Embedded wireless passive bolt tightness state monitoring method based on surface acoustic wave technology

Abstract

The invention relates to the technical field of bolt state monitoring, and discloses an embedded wireless passive bolt tightness state monitoring method based on a surface acoustic wave technology, and the method specifically comprises the following steps: obtaining a frequency drift amount in real time based on a surface acoustic wave resonator, carrying out the real-time judgment of the loosening risk of a bolt, and generating a loosening warning signal and a safety signal; based on the warning signal, carrying out change rate analysis on the frequency drift amount before the warning signal is generated, and judging the change rate degree; and on the basis of a judgment result of the change rate degree, predicting a time point when the frequency drift amount reaches the frequency drift amount risk value. The bolt loosening risk can be judged in real time, the warning signal is generated in time when the bolt is loosened, related personnel are reminded to pay attention to the bolt state, the situation that bolt loosening is further developed and is not perceived is avoided, and therefore the possibility of equipment failures and accidents is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of bolt state monitoring, and in particular to an embedded wireless passive bolt tightness state monitoring method based on surface acoustic wave technology. Background Art

[0002] The surface acoustic wave resonator is prefabricated in the bolt body. When the force state of the bolt changes, the oscillation loop parameters of the surface acoustic wave resonator will change, thereby causing its center frequency to drift. When the system is working, the integrated terminal device sends an excitation signal to stimulate the surface acoustic wave resonator to vibrate. When the excitation signal stops, the reader switches to the receiving state and receives the free oscillation signal with a continuously decaying amplitude sent by the sensor. The frequency of the signal is measured by a frequency meter to obtain the frequency drift, which is used to measure the change in the stress state of the bolt and thus determine the tightness of the bolt. The wireless RF excitation and echo signal frequency detection method is adopted, which does not require wiring and external power supply, thus solving the wiring difficulties and power supply problems of traditional monitoring methods. It can realize wireless passive monitoring of the tightness of bolts in harsh environments such as high and low temperatures, dust, and large machinery where wiring and power supply are difficult. However, during the long-term observation and research on the actual application scenarios of bolt status monitoring using surface acoustic wave technology, it was found that when monitoring the bolts, although the frequency drift can be used to determine whether the bolts have entered a loosening warning state, for those bolts that have already issued a warning signal, it is impossible to accurately determine the speed of loosening. In the analysis of multiple equipment failure cases, it was found that some bolts became seriously loose shortly after the warning signal was issued, resulting in equipment failure. However, due to the lack of basis for judging the speed of loosening development, maintenance personnel failed to take timely measures. Summary of the invention

[0003] The object of the present invention is to provide an embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology to solve at least one of the above-mentioned prior art problems.

[0004] The present invention provides an embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology, which specifically includes the following steps: obtaining frequency drift in real time based on a surface acoustic wave resonator, and making a real-time judgment on the loosening risk of the bolt, and generating a loosening warning signal and a safety signal; Based on the warning signal, a change rate analysis is performed on the frequency drift amount before the warning signal is generated, and the degree of the change rate is determined; Based on the judgment result of the degree of change rate, the time point when the frequency drift reaches the frequency drift risk value is predicted; The change rate degree judgment change result includes generating a fast change rate signal and a slow change rate signal.

[0005] As a further solution of the present invention: the process of real-time judgment of the loosening risk of the bolt is: Obtain the real-time frequency drift of the bolt, set the frequency drift warning value and the frequency drift risk value, and the frequency drift warning value is smaller than the frequency drift risk value; The real-time frequency drift is compared with the frequency drift warning value, and if the real-time frequency drift is greater than or equal to the frequency drift warning value, a warning signal is generated.

[0006] As a further solution of the present invention: the process of judging the degree of change rate is: The frequency drift is analyzed, and the change rate mean ratio, extreme value change ratio and change rate quantity ratio are calculated; The rate characterization value is obtained by performing weighted sum calculation on the change rate mean ratio, the extreme value change ratio and the change rate quantity ratio; Setting a rate characterization threshold, wherein the rate characterization threshold is set by a person skilled in the art based on a summary of historical bolt loosening change data; If the rate characterization value is greater than the rate judgment characterization threshold, it means that the rate changes rapidly, and a signal with a fast rate of change is generated; If the rate characterization value is less than or equal to the rate judgment characterization threshold, it means that the rate change degree is slow, and a slow change rate signal is generated.

[0007] As a further solution of the present invention: the process of obtaining the change rate mean ratio and the extreme value change ratio is: Obtain the time point at which the warning signal is generated and mark it as the warning time point; Get the frequency drift sequence before the warning time point: ,in, represents the frequency drift corresponding to the i-th sampling moment, i=1,2,…,n; and the corresponding sampling time series: ; Calculate the rate of change of two adjacent frequency drifts , the calculation formula is: , calculate the change rate sequence: ; The values ​​in the change rate sequence are summed and averaged to obtain the change rate mean, and the change rate mean is calculated to be a ratio of the change rate mean to the change rate limit value to obtain the change rate mean ratio; The maximum value and the minimum value of the change rate are extracted, and the difference is calculated to obtain the extreme value of the change rate. The ratio of the extreme value of the change rate to the minimum value of the change rate is calculated to obtain the extreme value change ratio.

[0008] As a further solution of the present invention: the process of obtaining the change rate quantity ratio is: The change rate is compared with the change rate threshold, the change rates greater than the change rate threshold are extracted, and their number is counted, and then the ratio is calculated with the total number of rate change values ​​to obtain the high change rate number ratio.

[0009] As a further solution of the present invention: the process of predicting the time point when the frequency drift reaches the frequency drift risk value includes: Based on the fast changing rate signal, the maximum changing rate is obtained, and the maximum changing rate is used as the predicted changing rate; Obtain the frequency drift amount corresponding to the generated warning signal, and mark it as the warning frequency drift amount; The difference between the frequency drift risk value and the warning frequency drift is calculated, and the ratio is calculated with the predicted change rate to obtain the predicted time value.

[0010] As a further solution of the present invention: the process of predicting the time point when the frequency drift reaches the frequency drift risk value also includes: Based on the slow-changing signal, the warning frequency drift is obtained, and the average of the frequency drift risk value and the warning frequency drift is taken as the analysis frequency drift; After the warning time point, the frequency drift amount is continuously acquired in real time, and the frequency drift amount between the warning frequency drift amount and the analysis frequency drift amount is obtained, and marked as a sequence to be analyzed; Determine whether the sequence to be analyzed changes linearly; Based on linear changes, the fitted model is used Predict the time point when the frequency drift reaches the frequency drift risk value, that is, substitute the frequency drift risk value into the fitting model, and the output x value is the predicted time value; Based on nonlinear changes, a radial basis function neural network (RBFNN) model is used to build a prediction model; The frequency drift risk value is input into the model, and the model output result is the predicted time value.

[0011] As a further solution of the present invention: the process of determining whether the sequence to be analyzed changes linearly is: Fit the values ​​in the sequence to be analyzed by the least squares method to obtain the fitting model ; Based on the fitted model, calculate its goodness of fit , the calculation formula is: , where m is the number of data points, is the jth actual value, represents the jth predicted value, Indicates the average of actual values; Set the goodness of fit threshold. If the goodness of fit is greater than the goodness of fit threshold, the values ​​in the sequence to be analyzed change linearly; otherwise, they change nonlinearly.

[0012] As a further solution of the present invention: it also includes: adjusting the monitoring frequency of the frequency drift amount based on the obtained predicted time value; Obtaining a predicted time value corresponding to when a fast-changing rate signal is generated and a predicted time value corresponding to when a slow-changing rate signal is generated, and setting a first time threshold and a second time threshold; Get the current monitoring frequency of the frequency drift; Comparing the predicted time value corresponding to when the fast-changing-rate signal is generated with the first time threshold; If the predicted time value corresponding to the fast-changing signal is less than the first time threshold, the predicted time value corresponding to the fast-changing signal is adjusted; comparing the predicted time value corresponding to when the slow rate of change signal is generated with the second time threshold; If the predicted time value corresponding to the signal with a slow changing rate is less than the second time threshold, the predicted time value corresponding to the signal with a fast changing rate is adjusted.

[0013] As a further solution of the present invention: the process of adjusting the monitoring frequency of the frequency drift is: The predicted time value corresponding to the generation of the fast-changing rate signal is calculated by difference with the first time threshold, then the predicted time value is calculated by ratio with the first time threshold, and then the predicted time value is calculated by multiplication with the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value; The predicted time value corresponding to the generation of the slow change rate signal is calculated by difference with the second time threshold, then the ratio is calculated with the second time threshold, and then the product is calculated with the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value.

[0014] Beneficial effects of the present invention: The present invention can determine the risk of bolt loosening in real time, and generate a warning signal in time when the bolt shows signs of loosening, reminding relevant personnel to pay attention to the bolt status, so as to avoid the further development of bolt loosening without being detected, thereby reducing the possibility of equipment failure and accidents. The present invention analyzes the frequency drift change rate in multiple dimensions, and the rate characterization value obtained can more accurately characterize the dynamic process of bolt loosening, thereby improving the accuracy and reliability of judging the change rate of bolt loosening, so that maintenance personnel can be warned in advance before the bolt loosening develops to a serious degree, which is convenient for planning maintenance work in advance, reducing equipment failures, accidents and casualties caused by bolt loosening, and can also deploy personnel in advance according to the warning; The present invention can predict the time when the frequency drift reaches the risk value, so that maintenance personnel can plan maintenance work in advance and reasonably arrange the time to replace or tighten bolts, so as to avoid equipment failure, accidents and casualties caused by loose bolts. Personnel can also be deployed in advance according to the predicted time. At the same time, the monitoring frequency can be adjusted according to the predicted time value. When the predicted time value is large, the existing frequency is maintained to balance the monitoring cost and the demand for monitoring the equipment operation status. When the predicted time value is small, the monitoring is strengthened in time, the monitoring frequency is increased, the safe operation of the equipment is guaranteed, and the reliability and safety of the equipment operation are further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 It is a flow chart of the embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology of the present invention; Figure 2 It is an architecture diagram of the embedded wireless passive bolt tightness status monitoring system based on surface acoustic wave technology of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0018] Embodiment 1 Figure 1The flowchart of the embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology provided in the first embodiment of the present invention, the embodiment of the present invention can be applied to the situation of bolt status monitoring, the embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology can be executed by an embedded wireless passive bolt tightness status monitoring system based on surface acoustic wave technology, the embedded wireless passive bolt tightness status monitoring system based on surface acoustic wave technology can be implemented by software and / or hardware, and the embedded wireless passive bolt tightness status monitoring system based on surface acoustic wave technology can be configured in an embedded wireless passive bolt tightness status monitoring device based on surface acoustic wave technology. Optionally, the embedded wireless passive bolt tightness status monitoring device based on surface acoustic wave technology can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0019] The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology provided in the embodiment of the present invention specifically includes the following steps: Step 1: Based on the real-time acquisition of frequency drift of the surface acoustic wave resonator, the loosening risk of the bolt is judged in real time, and a loosening warning signal and a safety signal are generated; In some embodiments, when the stress state of the bolt changes, the oscillation loop parameters of the surface acoustic wave resonator will change, thereby causing the center frequency to drift. When the system is working, the integrated terminal device sends an excitation signal to excite the surface acoustic wave resonator to vibrate. When the excitation signal stops, the reader switches to a receiving state to receive a free oscillation signal with a continuously decaying amplitude emitted by the sensor. The frequency of the signal is measured by a frequency meter to obtain a frequency drift, thereby measuring the change in the stress state of the bolt and determining the tightness of the bolt. Obtain the real-time frequency drift of the bolt, set the frequency drift warning value and the frequency drift risk value, and the frequency drift warning value is smaller than the frequency drift risk value; Among them, the frequency drift warning value and the frequency drift risk value are summarized and set by technical personnel in this field based on the test data of the system debugging stage. In the system debugging stage, standard bolt samples with different tightness are used to obtain the frequency value of the surface acoustic wave resonator under each standard state. By comparing the reference frequency of the resonator when the bolt is in the standard tightening state, the frequency drift under different tightness is calculated, and an initial corresponding relationship database between the tightness of the bolt and the frequency drift is established; For example, 10 standard bolts with different pre-tightening forces (representing different degrees of tightness) are tested, and the corresponding frequencies are recorded and compared with the tightening reference frequency to obtain frequency drift data; The real-time frequency drift is compared with the frequency drift warning value. If the real-time frequency drift is less than the frequency drift warning value, a safety signal is generated. If the real-time frequency drift is greater than or equal to the frequency drift warning value, a warning signal is generated. Step 2: Based on the warning signal, the frequency drift amount before the warning signal is generated is analyzed for the rate of change, and the degree of the rate of change is determined; In some embodiments, a time point at which a warning signal is generated is obtained and marked as a warning time point; Get the frequency drift sequence before the warning time point: ,in, represents the frequency drift corresponding to the i-th sampling moment, i=1,2,…,n; and the corresponding sampling time series: ; Calculate the rate of change of two adjacent frequency drifts , the calculation formula is: , calculate the change rate sequence: ; The values ​​in the change rate sequence are summed and averaged to obtain the change rate mean, and the change rate mean is calculated to be a ratio of the change rate mean to the change rate limit value to obtain the change rate mean ratio; Extract the maximum value and the minimum value of the change rate, perform difference calculation to obtain the extreme value of the change rate, perform ratio calculation on the extreme value of the change rate and the minimum value of the change rate, and obtain the extreme value change ratio; Compare the change rate with the change rate threshold, extract the change rate greater than the change rate threshold, count the number of change rates, and then calculate the ratio with the total number of rate change values ​​to obtain the high change rate number ratio; The rate characterization value is obtained by performing weighted sum calculation on the change rate mean ratio, the extreme value change ratio and the change rate quantity ratio; The rate characterization value can more accurately characterize the dynamic process of bolt loosening through multi-dimensional analysis, thus improving the accuracy and reliability of judgment; Since the rate of change of bolt loosening can be determined more accurately, a fast change rate signal can be issued in time for the situation of fast change rate, which enables early warning before the bolt loosening develops to a serious degree, buying more time for taking maintenance measures; The rate characterization value is used to determine the rate of change of the frequency drift, providing support for predicting the time to reach the frequency drift risk value after the frequency drift reaches the frequency drift warning value; Setting a rate characterization threshold, wherein the rate characterization threshold is set by a person skilled in the art based on a summary of historical bolt loosening change data; If the rate characterization value is greater than the rate judgment characterization threshold, it means that the rate changes rapidly, and a fast rate change signal is generated; If the rate characterization value is less than or equal to the rate judgment characterization threshold, it means that the rate change is slow, and a slow change rate signal is generated; The technical solution of this embodiment is: based on the surface acoustic wave resonator, the frequency drift of the bolt is obtained in real time to judge the loosening risk of the bolt. The specific operation is to set the frequency drift warning value and risk value, compare the real-time frequency drift with the warning value, and if the real-time frequency drift is less than the warning value, a safety signal is generated. If it is greater than or equal to the warning value, a warning signal is generated. After the warning signal is generated, the frequency drift sequence and the sampling time sequence before the warning time point are obtained, and the change rate sequence is obtained by calculating the change rate of adjacent frequency drifts, and then the change rate mean ratio, extreme value change ratio and high change rate number ratio are obtained. The three ratios are weighted and summed to obtain the rate characterization value. According to the comparison result of the rate characterization value and the rate characterization threshold, the degree of the frequency drift change rate is judged, and a fast change rate signal or a slow change rate signal is generated; In this way, the risk of bolt loosening can be judged in real time, and a warning signal can be generated in time when the bolt shows signs of loosening, reminding relevant personnel to pay attention to the status of the bolt to avoid further development of bolt loosening without being detected, thereby reducing the possibility of equipment failure and accidents. By analyzing the change rate of frequency drift in multiple dimensions, the rate characterization value obtained can more accurately characterize the dynamic process of bolt loosening, improve the accuracy and reliability of judging the change rate of bolt loosening, and enable maintenance personnel to issue early warnings before the bolt loosening develops to a serious level, thereby buying more time for taking maintenance measures, facilitating early planning of maintenance work, and reducing equipment failures, accidents and casualties caused by bolt loosening. Personnel can also be deployed in advance based on early warnings.

[0020] Embodiment 2 Based on the above embodiments, Figure 1 As shown, the embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology provided by the embodiment of the present invention specifically includes the following steps: Step 3: Based on the result of judging the degree of the change rate, predict the time point when the frequency drift reaches the frequency drift risk value; In some embodiments, based on the fast change rate signal, a maximum change rate is obtained, and the maximum change rate is used as the predicted change rate; Obtain the frequency drift amount corresponding to the generated warning signal, and mark it as the warning frequency drift amount; The difference between the frequency drift risk value and the warning frequency drift is calculated, and the ratio is calculated with the predicted change rate to obtain the predicted time value; The calculated predicted time value is the time from the warning frequency drift value to the frequency drift risk value. Maintenance personnel can plan maintenance work in advance to reduce equipment failures, accidents and even casualties caused by loose bolts, and can deploy personnel in advance according to the predicted time value; The reason for using the maximum value of the change rate as the predicted change rate is that: using the maximum value of the change rate as the predicted change rate is mainly to provide the safest prediction when the bolt loosening rate is fast, so as to minimize the risk caused by bolt loosening. During the bolt loosening process, if the frequency drift changes quickly, it means that the bolt condition deteriorates rapidly. Predicting with the maximum value of the change rate can estimate the time when the frequency drift reaches the risk value the fastest. This prediction method enables maintenance personnel to carry out maintenance work in time before the bolt loosening problem develops to a dangerous level, replace or tighten the bolts, ensure the safe and stable operation of the equipment, and avoid equipment failures, accidents, and even casualties. Based on the slow-changing signal, the warning frequency drift is obtained, and the average of the frequency drift risk value and the warning frequency drift is taken as the analysis frequency drift; After the warning time point, the frequency drift is continued to be acquired in real time, and the frequency drift between the warning frequency drift and the analysis frequency drift is obtained, and marked as the sequence to be analyzed: ,in, is the warning frequency drift, To analyze the frequency drift; Fit the values ​​in the sequence to be analyzed by the least squares method to obtain the fitting model ; Based on the fitted model, calculate its goodness of fit , the calculation formula is: , where m is the number of data points, is the jth actual value, represents the jth predicted value, Indicates the average of actual values; Set the goodness of fit threshold. If the goodness of fit is greater than the goodness of fit threshold, it means that the data fits the fitting line better and the values ​​in the sequence to be analyzed change linearly. Otherwise, they change nonlinearly. Based on linear changes, the fitted model is used Predict the time point when the frequency drift reaches the frequency drift risk value, that is, substitute the frequency drift risk value into the fitting model, and the output x value is the predicted time value; Based on nonlinear changes, other models are used to build a prediction model. The specific process is as follows: In one possible embodiment, a radial basis function neural network (RBFNN) model is used to construct a prediction model; Normalize the values ​​in the sequence to be analyzed, for example, use the minimum-maximum normalization method to map the data to the [0,1] interval; The normalized values ​​are divided into training set and validation set in a ratio of 3:7; Set the input layer, hidden layer, and output layer; The number of neurons in the input layer depends on the number of features of the input data. Since we mainly focus on the change of frequency drift over time to predict the time to reach the risk value, the number of neurons in the input layer is 1, that is, the input is the current frequency drift, and the number of neurons in the output layer is also 1, and the predicted time value is output; Experimentally test different numbers of hidden layer neurons and observe the performance of the model on the validation set, including but not limited to: mean square error, mean absolute error; Choose the number of hidden layer neurons that optimizes the model performance. Generally, you can start with a small number, such as 5, and then gradually increase it until the model performance no longer improves or overfitting occurs. Initializing the radial basis function of the hidden layer neurons requires determining the center vector. Randomly select N different data points (N is the number of hidden layer neurons) from the training set as the initial center vector, so that the center vector has a certain representativeness in the data space. Initialization width parameter determines the width of radial basis function and affects the local approximation ability of the model. Usually, it can be initialized with a fixed value. For example, an initial value D is set first, and then the width parameter of all hidden layer neurons is set to D. It can be adjusted by optimization algorithm in the model training process. An empirical method to determine D is to calculate the average distance d between all data points in the training set, and then take , where N is the number of neurons in the hidden layer; Output layer weight initialization: Output layer weight (p represents hidden layer neurons, l represents output layer neurons) Random initialization is usually used to randomly generate initial weight values ​​within a certain range (such as [-1, 1]); Use the training set data to train the model. The goal of the training is to adjust the model parameters so that the error between the model's predicted output and the actual time value in the training set is minimized. Commonly used training algorithms are gradient descent and its variants, such as stochastic gradient descent (SGD) and mini-batch gradient descent (Mini-Batch SGD); Use the test set data to evaluate the trained RBFNN model and calculate the performance indicators of the model on the test set, such as mean square error (MSE) and mean absolute error; To obtain a prediction model with satisfactory performance, input the frequency drift risk value (normalized value) into the model, and the model output is the predicted time value; The output is the normalized time value, which needs to be denormalized to the actual time scale to finally get the predicted time value; For example, if the minimum-maximum normalization method is used; Step 4: Based on the predicted time value, adjust the monitoring frequency of the frequency drift; In some embodiments, a predicted time value corresponding to when a fast-changing rate signal is generated and a predicted time value corresponding to when a slow-changing rate signal is generated are obtained, and a first time threshold and a second time threshold are set; Get the current monitoring frequency of the frequency drift; Comparing the predicted time value corresponding to when the fast-changing-rate signal is generated with the first time threshold; If the predicted time value corresponding to the fast-changing signal is greater than or equal to the first time threshold, the current monitoring frequency is maintained; If the predicted time value corresponding to the fast-changing signal is less than the first time threshold, the predicted time value corresponding to the fast-changing signal is adjusted; Specifically, the predicted time value corresponding to the generation of the fast-changing rate signal is calculated by difference with the first time threshold, and then the ratio is calculated with the first time threshold to obtain the adjustment coefficient, the adjustment coefficient is multiplied by the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value; comparing the predicted time value corresponding to when the slow rate of change signal is generated with the second time threshold; If the predicted time value corresponding to the slow-changing signal is greater than or equal to the second time threshold, the current monitoring frequency is maintained; If the predicted time value corresponding to the signal with a slow rate of change is less than the second time threshold, the predicted time value corresponding to the signal with a fast rate of change is adjusted; Specifically, the predicted time value corresponding to the generation of the slow change rate signal is calculated by difference with the second time threshold, and then the ratio is calculated with the second time threshold to obtain the adjustment coefficient, the adjustment coefficient is multiplied by the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value; It should be noted that when a slow-rate-of-change signal is generated, the monitoring frequency is adjusted after the frequency drift value reaches the analysis frequency drift amount, so the second time threshold is different from the first time threshold; Therefore, the existing frequency can be maintained when the predicted time value is large to balance the monitoring cost and the equipment operation status monitoring needs, while adjustments can be made when the predicted time value is small, in line with the principle of timely strengthening monitoring, increasing monitoring frequency, and ensuring safe operation of equipment; The technical solution of this embodiment is: based on the fast and slow change rate signals, the time point at which the frequency drift reaches the risk value is predicted. When a fast change rate signal is received, the maximum change rate is used as the predicted change rate, and the predicted time value is calculated by the difference between the frequency drift risk value and the warning frequency drift and the predicted change rate. When a slow change rate signal is received, the average of the frequency drift risk value and the warning frequency drift is taken as the analysis frequency drift. The change characteristics of the frequency drift sequence obtained after the warning time point are judged according to the goodness of fit. The linear change is predicted by the fitting model, and the nonlinear change is predicted by the radial basis function neural network (RBFNN) model. The frequency drift monitoring frequency is adjusted according to the obtained predicted time value, and the predicted time value is compared with the corresponding time threshold. When the predicted time value is greater than or equal to the threshold, the current monitoring frequency is maintained, and when the predicted time value is less than the threshold, the frequency adjustment amount is obtained by calculating the adjustment coefficient, and then the monitoring frequency adjustment value is obtained; Therefore, by predicting the time when the frequency drift reaches the risk value, maintenance personnel can plan maintenance work in advance and reasonably arrange the time to replace or tighten bolts to avoid equipment failure, accidents and casualties due to loose bolts. Personnel can also be deployed in advance according to the predicted time. At the same time, the monitoring frequency can be adjusted according to the predicted time value. When the predicted time value is large, the existing frequency can be maintained to balance the monitoring cost and the equipment operation status monitoring needs. When the predicted time value is small, timely strengthen monitoring, increase the monitoring frequency, ensure the safe operation of the equipment, and further improve the reliability and safety of equipment operation.

[0021] Embodiment 3 Based on the above embodiments, Figure 2 As shown, the embedded wireless passive bolt tightness status monitoring system based on surface acoustic wave technology provided by the embodiment of the present invention specifically includes: Real-time judgment module: Based on the real-time acquisition of frequency drift of the surface acoustic wave resonator, the loosening risk of the bolts is judged in real time, and loosening warning signals and safety signals are generated; Change rate judgment module: Based on the warning signal, the change rate of the frequency drift before the warning signal is generated is analyzed, and the degree of the change rate is judged; Risk prediction module: based on the change rate, the time point when the frequency drift reaches the frequency drift risk value is predicted; Frequency adjustment module: adjusts the monitoring frequency of the frequency drift based on the predicted time value.

[0022] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0023] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology is characterized by: The following steps are involved: Obtain frequency drift in real time, make real-time judgment on the risk of bolt loosening, and generate warning signals; Based on the warning signal, the frequency drift amount before the warning signal is generated is analyzed and judged for the change rate, and a fast change rate signal and a slow change rate signal are generated; Based on the result of judging the degree of the rate of change, the time point at which the frequency drift reaches the frequency drift risk value is predicted.

2. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 1 is characterized in that: The process of real-time judgment of the loosening risk of bolts is as follows: The real-time frequency drift of the bolt is obtained. If the real-time frequency drift is greater than or equal to the frequency drift warning value, a warning signal is generated.

3. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 1 is characterized in that: The process of judging the degree of change rate is as follows: The frequency drift is analyzed and calculated to obtain the change rate mean ratio, the extreme value change ratio and the change rate quantity ratio, and the change rate mean ratio, the extreme value change ratio and the change rate quantity ratio are weighted to obtain the rate characterization value; If it is greater than the rate judgment characterization threshold, a fast change rate signal is generated, otherwise, a slow change rate signal is generated.

4. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 3 is characterized in that: The process of obtaining the change rate mean ratio and the extreme value change ratio is as follows: Obtain a frequency drift sequence before generating a warning signal, calculate the change rates of two adjacent frequency drifts, and obtain a change rate sequence; The values ​​in the change rate sequence are processed by averaging, and then the ratio is calculated with the change rate limit to obtain the change rate mean ratio; Calculate the deviation between the maximum value of the change rate and the minimum value of the change rate, and then calculate the ratio with the minimum value of the change rate to obtain the extreme value change ratio.

5. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 4 is characterized in that: The process of obtaining the change rate quantity ratio is as follows: The change rates that are greater than the change rate threshold are extracted, and their number is counted. The ratio is then calculated with the total number of rate change values ​​to obtain the high change rate number ratio.

6. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 1 is characterized in that: The process of predicting the time point at which the frequency drift reaches the frequency drift risk value includes: Based on the fast-changing rate signal, the maximum changing rate is obtained, the maximum changing rate is used as the predicted changing rate, and the frequency drift amount corresponding to the generated warning signal is marked as the warning frequency drift amount; The difference between the frequency drift risk value and the warning frequency drift is calculated, and the ratio is calculated with the predicted change rate to obtain the predicted time value.

7. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 1 is characterized in that: The process of predicting the time point at which the frequency drift reaches the frequency drift risk value also includes: Based on the slow-changing signal, the average of the frequency drift risk value and the warning frequency drift is marked as the analysis frequency drift, the frequency drift between the warning frequency drift and the analysis frequency drift is obtained, marked as the sequence to be analyzed, and it is determined whether the sequence to be analyzed changes linearly; If it is a linear change, the frequency drift risk value is substituted into the linear fitting model, and the output value is the predicted time value. If it is a nonlinear change, a radial basis function neural network model is used to build a prediction model and output the predicted time value.

8. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 7 is characterized in that: The process of determining whether the sequence to be analyzed changes linearly is as follows: Fit the values ​​in the sequence to be analyzed by the least square method to obtain a fitting model; Based on the fitting model, the goodness of fit is calculated. If the goodness of fit is greater than the goodness of fit threshold, the values ​​in the sequence to be analyzed change linearly; otherwise, they change nonlinearly.

9. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 1 is characterized in that: Also includes: Based on the predicted time value, the monitoring frequency of the frequency drift is adjusted; Obtaining a predicted time value corresponding to when a fast-changing rate signal is generated and a predicted time value corresponding to when a slow-changing rate signal is generated, and setting a first time threshold and a second time threshold; If the predicted time value corresponding to the fast-changing signal is less than the first time threshold, the predicted time value corresponding to the fast-changing signal is adjusted; If the predicted time value corresponding to the signal with a slow changing rate is less than the second time threshold, the predicted time value corresponding to the signal with a fast changing rate is adjusted.

10. The embedded wireless passive bolt tightness status monitoring method based on surface acoustic wave technology according to claim 9 is characterized in that: The process of adjusting the monitoring frequency of the frequency drift is as follows: The predicted time value corresponding to the generation of the fast-changing rate signal is calculated by difference with the first time threshold, and the ratio is calculated by the first time threshold, and then the product is calculated by multiplication with the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value; The predicted time value corresponding to the generation of the slow change rate signal is calculated by difference with the second time threshold, and the ratio is calculated with the second time threshold, and then multiplied with the current monitoring frequency to obtain the frequency adjustment amount, and the current monitoring frequency is calculated by difference with the frequency adjustment amount to obtain the monitoring frequency adjustment value.

Images