormal data points and several second abnormal data points.

[0116] In this embodiment, the correlation coefficient includes but is not limited to the Pearson correlation coefficient.

[0117] The working principle of the above technical solution is as follows: a time series point is randomly selected from the entire time series data, and the corresponding data for multiple dimensions is obtained. When only one anomaly flag is present in the multiple dimensions corresponding to this time series point, the data point in the dimension with the anomaly flag is defined as the second target data point. A target area is defined with the second target data point as the center and a preset radius. This target area includes other data points that are close to the second target data point in time and value. When the sum of the correlation coefficients is less than or equal to a preset correlation threshold, it indicates that the second target data point has a low degree of correlation with the surrounding data points and is more abnormal. In this case, the second target data point is upgraded to a first anomaly data point. The preset correlation threshold is set based on extensive historical data and experience and is used to determine the degree of anomaly of a data point. When the number of anomaly flags in the data for multiple dimensions is greater than one, a first preset algorithm is used to determine the anomaly evaluation value for the combination of dimensions containing the anomaly flag. The calculated anomaly evaluation value is then compared with the preset anomaly evaluation threshold. The preset anomaly evaluation threshold is also set based on historical data and experience and is used to determine whether the degree of anomaly reaches a level that requires special attention. When the anomaly evaluation value is greater than or equal to the preset anomaly evaluation threshold, it indicates that the degree of anomaly of the dimension combination is high, and the data points corresponding to these anomaly marks are determined as the second anomaly data points; repeat the above steps for each time series point in the entire time series, judge the multiple dimensional data corresponding to each time series point in turn, and determine the first anomaly data point and the second anomaly data point.

[0118] The beneficial effect of the above technical solution is that this technology can more accurately locate abnormal data points by analyzing the number of abnormal markers in the multi-dimensional data of each time series point, laying the foundation for subsequent data cleaning.

[0119] Example 6

[0120] The first preset algorithm includes:

[0121]

[0122] Among them, Y a,m It represents the abnormal evaluation value of the mth abnormal marking dimension combination corresponding to the ath time series point; M represents the total number of abnormal marking dimensions; It represents the mean of the data values of all data points within the preset range of the abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination, δ m,i,j It represents the fluctuation coefficient of the data value of the jth abnormal data point in the i-th abnormal mark dimension in the m-th abnormal mark dimension combination within the preset range, τ m,i,j represents the data value of the jth abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination; f i Represents the weight value of the data in the i-th abnormal marker dimension; exp() represents an exponential function with a natural constant as the base.

[0123] In this embodiment, the specific calculation only involves numerical calculation, and the dimension is ignored.

[0124] In this embodiment, the specific method for obtaining the fluctuation coefficient is: the difference between the data value of the abnormal marked data point and the mean of the data values of all data points within the preset range is used as the first difference; the difference between the data value of the abnormal marked data point and the data values of all data points within the preset range is used to obtain several second differences; the sum of the several second differences is used as the target difference; and the ratio of the first difference to the target difference is used as the fluctuation coefficient.

[0125] The beneficial effects of the above technical solution are: when judging that abnormalities occur simultaneously in multiple dimensions such as temperature and pressure, the degree of abnormalities and their mutual relationships in each dimension can be comprehensively analyzed; by adopting different weight values for data of different dimensions, the algorithm can adapt to the differences in the importance of different parameters of the flue gas waste heat recovery device in a complex industrial environment, and further improve the accuracy of abnormal data point identification through the abnormal evaluation value of the abnormal combination.

[0126] Example 7

[0127] The method for constructing a fault detection model includes:

[0128] Obtain a fault detection training dataset;

[0129] The neural network model is trained based on the acquired fault detection training data set to obtain an initial fault detection model;

[0130] Obtain a fault detection test dataset;

[0131] The fault detection test data set is input into the initial fault detection model for testing to obtain a trained fault detection model.

[0132] Example 8

[0133] After the failure of the flue gas waste heat recovery device is handled based on the solution strategy, the method further includes:

[0134] Evaluate the flue gas waste heat recovery device after the fault processing is completed based on the second preset algorithm to obtain an evaluation value of the flue gas waste heat recovery device;

[0135] The evaluation value of the flue gas waste heat recovery device is compared with a preset evaluation threshold value, and when it is determined that the evaluation value of the flue gas waste heat recovery device is greater than or equal to the preset evaluation threshold value, the fault processing is completed.

[0136] In this embodiment, the evaluation of the flue gas waste heat recovery device after the fault processing is completed mainly evaluates the operating status of the flue gas waste heat recovery device after the fault processing is completed.

[0137] The working principle of the above technical solution is: based on the second preset algorithm, the flue gas waste heat recovery device is evaluated after the fault processing is completed; the algorithm will comprehensively consider multiple operating parameters and performance indicators of the device to calculate the evaluation value; the calculated evaluation value of the flue gas waste heat recovery device is compared with the preset evaluation threshold; the preset evaluation threshold is determined based on multiple factors such as the design standards of the device, historical operating data, and industry best practices; it represents an ideal performance level that the device should achieve after fault processing; when it is determined that the evaluation value of the flue gas waste heat recovery device is greater than or equal to the preset evaluation threshold, it indicates that the device after the fault processing has achieved the expected standards in various key indicators and is in good operating condition, thereby completing the fault processing.

[0138] The beneficial effects of this technical solution include: using a second preset algorithm to evaluate the device after fault resolution, comprehensively considering various operating indicators and performance parameters of the device to generate a quantitative evaluation value; accurately determining whether fault resolution is complete, ensuring that the device is always in good operating condition, and maximizing waste heat recovery and utilization. This reduces energy waste caused by device failure or improper resolution, further enhancing energy conservation and emission reduction.

[0139] Example 9

[0140] The second preset algorithm includes:

[0141]

[0142] Among them, φ represents the evaluation value of the flue gas waste heat recovery device; U represents the voltage value at both ends of the flue gas waste heat recovery device when it is working; I represents the current value at both ends of the flue gas waste heat recovery device when it is working; R represents the internal resistance value of the flue gas waste heat recovery device; t1 represents the time value of the flue gas waste heat recovery device that has been in use, t2 represents the ideal service time of the flue gas waste heat recovery device; μ represents the flow index of the flue gas waste heat recovery device; γ represents the heat exchange efficiency of the flue gas waste heat recovery device; θ represents the theoretical remaining service life of the flue gas waste heat recovery device; δ represents the number of failures of the flue gas waste heat recovery device.

[0143] The beneficial effects of this technical solution are as follows: the algorithm incorporates the device's operating voltage (U), current (I), and internal resistance (R). These electrical parameters provide a direct reflection of the device's electrical performance and energy consumption. It also considers the actual operating time (t1) and the ideal operating time (t2) to assess the impact of device aging on performance. Complex and rigorous mathematical calculations yield an evaluation value (φ), providing a quantitative indicator of device performance. This evaluation value allows companies to dynamically manage the device throughout its lifecycle. After troubleshooting, the algorithm calculates the evaluation value, providing a direct assessment of the effectiveness of the repair.

[0144] like Figure 3 As shown, in order to achieve the above-mentioned purpose, the second embodiment of the present invention proposes a fault detection and processing system for a flue gas waste heat recovery device, comprising:

[0145] The first acquisition module is used to obtain the operating data of the flue gas waste heat recovery device within a preset period;

[0146] A preprocessing module, used for preprocessing the operation data;

[0147] The detection module is used to input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results;

[0148] The second acquisition module is used to obtain the solution strategy corresponding to the detection result;

[0149] The processing module is used to process the failure of the flue gas waste heat recovery device based on the solution strategy.

[0150] The beneficial effects of the above technical solution are: by obtaining operating data within a preset period, the operating status of the flue gas waste heat recovery device can be monitored in real time; subtle changes in the operation of the device, such as abnormal fluctuations in parameters such as temperature, pressure, and flow, can be captured in a timely manner; compared with traditional manual inspections, the timeliness of fault detection is greatly improved, and valuable time is gained for subsequent fault handling. At the same time, by inputting data into a pre-trained fault detection model and utilizing the model's powerful data processing and analysis capabilities, the fault type can be accurately identified, avoiding misjudgments or missed judgments due to manual errors, thereby improving the accuracy of fault detection; pre-processing the operating data can filter, clean, and organize the data to make it more suitable for input into the fault detection model, thereby speeding up the model's detection speed. Once the test results are determined, the corresponding solution strategy can be quickly obtained and implemented; waste of waste heat caused by insufficient heat exchange and subsequent environmental protection equipment operation problems can be avoided, effectively shortening the fault handling time and improving the overall operating efficiency of the device; timely, accurate fault detection and efficient handling can effectively avoid the deterioration of equipment failures.

[0151] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for detecting and processing a fault of a flue gas waste heat recovery device, characterized in that: include: Obtaining the operating data of the flue gas waste heat recovery device within a preset period; Preprocessing the operating data; Input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results; Obtain the solution strategy corresponding to the test results; Handle the failure of the flue gas waste heat recovery device based on the solution strategy; Preprocessing the operating data includes: performing data cleaning on the operating data to obtain a data cleaning result; The data cleaning results are used as pre-processed running data; Performing data cleaning on the operating data to obtain data cleaning results includes: Align the data of multiple dimensions in the running data based on time series; Perform anomaly detection and labeling on the data points in each dimension of the aligned running data to obtain anomaly labels corresponding to the data points in each dimension; Obtain the number of abnormal markers in the data of multiple dimensions corresponding to each time series point and the data type of the dimension where the abnormal markers are located; The multiple dimensional data corresponding to each time series point are judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined; Taking a plurality of first abnormal data points and a plurality of second abnormal data points as target data points to be cleaned; taking data corresponding to the target data points to be cleaned as target data to be cleaned; Obtain the data type corresponding to the target data point to be cleaned; Obtaining a target data cleaning method corresponding to the target data to be cleaned based on the data type; Performing data cleaning on the target data to be cleaned based on the target data cleaning method; Traverse the data of multiple dimensions corresponding to all time series points to obtain the data cleaning results.

2. The fault detection and processing method for the flue gas waste heat recovery device according to claim 1 is characterized in that: Anomaly detection and labeling are performed on the data points in each dimension of the aligned running data to obtain the anomaly labels corresponding to the data points in each dimension, including: Use the data of any dimension in the aligned running data as the target data set; Divide the data in the target dataset into several target sub-datasets evenly; Calculate the mean of the data values corresponding to each data point in each target sub-dataset to obtain several target means; Randomly select a data point in the first sub-data set as the first target data point; Calculate the difference between the data value of the first target data point and a plurality of target means to obtain a plurality of difference values; Calculate the mean of several differences to obtain the abnormality value of the first target data point; Comparing the abnormality level value with a preset abnormality level threshold, and marking the first target data point as abnormal when it is determined that the abnormality level value is greater than or equal to the preset abnormality level threshold; Traverse all data points in the target data set, mark the data points as abnormal based on the abnormality value of each data point, and obtain several abnormal labels; Traverse the running data of all dimensions and obtain the abnormal labels corresponding to the data points in each dimension data.

3. The fault detection and processing method for the flue gas waste heat recovery device according to claim 2 is characterized in that: The multiple dimensional data corresponding to each time series point is judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined, including: Take any multiple-dimensional data corresponding to a time series point; If the number of abnormal markers in the data of multiple dimensions is 1, the data point in the dimension where the abnormal marker is located is used as the second target data point; a target area is determined with the second target data point as the center and a preset distance as the radius; the correlation coefficient between the second target data point and other data points in the target area is calculated; when the sum of the correlation coefficients is less than or equal to a preset correlation threshold, the second target data point is used as the first abnormal data point; If the number of abnormal markers in the data of multiple dimensions is greater than 1, then determining an abnormality evaluation value of the combination of dimensions where the abnormal markers are located based on a first preset algorithm; comparing the abnormality evaluation value with a preset abnormality evaluation threshold; when it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the data point corresponding to the abnormal marker is used as a second abnormal data point; Traverse each time series point to obtain several first abnormal data points and several second abnormal data points.

4. The fault detection and processing method for a flue gas waste heat recovery device according to claim 3 is characterized in that: The first preset algorithm includes: Among them, Y a,m It represents the abnormal evaluation value of the mth abnormal marking dimension combination corresponding to the ath time series point; M represents the total number of abnormal marking dimensions; It represents the mean of the data values of all data points within the preset range of the abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination, δ m,i,j It represents the fluctuation coefficient of the data value of the jth abnormal data point in the i-th abnormal mark dimension in the m-th abnormal mark dimension combination within the preset range, τ m,i,j represents the data value of the jth abnormal marker data point in the i-th abnormal marker dimension in the m-th abnormal marker dimension combination; f i Represents the weight value of the data in the i-th abnormal marker dimension; exp() represents an exponential function with a natural constant as the base.

5. The fault detection and processing method for a flue gas waste heat recovery device according to claim 1, characterized in that: The method for constructing a fault detection model includes: Obtain a fault detection training dataset; The neural network model is trained based on the acquired fault detection training data set to obtain an initial fault detection model; Obtain a fault detection test dataset; The fault detection test data set is input into the initial fault detection model for testing to obtain a trained fault detection model.

6. The method for fault detection and processing of a flue gas waste heat recovery device according to claim 1, characterized in that: After the failure of the flue gas waste heat recovery device is handled based on the solution strategy, the method further includes: Evaluate the flue gas waste heat recovery device after the fault processing is completed based on the second preset algorithm to obtain an evaluation value of the flue gas waste heat recovery device; The evaluation value of the flue gas waste heat recovery device is compared with a preset evaluation threshold value, and when it is determined that the evaluation value of the flue gas waste heat recovery device is greater than or equal to the preset evaluation threshold value, the fault processing is completed.

7. The method for detecting and processing a fault of a flue gas waste heat recovery device according to claim 6, characterized in that: The second preset algorithm includes: Wherein, φ represents the evaluation value of the flue gas waste heat recovery device; U represents the voltage value at both ends of the flue gas waste heat recovery device when it is working; I represents the current value at both ends of the flue gas waste heat recovery device when it is working; R represents the internal resistance value of the flue gas waste heat recovery device; t1 represents the time value of the flue gas waste heat recovery device in use; t2 represents the ideal use time of the flue gas waste heat recovery device; μ represents the flow index of the flue gas waste heat recovery device; γ represents the heat exchange efficiency of the flue gas waste heat recovery device: It indicates the theoretical remaining service life of the flue gas waste heat recovery device; δ indicates the number of failures of the flue gas waste heat recovery device.

8. A fault detection and processing system for a flue gas waste heat recovery device, characterized in that: include: The first acquisition module is used to obtain the operating data of the flue gas waste heat recovery device within a preset period; A preprocessing module, used for preprocessing the operation data; The detection module is used to input the pre-processed operating data into the pre-trained fault detection model for detection and determine the detection results; The second acquisition module is used to obtain the solution strategy corresponding to the detection result; a processing module, configured to process the failure of the flue gas waste heat recovery device based on the solution strategy; The method for preprocessing the operating data by the preprocessing module includes: Preprocessing the operating data includes: performing data cleaning on the operating data to obtain a data cleaning result; The data cleaning results are used as pre-processed running data; Performing data cleaning on the operating data to obtain data cleaning results includes: Align the data of multiple dimensions in the running data based on time series; Perform anomaly detection and labeling on the data points in each dimension of the aligned running data to obtain anomaly labels corresponding to the data points in each dimension; Obtain the number of abnormal markers in the data of multiple dimensions corresponding to each time series point and the data type of the dimension where the abnormal markers are located; The multiple dimensional data corresponding to each time series point are judged based on the number of abnormal marks in the multiple dimensional data corresponding to each time series point, and a plurality of first abnormal data points and a plurality of second abnormal data points in the multiple dimensional data corresponding to each time series point are determined; Taking a plurality of first abnormal data points and a plurality of second abnormal data points as target data points to be cleaned; taking data corresponding to the target data points to be cleaned as target data to be cleaned; Obtain the data type corresponding to the target data point to be cleaned; Obtaining a target data cleaning method corresponding to the target data to be cleaned based on the data type; Performing data cleaning on the target data to be cleaned based on the target data cleaning method; Traverse the data of multiple dimensions corresponding to all time series points to obtain the data cleaning results.

Images