A prediction method for the wear of the friction disc of a fan coupling

Abstract

The present invention discloses a method for predicting the wear of the friction plate of a fan coupling. A loading test is carried out on the coupling to obtain the temperature reference value when there is no slip, the rotation speed and temperature when there is slip; a temperature curve graph is established based on the temperature data; after correction fitting of the temperature curve graph, feature extraction is carried out to form a set of temperature feature values; the rotation speed corresponding to the set of temperature feature values is obtained to form a set of rotation speed feature values; the critical temperature warning value is obtained by processing the set of temperature feature values; the set of temperature feature values, the set of rotation speed feature values and the critical temperature warning value are input into a neural network for training; a set of target temperature feature values and a set of target rotation speed feature values are obtained; the set of target temperature feature values and the set of target rotation speed feature values are input into a neural network model for prediction; the set of target temperature feature values and the target critical temperature warning value are compared; if the target critical temperature warning value is greater than or equal to the data in the set of target temperature feature values, the staff is notified to maintain or replace the friction plate.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment fault monitoring, and specifically to a method for predicting the wear of the friction plate of a fan coupling. Background Art

[0002] The wind power coupling is used to connect the rotor of the fan and the rotor of the generator, and is used to transmit the rotational torque generated by the fan to the generator. It is a key component for converting wind energy into electrical energy. When the fan load is too large, the coupling slips to prevent excessive torque from being transmitted to the generator, thus avoiding damage to the generator. As the service time increases, the wear degree of the friction plate intensifies, and ultimately the friction plate will be worn to the point where it cannot be used and needs maintenance or replacement. However, since the coupling is sealed inside the fan shroud and pressed against the friction flange, the existing technical means cannot monitor the wear degree of the friction plate in real time. Only by regularly dispatching staff to disassemble the fan shroud and the coupling to detect the wear degree of the friction plate. This method not only wastes labor costs, but also may cause damage to the coupling or other components during the process of disassembling and reinstalling the shroud and the coupling, further affecting the normal operation of the fan equipment.

[0003] Therefore, designing a method that can monitor the wear degree of the friction plate in real time has become an urgent problem to be solved. Summary of the Invention

[0004] In order to at least overcome the above deficiencies in the prior art, the purpose of the present application is to provide a method for predicting the wear of the friction plate of a fan coupling.

[0005] The embodiment of the present application provides a method for predicting the wear of the friction plate of a fan coupling, including:

[0006] S1: Conduct rotational loading tests at different rotational speeds on the coupling to be experimentally detected under different test environmental temperature conditions, obtain the normal working temperature reference values of the friction plate and the friction flange when there is no slippage, and obtain the rotational speed and temperature data of the friction plate and the friction flange during different slippage periods, and establish a mapping coordinate set of the rotational speed and temperature data;

[0007] S2: Establish a temperature curve graph based on the temperature data;

[0008] S3: Perform fitting and correction processing on the temperature curve graph according to the normal working temperature reference value, and perform feature extraction on the fitted and corrected temperature curve graph to form a temperature feature value set;

[0009] S4: Update the temperature feature value set to the mapping coordinate set, and obtain the rotational speed corresponding to the temperature feature value to form a rotational speed feature value set;

[0010] S5: Extract the temperature characteristic values of the friction plate in the temperature characteristic value set under the working conditions where the wear degree of the friction plate reaches the level that requires maintenance or replacement to form a wear temperature characteristic value set, and calculate the critical temperature warning value for the wear temperature characteristic value set. The critical temperature warning value is the critical temperature when the wear degree of the friction plate reaches the level that requires maintenance or replacement.

[0011] S6: Assign the critical temperature warning value, the rotational speed characteristic value set, and the temperature characteristic value set as sample data to the neural network model for prediction training. The output data of the neural network model is the critical temperature warning value, and the input data is the rotational speed characteristic value set and the temperature characteristic value set.

[0012] S7: Establish a warning notification model.

[0013] S8: Obtain the target temperature characteristic value set of the friction plate and the friction flange of the coupling under the actual working conditions during different slipping periods, and the corresponding target rotational speed characteristic value set of the target temperature characteristic value set.

[0014] S9: Assign the target rotational speed characteristic value set and the target temperature characteristic value set to the neural network model for prediction, and the neural network model predicts the corresponding target critical temperature warning value.

[0015] S10: Compare the target critical temperature warning value with the target temperature characteristic value set by the warning notification model.

[0016] S11: When at least one of the data in the target temperature characteristic value set is greater than or equal to the critical temperature warning value, trigger the warning switch to the on state and notify the staff to repair or replace the friction plate.

[0017] During the implementation of this embodiment, as the service time of the friction disc of the fan coupling increases, the abrasive grains evenly distributed on its surface will gradually decrease, and even cracks will occur on the surface of the friction disc in some specific cases, resulting in an increase in temperature when the coupling slips. Due to the reduction of abrasive grains, the contact area between the friction disc and the friction flange will relatively increase, resulting in an increase in pressure per unit area, and then an increase in frictional force, and the heat generated thereby also rises. Secondly, in some specific cases, the surface of the worn friction disc may form irregular shapes and tiny cracks, and these defects will cause local stress concentration, resulting in uneven contact of the friction surface, leading to fluctuations in frictional force and concentration of heat, further increasing the heat generated by friction. Based on the above phenomena, the inventor of the present application conducted a rotational loading test on the coupling. When the rotational speed increases, the coupling will slip. Based on a large number of rotational loading experiments, the inventor of the present application found that the heat generated by the friction disc during the slipping process can be used to characterize the wear degree of the friction disc. When the wear degree of the friction disc needs to be maintained or replaced, as the rotational speed increases, the wear temperature of the friction disc will rise to the critical temperature warning value. Therefore, the purpose of the present application is to find the critical temperature warning value when the wear degree of the friction disc reaches the level that requires maintenance or replacement. When the highest temperature generated by friction reaches or exceeds the critical temperature warning value, the staff will be notified to maintain or replace the friction disc.

[0018] During the implementation of this embodiment, since the fans under actual working conditions are in different ambient temperature conditions, there are corresponding different critical temperature warning values under the influence of different ambient temperatures. Based on this, the inventor of the present application set different test ambient temperatures in the laboratory to simulate different ambient temperatures, and conducted rotational loading tests at different rotational speeds on the coupling to be experimentally detected under different ambient temperature conditions. During the test process, the normal working temperature reference value of the friction disc and the friction flange when not slipping was obtained. In this embodiment, the working temperature reference value is the average value within the normal temperature range of the coupling when it is in the non-slip state, and the rotational speed and temperature data of the friction disc and the friction flange during different slipping periods were obtained, and a mapping coordinate set of the rotational speed and temperature data was established; in this embodiment, a coordinate in the mapping coordinate set includes the rotational speed of the friction disc at the current moment, the rotational speed of the friction flange at the current moment, and the temperature data generated when the friction flange and the friction disc slip at the current moment.

[0019] When this embodiment is implemented, after the temperature curve graph is subjected to fitting and correction processing, feature extraction is performed to form a temperature feature value set. The temperature feature values in the temperature feature value set are the peak values of each curve segment in the temperature curve graph. Then, the rotational speed values corresponding to each temperature feature value are extracted to form a rotational speed feature value set; the temperature feature values under the working conditions where the wear degree of the friction plate in the temperature feature value set reaches the requirement of maintenance or replacement are extracted to form a wear temperature feature value set, and the critical temperature warning value is calculated from the temperature feature values in the wear temperature feature value set.

[0020] When this embodiment is implemented, the critical temperature warning value, the rotational speed feature value set, and the temperature feature value set are used as sample data and assigned to the neural network model for prediction training. After the neural network model is trained, the target rotational speed feature value set and the target temperature feature value set in the actual working condition are assigned to the neural network model for prediction. The neural network model predicts the target critical temperature warning value, and the target critical temperature warning value is compared with the data in the target temperature feature value set. When there is data in the target temperature feature value set that is greater than or equal to the target critical temperature warning value, the switch for triggering and turning on the warning notification model is activated, and a warning text message for notifying the staff to repair or replace the friction plate is sent.

[0021] In a possible implementation manner, in step S2, the steps of establishing the temperature curve graph include:

[0022] Use a Kalman filter to process the temperature data to filter out the noise points in the temperature data;

[0023] Use a smoothing algorithm to smooth the temperature data and extract the data trend of the temperature data during the slip period;

[0024] According to the temperature data and the data trend, use the Matplotlib tool to draw the temperature curve graph.

[0025] In a possible implementation manner, the specific steps of step S3 include:

[0026] S301: Use a fitting equation to perform fitting processing on the temperature curve graphs in different slip periods under the same ambient temperature condition, and obtain multiple fitted temperature curves in each slip period, and make the starting temperature and the ending temperature of each fitted temperature curve be the normal working temperature reference value. The fitting equation is:

[0027]

[0028] In the formula, y is the temperature generated during the slip period, x is the time corresponding to the temperature, and are fitting parameter values;

[0029] S302: If there is an overlapping region between the current fitted temperature curve and the previous fitted temperature curve, take the temperature value corresponding to the intersection point of the current fitted temperature curve and the previous fitted temperature curve as the demarcation line, and divide the overlapping region into a front overlapping region and a rear overlapping region;

[0030] S303: Eliminate the front overlapping region, and use the correction equation to correct the current fitted temperature curve to obtain the corrected and accurate current temperature curve;

[0031] S304: Perform a slip process on the current temperature curve so that the starting temperature position of the current temperature curve slips to the ending temperature position of the previous fitted temperature curve to obtain a complete and continuous temperature curve graph;

[0032] S305: Establish a working temperature comparison table, and store the ambient temperature and the normal working temperature reference value into the working temperature comparison table;

[0033] S306: Extract features from the temperature curve graph after fitting and correction to form a temperature feature value set.

[0034] In a possible implementation manner, the correction equation is:

[0035]

[0036] In the formula, is the corrected current fitted temperature, is the normal working temperature reference value, is the moment corresponding to the intersection point of the current fitted temperature curve and the previous fitted temperature curve, is the moment when the temperature of the previous fitted temperature curve drops to the temperature reference value, is the moment when the temperature of the current fitted temperature curve drops to the temperature reference value, is the temperature function of the current fitted temperature curve, is the temperature function of the previous fitted temperature curve.

[0037] In a possible implementation manner, the steps of obtaining the target temperature feature value set in step S8 include:

[0038] S801: Continuously record the target temperature data of the friction plate and the friction flange by setting a temperature sensor in the wrapping cover wrapping the coupling;

[0039] S802: Perform frequency statistical analysis on the target temperature data, and count the frequency of occurrence of each target temperature data;

[0040] S803: Take the target temperature data with the highest frequency of occurrence as the target ambient temperature;

[0041] S804: In the working temperature comparison table, extract the normal working temperature reference value corresponding to the target ambient temperature as the target working temperature reference value;

[0042] S805: Based on the target temperature data, establish a target temperature curve graph;

[0043] S806: Perform fitting and correction processing on the target temperature curve graph according to the target working temperature reference value, and perform feature extraction on the fitted and corrected target temperature curve graph to form a target temperature eigenvalue set.

[0044] In a possible implementation manner, the formula for calculating the critical temperature warning value in step S5 is:

[0045]

[0046] In the formula, is the critical temperature warning value, is the mean value of the wear temperature eigenvalue, K is the temperature warning safety factor, is the standard deviation of the wear temperature eigenvalue.

[0047] In a possible implementation manner, the neural network model in step S6 is a temperature DNN neural network model.

[0048] In a possible implementation manner, the training steps of the temperature DNN neural network model include:

[0049] Take the set of rotational speed eigenvalues and the set of temperature eigenvalues as the input feature X, and the critical temperature warning value as the label Y, and input them into the input layer of the temperature DNN neural network model for normalization and standardization processing;

[0050] The hidden layer uses an activation function to obtain the output value delivered from the input layer to each hidden layer neuron;

[0051] The output layer calculates the predicted critical temperature warning value through the activation function;

[0052] Use a loss function to evaluate the predicted critical temperature warning value, and until the evaluation is qualified, use the backpropagation algorithm to update the weight parameters of the temperature DNN neural network model;

[0053] The output layer outputs the evaluated qualified critical temperature warning value as the final result.

[0054] In a possible implementation manner, the specific steps of step S11 include:

[0055] The warning notification model performs a traversal operation on all values in the target temperature eigenvalue set to detect whether at least one value is greater than or equal to the critical temperature warning value;

[0056] When the detection condition is satisfied, stop the traversal operation, and the early warning notification model triggers the early warning notification switch to the on state;

[0057] The early warning notification model calls the SMS service interface and sends the early warning information to the staff;

[0058] After the early warning information is sent, the early warning notification model writes the time, content, target temperature eigenvalue set, and critical temperature early warning value of the early warning into the log.

[0059] A prediction method for the wear of the friction plate of a fan coupling in the present invention. Through the above technical solutions, the rotational speed and temperature data of the friction plate and the friction flange of the fan coupling in the actual working condition can be monitored in real time. After processing the temperature data, a target temperature eigenvalue set is formed. After assigning the target temperature eigenvalue set and the expected corresponding target rotational speed eigenvalue set to the neural network model, the neural network model predicts the target critical temperature early warning value of the friction plate. By comparing the target critical temperature early warning value with the target temperature eigenvalue set, the current wear degree of the friction plate can be judged, avoiding the phenomenon of wasting human resources to frequently send staff to disassemble the fan shroud and coupling regularly to detect the wear degree of the friction plate, and at the same time avoiding the situation that the coupling or other components may be damaged when the shroud and coupling are frequently disassembled and installed. Description of the Drawings

[0060] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not limit the embodiments of the present invention. In the drawings:

[0061] Figure 1 is the flowchart of the prediction method of the present invention;

[0062] Figure 2 is the flowchart of the fitting and correction processing of the temperature curve graph of the present invention and the feature extraction;

[0063] Figure 3 is the flowchart of obtaining the target temperature eigenvalue set of the present invention;

[0064] Figure 4 is the temperature curve graph before fitting and correction of the present invention;

[0065] Figure 5 is the temperature curve graph after fitting of the present invention;

[0066] Figure 6 is the temperature curve graph after the regional division of the fitted temperature curve graph of the present invention;

[0067] Figure 7 is the corrected temperature curve graph of the present invention;

[0068] Figure 8 The temperature curve diagram after slip processing of the corrected temperature curve of the present invention. Detailed implementation manners

[0069] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with embodiments and drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0070] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention.

[0071] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0072] In the present invention, unless otherwise clearly defined and limited, the terms "mounted", "connected", "connected to", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0073] In the present invention, unless otherwise clearly specified and defined, the first feature being "above" or "below" the second feature may include direct contact between the first and second features, or may include the first and second features not being in direct contact but in contact through additional features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes the first feature being directly above and obliquely above the second feature, or merely indicating that the horizontal height of the first feature is higher than that of the second feature. The first feature being "below", "beneath" and "underneath" the second feature includes the first feature being directly below and obliquely below the second feature, or merely indicating that the horizontal height of the first feature is less than that of the second feature.

[0074] In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the fact that those skilled in the art can implement them. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of the disclosure of the present invention.

[0075] In the subsequent description, suffixes such as "module", "component", "assembly" or "unit" are only used to facilitate the description of the present invention and have no specific meaning in themselves. Therefore, they can be used interchangeably.

[0076] The present invention will be further described in detail below with reference to the specific embodiments in conjunction with the accompanying drawings.

[0077] Please refer to Figure 1 , which is a schematic flowchart of a method for predicting the wear of a friction plate of a fan coupling provided by an embodiment of the present invention. Further, the method for predicting the wear of the friction plate of the fan coupling may specifically include the contents described in the following steps S1 to step S11.

[0078] S1: Conduct rotational loading tests on the coupling to be experimentally detected at different test environmental temperature conditions at different rotational speeds, obtain the normal working temperature reference values of the friction plate and the friction flange when there is no slippage, and obtain the rotational speed and temperature data of the friction plate and the friction flange during different slippage periods, and establish a mapping coordinate set of the rotational speed and the temperature data;

[0079] S2: Establish a temperature curve graph based on the temperature data;

[0080] S3: Perform fitting and correction processing on the temperature curve graph according to the normal working temperature reference value, and perform feature extraction on the temperature curve graph after fitting and correction to form a temperature feature value set;

[0081] S4: Update the temperature feature value set to the mapping coordinate set, and obtain the rotational speed corresponding to the temperature feature value to form a rotational speed feature value set;

[0082] S5: Extract the temperature characteristic values of the friction plates in the temperature characteristic value set under the working conditions where the wear degree of the friction plates reaches the condition requiring maintenance or replacement to form a wear temperature characteristic value set, and calculate the critical temperature warning value for the wear temperature characteristic value set. The critical temperature warning value is the critical temperature when the wear degree of the friction plates reaches the condition requiring maintenance or replacement.

[0083] S6: Assign the critical temperature warning value, the rotational speed characteristic value set, and the temperature characteristic value set as sample data to a neural network model for prediction training. The output data of the neural network model is the critical temperature warning value, and the input data is the rotational speed characteristic value set and the temperature characteristic value set.

[0084] S7: Establish a warning notification model.

[0085] S8: Obtain the target temperature characteristic value set of the friction plates and friction flanges of the coupling under the actual working conditions during different slipping periods, and the corresponding target rotational speed characteristic value set of the target temperature characteristic value set.

[0086] S9: Assign the target rotational speed characteristic value set and the target temperature characteristic value set to the neural network model for prediction. The neural network model predicts the corresponding target critical temperature warning value.

[0087] S10: Assign the target critical temperature warning value and the target temperature characteristic value set to the warning notification model for comparison.

[0088] S11: When at least one of the data in the target temperature characteristic value set is greater than or equal to the critical temperature warning value, trigger the warning switch to the on state and notify the staff to repair or replace the friction plates.

[0089] When implementing this embodiment, the inventor prepared friction plates in three states. There are several friction plates in each state. The first group of friction plates is in a brand-new and unused state. The second group of friction plates is in a state where the friction plates have experienced a certain degree of wear but do not reach the condition for maintenance or replacement. The third group is in a state where the friction plates reach the condition for maintenance or replacement. Install the friction plates in the three states on the coupling respectively, and conduct rotational speed loading tests on the coupling to be experimentally detected at different rotational speeds under different ambient temperature conditions. During the test process, obtain the normal working temperature reference value of each group of friction plates and friction flanges when not slipping, and obtain the rotational speed and temperature data of each group of friction plates and friction flanges during different slipping periods, and assign the rotational speed and temperature data to the rotational speed-temperature mapping coordinate system to form a mapping coordinate set, and then draw a temperature curve graph based on the temperature data using the Matplotlib tool.

[0090] In this embodiment, after performing fitting and correction processing on the temperature curve graph, an accurate temperature curve graph is obtained. Then, feature extraction is performed on the accurate temperature curve graph to form a temperature eigenvalue set, and the temperature eigenvalues in the temperature eigenvalue set are the peak values of each curve segment in the temperature curve graph. Update each temperature eigenvalue into the mapping coordinate set, and then extract the rotational speed values corresponding to each temperature eigenvalue in the mapping coordinate set to form a rotational speed eigenvalue set. Extract the temperature eigenvalues under the working conditions where the wear degree of the friction plate in the temperature eigenvalue set reaches the requirement for maintenance or replacement to form a wear temperature eigenvalue set, and calculate the critical temperature warning value for the temperature eigenvalues in the wear temperature eigenvalue set. Assign the temperature eigenvalue set, the rotational speed eigenvalue set, and the critical temperature warning value to the neural network model for training.

[0091] When this embodiment is implemented, assign the target rotational speed eigenvalue set and the target temperature eigenvalue set in the actual working conditions to the neural network model for prediction. The neural network model predicts the target critical temperature warning value, and compare the target critical temperature warning value with the data in the target temperature eigenvalue set. When there is data in the target temperature eigenvalue set that is greater than or equal to the target critical temperature warning value, trigger the switch to turn on the warning notification model, and send a warning message to notify the staff to repair or replace the friction plate.

[0092] In a possible implementation manner, the steps of establishing the temperature curve graph include:

[0093] Use a Kalman filter to process the temperature data and filter out the noise points in the temperature data;

[0094] Use a smoothing algorithm to smooth the temperature data and extract the data trend of the temperature data during the slip period;

[0095] According to the temperature data and the data trend, use the Matplotlib tool to draw the temperature curve graph.

[0096] When this embodiment is implemented, using a Kalman filter to process the temperature data can effectively filter out the noise in the sensor data and provide a more accurate temperature reading. Secondly, the smoothing algorithm helps to extract the temperature data trend during the slip period, making the temperature change at critical moments clearer, thus facilitating analysis and decision-making. Finally, using the Matplotlib tool to draw the temperature curve graph can not only intuitively display the change of temperature over time, but also help users better understand the law and abnormality of temperature change through visualization means.

[0097] In a possible implementation manner, please refer to Figure 2 、 Figures 4 to 8 The specific steps of step S3 include:

[0098] S301: Use the fitting equation to perform fitting processing on the temperature curve graphs within different slip time periods under the same ambient temperature condition, obtaining multiple fitted temperature curves within each slip time period, and making the starting temperature and the ending temperature of each of the fitted temperature curves be the normal operating temperature reference value. The fitting equation is:

[0099]

[0100] In the formula, y is the temperature generated within the slip time period, and x is the time corresponding to the temperature. and are the fitting parameter values;

[0101] S302: If there is an overlapping region between the current fitted temperature curve and the previous fitted temperature curve, use the temperature value corresponding to the intersection point of the current fitted temperature curve and the previous fitted temperature curve as the demarcation line to divide the overlapping region into a front overlapping region and a rear overlapping region;

[0102] S303: Eliminate the front overlapping region, and use the correction equation to correct the current fitted temperature curve to obtain the corrected and accurate current temperature curve;

[0103] S304: Perform a sliding process on the current temperature curve, making the starting temperature position of the current temperature curve slide to the ending temperature position of the previous fitted temperature curve to obtain a complete and continuous temperature curve graph;

[0104] S305: Establish a working temperature comparison table, and store the ambient temperature and the normal operating temperature reference value into the working temperature comparison table;

[0105] S306: Perform feature extraction on the temperature curve graph after fitting and correction to form a temperature feature value set.

[0106] When this embodiment is implemented, the inventors of the present application found that when the coupling undergoes multiple consecutive slips, the temperature data generated by the friction plate is distorted and is not real temperature data. And the temperature data will directly affect the subsequent calculated critical temperature warning value, and the critical temperature warning value is the key index for judging whether the friction disc is worn to the extent that it needs to be replaced or maintained. If the critical temperature warning value is inaccurate, it will lead to inaccurate result data predicted by the neural network model. Therefore, how to "eliminate false and retain true" for the temperature data generated by continuous slips has become a key issue. In this embodiment, as Figure 4 shown, in this figure, the abscissa is time and the ordinate is temperature. In this figure, there are two consecutive slips, that is, the previous temperature curve starts from the temperature of the normal operating temperature reference value ( ) starts to slip. At this time, the temperature begins to rise with time. When the temperature rises to the peak temperature, the slipping stops. Subsequently, the temperature begins to decrease. However, before it decreases to the normal operating temperature reference value ( ), at the time of , the second slipping occurs continuously to form the current temperature curve. After the current temperature curve rises to the peak temperature, the slipping stops. Subsequently, the temperature decreases to the normal operating temperature reference value ( ).

[0107] During the two consecutive slipping processes described above, the peak value of the current temperature curve has been higher than the true critical temperature warning value. That is, during the second slipping process, the slipping starts before the temperature generated by the previous slipping has decreased to the normal operating temperature reference value ( ), and there is a situation of temperature superposition. Therefore, the peak value of the second slipping is higher than its true peak value. Based on this, the present invention calculates the true temperature curve of the second slipping through a fitting and correction method.

[0108] In the implementation of this embodiment, as Figure 5 shown, in this figure, the abscissa is time and the ordinate is temperature. The previous temperature curve and the current temperature curve are fitted through a fitting equation, so that the starting temperature and the ending temperature of the previous temperature curve and the current temperature curve are both the normal operating temperature reference value ( ), forming the previous fitted temperature curve and the current fitted temperature curve; in this embodiment, as Figure 6 shown, in this figure, the abscissa is time and the ordinate is temperature. Taking the temperature value corresponding to the intersection point of the current fitted temperature curve and the previous fitted temperature curve as the dividing line (i.e., taking the temperature value at the time of as the dividing line), the overlapping area between the current fitted temperature curve and the previous fitted temperature curve is divided into a front overlapping area (i.e., the area composed of the underlines in Figure 6 ) and a rear overlapping area (i.e., the overlapping area composed of the wavy lines in Figure 6 ). After removing the front overlapping area, the current fitted temperature curve is corrected using a correction equation, and then the accurate current temperature curve after correction can be obtained. The current temperature curve after correction is as Figure 7 shown, in this figure, the abscissa is time and the ordinate is temperature. In Figure 7 , the true peak value of the current temperature curve after correction is less than the critical temperature warning value; in this embodiment, as Figure 8As shown in the figure, the abscissa represents time and the ordinate represents temperature. The corrected current temperature curve is slid so that the starting temperature position of the current temperature curve slides to the ending temperature position of the previous fitted temperature curve, obtaining a complete and continuous temperature curve graph. By performing feature extraction on the complete and continuous temperature curve graph, a set of temperature feature values can be obtained, and the set of temperature feature values is the respective peaks in the complete and continuous temperature curve graph.

[0109] In a possible implementation manner, the correction equation is as follows:

[0110]

[0111] In the formula, is the corrected current fitted temperature, is the normal operating temperature reference value, is the moment corresponding to the intersection point of the current fitted temperature curve and the previous fitted temperature curve, is the moment when the temperature of the previous fitted temperature curve drops to the temperature reference value, is the moment when the temperature of the current fitted temperature curve drops to the temperature reference value, is the temperature function of the current fitted temperature curve, is the temperature function of the previous fitted temperature curve.

[0112] In a possible implementation manner, please refer to Figure 3 , the steps of obtaining the set of target temperature feature values in the step S8 include:

[0113] S801: Continuously record the target temperature data of the friction plate and the friction flange by setting a temperature sensor inside the wrapping cover that wraps the coupling;

[0114] S802: Perform frequency statistical analysis on the target temperature data, and count the frequency of occurrence of each target temperature data;

[0115] S803: Take the target temperature data with the highest frequency of occurrence as the target ambient temperature;

[0116] S804: In the working temperature comparison table, extract the normal operating temperature reference value corresponding to the target ambient temperature as the target working temperature reference value;

[0117] S805: Establish a target temperature curve graph based on the target temperature data;

[0118] S806: Perform fitting and correction processing on the target temperature curve graph according to the target working temperature reference value, and perform feature extraction on the fitted and corrected target temperature curve graph to form a set of target temperature feature values.

[0119] When this embodiment is implemented, when extracting the temperature data during the slipping period, according to the time series, the temperature data within the first 10 s before the start of slipping and the temperature data within the last 10 s after the slipping stops until the lowest temperature are extracted within the entire slipping time period, and frequency statistical analysis is performed. This processing method enables the target ambient temperature analyzed and statistically calculated by us to be more in line with the ambient temperature of the fan coupling under actual working conditions.

[0120] In a possible implementation manner, the formula for calculating the critical temperature warning value in the step S5 is:

[0121]

[0122] In the formula, is the critical temperature warning value, is the mean value of the wear temperature characteristic value, K is the temperature warning safety factor, is the standard deviation of the wear temperature characteristic value.

[0123] In a possible implementation manner, in the step S6, the neural network model is a temperature DNN neural network model.

[0124] In a possible implementation manner, the training steps of the temperature DNN neural network model include:

[0125] Taking the set of rotational speed characteristic values and the set of temperature characteristic values as the input feature X, and the critical temperature warning value as the label Y, and inputting them into the input layer of the temperature DNN neural network model for normalization and standardization processing;

[0126] The hidden layer uses an activation function to obtain the output values delivered from the input layer to each hidden layer neuron;

[0127] The output layer calculates the predicted critical temperature warning value through the activation function;

[0128] Using a loss function to evaluate the predicted critical temperature warning value, and until the evaluation is qualified, using the backpropagation algorithm to update the weight parameters of the temperature DNN neural network model;

[0129] The output layer outputs the qualified critical temperature warning value as the final result.

[0130] When this embodiment is implemented, the DNN neural network model has a powerful non-linear modeling ability, can effectively capture the complex relationship between the input features and the output labels, and is superior to the traditional linear model; secondly, the DNN neural network model can automatically extract features, reduce manual intervention, improve the adaptability and prediction accuracy of the model, and make the predicted critical temperature warning value more accurate.

[0131] In a possible implementation, the warning notification model traverses all the values in the set of target temperature characteristic values to detect whether at least one value is greater than or equal to the critical temperature warning value;

[0132] When the detection condition is met, the traversal operation is stopped, and the warning notification model triggers the warning notification switch to the on state;

[0133] The warning notification model calls the SMS service interface to send the warning information to the staff;

[0134] After the warning information is sent, the warning notification model writes the warning time, content, the set of target temperature characteristic values, and the critical temperature warning value into the log.

[0135] When this embodiment is implemented, there is a log document dedicated to recording warning events. The role of the log document is to provide the ability to trace warning events in detail, facilitating subsequent analysis and auditing; secondly, the set of target temperature characteristic values, the set of target rotational speed characteristic values, and the target critical temperature warning value in the log will be regularly pushed to the DNN neural network model through timestamps for training and learning, providing valuable historical data support for the subsequent prediction training and data analysis of the DNN neural network model, and contributing to the optimization and improvement of the DNN neural network model.

[0136] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting wear of friction plates of fan couplings, characterized in that: The steps of the prediction method include: S1: performing a rotation loading test at different speeds on the coupling to be tested under different test environment temperature conditions, obtaining a normal working temperature reference value of the friction plate and the friction flange when there is no slippage, and obtaining the rotation speed and temperature data of the friction plate and the friction flange in different slippage periods, and establishing a mapping coordinate set of the rotation speed and the temperature data; S2: Establishing a temperature curve graph based on the temperature data; S3: performing fitting correction processing on the temperature curve according to the normal working temperature reference value, and performing feature extraction on the fitted and corrected temperature curve to form a temperature feature value set; S4: updating the temperature characteristic value set to the mapping coordinate set, and obtaining the rotation speed corresponding to the temperature characteristic value to form a rotation speed characteristic value set; S5: extracting the temperature characteristic values ​​under the working condition that the wear degree of the friction plate reaches the condition that maintenance or replacement is required from the temperature characteristic value set to form a wear temperature characteristic value set, and calculating the wear temperature characteristic value set to obtain a critical temperature warning value, wherein the critical temperature warning value is the critical temperature when the wear degree of the friction plate reaches the condition that maintenance or replacement is required, wherein the formula for calculating the critical temperature warning value is: In the formula, is the critical temperature warning value, is the mean of the wear temperature characteristic values, K is the temperature warning safety factor, is the standard deviation of the wear temperature characteristic value; S6: assigning the critical temperature warning value, the rotation speed characteristic value set and the temperature characteristic value set as sample data to a neural network model for prediction training, wherein the output data of the neural network model is the critical temperature warning value, and the input data is the rotation speed characteristic value set and the temperature characteristic value set; S7: Establish an early warning notification model; S8: Obtaining a target temperature characteristic value set of the friction plate and the friction flange of the coupling in different slipping periods under actual working conditions, and a target speed characteristic value set corresponding to the target temperature characteristic value set; S9: assigning the target speed characteristic value set and the target temperature characteristic value set to the neural network model for prediction, and the neural network model predicts a corresponding target critical temperature warning value; S10: assigning the target critical temperature warning value and the target temperature characteristic value set to the warning notification model for comparison; S11: When at least one of the data in the target temperature characteristic value set is greater than or equal to the target critical temperature warning value, the warning switch state is triggered to be on, and the staff is notified to repair or replace the friction plate.

2. A method for predicting wear of a fan coupling friction plate according to claim 1, characterized in that: In step S2, the step of establishing a temperature curve diagram includes: Processing the temperature data using a Kalman filter to filter out noise in the temperature data; Using a smoothing algorithm to smooth the temperature data and extract the data trend of the temperature data within the slip period; A temperature curve graph is drawn using Matplotlib tool according to the temperature data and the data trend.

3. A method for predicting wear of a fan coupling friction plate according to claim 2, characterized in that: The specific steps of step S3 include: S301: Using a fitting equation to fit the temperature curves in different slipping periods under the same ambient temperature condition, a plurality of fitting temperature curves in each slipping period are obtained, and the starting temperature and the ending temperature of each fitting temperature curve are both the normal operating temperature reference value, and the fitting equation is: In the formula, y is the temperature generated during the slip period, x is the time corresponding to the temperature, and is the fitting parameter value; S302: If there is an overlapping area between the current fitting temperature curve and the previous fitting temperature curve, the overlapping area is divided into a front overlapping area and a rear overlapping area by using the temperature value corresponding to the intersection of the current fitting temperature curve and the previous fitting temperature curve as a dividing line; S303: Eliminate the front overlapping area, and use a correction equation to correct the current fitting temperature curve to obtain a corrected and accurate current temperature curve; S304: performing a sliding process on the current temperature curve so that the starting temperature position of the current temperature curve slides to the ending temperature position of the previous fitting temperature curve, thereby obtaining a complete and continuous temperature curve graph; S305: Establishing a working temperature comparison table, and storing the ambient temperature and the normal working temperature reference value in the working temperature comparison table; S306: extracting features from the temperature curve after fitting correction to form a set of temperature feature values.

4. A method for predicting wear of a fan coupling friction plate according to claim 3, characterized in that: The correction equation is: In the formula, is the corrected current fitting temperature, is the normal operating temperature reference value, is the time corresponding to the intersection of the current fitting temperature curve and the previous fitting temperature curve, is the time when the temperature of the previous fitting temperature curve drops to the temperature reference value, is the time when the temperature of the current fitting temperature curve drops to the temperature reference value. is the temperature function of the current fitting temperature curve, is the temperature function of the previous fitting temperature curve.

5. The method for predicting wear of friction plates of fan coupling according to claim 3, characterized in that: The step of obtaining the target temperature characteristic value set in step S8 includes: S801: Continuously record target temperature data of the friction plate and the friction flange by setting a temperature sensor in a wrapping cover wrapping the coupling; S802: Perform frequency statistical analysis on the target temperature data to count the frequency of occurrence of each target temperature data; S803: taking the target temperature data with the highest frequency as the target ambient temperature; S804: extracting, from the operating temperature comparison table, a normal operating temperature reference value corresponding to the target ambient temperature as a target operating temperature reference value; S805: Establishing a target temperature curve graph based on the target temperature data; S806: performing fitting correction processing on the target temperature curve according to the target operating temperature reference value, and performing feature extraction on the fitted and corrected target temperature curve to form a target temperature feature value set.

6. The method for predicting wear of a fan coupling friction plate according to claim 1, characterized in that: In step S6, the neural network model is a temperature DNN neural network model.

7. A method for predicting wear of a fan coupling friction plate according to claim 6, characterized in that: The temperature DNN neural network model training steps include: The speed characteristic value set and the temperature characteristic value set are used as input feature X, and the critical temperature warning value is used as label Y, and are input into the input layer of the temperature DNN neural network model for normalization and standardization processing; The hidden layer uses an activation function to obtain the output value sent from the input layer to each hidden layer neuron; The output layer calculates the predicted critical temperature warning value through the activation function; The predicted critical temperature warning value is evaluated using a loss function, and the weight parameters of the temperature DNN neural network model are updated using a back propagation algorithm after the evaluation is qualified; The output layer outputs the qualified critical temperature warning value as the final result.

8. The method for predicting wear of a fan coupling friction plate according to claim 1, characterized in that: The specific steps of step S11 include: The early warning notification model performs a traversal operation on all values ​​in the target temperature characteristic value set to detect whether at least one value is greater than or equal to the target critical temperature early warning value; When the detection condition is met, the traversal operation is stopped, and the warning notification model triggers the warning notification switch state to be turned on; The warning notification model calls the SMS service interface to send the warning information to the staff; After the warning information is sent, the warning notification model writes the time, content, target temperature characteristic value set and target critical temperature warning value of the warning into the log.

Images