A method and device for diagnosing faults of turbine cooler under variable speed

Abstract

The present application provides a method and device for diagnosing faults of a turbine cooler under variable speed, which belongs to the field of aviation electromechanics. The method provided by the present application includes: determining a monitored fault signal based on historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault; determining a critical value of the fault signal based on the historical fault, and the critical value is the value of the fault signal when the historical fault occurs; calculating a first relationship between the speed of the turbine cooler and a historical fault judgment threshold based on the critical value; correcting the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship; obtaining real-time information of the turbine cooler under variable speed; and identifying the fault of the turbine cooler based on the real-time information and the second relationship. The method and device for diagnosing faults of a turbine cooler under variable speed provided by the present application can support rapid fault location of the turbine cooler under complex variable speed conditions.

Description

Technical Field

[0001] The present application relates to the field of aviation electromechanical technology, and in particular to a method and device for diagnosing turbine cooler faults under variable speed. Background Art

[0002] The turbine cooler is a core component of the aircraft environmental control system. It uses the compressed hot air from the engine compressor. After being cooled in the front stage, it enters the fuel-air heat exchanger and flows into the nozzle ring along the turbine cooler volute. The high-speed air flows into the turbine disc blades from the nozzle ring, impacts the impeller to rotate and do work, the air expands, the pressure decreases, the temperature drops, and the kinetic energy and enthalpy drop of the air are converted into mechanical work, which is consumed by the fan. After the air works on the blades of the turbine disc, it leaves the turbine cooler at low pressure and low temperature and is supplied to the aircraft cabin and instrument compartment, while part of the air is used to cool the bearings of the turbine cooler.

[0003] As a core component for cooling in aviation environmental control systems, a turbine cooler will have serious consequences and even affect flight safety if it fails. Due to the importance of turbine coolers in aviation environmental control systems, the current method mainly monitors the operating status of turbine coolers online to detect faults and issue early warnings. However, there is a lack of online fault diagnosis for turbine coolers under variable speed conditions. Therefore, it is necessary to study the problem of rapid fault location of turbine coolers under complex variable speed conditions. Summary of the invention

[0004] In view of this, the present application provides a method and device for diagnosing turbine cooler faults under variable speed, which can support rapid fault location of the turbine cooler under complex variable speed conditions.

[0005] Specifically, the present application is implemented through the following technical solutions:

[0006] A first aspect of the present application provides a method for diagnosing faults of a turbine cooler under variable speed conditions, the method comprising:

[0007] Determine a monitored fault signal based on historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault, the monitored fault signal corresponding to each historical fault is not completely the same, and the magnitude of the change of the monitored fault signal is different under different speeds;

[0008] Determine a critical value of the fault signal based on the historical fault, wherein the critical value is the value of the fault signal when the historical fault occurs;

[0009] Calculating a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value based on the critical value to obtain a correlation between the rotation speed and the fault judgment threshold value;

[0010] Correcting the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, a change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to a change direction of the speed change rate;

[0011] Get real-time information about the turbine cooler at variable speeds;

[0012] A fault in the turbine cooler is identified based on the real-time information and the second relationship.

[0013] A second aspect of the present application provides a turbine cooler fault diagnosis device under variable speed, the device comprising a determination module, a calculation module, a correction module, an acquisition module and an identification module;

[0014] Wherein, the determination module is used to determine the monitored fault signal based on the historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault, the monitored fault signal corresponding to each historical fault is not completely the same, and the amplitude of the change of the monitored fault signal is different under different speeds;

[0015] The determination module is further configured to determine a critical value of the fault signal based on the historical fault, wherein the critical value is a value of the fault signal when the historical fault occurs;

[0016] The calculation module is used to calculate a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value based on the critical value, and obtain a correlation between the rotation speed and the fault judgment threshold value;

[0017] The correction module is used to correct the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, the change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to the change direction of the speed change rate;

[0018] The acquisition module is used to acquire real-time information of the turbine cooler under variable speed;

[0019] The identification module is used to identify a fault of the turbine cooler based on the real-time information and the second relationship.

[0020] The turbine cooler fault diagnosis method and device under variable speed provided by the present application can determine the monitored fault signal based on the historical fault data under variable speed, can reasonably select the type and layout of the sensor, reduce unnecessary waste, and improve the accuracy and reliability of fault signal recognition. By determining the critical value of the fault signal and dynamically adjusting the fault judgment threshold based on the critical value, the false alarm or missed alarm problem caused by the fixed threshold can be avoided. The judgment threshold of different stages is set according to the speed working condition, so that the monitoring accuracy is greatly improved. In addition, by correcting the speed change rate, the threshold of fault judgment can be adjusted in time under rapidly changing working conditions, the sensitivity and response speed of detection can be improved, and potential faults can be discovered in time. By obtaining real-time information under variable speed and combining the second relationship, real-time monitoring can be achieved, faults can be identified and diagnosed in time, and early warnings can be provided to prevent further deterioration of faults. In this way, by combining historical fault data, real-time speed changes and dynamic adjustment of the speed change rate, the fault analysis problem of the turbine cooler under variable speed conditions is effectively solved. Specifically, through flexible threshold adjustment and real-time fault identification, the system's adaptability to complex working conditions is improved, avoiding misjudgment or missed judgment due to speed fluctuations, and ensuring the safety and reliability of the equipment under various operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a first embodiment of a method for diagnosing a turbine cooler fault under variable speed provided by the present application;

[0022] Figure 2 A diagram showing the relationship between changes in fault signals under different working conditions according to an exemplary embodiment of the present application;

[0023] Figure 3 This is a schematic diagram of the fundamental frequency amplitude under an unbalanced fault according to an exemplary embodiment of the present application;

[0024] Figure 4 A schematic diagram of the fundamental frequency amplitude under unbalanced fault at different speeds shown in an exemplary embodiment of the present application;

[0025] Figure 5 This is a schematic structural diagram of the first embodiment of the turbine cooler fault diagnosis device under variable speed provided in the present application. DETAILED DESCRIPTION

[0026] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0027] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0028] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0029] Specific embodiments are given below to introduce the technical solution of the present application in detail.

[0030] Figure 1 This is a flow chart of Embodiment 1 of the method for diagnosing turbine cooler faults under variable speed provided by this application. Figure 1 , the method provided in this embodiment may include:

[0031] S101. Determine a monitored fault signal based on historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault, the monitored fault signal corresponding to each historical fault is not exactly the same, and the magnitude of change of the monitored fault signal under different speeds is different.

[0032] It should be noted that the variable speed turbine cooler means that under different working conditions (or working conditions), the speed of the turbine cooler will change continuously, and the performance of the fault signal at different speeds (such as the amplitude of the change) may be different, and the monitored fault signals corresponding to historical faults are not exactly the same. In addition, due to the aerodynamic influence and large fluctuations in the working speed of the turbine cooler during operation, the collected vibration signal has nonlinear and non-stationary characteristics, which seriously affects the identification of fault signals.

[0033] Specifically, the fault signal to be monitored is determined based on the historical faults of the turbine cooler under variable speed, including: collecting historical fault data of the turbine cooler under different operating conditions, and recording and analyzing the fault data under different conditions; according to the analysis results, determining the fault signal and the fault characteristics of the fault signal under different speeds, loads and working conditions and their change amplitude. It should be noted that the historical fault data collected for the turbine cooler under different operating conditions include common fault types and fault signals corresponding to the fault types. For example, in one embodiment, according to the analysis of historical fault data, it is obtained that common faults of the turbine cooler are imbalance and bearing faults, and these two faults are usually displayed through vibration signals, that is, the fault signals corresponding to imbalance and bearing faults are vibration signals. At this time, the sensor can be arranged at the bearing seat position to measure the bearing in the optimal path to obtain the vibration signal (the purpose is to reduce the attenuation effect of the signal transmission path). In addition, the fault signal can also include temperature signals, pressure signals, etc.

[0034] As an optional embodiment, the historical faults include faults of the turbine cooler at various speeds. Each fault has multiple fault signals, such as abnormal temperature, abnormal speed, abnormal vibration, etc. Each fault signal corresponds to an amplitude. In a fault, the amplitude of each fault signal change is not exactly the same. Under different faults, the fault signals are not exactly the same, and the amplitude of the same fault signal change under different faults is not exactly the same. For example, Figure 2 As shown, Figure 2 Figure a shows the change amplitude of the turbine vibration signal. Figure 2 Figure b shows the change amplitude of the turbine end temperature signal. Figure 2 Figure c shows the change amplitude of the fan end temperature signal. Figure 2 The d figure in the figure shows the change amplitude of the turbine speed signal. Under different working conditions, the change amplitude of each fault signal also changes. Furthermore, in order to unify the comparison dimensions of different fault signals, the percentage change of each amplitude relative to the amplitude under the standard state can be directly calculated as the dimension, thereby realizing the comparison of different fault signal types in the same dimension.

[0035] Specifically, the fault signal determined and monitored based on the historical fault of the turbine cooler under variable speed includes:

[0036] Determine all fault signals under each historical fault, determine the common fault signal type of all historical faults, and at the same time use the fault signal in the common fault signal type with the largest amplitude change under each historical fault as the monitored fault signal corresponding to the historical fault, that is, the monitored fault signal types corresponding to different faults can be different or the same. Furthermore, each monitored fault signal type also corresponds to a critical value. Therefore, even if the fault signal types corresponding to different faults are the same, their critical values ​​are not completely the same.

[0037] As another optional embodiment, all fault signals under each historical fault are determined, and the signal whose fault signal change amplitude exceeds a preset threshold is used as the monitored fault signal. At this time, each fault corresponds to one or more monitored fault signals, and each fault signal is the signal that changes most drastically under the fault mode.

[0038] S102: Determine a critical value of the fault signal based on the historical fault, where the critical value is the value of the fault signal when the historical fault occurs.

[0039] It should be noted that the critical value of the fault signal is determined based on the historical fault, and the critical value is the value of the fault signal when the historical fault occurs, including:

[0040] (1) Extracting fault signal features based on the historical fault data of the turbine cooler.

[0041] It should be noted that the historical fault data of the turbine cooler may include vibration signals, temperature signals, acoustic emission signals, etc., and before extracting the fault signal features, the collected data may be cleaned and classified, and then the key features of the fault signal may be extracted from the cleaned data, such as the spectral features of the vibration signal (such as peak frequency and amplitude), the change trend of the temperature signal, etc.

[0042] (2) According to the fault type, count the fault signal characteristic values ​​in the historical fault data, calculate their statistics, and determine the critical value of each fault type.

[0043] The historical fault data is classified according to the fault type (such as unbalance fault, bearing fault), and for each fault type, the fault signal characteristic values ​​extracted from all historical fault data are counted. Specifically, the characteristic value statistics can be performed through methods such as mean calculation, standard deviation calculation and distribution analysis. Then, the critical value of each fault type is determined based on the statistical results. For example, the critical value can be calculated by statistical methods or empirical methods. Among them, the statistical method is based on the mean and standard deviation, and the critical value is determined by adding or subtracting several standard deviations from the mean; the empirical method is based on the distribution of the fault signal characteristic values ​​in the historical data, and an appropriate percentile (such as 95%, 99%) is selected as the critical value.

[0044] S103: Calculate a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold based on the critical value to obtain a correlation between the rotation speed and the fault judgment threshold.

[0045] It should be noted that calculating the first relationship between the rotation speed of the turbine cooler and the historical fault judgment threshold based on the critical value includes:

[0046] (1) Based on the historical faults, the rotation speeds at different times in the fault data are obtained and matched with the corresponding fault signal critical values ​​one by one, and a scatter plot of the rotation speed and the fault signal critical value is drawn; the horizontal axis of the scatter plot is the rotation speed, and the vertical axis is the fault signal critical value.

[0047] It should be noted that the rotational speed and the corresponding fault signal critical value when each fault event occurred are extracted from the historical fault data, and the rotational speed value of each fault event is paired with the corresponding fault signal critical value. Then, a scatter plot is drawn with the rotational speed as the horizontal axis and the fault signal critical value as the vertical axis to show the data point distribution of each historical fault event.

[0048] (2) Fit the scatter plot according to the fitting method to obtain a curve of the relationship between the rotation speed and the critical value.

[0049] According to the distribution of data points, select a suitable fitting method (such as linear regression, quadratic polynomial fitting or other nonlinear fitting methods), use the selected fitting method to fit the scatter plot, and obtain the relationship curve between the rotational speed and the critical value of the fault signal.

[0050] (3) Calculating historical fault judgment thresholds at different speeds according to the relationship curve, and calculating dynamic thresholds based on the historical fault judgment thresholds.

[0051] It should be noted that the critical values ​​of fault signals at different speeds are calculated using the fitted relationship curve, and these values ​​are combined into the historical fault judgment threshold. Then, according to the actual operating conditions, a safety margin (used to measure the gap or reserve between the turbine cooler under normal working conditions and its tolerance limit) is added to each critical value to obtain a dynamic threshold. It should be noted that the historical fault judgment threshold and dynamic threshold in this application are both expressed in percentage form.

[0052] Wherein, the value of the safety margin may be different under different conditions. Specifically, the dynamic threshold is calculated based on the historical fault judgment threshold, including: identifying factors affecting the safety margin; the factors affecting the safety margin include the current operating state, environmental conditions and operating conditions of the turbine cooler; selecting a calculation method for the safety margin based on the determined factors affecting the safety margin, and calculating the safety margin; the calculation method includes a fixed percentage method, a condition-based dynamic adjustment method and a multivariate regression or machine learning model method; the dynamic threshold is calculated based on the calculated safety margin and the historical fault judgment threshold. Wherein, the current operating state of the turbine cooler may cause changes in signals such as temperature, pressure and vibration, environmental conditions may include ambient temperature and humidity, and operating conditions may include information such as equipment load and usage time.

[0053] It should be noted that the above-mentioned fixed percentage method is to set a fixed proportion of safety margin (the proportion is different at different times); the multiple regression or machine learning model method is to predict the safety margin based on historical failure data using a multiple regression or machine learning model.

[0054] It should also be noted that the condition-based dynamic adjustment method is to set a basic safety margin, and then obtain the state factor and the first safety margin adjustment coefficient based on the operating state of the equipment (reflecting the current operating state of the equipment: such as the degree of influence of temperature, pressure, vibration, etc. on the safety margin), and obtain the environmental factor and the second safety margin adjustment coefficient based on the environmental conditions (reflecting the degree of influence of environmental conditions: such as ambient temperature, humidity, etc. on the safety margin), and combine the basic safety margin, the state factor and the first safety margin adjustment coefficient, the environmental factor and the second safety margin adjustment coefficient to obtain a comprehensive safety margin as the final safety margin for calculating the dynamic threshold. For example, the obtained safety margin can be added to the historical fault judgment threshold to obtain the dynamic threshold.

[0055] It should also be noted that the historical fault judgment threshold at different speeds is calculated according to the relationship curve, and the dynamic threshold is calculated based on the historical fault judgment threshold. After that, it includes: analyzing the speed and the historical faults to determine the fault occurrence rate at different speeds; based on the fault occurrence rate, establishing a first relationship between the speed and the historical fault judgment threshold.

[0056] It should be noted that the above thresholds are set because, under a single threshold, if the threshold is set too large, it is easy to miss reports, making it difficult to detect early faults, causing the fault to continue to deteriorate and affect system safety; if the threshold is set too small, it is easy to be affected by the working conditions and cause false alarms. Therefore, this application sets dynamic thresholds at different stages according to the speed working conditions, which greatly improves the accuracy of fault monitoring.

[0057] S104. Correct the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, a change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to a change direction of the speed change rate.

[0058] It should be noted that the first relationship is corrected based on the speed change rate of the turbine cooler to obtain the second relationship, including:

[0059] (1) Calculating speed change rate data of the turbine cooler under different operating conditions based on the speed of the turbine cooler.

[0060] The speed data of the turbo cooler under different working conditions are obtained, including the speed change under various operating conditions, and the speed change rate of the turbo cooler under different working conditions is calculated based on the collected speed data. The speed change rate usually refers to the change in speed per unit time.

[0061] (2) A correction factor is determined based on the rotational speed change rate data and its corresponding critical value, wherein different rotational speed change rate data correspond to different critical values.

[0062] It should be noted that the statistical analysis of the speed change rate data pays special attention to the working conditions with fast speed change rate. The fast changing speed may have a significant impact on the operating status and fault occurrence rate of the system. Then, based on the analysis results, a correction factor is determined. The correction factor reflects the degree of influence of the speed change rate on the fault judgment threshold. If the speed change rate is large, the correction factor may be large; conversely, if the speed change rate is small, the correction factor may be small. Among them, the correction factor is defined by analyzing the speed change rate data to define the critical value of the speed change rate (when the speed change rate exceeds this critical value, the equipment risk increases significantly), and then the impact of the fault risk is determined based on the critical value (the greater the difference between the speed change rate and the critical value, the greater the impact of the fault risk), and finally determined based on the impact of the fault risk.

[0063] (3) Correcting the first relationship according to the correction factor to obtain a second relationship; wherein the correction process is to reduce the historical fault judgment threshold when the speed change rate is large.

[0064] Specifically, when the speed change rate is large, the historical fault judgment threshold is reduced according to the correction factor (wherein the historical fault judgment threshold will no longer be reduced after being reduced to a specified range, otherwise it is easy to identify even very small faults, resulting in false alarms) to adapt to rapidly changing working conditions, which means that when the speed change rate is fast, the system will respond more sensitively to potential fault signals. Based on the corrected fault judgment threshold and speed data, a second relationship is established, wherein the second relationship describes the relationship between the corrected speed and the updated historical fault judgment threshold.

[0065] In the above process, when a fault is identified based on the critical value (exceeding the critical value), the relationship between the speed change rate and the fault judgment threshold value (opposite) indicates that a fault has occurred. Therefore, the fault judgment threshold value should be reduced for this scenario to make the fault more sensitive. In particular, in another scenario, if the speed change rate is large at this time, but the fault has not been identified based on historical fault data (has not reached the critical value), the fault judgment threshold value should be appropriately increased to avoid false alarms.

[0066] For better explanation, the relationship between the speed change rate and the fault judgment threshold in the above two situations is distinguished according to the first threshold and the second threshold. Among them, the speed change rate at the first threshold is greater than the speed change rate at the second threshold. When the first threshold is reached, the fault judgment threshold is increased, and when the second threshold is reached, the fault judgment threshold is reduced. Among them, the fault judgment threshold amplitude increased at the first threshold is greater than the fault judgment threshold amplitude decreased at the second threshold. For example, in one embodiment, the fault judgment threshold amplitude increased by the first threshold is 8%, and the fault judgment threshold amplitude decreased by the second threshold is 5%.

[0067] S105: Acquire real-time information of the turbine cooler under variable speed.

[0068] The operating status of the turbine cooler is monitored by the installed sensors, and real-time information is collected. The operating status of the turbine cooler can be monitored at any time through the real-time information. It should be noted that after the real-time information is collected, the collected real-time data can be processed and analyzed in real time, which helps to timely discover potential signs of failure or abnormal conditions so that appropriate measures can be taken for preventive maintenance or emergency repairs.

[0069] S106 . Identify a fault of the turbine cooler based on the real-time information and the second relationship.

[0070] It should be noted that identifying the fault of the turbine cooler based on the real-time information and the second relationship includes:

[0071] (1) Performing order analysis based on the real-time information to convert the non-stationary vibration signal of the variable speed condition into a stable order spectrum line signal.

[0072] It should be noted that order analysis is used to process the non-steady-state characteristics of vibration signals caused by speed changes. It converts non-steady-state signals into steady-state signals based on the rotational periodicity of the signal in the rotor rotating coordinate system, so as to make it easier to diagnose and analyze vibration problems. Decoupling the variable speed condition based on the order analysis method can convert the non-stationary vibration signal of the variable speed condition into a stable order spectrum signal. The decoupling process means decomposing the signal into components of different orders, such as first order, second order, etc., and each order component corresponds to a specific multiple (order) of the rotation frequency.

[0073] In addition, spectrum analysis is performed on each order component to calculate its amplitude and spectrum characteristics.

[0074] (2) Based on the historical fault judgment threshold in the second relationship and the fundamental frequency amplitude under the order spectrum, the bearing fault frequency amplitude and its multiples, determine whether a fault has occurred, determine the fault type, and evaluate its severity.

[0075] Figure 3 is a schematic diagram of the fundamental frequency amplitude under an unbalanced fault according to an exemplary embodiment of the present application. Figure 4 This is a schematic diagram of the fundamental frequency amplitude under unbalanced fault at different speeds shown in an exemplary embodiment of the present application. Please also refer to Figure 3 and Figure 4 , the order spectrum obtained by order analysis needs to pay special attention to the fundamental frequency component (i.e. the frequency corresponding to the rotation speed). The vibration caused by imbalance usually manifests as a significant increase in the fundamental frequency. Therefore, by monitoring the amplitude change of the fundamental frequency under the order spectrum, it is possible to determine whether there is an imbalance fault and assess its severity. An increase in the amplitude usually indicates that the imbalance problem is more serious.

[0076] It should be noted that different types of bearing faults (such as inner ring, outer ring, rolling element, and cage) will appear as harmonic components of specific frequencies and their multiples in the order spectrum. By analyzing the amplitude changes of these specific frequency components under the order spectrum, it is possible to determine whether a bearing fault has occurred, and to infer its specific type (based on the frequency) and severity (based on the amplitude changes).

[0077] This application uses order tracking to convert the variable speed vibration non-stationary signal into an angle domain stationary signal, and extracts order characteristics in combination with the fault mechanism, which effectively reduces the interference of complex environments and can quickly locate faults under complex variable speed conditions.

[0078] It should also be noted that the fault of the turbine cooler is identified based on the real-time information and the second relationship, and then the following steps are included: extracting fault features based on the identified fault, and combining the relationship between each fault in the historical fault data and the remaining life of the turbine cooler to establish a corresponding relationship between the current fault feature and the remaining life of the turbine cooler, and perform a health status warning. In this way, a corresponding early warning strategy can be formulated based on the predicted remaining life. For example, when the remaining life reaches a certain threshold, maintenance recommendations or more frequent monitoring are made. In addition, the early warning strategy should adjust the maintenance plan according to the severity and possible impact of the fault type to avoid unexpected downtime and losses.

[0079] In this way, by first determining whether the turbine cooler has an abnormality, and then identifying the type of fault after the abnormality occurs, and quantitatively describing the degree of the fault, it is possible to effectively guide the subsequent maintenance and support strategies and achieve the optimal arrangement of support timing and resources.

[0080] The method provided in this embodiment first determines the monitored fault signal based on the historical faults of the turbine cooler under variable speed, and then determines the critical value of the fault signal based on the historical faults, thereby calculating the first relationship between the speed of the turbine cooler and the historical fault judgment threshold based on the critical value, and then correcting the first relationship based on the speed change rate of the turbine cooler to obtain the second relationship, and then obtaining the real-time information of the turbine cooler under variable speed, and identifying the fault of the turbine cooler based on the real-time information and the second relationship. In this way, by determining the monitored fault signal based on the historical fault data under variable speed, the type and layout of the sensor can be reasonably selected, unnecessary waste can be reduced, and the accuracy and reliability of fault signal identification can be improved. By determining the critical value of the fault signal and dynamically adjusting the fault judgment threshold based on the critical value, the problem of false alarm or missed alarm caused by the fixed threshold can be avoided, and the judgment threshold of different stages can be set according to the speed condition, so that the monitoring accuracy is greatly improved. In addition, by correcting the speed change rate, the threshold of fault judgment can be adjusted in time under rapidly changing working conditions, the sensitivity and response speed of detection can be improved, and potential faults can be discovered in time. By obtaining real-time information under variable speed and combining the second relationship, real-time monitoring can be achieved, and faults can be identified and diagnosed in time, providing early warnings to prevent further deterioration of faults. In this way, by combining historical fault data, real-time speed changes, and dynamic adjustment of the speed change rate, the fault analysis problem of the turbine cooler under variable speed conditions is effectively solved. Specifically, through flexible threshold adjustment and real-time fault identification, the system's adaptability to complex working conditions is improved, and misjudgment or missed judgment caused by speed fluctuations is avoided, ensuring the safety and reliability of the equipment under various operating conditions.

[0081] Corresponding to the aforementioned embodiment of a method for diagnosing faults of a turbine cooler under variable speed, the present application also provides an embodiment of a device for diagnosing faults of a turbine cooler under variable speed.

[0082] Figure 5 This is a schematic diagram of the structure of the first embodiment of the turbine cooler fault diagnosis device under variable speed provided by this application. Figure 5 , the device provided in this embodiment includes a determination module 510, a calculation module 520, a correction module 530, an acquisition module 540 and an identification module 550;

[0083] The determination module 510 is used to determine the monitored fault signal based on the historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault, the monitored fault signal corresponding to each historical fault is not completely the same, and the magnitude of the change of the monitored fault signal is different under different speeds;

[0084] The determination module 510 is further configured to determine a critical value of the fault signal based on the historical fault, wherein the critical value is the value of the fault signal when the historical fault occurs;

[0085] The calculation module 520 is used to calculate a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value based on the critical value, and obtain a correlation between the rotation speed and the fault judgment threshold value;

[0086] The correction module 530 is used to correct the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, the change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to the change direction of the speed change rate;

[0087] The acquisition module 540 is used to acquire real-time information of the turbine cooler under variable speed;

[0088] The identification module 550 is configured to identify a fault of the turbine cooler based on the real-time information and the second relationship.

[0089] The device of this embodiment can be used to perform Figure 1 The steps, specific implementation principles and implementation processes of the method embodiment shown are similar and will not be repeated here.

[0090] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0091] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0092] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for diagnosing turbine cooler faults under variable speed, characterized in that: The method comprises: Determine a monitored fault signal based on historical faults of the turbine cooler under variable speed, wherein the fault signal changes at each historical fault, the monitored fault signal corresponding to each historical fault is not completely the same, and the magnitude of the change of the monitored fault signal is different at different speeds; Determine a critical value of the fault signal based on the historical fault, wherein the critical value is the value of the fault signal when the historical fault occurs; Calculating a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value based on the critical value, and obtaining a correlation between the rotation speed and the historical fault judgment threshold value; Correcting the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, a change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to a change direction of the speed change rate; Get real-time information about the turbine cooler at variable speeds; identifying a fault in the turbine cooler based on the real-time information and the second relationship; The calculating, based on the critical value, a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value comprises: Based on the historical faults, the rotation speeds at different times in the fault data are obtained and matched one by one with the corresponding fault signal critical values, and a scatter plot of the rotation speed and the fault signal critical value is drawn; the horizontal axis of the scatter plot is the rotation speed, and the vertical axis is the fault signal critical value; Fit the scatter plot according to a fitting method to obtain a relationship curve between the rotation speed and the critical value; According to the relationship curve, the historical fault judgment thresholds at different speeds are calculated, and the dynamic threshold is calculated based on the historical fault judgment thresholds; wherein, the fault signal critical values ​​at different speeds are calculated by using the relationship curve, and the fault signal critical values ​​are combined into the historical fault judgment thresholds, and then according to the actual operating conditions, the safety margin is added to each fault signal critical value to obtain the dynamic threshold; The method further comprises: calculating the historical fault judgment thresholds at different speeds according to the relationship curve, and calculating the dynamic thresholds based on the historical fault judgment thresholds, and then: Analyze the rotation speed and the historical faults to determine the fault occurrence rate at different rotation speeds; Based on the fault occurrence rate, a first relationship between the rotation speed and the historical fault judgment threshold is established.

2. The method according to claim 1, characterized in that The first relationship is corrected based on the speed change rate of the turbine cooler to obtain the second relationship, including: Calculating the speed change rate data of the turbine cooler under different working conditions based on the speed of the turbine cooler; Determining a correction factor based on the rotational speed change rate data and a critical value corresponding thereto, wherein different rotational speed change rate data correspond to different critical values; The first relationship is corrected according to the correction factor to obtain a second relationship; wherein the correction process is to reduce the historical fault judgment threshold when the speed change rate is large.

3. The method according to claim 1, characterized in that The determining of the critical value of the fault signal based on the historical fault, wherein the critical value is the value of the fault signal when the historical fault occurs, comprises: Extracting fault signal characteristics based on the historical fault data of the turbine cooler; According to the fault type, the fault signal characteristic values ​​in the historical fault data are counted, and their statistics are calculated to determine the critical value of each fault type.

4. The method according to claim 1, characterized in that: The identifying the fault of the turbine cooler based on the real-time information and the second relationship comprises: Performing order analysis based on the real-time information to convert the non-stationary vibration signal of the variable speed condition into a stable order spectrum line signal; According to the historical fault judgment threshold in the second relationship and the fundamental frequency amplitude under the order spectrum, the bearing fault frequency amplitude and its multiple frequencies, it is judged whether a fault occurs, the fault type is determined, and its severity is evaluated.

5. The method according to claim 1, characterized in that The fault signal determined and monitored based on the historical fault of the turbine cooler under variable speed includes: Collect historical fault data of the turbine cooler under different operating conditions, and record and analyze the fault data under different conditions; based on the analysis results, determine the fault signal and the fault characteristics and variation range of the fault signal under different speeds, loads and operating conditions.

6. The method according to claim 1, characterized in that The method further comprises: identifying a fault of the turbine cooler based on the real-time information and the second relationship, and then: Based on the identified faults, fault features are extracted, and combined with the relationship between each fault in the historical fault data and the remaining life of the wheel cooler, the corresponding relationship between the current fault features and the remaining life of the wheel cooler is established to provide a health status warning.

7. The method according to claim 1, characterized in that The calculating of the dynamic threshold based on the historical fault judgment threshold comprises: Identifying factors affecting the safety margin; the factors affecting the safety margin include the current operating state, environmental conditions and operating conditions of the turbine cooler; Selecting a calculation method for the safety margin based on the determined factors affecting the safety margin to calculate the safety margin; the calculation method includes a fixed percentage method, a condition-based dynamic adjustment method, and a multiple regression or machine learning model method; A dynamic threshold is calculated based on the calculated safety margin and the historical fault judgment threshold.

8. A turbine cooler fault diagnosis device under variable speed, characterized in that: The device includes a determination module, a calculation module, a correction module, an acquisition module and an identification module; wherein, The determination module is used to determine the monitored fault signal based on the historical faults of the turbine cooler under variable speed, wherein the fault signal changes in each historical fault, the monitored fault signal corresponding to each historical fault is not completely the same, and the amplitude of the change of the monitored fault signal is different under different speeds; The determination module is further configured to determine a critical value of the fault signal based on the historical fault, wherein the critical value is a value of the fault signal when the historical fault occurs; The calculation module is used to calculate a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value based on the critical value, and obtain a correlation between the rotation speed and the fault judgment threshold value; The correction module is used to correct the first relationship based on the speed change rate of the turbine cooler to obtain a second relationship, wherein after the correction, the change direction of the historical fault judgment threshold obtained according to the second relationship is opposite to the change direction of the speed change rate; The acquisition module is used to acquire real-time information of the turbine cooler under variable speed; The identification module is used to identify a fault of the turbine cooler based on the real-time information and the second relationship; The calculating, based on the critical value, a first relationship between the rotation speed of the turbine cooler and a historical fault judgment threshold value comprises: Based on the historical faults, the rotation speeds at different times in the fault data are obtained and matched one by one with the corresponding fault signal critical values, and a scatter plot of the rotation speed and the fault signal critical value is drawn; the horizontal axis of the scatter plot is the rotation speed, and the vertical axis is the fault signal critical value; Fit the scatter plot according to a fitting method to obtain a relationship curve between the rotation speed and the critical value; According to the relationship curve, the historical fault judgment thresholds at different speeds are calculated, and the dynamic threshold is calculated based on the historical fault judgment thresholds; wherein, the fault signal critical values ​​at different speeds are calculated by using the relationship curve, and the fault signal critical values ​​are combined into the historical fault judgment thresholds, and then according to the actual operating conditions, the safety margin is added to each fault signal critical value to obtain the dynamic threshold; The method further comprises: calculating the historical fault judgment thresholds at different speeds according to the relationship curve, and calculating the dynamic thresholds based on the historical fault judgment thresholds, and then: Analyze the rotation speed and the historical faults to determine the fault occurrence rate at different rotation speeds; Based on the fault occurrence rate, a first relationship between the rotation speed and the historical fault judgment threshold is established.

Images