Heat Exchanger Fault Diagnosis and Predictive Maintenance System and Method Based on Data Analysis

Abstract

The present invention relates to the technical field of heat exchanger fault detection, specifically a heat exchanger fault diagnosis and predictive maintenance system and method based on data analysis. By preprocessing the working data of the heat exchanger, setting a qualified range for the heat exchanger according to the preprocessed working data, then creating and training a heat exchanger standard model to obtain the trained heat exchanger standard model, and finally judging whether the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold based on the real-time evaluation of the heat exchanger. If the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, obtain the suspected area and calculate the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether a warning needs to be issued based on the qualified rate trend of the heat exchanger. This application finds the suspected area of the heat exchanger and calculates the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, so as to issue a warning in time before the heat exchanger is damaged.

Description

Technical Field

[0001] The present invention relates to the technical field of heat exchanger fault detection, and particularly to a heat exchanger fault diagnosis and predictive maintenance system and method based on data analysis. Background Art

[0002] ‌A heat exchanger is an energy-saving device that realizes heat transfer between materials among two or more fluids at different temperatures, enabling heat to be transferred from a fluid with a higher temperature to a fluid with a lower temperature, so that the fluid temperature reaches the specified index of the process to meet the requirements of the process conditions. It is also one of the main devices for improving energy utilization efficiency. The heat exchanger industry involves nearly 30 industries such as heating ventilation, pressure vessels, medium water treatment equipment, chemical engineering, and petroleum, forming an industrial chain with each other.

[0003] Chinese Patent with the publication number CN118067422A discloses a heat exchanger fault diagnosis method, device, equipment and medium. This method calculates the statistic of the to-be-detected operation data based on the to-be-detected operation data and the standard distance k-nearest neighbor algorithm; determines whether the statistic of the to-be-detected operation data is greater than the upper control limit of the confidence level, and determines whether the heat exchanger is faulty according to the judgment result. However, in the prior art, the current state of the heat exchanger is judged based on real-time data, but the state trend of the heat exchanger is not predicted, making it difficult to issue a warning in time before an accident occurs. Summary of the Invention

[0004] The object of the present invention is to address the problems in the background art and propose a heat exchanger fault diagnosis and predictive maintenance system and method based on data analysis.

[0005] The technical solution of the present invention:

[0006] On the one hand, the present application provides a heat exchanger fault diagnosis and predictive maintenance method based on data analysis, including:

[0007] Set acquisition parameters, collect the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain preprocessed working data, and set the qualified interval of the heat exchangers according to the preprocessed working data;

[0008] Create a heat exchanger standard model, train the heat exchanger standard model through the preprocessed working data, so that the heat exchanger standard model judges the working state of the heat exchanger based on the working data of the heat exchanger, and obtain the trained heat exchanger standard model;

[0009] Collect the real-time data of the heat exchanger, input the real-time data of the heat exchanger into the trained heat exchanger standard model to obtain the real-time evaluation of the heat exchanger, and judge whether the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold based on the real-time evaluation of the heat exchanger;

[0010] If the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, obtain the suspected area and calculate the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, and determine whether to issue a warning based on the qualified rate trend of the heat exchanger.

[0011] Preferably, set the acquisition parameters, acquire the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain preprocessed working data, and set the qualified interval of the heat exchangers according to the preprocessed working data, including:

[0012] Create a heat exchanger data table;

[0013] Divide the heat exchanger into multiple heat exchange areas;

[0014] Set the acquisition parameters for each of the multiple heat exchange areas of each heat exchanger; the acquisition parameters include the acquisition period, the acquisition frequency, and the acquisition location;

[0015] For each heat exchanger, acquire the working data of the multiple heat exchange areas of the heat exchanger according to the acquisition parameters of the heat exchanger, and put the acquired working data into the heat exchanger data table; the working data includes multiple acquisition items such as heat exchanger temperature data, heat exchanger pressure data, and heat exchanger flow data.

[0016] Preferably, set the acquisition parameters, acquire the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain preprocessed working data, and set the qualified interval of the heat exchangers, further including:

[0017] Randomly select a heat exchanger from the heat exchanger data table and obtain the working data of the heat exchanger;

[0018] Select an acquisition item and calculate the average value of the acquisition item;

[0019] For this acquisition item, sequentially determine whether there is working data at each acquisition node according to the chronological order of the acquisition time;

[0020] If there is no working data at the acquisition node, fill the average value of the acquisition item into the acquisition node to complete the working data;

[0021] Set a deviation threshold, calculate the upper and lower boundary values by combining the mean value of this acquisition item with the deviation threshold, and set the qualified interval based on the upper and lower boundary values;

[0022] Return to select an acquisition item and calculate the average value of the acquisition item until the qualified interval of each acquisition item of the heat exchanger is obtained;

[0023] Return to randomly select a heat exchanger from the heat exchanger data sheet until all the heat exchangers in the working data sheet are selected, and obtain the qualified intervals of each acquisition item for all the heat exchangers.

[0024] Preferably, create a standard heat exchanger model, and train the standard heat exchanger model through preprocessing the working data, so that the standard heat exchanger model judges the working state of the heat exchanger based on the working data of the heat exchanger, and obtain the trained standard heat exchanger model, including:

[0025] Create a standard heat exchanger model;

[0026] Divide the preprocessed working data of all the heat exchangers into a training set and a test set in a random proportion;

[0027] Input the training set into the standard heat exchanger model, so that the standard heat exchanger model continuously learns the coupling relationship between the working data of the heat exchanger and the heat exchanger state, and obtain the trained standard heat exchanger model;

[0028] Input the test set into the trained standard heat exchanger model to verify whether the trained standard heat exchanger model is trained successfully.

[0029] Preferably, input the training set into the standard heat exchanger model, so that the standard heat exchanger model continuously learns the coupling relationship between the working data of the heat exchanger and the heat exchanger state, and obtain the trained standard heat exchanger model, including:

[0030] For each heat exchanger in the training set, respectively obtain the working data of each heat exchanger;

[0031] Select a heat exchanger, and sequentially judge whether the working data of each acquisition item of this heat exchanger is within the qualified interval;

[0032] If the working data of the acquisition item is within the qualified interval, mark this heat exchanger as a qualified state;

[0033] If the working data of the acquisition item is not within the qualified interval, mark this heat exchanger as an unqualified state;

[0034] Return to select a heat exchanger until all the heat exchangers are selected, and obtain the working state of each heat exchanger;

[0035] Based on the working data of each heat exchanger and the working state under this working data respectively, establish the coupling relationship of heat exchanger - working data - working state, and use the coupling relationship of heat exchanger - working data - working state as a training sample, so as to obtain multiple training samples;

[0036] Input multiple training samples into the heat exchanger standard model in sequence, enabling the heat exchanger standard model to continuously learn the corresponding relationship between the working data of the heat exchanger and the heat exchanger state, and obtaining the trained heat exchanger standard model.

[0037] Preferably, collect the real-time data of the heat exchanger, input the real-time data of the heat exchanger into the trained heat exchanger standard model to obtain the real-time evaluation of the heat exchanger, and judge whether the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold based on the real-time evaluation of the heat exchanger, including:

[0038] Collect the real-time data of each heat exchange area of the heat exchanger;

[0039] Input the real-time data of each heat exchange area of the heat exchanger into the trained heat exchanger standard model to obtain the real-time evaluation of each heat exchange area of the heat exchanger output by the trained heat exchanger standard model;

[0040] Set the qualification rate threshold;

[0041] Judge in sequence whether the real-time evaluation of each heat exchange area of the heat exchanger is qualified, and count the qualification rate of all heat exchange areas of the heat exchanger;

[0042] Judge whether the qualification rate of all heat exchange areas of the heat exchanger is greater than or equal to the qualification rate threshold;

[0043] If the qualification rate of a heat exchange area of the heat exchanger is less than the qualification rate threshold, stop the operation of the heat exchanger and issue a warning.

[0044] Preferably, if the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold, obtain the suspected area and calculate the qualification rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether a warning needs to be issued based on the qualification rate trend of the heat exchanger, including:

[0045] If the qualification rate of all heat exchange areas of the heat exchanger is greater than or equal to the qualification rate threshold, judge whether there is an unqualified heat exchange area;

[0046] If there is no unqualified heat exchange area, keep the heat exchanger operating;

[0047] If there is an unqualified heat exchange area, obtain the suspected area according to the unqualified heat exchange area.

[0048] Preferably, if there is an unqualified heat exchange area, obtain the suspected area according to the unqualified heat exchange area, including:

[0049] Select an unqualified heat exchange area;

[0050] Obtain the adjacent heat exchange areas of the unqualified heat exchange area;

[0051] Judge whether the working status of the adjacent heat exchange areas is qualified;

[0052] If the working status of adjacent heat exchange areas is qualified, mark the adjacent heat exchange areas as observation areas and obtain the historical working data of the observation areas;

[0053] Set an error threshold;

[0054] Calculate the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area, and determine whether the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is greater than or equal to the error threshold;

[0055] If the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is less than or equal to the error threshold, mark the observation area as a suspected area;

[0056] Return and select an unqualified heat exchange area until all unqualified heat exchange areas are selected to obtain multiple suspected areas.

[0057] Preferably, if the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold, obtain the suspected areas and calculate the qualification rate trend of the heat exchanger by combining the suspected areas and the unqualified areas, and determine whether a warning needs to be issued based on the qualification rate trend of the heat exchanger. It further includes:

[0058] Recalculate the qualification rate of the heat exchanger by combining the suspected areas and the unqualified heat exchange areas to obtain the trend qualification rate of the heat exchanger;

[0059] Determine whether the trend qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold;

[0060] If the trend qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold, maintain the operation of the heat exchanger;

[0061] If the trend qualification rate of the heat exchanger is less than the qualification rate threshold, issue a warning.

[0062] On the other hand, the present application also provides a heat exchanger fault diagnosis and predictive maintenance system based on data analysis, including:

[0063] An acquisition unit that acquires the working data of the heat exchanger through the acquisition component;

[0064] A data processing unit that executes the heat exchanger fault diagnosis and predictive maintenance method based on data analysis described in any one of the foregoing through the data processing unit. The data processing unit includes a data processing subunit and a control subunit. The working data of the heat exchanger is processed by the data processing subunit, and the working state of the heat exchanger is controlled by the control subunit.

[0065] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0066] By collecting the working data of multiple heat exchangers, preprocessing the working data of the heat exchangers to obtain preprocessed working data, setting a qualified range for the heat exchangers according to the preprocessed working data, then creating and training a heat exchanger standard model, enabling the heat exchanger standard model to judge the working state of the heat exchanger based on the working data of the heat exchanger, obtaining the trained heat exchanger standard model, inputting the real-time data of the heat exchanger into the trained heat exchanger standard model to obtain the real-time evaluation of the heat exchanger, and based on the real-time evaluation of the heat exchanger, judging whether the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold. If the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold, then obtain the suspected area and calculate the qualification rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether it is necessary to issue an early warning based on the qualification rate trend of the heat exchanger. In this application, by finding the suspected area of the heat exchanger and calculating the qualification rate trend of the heat exchanger by combining the suspected area and the unqualified area, an early warning can be issued in time before the heat exchanger is damaged. Description of the Drawings

[0067] Figure 1 It is a schematic flowchart of a method for heat exchanger fault diagnosis and predictive maintenance based on data analysis proposed by the present invention;

[0068] Figure 2 It is a schematic structural diagram of a heat exchanger fault diagnosis and predictive maintenance system based on data analysis proposed by the present invention.

[0069] Reference numerals: 100, acquisition unit; 200, data processing unit; 201, data processing subunit;

[0070] 202, control subunit. Detailed Embodiments

[0071] Embodiment 1, as Figure 1 shown, the method for heat exchanger fault diagnosis and predictive maintenance based on data analysis proposed by the present invention includes:

[0072] S100, set acquisition parameters, collect the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain preprocessed working data, and set a qualified range for the heat exchangers according to the preprocessed working data;

[0073] S200, create a heat exchanger standard model, train the heat exchanger standard model with the preprocessed working data, enable the heat exchanger standard model to judge the working state of the heat exchanger based on the working data of the heat exchanger, and obtain the trained heat exchanger standard model;

[0074] S300, collect the real-time data of the heat exchanger, input the real-time data of the heat exchanger into the trained standard heat exchanger model to obtain the real-time evaluation of the heat exchanger, and judge whether the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold based on the real-time evaluation of the heat exchanger;

[0075] S400, if the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, obtain the suspected area, calculate the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether a warning needs to be issued based on the qualified rate trend of the heat exchanger.

[0076] In the present invention, by collecting the working data of multiple heat exchangers, preprocessing the working data of the heat exchanger to obtain the preprocessed working data, setting the qualified interval of the heat exchanger according to the preprocessed working data, then creating and training the standard heat exchanger model, enabling the standard heat exchanger model to judge the working state of the heat exchanger based on the working data of the heat exchanger to obtain the trained standard heat exchanger model, inputting the real-time data of the heat exchanger into the trained standard heat exchanger model to obtain the real-time evaluation of the heat exchanger, judging whether the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold based on the real-time evaluation of the heat exchanger, if the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, obtain the suspected area, calculate the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether a warning needs to be issued based on the qualified rate trend of the heat exchanger. This application finds the suspected area of the heat exchanger and calculates the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, so as to issue a warning in time before the heat exchanger is damaged.

[0077] In an optional embodiment, the S100 includes:

[0078] S110, create a heat exchanger data table;

[0079] S120, divide each heat exchanger into multiple heat exchange areas;

[0080] Specifically, for different heat exchange areas of the same heat exchanger, the areas of different heat exchange areas should be guaranteed to be equal when dividing the heat exchange areas;

[0081] S130, set collection parameters for multiple heat exchange areas of each heat exchanger respectively; the collection parameters include collection period, collection frequency and collection position;

[0082] S140, for each heat exchanger, collect the working data of multiple heat exchange areas of the heat exchanger according to the collection parameters of the heat exchanger, and put the collected working data into the heat exchanger data table; the working data includes multiple collection items such as heat exchanger temperature data, heat exchanger pressure data and heat exchanger flow data.

[0083] It should be noted that by collecting the working data of multiple heat exchangers and using the working data of multiple heat exchangers as training samples to train the heat exchanger standard model, each heat exchanger is divided into multiple heat exchange areas to ensure that when verifying whether the qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold in the follow-up, the heat exchanger can be regarded as multiple independent areas, so as to realize a more detailed control method for the heat exchanger.

[0084] In an optional embodiment, the S100 includes:

[0085] S150, randomly select a heat exchanger from the heat exchanger data table and obtain the working data of the heat exchanger;

[0086] S160, select a collection item and calculate the average value of the collection item;

[0087] S170, for this collection item, sequentially judge whether there is working data at each collection node according to the chronological order of the collection time;

[0088] S180, if there is no working data at the collection node, fill the average value of this collection item into this collection node to complete the working data;

[0089] S190, set a deviation threshold, calculate the upper and lower boundary values in combination with the average value calculation of this collection item and the deviation threshold, and set a qualified interval based on the upper and lower boundary values;

[0090] S191, return to step S160 until the qualified interval of each collection item of this heat exchanger is obtained;

[0091] S192, return to step S150 until all the heat exchangers in the working data table are selected, and obtain the qualified interval of each collection item of all the heat exchangers;

[0092] Optionally, in order to avoid the situation of missing working data caused by the damage of the collection unit, a missing threshold can be set, and it is judged whether the number of missing data of the collection item is greater than or equal to the missing threshold. If the number of missing data of the collection item is greater than or equal to the missing threshold, the working data of this collection item is deleted.

[0093] It should be noted that the qualified interval of the collection item is set based on the average value of each collection item. When the working data of the heat exchanger is within the qualified interval, it means that the heat exchanger is in a normal working state, while when the working data of the heat exchanger is not within the qualified interval, it means that the heat exchanger may have an abnormality.

[0094] When calculating the qualified range, if the average value of the collected item A is A and the deviation threshold is set to 20%, then the qualified range of the collected item A is [A * 80%, A * 120%]. For different collected items, the set deviation threshold is also different. The smaller the set deviation threshold, the smaller the range of the qualified range of the collected item, and the higher the qualified requirement for the collected item.

[0095] In an alternative embodiment, the step S200 includes:

[0096] S210, creating a standard heat exchanger model;

[0097] S220, dividing all the preprocessed working data of the heat exchangers into a training set and a test set at a random ratio;

[0098] S230, inputting the training set into the standard heat exchanger model, enabling the standard heat exchanger model to continuously learn the coupling relationship between the heat exchanger working data and the heat exchanger state, and obtaining the trained standard heat exchanger model;

[0099] S240, inputting the test set into the trained standard heat exchanger model to verify whether the trained standard heat exchanger model is trained successfully.

[0100] It should be noted that by creating and training the standard heat exchanger model, the trained standard heat exchanger model can judge the working state of the heat exchanger according to the input heat exchanger working data, and judge whether a warning needs to be issued based on the working state of the heat exchanger. The standard heat exchanger model can perform all-day and all-round detection, improving the detection efficiency of the heat exchanger.

[0101] In an alternative embodiment, the S230 includes:

[0102] S231, for each heat exchanger in the training set, respectively obtaining the working data of each heat exchanger;

[0103] S232, selecting a heat exchanger and sequentially judging whether the working data of each collected item of the heat exchanger is within the qualified range;

[0104] S233, if the working data of the collected item is within the qualified range, marking the heat exchanger as in a qualified state;

[0105] S234, if the working data of the collected item is not within the qualified range, marking the heat exchanger as in an unqualified state;

[0106] S235, returning to select a heat exchanger until all the heat exchangers are selected, and obtaining the working state of each heat exchanger;

[0107] S236. Based on the working data of each heat exchanger and its working state under this working data, establish the coupling relationship of heat transfer area - working data - working state, and use the heat exchanger, working data, and the coupling relationship of heat transfer area - working data - working state as a training sample, so as to obtain multiple training samples;

[0108] S237. Input multiple training samples into the heat exchanger standard model in sequence, so that the heat exchanger standard model continuously learns the corresponding relationship between the working data of the heat transfer area of the heat exchanger and the heat exchanger state, and obtain the trained heat exchanger standard model.

[0109] It should be noted that when training the heat exchanger standard model, by inputting the heat exchanger, working data, and the heat transfer area - working data - working state as a training sample into the heat exchanger standard model, the heat exchanger standard model continuously learns the relationship between the working data and the working state.

[0110] After obtaining the trained heat exchanger standard model, by inputting the working data of the heat exchanger in the test set into the trained heat exchanger standard model, the predicted working state output by the trained heat exchanger standard model is obtained, and it is determined whether the predicted working state is consistent with the working state in the test set. If the predicted working state is consistent with the working state in the test set, it proves that the trained heat exchanger standard model has been trained. If there are some predicted working states that are inconsistent with the working state in the test set, return to step S220 until the predicted working state is consistent with the working state in the test set.

[0111] In an optional embodiment, the S300 includes:

[0112] S310. Collect the real-time data of each heat transfer area of the heat exchanger;

[0113] S320. Input the real-time data of each heat transfer area of the heat exchanger into the trained heat exchanger standard model, and obtain the real-time evaluation of each heat transfer area of the heat exchanger output by the trained heat exchanger standard model;

[0114] Specifically, the real-time evaluation includes that the heat transfer area is qualified or the heat transfer area is unqualified;

[0115] S330. Set the qualified rate threshold;

[0116] S340. Sequentially determine whether the real-time evaluation of each heat transfer area of the heat exchanger is qualified, and count the qualified rate of all heat transfer areas of the heat exchanger;

[0117] S350. Determine whether the qualified rate of all heat transfer areas of the heat exchanger is greater than or equal to the qualified rate threshold;

[0118] S360, if the qualification rate of all heat exchange areas of the heat exchanger is less than the qualification rate threshold, stop the operation of the heat exchanger and issue a warning.

[0119] It should be noted that since the heat exchanger is divided into multiple heat exchange areas, for a heat exchanger, each of its heat exchange areas can be judged separately, so that the normal operation of the heat exchanger can be maintained when the unqualified heat exchange area does not affect the normal operation of the heat exchanger.

[0120] When judging whether the heat exchanger can operate normally, by setting the qualification rate threshold and judging whether the total qualification rate of all heat exchange areas included in the heat exchanger is greater than or equal to the qualification rate threshold, when the qualification rate of all heat exchange areas of the heat exchanger is less than the qualification rate threshold, it is necessary to stop the operation of the heat exchanger in time to avoid greater damage to the heat exchanger.

[0121] In this application, by dividing the heat exchange areas of the heat exchanger, when the proportion of unqualified heat exchange areas is less than the qualification rate threshold, the normal operation of the heat exchanger can be maintained and a warning is sent to the user, so that the user can timely detect the abnormality of the heat exchanger on the premise of ensuring the heat exchange efficiency of the heat exchanger.

[0122] In an optional embodiment, the S400 includes:

[0123] S410, if the qualification rate of all heat exchange areas of the heat exchanger is greater than or equal to the qualification rate threshold, judge whether there is an unqualified heat exchange area;

[0124] S420, if there is no unqualified heat exchange area, maintain the operation of the heat exchanger;

[0125] S430, if there is an unqualified heat exchange area, obtain a suspected area according to the unqualified heat exchange area;

[0126] Specifically, the suspected area refers to a heat exchange area that is still in a qualified state but may be damaged. For such a heat exchange area, it is necessary to increase the detection intensity to issue a warning in time before it affects the normal operation of the heat exchanger.

[0127] It should be noted that when the qualification rate of all heat exchange areas of the heat exchanger is greater than or equal to the qualification rate threshold, there are still two situations, that is, all heat exchange areas are qualified and there are some unqualified heat exchange areas. For these two situations, this application still adopts different control strategies. For the situation where all heat exchange areas are qualified, it can represent that the heat exchanger is intact and there is no need to issue a warning, and the normal operation state of the heat exchanger can be maintained. For the situation where there are some unqualified heat exchange areas, it represents that the heat exchanger may have reached the verge of damage. Therefore, in this case, it is necessary to conduct subsequent inspections on the heat exchanger to issue a warning in advance.

[0128] For heat exchanger A, its corresponding heat exchange areas are heat exchange area A-1, heat exchange area A-2, heat exchange area A-3, heat exchange area A-4, and heat exchange area A-5, and the set pass rate threshold is 80%. After the working data of each heat exchange area are respectively input into the trained standard model of the heat exchanger, the obtained working states are qualified, qualified, qualified, unqualified, and qualified. Then, for heat exchanger A, its pass rate is 80%, which is equal to the pass rate threshold. In this case, heat exchanger A can continue to work, but it is necessary to find the suspected area of the heat exchanger.

[0129] In an alternative embodiment, S430 includes:

[0130] S431, select an unqualified heat exchange area;

[0131] S432, obtain the adjacent heat exchange areas of the unqualified heat exchange area;

[0132] S433, determine whether the working states of the adjacent heat exchange areas are qualified;

[0133] S434, if the working states of the adjacent heat exchange areas are qualified, record the adjacent heat exchange areas as observation areas, and obtain the historical working data of the observation areas;

[0134] S435, set an error threshold;

[0135] S436, calculate the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area, and determine whether the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is greater than or equal to the error threshold;

[0136] Specifically, when calculating the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area, the working data of the first N acquisition nodes located before the acquisition node of the real-time acquired data are calculated, and the calculation needs to be performed for each acquisition item;

[0137] S437, if the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is less than or equal to the error threshold, record the observation area as a suspected area;

[0138] S438, return to select an unqualified heat exchange area until all unqualified heat exchange areas are selected, and obtain multiple suspected areas.

[0139] It should be noted that during the actual use process, the heat exchange areas near the unqualified heat exchange areas are also relatively prone to damage. Therefore, during the process of finding the suspected areas, first observe the qualified areas adjacent to the unqualified heat exchange areas. By calculating the error value between the historical working data of the observed areas and the historical working data of the unqualified heat exchange areas, the smaller the error value, the closer the working state of the observed areas is to the working state of the unqualified heat exchange areas, and the more likely it is to be damaged. Therefore, when the error is less than or equal to the error threshold, it can be considered that there is a greater possibility of damage in the observed areas, and the observed areas are recorded as suspected areas.

[0140] In an alternative embodiment, the S400 further includes:

[0141] S440, recalculate the qualification rate of the heat exchanger by combining the suspected areas and the unqualified heat exchange areas to obtain the trend qualification rate of the heat exchanger;

[0142] S450, determine whether the trend qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold;

[0143] S460, if the trend qualification rate of the heat exchanger is greater than or equal to the qualification rate threshold, maintain the operation of the heat exchanger;

[0144] S470, if the trend qualification rate of the heat exchanger is less than the qualification rate threshold, issue a warning.

[0145] It should be noted that when recalculating the qualification rate of the heat exchanger, the suspected areas need to be regarded as unqualified heat exchange areas to play a predictive role. After including the suspected areas, the qualification rate of the heat exchanger will definitely decrease. If it is the trend qualification rate of the heat exchanger, and if the trend qualification rate of the heat exchanger is less than the qualification rate threshold, it is considered that the heat exchanger has a tendency of abnormal operation. Therefore, a warning needs to be issued to the user.

[0146] This application finds the adjacent suspected areas of the unqualified heat exchange areas and adds the suspected areas to the calculation of the qualification rate of the heat exchanger, so as to issue a warning to the customer in advance before the suspected areas are damaged.

[0147] As Figure 2 shown, this application also provides a heat exchanger fault diagnosis and predictive maintenance system based on data analysis, including an acquisition unit 100 and a data processing unit 200.

[0148] The working data of the heat exchanger is collected by the collection unit 100, and the data processing unit 200 executes the heat exchanger fault diagnosis and predictive maintenance method based on data analysis as described in any one of the first embodiments. The data processing unit 200 includes a data processing subunit 201 and a control subunit 202. The working data of the heat exchanger is processed by the data processing subunit 201, and the working state of the heat exchanger is controlled by the control subunit 202.

[0149] It should be noted that for a heat exchanger, each heat exchange area corresponds to at least one collection unit 100. For example, for a heat exchanger including multiple heat exchange tubes, at least one collection unit 100 is provided for each heat exchange tube. The collection unit 100 includes a variety of sensors, which can be respectively used to collect the working data of multiple different collection items in the heat exchange area. All the collected working data is transmitted to the data processing unit 200. The data processing unit 200 includes a standard model of the heat exchanger, so as to judge whether a warning needs to be issued according to the input working data of the heat exchanger.

[0150] The embodiments of the present invention have been described in detail above with reference to the drawings. However, the present invention is not limited thereto. Various changes can be made without departing from the spirit of the present invention within the scope of knowledge possessed by those skilled in the art to which the present invention pertains.

Claims

1. A method for fault diagnosis and predictive maintenance of a heat exchanger based on data analysis, characterized in that, Including: Set acquisition parameters, collect the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain preprocessed working data, and set the qualified range of the heat exchangers according to the preprocessed working data; The setting of the acquisition parameters, collecting the working data of multiple heat exchangers based on the acquisition parameters, preprocessing the working data of the heat exchangers to obtain preprocessed working data, and setting the qualified range of the heat exchangers according to the preprocessed working data includes: Divide each heat exchanger into multiple heat exchange areas; Set acquisition parameters for each of the multiple heat exchange areas of each heat exchanger; the acquisition parameters include acquisition period, acquisition frequency, and acquisition location; For each heat exchanger, collect the working data of multiple heat exchange areas of the heat exchanger according to the acquisition parameters of the heat exchanger, and put the collected working data into the heat exchanger data table; the working data includes multiple acquisition items such as heat exchanger temperature data, heat exchanger pressure data, and heat exchanger flow data; Create a heat exchanger standard model, train the heat exchanger standard model with the preprocessed working data, so that the heat exchanger standard model judges the working state of the heat exchanger based on the working data of the heat exchanger, and obtain the trained heat exchanger standard model; The creation of the heat exchanger standard model, training the heat exchanger standard model with the preprocessed working data, so that the heat exchanger standard model judges the working state of the heat exchanger based on the working data of the heat exchanger, and obtain the trained heat exchanger standard model includes: For each heat exchanger in the training set, obtain the working data of each heat exchanger respectively; Select a heat exchanger, and sequentially judge whether the working data of each acquisition item of the heat exchanger is within the qualified range; If the working data of the acquisition item is within the qualified range, mark the heat exchanger as a qualified state; If the working data of the acquisition item is not within the qualified range, mark the heat exchanger as an unqualified state; Return to select a heat exchanger until all heat exchangers have been selected, and obtain the working state of each heat exchanger; Collect the real-time data of each heat exchange area of the heat exchanger; Input the real-time data of each heat exchange area of the heat exchanger into the trained heat exchanger standard model, and obtain the real-time evaluation of each heat exchange area of the heat exchanger output by the trained heat exchanger standard model; Set the pass rate threshold; Sequentially judge whether the real-time evaluation of each heat exchange area of the heat exchanger is qualified, and count the pass rate of all heat exchange areas of the heat exchanger; Judge whether the pass rate of all heat exchange areas of the heat exchanger is greater than or equal to the pass rate threshold; If the pass rate of a heat exchange area of the heat exchanger is less than the pass rate threshold, stop the operation of the heat exchanger and issue a warning; If the pass rate of all heat exchange areas of the heat exchanger is greater than or equal to the pass rate threshold, judge whether there is an unqualified heat exchange area; If there is no unqualified heat exchange area, keep the heat exchanger working; If there is an unqualified heat exchange area, obtain the suspected area according to the unqualified heat exchange area; And calculate the pass rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether a warning needs to be issued based on the pass rate trend of the heat exchanger. Obtaining the suspected area includes: Select an unqualified heat exchange area; Obtain the adjacent heat exchange areas of the unqualified heat exchange area; Judge whether the working status of the adjacent heat exchange areas is qualified; If the working status of the adjacent heat exchange areas is qualified, record the adjacent heat exchange areas as the observation areas and obtain the historical working data of the observation areas; Set the error threshold; Calculate the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area, and judge whether the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is greater than or equal to the error threshold; If the error between the historical working data of the observation area and the historical working data of its corresponding unqualified heat exchange area is less than or equal to the error threshold, record the observation area as a suspected area; Return to select an unqualified heat exchange area until all unqualified heat exchange areas are selected, and obtain multiple suspected areas.

2. The method for heat exchanger fault diagnosis and predictive maintenance based on data analysis according to claim 1, characterized in that, Set the acquisition parameters, acquire the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain the preprocessed working data, and set the qualified range of the heat exchangers according to the preprocessed working data, including: Create a heat exchanger data table.

3. The method for heat exchanger fault diagnosis and predictive maintenance based on data analysis according to claim 2, characterized in that Set the acquisition parameters, acquire the working data of multiple heat exchangers based on the acquisition parameters, preprocess the working data of the heat exchangers to obtain the preprocessed working data, and set the qualified range of the heat exchangers according to the preprocessed working data, also including: Randomly select a heat exchanger from the heat exchanger data table and obtain the working data of this heat exchanger; Select an acquisition item and calculate the average value of this acquisition item; For this acquisition item, judge whether there is working data at each acquisition node in turn according to the chronological order of the acquisition time; If there is no working data at the acquisition node, fill the average value of this acquisition item into this acquisition node to complete the working data; Set the deviation threshold, calculate the upper and lower boundary values in combination with the mean calculation of this acquisition item and the deviation threshold, and set the qualified range based on the upper and lower boundary values; Return to select an acquisition item and calculate the average value of this acquisition item until the qualified range of each acquisition item of this heat exchanger is obtained; Return to randomly select a heat exchanger from the heat exchanger data table until all heat exchangers in the working data table are selected, and obtain the qualified range of each acquisition item of all heat exchangers.

4. The method for heat exchanger fault diagnosis and predictive maintenance based on data analysis according to claim 3, wherein Create a heat exchanger standard model, train the heat exchanger standard model through the preprocessed working data, so that the heat exchanger standard model judges the working status of the heat exchanger based on the working data of the heat exchanger, and obtain the trained heat exchanger standard model, including: Create a heat exchanger standard model; Divide the preprocessed working data of all heat exchangers into a training set and a test set in a random ratio; Input the training set into the heat exchanger standard model, so that the heat exchanger standard model continuously learns the coupling relationship between the heat exchanger working data and the heat exchanger status, and obtain the trained heat exchanger standard model; Input the test set into the trained heat exchanger standard model to verify whether the trained heat exchanger standard model is trained.

5. The method for heat exchanger fault diagnosis and predictive maintenance based on data analysis according to claim 4, characterized in that Input the training set into the heat exchanger standard model, so that the heat exchanger standard model continuously learns the coupling relationship between the heat exchanger working data and the heat exchanger status, and obtain the trained heat exchanger standard model, including: Based on the working data of each heat exchanger and its working state under this working data, establish the coupling relationship of heat transfer area - working data - working state, and use the heat exchanger, working data, and the coupling relationship of heat transfer area - working data - working state as a training sample, so as to obtain multiple training samples; Input multiple training samples into the heat exchanger standard model in sequence, so that the heat exchanger standard model continuously learns the corresponding relationship between the working data of the heat exchanger and the heat exchanger state, and obtain the trained heat exchanger standard model.

6. The method for heat exchanger fault diagnosis and predictive maintenance based on data analysis according to claim 5, characterized in that, If the qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, obtain the suspected area and calculate the qualified rate trend of the heat exchanger by combining the suspected area and the unqualified area, and judge whether it is necessary to issue a warning based on the qualified rate trend of the heat exchanger. It also includes: Recalculate the qualified rate of the heat exchanger by combining the suspected area and the unqualified heat transfer area to obtain the trend qualified rate of the heat exchanger; Judge whether the trend qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold; If the trend qualified rate of the heat exchanger is greater than or equal to the qualified rate threshold, maintain the operation of the heat exchanger; If the trend qualified rate of the heat exchanger is less than the qualified rate threshold, issue a warning.

7. A heat exchanger fault diagnosis and predictive maintenance system based on data analysis, characterized in that, It includes: A collection unit that collects the working data of the heat exchanger through the collection unit; A data processing unit that executes the heat exchanger fault diagnosis and prediction maintenance method based on data analysis as described in any one of claims 1 to 6 through the data processing unit. The data processing unit includes a data processing subunit and a control subunit, processes the working data of the heat exchanger through the data processing subunit, and controls the working state of the heat exchanger through the control subunit.

Images