Bolt fastening state intelligent monitoring method based on sensor

Abstract

The invention relates to the technical field of bolt fastening monitoring, in particular to a bolt fastening state intelligent monitoring method based on a sensor. The method comprises the following steps: acquiring a pressure change characteristic value corresponding to a time window, according to the difference between the pressure change characteristic values corresponding to any two adjacent time windows in the current monitoring time period, determining the pressure change characteristic values; the connecting piece temperature mean value difference between the sub connecting piece temperature data sequences corresponding to two adjacent time windows and the bolt gasket pressure mean value difference between the sub bolt gasket pressure data sequences corresponding to two adjacent time windows are calculated; obtaining a first change relation coefficient and a second change relation coefficient between two adjacent time windows, and obtaining a bolt abnormity characterization value corresponding to each time window according to the first change relation coefficient and the second change relation coefficient; monitoring the fastening state of the bolt according to the abnormal characterization value of the bolt; and the accuracy and reliability of monitoring the fastening state of the bolt can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bolt tightening monitoring, and in particular to a sensor-based intelligent monitoring method for bolt tightening status. Background Art

[0002] Since the tightening state of the bolts is crucial to ensuring equipment safety, improving production efficiency, and extending equipment life, it is currently necessary to monitor the tightening state of the bolts, and the monitoring of the tightening state of the bolts is mainly to monitor whether the bolts are loose or have a tendency to loosen; in the prior art, the tightening state of the bolts is usually monitored by means of an embedded pressure sensor, that is, in the prior art, if the pressure data monitored by the embedded sensor at a certain moment does not meet the specified requirements, it is usually determined that the bolts have a tightening abnormality, and the tightening abnormality refers to the phenomenon that the bolts are loose or have a tendency to loosen, but when the embedded sensor is used to monitor the tightening state of the bolts, the pressure data monitored by the embedded sensor at a certain moment does not meet the specified requirements, then ... the embedded sensor is used to monitor the tightening state of the bolts. During monitoring, the data monitored by the embedded sensor is easily affected by external factors, such as temperature, which may lead to misjudgment, that is, the influence of external factors may cause the monitoring results of the embedded sensor to be inaccurate or unreliable. If the pressure data monitored by the embedded sensor at a certain moment does not meet the specified requirements, then this phenomenon may be caused by abnormal tightening of the bolt, or it may be caused by external factors. Therefore, when the pressure data monitored by the embedded sensor does not meet the specified requirements, it cannot completely indicate that the bolt has abnormal tightening. How to improve the accuracy and reliability of monitoring the tightening status of the bolt becomes an urgent problem to be solved. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a sensor-based intelligent monitoring method for bolt tightening status, and the technical solution adopted is as follows:

[0004] An embodiment of the present invention provides a sensor-based intelligent monitoring method for bolt tightening status, comprising the following steps:

[0005] Using pressure sensors and temperature sensors to obtain bolt gasket pressure data sequences and connector temperature data sequences corresponding to the bolts in the application during the current monitoring period;

[0006] The current monitoring time period is divided by a sliding time window to obtain each time window on the current monitoring time period, and a sub-bolt gasket pressure data sequence and a sub-connector temperature data sequence corresponding to each time window are obtained from the bolt gasket pressure data sequence and the connector temperature data sequence;

[0007] According to the range and standard deviation of the sub-bolt gasket pressure data sequence, the pressure change characteristic value corresponding to each time window is obtained; according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, the difference in the mean temperature of the connecting part between the sub-connector temperature data sequences corresponding to the two adjacent time windows, and the difference in the mean bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to the two adjacent time windows, the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows are obtained; according to the first change relationship coefficient and the second change relationship coefficient, the bolt abnormality characterization value corresponding to each time window is obtained;

[0008] The tightening state of the bolt is monitored according to the abnormal characterization value of the bolt.

[0009] Beneficial effect: The present invention uses a pressure sensor and a temperature sensor to obtain the bolt gasket pressure data sequence and the connector temperature data sequence corresponding to the bolts in the application in the current monitoring time period; then the current monitoring time period is divided by a sliding time window to obtain each time window in the current monitoring time period, and in the bolt gasket pressure data sequence and the connector temperature data sequence, the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to each time window are obtained; then, according to the range and standard deviation of the sub-bolt gasket pressure data sequence, the pressure change characteristic value corresponding to each time window is obtained, and according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, the difference between the sub-connector temperature data sequences corresponding to the two adjacent time windows, the pressure change characteristic value corresponding to the sub-connector temperature data sequence ... The temperature mean difference and the bolt gasket pressure mean difference between the sub-bolt gasket pressure data sequences corresponding to two adjacent time windows are obtained to obtain the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows, and the bolt abnormality characterization value corresponding to each time window is obtained according to the first change relationship coefficient and the second change relationship coefficient; finally, the tightening state of the bolt is monitored according to the bolt abnormality characterization value; and the bolt abnormality characterization value obtained by the present invention according to the first change relationship coefficient and the second change relationship coefficient can improve the accuracy and reliability of monitoring the tightening state of the bolt, that is to say, the bolt abnormality characterization value obtained by the present invention according to the first change relationship coefficient and the second change relationship coefficient can improve the accuracy and reliability of monitoring the bolt loosening phenomenon or loosening trend. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0011] Figure 1 The present invention is a flow chart of a sensor-based intelligent monitoring method for bolt tightening status. DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention 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, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the embodiments of the present invention.

[0013] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0014] This embodiment provides a sensor-based intelligent monitoring method for bolt tightening status, which is described in detail as follows:

[0015] like Figure 1 As shown, the sensor-based intelligent monitoring method for bolt tightening status includes the following steps:

[0016] Step S001: using a pressure sensor and a temperature sensor to obtain a bolt gasket pressure data sequence and a connection component temperature data sequence corresponding to a bolt in an application in a current monitoring time period.

[0017] The main purpose of this embodiment is to improve the accuracy and reliability of monitoring the tightening state of the bolt, that is, the main purpose of this embodiment is to improve the accuracy and reliability of monitoring the loosening phenomenon or loosening trend of the bolt; in this embodiment, in order to facilitate analysis and understanding, only the bolts in any application are selected for monitoring, and the bolts in the application refer to two parts with through holes that are currently connected by the bolt, and the bolt is mainly composed of a head and a screw. The head of the bolt is its main load-bearing part, and usually has a hexagonal head, a round head, a square head and other shapes, among which the hexagonal head is the most commonly used. The screw usually refers to a cylindrical part with an external thread, which is used in conjunction with a nut to fasten and connect two parts; in addition, a washer or gasket is also used when the bolt is used to connect the parts, that is, although the washer or gasket is not a component of the bolt, it is often used in conjunction with the washer when the bolt is used. The washer is placed between the supporting surface of the bolt and the surface of the connected part, which increases the contact area, reduces the pressure per unit area and protects the parts.

[0018] This embodiment first uses a pressure sensor and a temperature sensor to obtain the bolt gasket pressure data and the connection part temperature data of the bolts in the application at each monitoring moment in the current monitoring time period, and records the time series sequence composed of all the bolt gasket pressure data obtained in the current monitoring time period as the bolt gasket pressure data sequence corresponding to the bolts in the application in the current monitoring time period, and records the time series sequence composed of all the connection part temperature data obtained in the current monitoring time period as the connection part temperature data sequence corresponding to the bolts in the application in the current monitoring time period. The bolt gasket pressure data refers to the pressure exerted on the gasket, and currently the preload or tightness of the bolt is usually monitored based on the pressure exerted on the gasket.

[0019] The sensor used in this embodiment is an embedded sensor, and the embedded sensor is generally embedded in a gasket or a washer. The sensor is usually embedded in the gasket between the bolt and the nut. As other implementation methods, a non-embedded sensor can also be used for data collection. However, it should be noted that if the temperature collected by the embedded sensor is the temperature of the gasket, but the gasket is used in conjunction with the bolt, the gasket temperature can also represent the temperature of the connector; and in specific applications, the acquisition frequency of the embedded sensor in the process of monitoring the tightening state of the bolt is generally determined according to the specific sensor type and application scenario. The common acquisition frequency may be lower than or equal to 1 Hz, and this embodiment can set the acquisition frequency of the sensor to 1 Hz, that is, in the process of collecting data in this embodiment, the time interval between adjacent monitoring moments is 1 second; in addition, in specific applications, the implementer also needs to set the duration of the current monitoring time period according to actual conditions. For example, this embodiment can set the duration of the current monitoring time period to 10 minutes or half an hour, but requires the last monitoring moment in the current monitoring time period to be the current monitoring moment.

[0020] Therefore, this embodiment can obtain the bolt gasket pressure data sequence and the connector temperature data sequence corresponding to the bolts in the application in the current monitoring time period through the above process, and the monitored and collected data will be transmitted to the analysis and monitoring module through wired or wireless transmission methods for monitoring and analysis. If abnormal tightening of the bolts is detected subsequently, timely early warning prompts will be issued.

[0021] Step S002, using a sliding time window to divide the current monitoring time period to obtain each time window on the current monitoring time period, and in the bolt gasket pressure data sequence and the connector temperature data sequence, obtain the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to each time window.

[0022] Currently, when monitoring the tightening status of bolts, external factors may cause the monitoring results to be less accurate or to be misjudged. Especially under external factors with large temperature changes, it is more likely to cause the monitoring results to be less accurate or less reliable. For example, when the temperature is high, it will cause thermal expansion of the connector material, which will cause the gasket pressure data monitored by the embedded sensor to increase. When the temperature is low, it will cause cold contraction of the connector material, which will cause the gasket pressure data monitored by the embedded sensor to decrease. That is, the pressure change range monitored by the bolt and the overall pressure will change with temperature. However, when the bolt tightening is monitored only based on the gasket pressure data collected by the embedded pressure sensor, the phenomenon of reduced pressure on the gasket caused by cold shrinkage may be judged as abnormal bolt tightening. However, the reduction of gasket pressure caused by cold shrinkage may not be due to abnormal bolt tightening. Therefore, when the bolt tightening is monitored only based on the gasket pressure data collected by the embedded pressure sensor, the influence of external factors may lead to misjudgment or inaccurate and unreliable monitoring. In order to improve the accuracy and reliability of the monitoring results, this embodiment will further monitor the tightness of the bolt by analyzing the temperature changes of the connecting parts and the bolt gasket pressure changes.

[0023] In order to improve the accuracy and reliability of the monitoring results, the present embodiment first needs to use a sliding time window to divide the current monitoring time period to obtain each time window on the current monitoring time period, and use a preset time window to divide the current monitoring time period. The specific process of obtaining each time window on the current monitoring time period is as follows: first set a sliding time window of size a×1, and then start the sliding time window from the starting moment of the current monitoring time period, and slide it on the current monitoring time period with a preset sliding step size b until the last moment of the current monitoring time period appears in the sliding time window for the first time, thereby obtaining each time window on the current monitoring time period during the sliding process. The number of time windows on the current monitoring time period is related to the number of sliding times. If the number of sliding times is N, then the number of time windows on the current monitoring time period is N+1, and a is the length of the sliding time window.

[0024] In addition, in specific applications, the implementer needs to set the length a of the sliding time window and the preset sliding step b according to actual conditions, but the value of the preset sliding step b is required to be no greater than the length of the sliding time window. For example, in this embodiment, the length a of the sliding time window can be set to 0.5 minutes, and the preset sliding step b can be set to 0.25 minutes.

[0025] After obtaining each time window in the current monitoring time period, the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to each time window in the current monitoring time period are obtained from the above-obtained bolt gasket pressure data sequence and the connector temperature data sequence; and for any time window in the current monitoring time period, the specific acquisition process of the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to the time window is: from the above-obtained bolt gasket pressure data sequence and the connector temperature data sequence, all the bolt gasket pressure data and all the connector temperature data whose acquisition time is located in the time window are obtained, and the time series sequence constructed by all the bolt gasket pressure data whose acquisition time is located in the time window is recorded as the sub-bolt gasket pressure data sequence corresponding to the time window, and the time series sequence constructed by all the connector temperature data whose acquisition time is located in the time window is recorded as the sub-connector temperature data sequence corresponding to the time window.

[0026] Therefore, this embodiment can obtain the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to each time window in the current monitoring time period through the above process.

[0027] Step S003, based on the range and standard deviation of the sub-bolt gasket pressure data sequence, obtain the pressure change characteristic value corresponding to the each time window, and according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, the difference in the mean temperature of the connecting part between the sub-connector temperature data sequences corresponding to the two adjacent time windows, and the difference in the mean bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to the two adjacent time windows, obtain the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows; based on the first change relationship coefficient and the second change relationship coefficient, obtain the bolt abnormality characterization value corresponding to each time window.

[0028] After obtaining the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to the time window, the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to the time window are specifically analyzed to obtain the bolt abnormality characterization value corresponding to each time window, and the tightening state of the bolt is subsequently monitored by the obtained bolt abnormality characterization value. However, before obtaining the bolt abnormality characterization value corresponding to each time window, it is necessary to first obtain the pressure change characteristic value corresponding to the time window, and then, on the basis of the obtained pressure change characteristic value, the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence are combined to obtain the bolt abnormality characterization value corresponding to the time window. That is, based on the above analysis, it can be seen that this embodiment will then obtain the pressure change characteristic value corresponding to each time window according to the sub-bolt gasket pressure data sequence and the sub-connector temperature data sequence corresponding to each time window, and for the sake of ease of understanding, this embodiment will subsequently use the pressure change characteristic value corresponding to any time window The specific acquisition process of the force change characteristic value is described in detail, that is, the specific acquisition process of the pressure change characteristic value corresponding to the time window is: obtain the range and standard deviation of the sub-bolt gasket pressure data sequence corresponding to the time window, and multiply the range of the sub-bolt gasket pressure data sequence corresponding to the time window by the standard deviation of the sub-bolt gasket pressure data sequence corresponding to the time window, and record it as the pressure change characteristic value corresponding to the time window, the range of the sub-bolt gasket pressure data sequence refers to the difference between the maximum value and the minimum value in the corresponding sub-bolt gasket pressure data sequence; since both the standard deviation and the range can characterize the change of data in the sequence, the larger the pressure change characteristic value corresponding to the time window, the larger the pressure change characteristic value corresponding to the time window, indicating that the pressure data change range and fluctuation degree in the sub-bolt gasket pressure data sequence corresponding to the time window are, and the pressure change characteristic value is mainly used for the subsequent analysis and acquisition of the first change relationship coefficient, and the first change relationship coefficient is the key to the subsequent acquisition of the bolt abnormality characterization value.

[0029] When the bolt is tightening the fastener, if the gasket pressure is affected by temperature during collection, then the change in the pressure change characteristic value of the bolt at this time and the change in the temperature of the connecting part will show a certain positive correlation, and the bolt gasket pressure size and the connecting part temperature will show a certain positive correlation, and when the bolt is not loose, the ratio of the change in the pressure change characteristic value between all adjacent time windows to the change in the connecting part temperature should be relatively close, and the ratio of the bolt gasket pressure size to the connecting part temperature between all adjacent time windows should also be relatively close, otherwise the difference is large; based on the above analysis, this embodiment will then, on the basis of the acquired pressure change characteristic value, according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, and the average connecting part temperature between the sub-connector temperature data sequences corresponding to the two adjacent time windows The difference and the bolt gasket pressure mean difference between the sub-bolt gasket pressure data sequences corresponding to the two adjacent time windows are obtained to obtain the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows, and the first change relationship coefficient can reflect the relationship between the pressure change characteristic value change of the adjacent time window and the overall temperature change of the adjacent time window, and the first change relationship coefficient can reflect the relationship between the overall pressure change of the adjacent time window and the temperature change of the adjacent time window; in addition, for ease of understanding, this embodiment will take the specific acquisition process of the first change relationship coefficient and the second change relationship coefficient between the i-th time window and the i-1-th time window in the current monitoring time period as an example to describe, i is greater than 1, that is, the specific acquisition process of the first change relationship coefficient and the second change relationship coefficient between the i-th time window and the i-1-th time window in the previous monitoring time period is:

[0030] According to the difference between the pressure change characteristic values ​​corresponding to the i-th time window and the i-1-th time window in the current monitoring time period and the difference in the mean temperature of the connector between the sub-connector temperature data sequences corresponding to the i-th time window and the i-1-th time window, the first change relationship coefficient between the i-th time window and the i-1-th time window in the current monitoring time period is obtained; according to the difference in the mean temperature of the connector between the sub-connector temperature data sequences corresponding to the i-th time window and the i-1-th time window in the current monitoring time period and the difference in the mean bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to the i-th time window and the i-1-th time window, the second change relationship coefficient between the i-th time window and the i-1-th time window in the current monitoring time period is obtained.

[0031] And the specific process of obtaining the first change relationship coefficient between the i-th time window and the i-th time window in the current monitoring time period according to the difference between the pressure change characteristic values ​​corresponding to the i-th time window and the i-1-th time window in the current monitoring time period and the difference in the mean temperature of the connector between the temperature data series of the sub-connectors corresponding to the i-th time window and the i-1-th time window is as follows: first, obtain the difference between the pressure change characteristic value corresponding to the i-th time window and the pressure change characteristic value corresponding to the i-1-th time window, and record it as the pressure change characteristic difference value, obtain the mean of the temperature data series of the sub-connectors corresponding to the i-th time window and the temperature data series of the sub-connectors corresponding to the i-1-th time window, and record it as the pressure change characteristic difference value; The mean of the connector temperature data sequence is obtained, and is recorded as the connector temperature mean corresponding to the i-th time window and the connector temperature mean corresponding to the i-1th time window, respectively. Then, the difference between the connector temperature mean corresponding to the i-th time window and the connector temperature mean corresponding to the i-1th time window is recorded as the connector temperature mean difference value, and the ratio of the pressure change characteristic difference value to the connector temperature mean difference value is obtained, and the ratio of the pressure change characteristic difference value to the connector temperature mean difference value is used as the first change relationship coefficient between the i-th time window and the i-1th time window; and the specific calculation expression for obtaining the first change relationship coefficient between the i-th time window and the i-1th time window is:

[0032]

[0033] Among them, K1 i,i-1 is the first change relationship coefficient between the i-th time window and the i-1-th time window, A i is the pressure change characteristic value corresponding to the i-th time window, A i-1 is the pressure change characteristic value corresponding to the i-1th time window, T i is the mean temperature of the connector corresponding to the i-th time window, T i-1 is the average temperature of the connection corresponding to the i-1th time window; and when the material of the bolt connection is affected by thermal expansion and contraction caused by temperature, A i -A i-1 With T i -T i-1 There will be a negative correlation, that is, if A i Less than A i-1 , A i -A i-1 When it is negative, then T i Greater than T i-1 , T i -T i-1 If A i -A i-1 is positive, then T i-T i-1 If A i -A i-1 When it gets smaller, T i -T i-1 Get bigger, A i -A i-1 When T i -T i-1 becomes smaller; in addition, K1 i,i-1 It is mainly used for the calculation of subsequent bolt abnormality characterization values, and its value cannot indicate the degree of correlation.

[0034] The specific process of obtaining the second change relationship coefficient between the i-th time window and the i-1-th time window in the current monitoring time period according to the difference in the mean temperature of the connector between the sub-connector temperature data sequences corresponding to the i-th time window and the i-1-th time window and the difference in the mean bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to the i-th time window and the i-1-th time window is as follows: first, obtain the mean of the sub-bolt gasket pressure data sequence corresponding to the i-th time window and the mean of the sub-bolt gasket pressure data sequence corresponding to the i-1-th time window, and respectively It is recorded as the mean value of the bolt gasket pressure corresponding to the i-th time window and the mean value of the bolt gasket pressure corresponding to the i-1-th time window, and then the difference between the mean value of the bolt gasket pressure corresponding to the i-th time window and the mean value of the bolt gasket pressure corresponding to the i-1-th time window is obtained, and recorded as the bolt gasket pressure mean difference value, and then the ratio of the bolt gasket pressure mean difference value to the connection part temperature mean difference value is taken as the second change relationship coefficient between the i-th time window and the i-1-th time window; and the specific calculation expression for obtaining the second change relationship coefficient between the i-th time window and the i-1-th time window is:

[0035]

[0036] Among them, K2 i,i-1 is the second change relationship coefficient between the i-th time window and the i-1-th time window, B i is the average bolt gasket pressure corresponding to the i-th time window, B i-1 is the average bolt gasket pressure corresponding to the i-1th time window, T i is the mean temperature of the connector corresponding to the i-th time window, T i-1 is the average temperature of the connector corresponding to the i-1th time window; and when the connector material is affected by thermal expansion and contraction caused by temperature, B i -B i-1 With T i -T i-1 There will be a positive correlation, that is, if B i -Bi-1 is negative, then T i -T i-1 is also negative, otherwise if B i -B i-1 is positive, then T i -T i-1 is also positive, B i -B i-1 When it gets smaller, T i -T i-1 Also becomes smaller, A i -A i-1 When T i -T i-1 Also gets bigger, same as K2 i,i-1 It is mainly used for the calculation of subsequent bolt abnormality characterization values, and its value cannot indicate the degree of correlation.

[0037] In addition, it should be noted that T i -T i-1 There may be a special case where it is equal to 0, and when T i -T i-1 is equal to 0, the above formula for calculating the change relationship coefficient does not hold. Therefore, in this embodiment, if T i -T i-1 If A is equal to 0, i -A i-1 The result is taken as the first change relationship coefficient between the i-th time window and the i-1-th time window, and B i -B i-1 The result is used as the second change relationship coefficient between the i-th time window and the i-1-th time window.

[0038] When there is no tightening abnormality in the bolt, that is, when the bolt is not loose, the difference between the multiple first change relationship coefficients obtained above will be relatively small, and the difference between the multiple second change relationship coefficients obtained will also be relatively small. However, when there is a tightening abnormality in the bolt, there will be a large difference between the multiple first change relationship coefficients obtained above, and there may also be a large difference between the multiple second change relationship coefficients obtained, that is, the change relationship coefficient is the key to the subsequent acquisition of the bolt abnormality characterization value; based on the above analysis, it can be seen that after obtaining the first change relationship coefficient and the second change relationship coefficient between two adjacent time windows, this embodiment combines the first change relationship coefficient and the second change relationship coefficient obtained between the two adjacent time windows to obtain the bolt abnormality characterization value corresponding to each time window, that is, this embodiment will then obtain the bolt abnormality characterization value corresponding to each time window according to the first change relationship coefficient and the second change relationship coefficient between any two adjacent time windows in the current monitoring time period, and the specific acquisition process is:

[0039] For the i-th time window in the current monitoring time period, i is greater than 1: first, in the current monitoring time period, the sequence constructed by all time windows that are temporally preceding the i-th time window is recorded as the preceding time window sequence corresponding to the i-th time window; then, according to the first change relationship coefficient between the two adjacent time windows in the preceding time window sequence, the first difference factor corresponding to the i-th time window is obtained, and according to the second change relationship coefficient between the two adjacent time windows in the preceding time window sequence, the second difference factor corresponding to the i-th time window is obtained; then, the normalized value of the result obtained by multiplying the first difference factor corresponding to the i-th time window by the second difference factor corresponding to the i-th time window is obtained, and used as the bolt abnormality characterization value corresponding to the i-th time window. The function used for normalization here is the Norm() function, and the value range of the bolt abnormality characterization value is 0 to 1.

[0040] In this embodiment, the specific process of obtaining the first difference factor corresponding to the i-th time window according to the first change relationship coefficient between two adjacent time windows in the previous time window sequence is:

[0041] First, the sequence constructed by the first change relationship coefficients between all two adjacent time windows in the previous time window sequence is taken as the previous first change relationship coefficient sequence, that is, the first change relationship coefficient between the mth time window and the m-1th time window in the previous time window sequence is the mth first change relationship coefficient in the previous first change relationship coefficient sequence; then, the reference weight values ​​of each first change relationship coefficient in the previous first change relationship coefficient sequence are obtained, and the reference weight value of the jth first change relationship coefficient in the previous first change relationship coefficient sequence is M-m+1, where M is the total number of data in the previous first change relationship coefficient sequence; then, the cumulative sum of the reference weight values ​​of all first change relationship coefficients in the previous first change relationship coefficient sequence is recorded as the first comprehensive reference weight value.

[0042] Then, according to each first change relationship coefficient in the previous first change relationship coefficient sequence, the reference weight value of each first change relationship coefficient in the previous first change relationship coefficient sequence, the first comprehensive reference weight value, and the first change relationship coefficient between the i-th time window and the i-1-th time window, the first difference factor corresponding to the i-th time window is obtained; and according to each first change relationship coefficient in the previous first change relationship coefficient sequence, the reference weight value of each first change relationship coefficient in the previous first change relationship coefficient sequence, the first comprehensive reference weight value, and the first change relationship coefficient between the i-th time window and the i-1-th time window, the specific process of obtaining the first difference factor corresponding to the i-th time window is: the first change relationship coefficient between the i-th time window and the i-1-th time window is recorded as the first eigenvalue, and according to each first change relationship coefficient in the previous first change relationship coefficient sequence and the reference weight value of each first change relationship coefficient in the previous first change relationship coefficient sequence, a first weighted coefficient difference sequence is obtained, and the j-th first weighted coefficient difference in the first weighted coefficient difference sequence is D j ×t j , D j is the absolute value of the difference between the jth first change relationship coefficient and the first eigenvalue in the previous first change relationship coefficient sequence, t j is the reference weight value of the jth first change relationship coefficient in the previous first change relationship coefficient sequence; then the cumulative sum of all first weighted coefficient differences in the first weighted coefficient difference sequence is obtained and recorded as the first cumulative value, and then the ratio of the first cumulative value to the first comprehensive reference weight value is recorded as the first difference factor corresponding to the i-th time window. And the specific calculation expression for obtaining the first difference factor corresponding to the i-th time window is:

[0043]

[0044] Among them, Y1 i is the first difference factor corresponding to the i-th time window, M is the total number of data in the first change relationship coefficient sequence, t1 is the first comprehensive reference weight value, D j =|K1 i,i-1 -K1 j |, K1 j is the jth first change relationship coefficient in the previous first change relationship coefficient sequence; and when D j ×t j The larger the value, the higher the K1 i,i-1 The difference between the first change relationship coefficient and the first change relationship coefficient sequence in the previous order is large, and when K1 i,i-1 When the difference between Y1 and the first change relationship coefficient in the previous first change relationship coefficient sequence is large, iThe value of is also large, and because K1 i,i-1 When the difference between the first change relationship coefficient and the first change relationship coefficient sequence in the previous order is large, the probability of abnormal tightening of the bolt is also large. i The larger the value of Y1, the greater the probability of abnormal tightening of the bolt, and the greater the probability of loosening of the bolt. i The smaller the value, the smaller the probability of abnormal tightening of the bolt.

[0045] In this embodiment, according to the second change relationship coefficient between two adjacent time windows in the previous time window sequence, the specific process of obtaining the second difference factor corresponding to the ith time window is as follows: first, a sequence constructed by the second change relationship coefficients between all two adjacent time windows in the previous time window sequence is used as the previous second change relationship coefficient sequence, that is, the second change relationship coefficient between the yth time window and the y-1th time window in the previous time window sequence is the yth second change relationship coefficient in the previous second change relationship coefficient sequence; then, the reference weight values ​​of the second change relationship coefficients in the previous second change relationship coefficient sequence are obtained, and the previous second change relationship coefficient sequence is the reference weight value of the second change relationship coefficient in the previous second change relationship coefficient sequence. The reference weight value of the gth second change relationship coefficient in the second change relationship coefficient sequence is G-g+1, where G is the total number of data in the previous second change relationship coefficient sequence; then the cumulative sum of the reference weight values ​​of all second change relationship coefficients in the previous second change relationship coefficient sequence is recorded as the second comprehensive reference weight value; then, based on each second change relationship coefficient in the previous second change relationship coefficient sequence, the reference weight values ​​of each second change relationship coefficient in the previous second change relationship coefficient sequence, the second comprehensive reference weight value and the second change relationship coefficient between the i-th time window and the i-1-th time window, the second difference factor corresponding to the i-th time window is obtained.

[0046] In this embodiment, the method for obtaining the second difference factor corresponding to the i-th time window according to the respective second change relationship coefficients in the preceding second change relationship coefficient sequence, the reference weight values ​​of the respective second change relationship coefficients in the preceding second change relationship coefficient sequence, the second comprehensive reference weight value, and the second change relationship coefficient between the i-th time window and the i-1-th time window is the same as the above-mentioned method for obtaining the first difference factor corresponding to the i-th time window according to the respective first change relationship coefficients in the preceding first change relationship coefficient sequence, the reference weight values ​​of the respective first change relationship coefficients in the preceding first change relationship coefficient sequence, the first comprehensive reference weight value, and the first change relationship coefficient between the i-th time window and the i-1-th time window, and therefore this embodiment will not be described in detail.

[0047] And when the second difference factor corresponding to the i-th time window is larger, it indicates that K2 i,i-1The difference between the second change relationship coefficient in the previous second change relationship coefficient sequence is large, and when K2 i,i-1 When the difference between the second change relationship coefficient in the previous second change relationship coefficient sequence is large, the second difference factor corresponding to the i-th time window is also large, and due to K2 i,i-1 When the difference between the second change relationship coefficient and the second change relationship coefficient in the previous sequence is large, the probability of abnormal tightening of the bolt is also large. Therefore, when the second difference factor corresponding to the i-th time window is larger, the probability of abnormal tightening of the bolt is greater, that is, the probability of loosening of the bolt is greater. Conversely, when the second difference factor corresponding to the i-th time window is smaller, the probability of abnormal tightening of the bolt is smaller.

[0048] In addition, in the above analysis process, the reason for adding the reference weight value to the difference factor calculation process is that: as the application time of the bolt increases, the probability of abnormal tightening of the bolt will increase, so the reference value of the data acquired in the early stage is greater, that is, for the i-th time window, the reference value of the change relationship coefficient between any adjacent time windows that are farther away from the i-th time window is greater, so a higher reference weight needs to be assigned; and the first change relationship coefficient and the second change relationship coefficient obtained above can reflect whether the bolt has abnormal tightening, that is, the first change relationship coefficient and the second change relationship coefficient obtained above can reflect whether the bolt is loose, so the above embodiment of the present invention determines the bolt abnormality characterization value based on the first change relationship coefficient and the second change relationship coefficient obtained.

[0049] It should be noted that the bolt abnormality characterization value cannot be calculated for the first time window in the current monitoring time period. Therefore, in this embodiment, the bolt abnormality characterization value corresponding to the first time window is assigned. Then, in this embodiment, the average of the bolt abnormality characterization values ​​corresponding to all time windows except the first time window is used as the bolt abnormality characterization value corresponding to the first time window; as other real-time methods, the bolt abnormality characterization value corresponding to the first time window can also be directly assigned to 0 or the first time window is required not to participate in subsequent analysis.

[0050] Therefore, this embodiment can obtain the bolt abnormality characterization value corresponding to each time window in the current monitoring time period through the above process, and the larger the bolt abnormality characterization value, the greater the probability of the bolt being abnormally tightened, that is, the greater the probability of the bolt being loosened. Conversely, the smaller the bolt abnormality characterization value, the smaller the probability of the bolt being abnormally tightened, that is, the smaller the probability of the bolt being loosened.

[0051] Step S004: monitoring the tightening state of the bolt according to the bolt abnormality characterization value.

[0052] This embodiment will then monitor the tightening state of the bolts according to the bolt abnormality characterization values ​​corresponding to each time window in the current monitoring time period, specifically:

[0053] Firstly, the sequence formed by the bolt abnormality characterization values ​​corresponding to all time windows in the current monitoring time period is recorded as the bolt abnormality characterization value sequence, and then a two-dimensional mapping space is constructed, the ordinate value of the two-dimensional mapping space is the bolt abnormality characterization value, the abscissa value is the position number value of each bolt abnormality characterization value in the bolt abnormality characterization value sequence, and the position number value of the f-th bolt abnormality characterization value in the bolt abnormality characterization value sequence is f; then each bolt abnormality characterization value in the bolt abnormality characterization value sequence and the position number value of each bolt abnormality characterization value are mapped to the two-dimensional mapping space, and all the mapping data points in the two-dimensional mapping space are obtained, that is, the abscissa value of the mapping data point is the position number value of the bolt abnormality characterization value, and the ordinate value is the bolt abnormality characterization value; then, the mapping data points in the two-dimensional mapping space are connected in sequence according to the order of the abscissa value from small to large, and the connected curve is recorded as the curve to be analyzed, and then according to the mapping data points on the curve to be analyzed, a sequence of mapping data points to be analyzed is obtained, and the sequence of mapping data points to be analyzed is converted into The sequence formed by the slopes between two adjacent mapping data points in is recorded as a slope sequence, and the mean value of the slope sequence is used as the abnormal trend index value, and the pth slope in the slope sequence is the slope value between the pth mapping data point and the p+1th mapping data point in the mapping data point sequence to be analyzed; in this embodiment, the mapping data point sequence to be analyzed is composed of a preset number of mapping data points located at the back of the curve to be analyzed, and in a specific application, the implementer needs to set the value of the preset number according to the actual situation, such as the preset number can be set to 5 in this embodiment, but the preset number is required to be no greater than the total number of mapping data points on the curve to be analyzed; in addition, as another real-time method, the sequence composed of all mapping data points on the curve to be analyzed can also be used as the mapping data point sequence to be analyzed; and the acquired abnormal trend index value can reflect the probability of abnormal tightening of the bolt after the current monitoring moment, and the larger the abnormal trend index value, the greater the probability of abnormal tightening of the bolt at the future monitoring moment or the more obvious the trend.

[0054] Since the last time window in the current monitoring time period includes the current monitoring moment, and the bolt abnormality characterization value can characterize the possibility of abnormal tightening of the bolt, the present embodiment determines whether the abnormal trend index value is greater than the preset trend threshold or whether the bolt abnormality characterization value corresponding to the last time window in the current monitoring time period is greater than the preset abnormality threshold. If only one of the conditions is met, it can be indicated that there is abnormal tightening of the bolt at the current monitoring moment or the greater the probability of abnormal tightening of the bolt at the future monitoring moment or the more obvious the trend of abnormal tightening, then at this time, in order to ensure equipment safety, improve production efficiency, and extend equipment life, it is necessary to immediately perform a bolt tightening abnormality alarm, that is, if the abnormal trend index value is greater than the preset trend threshold, it is necessary to immediately perform a bolt tightening abnormality alarm, if the bolt abnormality characterization value corresponding to the last time window in the current monitoring time period is greater than the preset abnormal threshold, it is also necessary to immediately perform a bolt tightening abnormality alarm, only when the abnormal trend index value is not greater than the preset trend threshold and the bolt abnormality characterization value corresponding to the last time window in the current monitoring time period is not greater than the preset abnormal threshold, it can be shown that there is no loosening of the bolt and no potential loosening of the bolt, so there is no need to perform an abnormal alarm; and in the present embodiment, bolt loosening refers to the axial movement of the current bolt relative to the connecting piece.

[0055] In addition, in a specific application, the implementer needs to set the preset trend threshold and the preset abnormality threshold according to the actual situation. For example, in this embodiment, the preset trend threshold and the preset abnormality threshold can be set to 0.1 and 0.8 respectively.

[0056] So far, this embodiment has completed the monitoring of the bolt tightening state.

[0057] To summarize, this embodiment first uses a pressure sensor and a temperature sensor to obtain a bolt gasket pressure data sequence and a connector temperature data sequence corresponding to the bolts in the application in the current monitoring time period; then uses a sliding time window to divide the current monitoring time period to obtain each time window in the current monitoring time period, and obtains a sub-bolt gasket pressure data sequence and a sub-connector temperature data sequence corresponding to each time window in the bolt gasket pressure data sequence and the connector temperature data sequence; then, according to the range and standard deviation of the sub-bolt gasket pressure data sequence, the pressure change characteristic value corresponding to each time window is obtained, and according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, and the difference between the sub-connector temperature data sequences corresponding to the two adjacent time windows, the connector temperature is obtained. The temperature mean difference and the bolt gasket pressure mean difference between the sub-bolt gasket pressure data sequences corresponding to two adjacent time windows are obtained to obtain the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows, and the bolt abnormality characterization value corresponding to each time window is obtained according to the first change relationship coefficient and the second change relationship coefficient; finally, the tightening state of the bolt is monitored according to the bolt abnormality characterization value; and the bolt abnormality characterization value obtained by this embodiment according to the first change relationship coefficient and the second change relationship coefficient can improve the accuracy and reliability of monitoring the tightening state of the bolt, that is, the bolt abnormality characterization value obtained by this embodiment according to the first change relationship coefficient and the second change relationship coefficient can improve the accuracy and reliability of monitoring the bolt loosening phenomenon or loosening trend.

[0058] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A sensor-based intelligent monitoring method for bolt tightening status, characterized in that: The method comprises the following steps: Using a pressure sensor and a temperature sensor to obtain a bolt gasket pressure data sequence and a connector temperature data sequence corresponding to the bolts in the application in the current monitoring time period, wherein the connector refers to a part connected by the bolts; The current monitoring time period is divided by a sliding time window to obtain each time window on the current monitoring time period, and a sub-bolt gasket pressure data sequence and a sub-connector temperature data sequence corresponding to each time window are obtained from the bolt gasket pressure data sequence and the connector temperature data sequence; According to the range and standard deviation of the sub-bolt gasket pressure data sequence, the pressure change characteristic value corresponding to each time window is obtained; according to the difference between the pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period, the difference in the mean temperature of the connecting part between the sub-connector temperature data sequences corresponding to the two adjacent time windows, and the difference in the mean bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to the two adjacent time windows, the first change relationship coefficient and the second change relationship coefficient between the two adjacent time windows are obtained; according to the first change relationship coefficient and the second change relationship coefficient, the bolt abnormality characterization value corresponding to each time window is obtained; The tightening state of the bolt is monitored according to the abnormal characterization value of the bolt.

2. The sensor-based intelligent monitoring method for bolt tightening status according to claim 1, characterized in that: The method for obtaining the pressure change characteristic value corresponding to each time window includes: For any time window, the product of the range and the standard deviation of the sub-bolt gasket pressure data sequence corresponding to the time window is recorded as the pressure change characteristic value corresponding to the time window.

3. The sensor-based intelligent monitoring method for bolt tightening status according to claim 1, characterized in that: The method for obtaining the first change relationship coefficient and the second change relationship coefficient between two adjacent time windows includes: Obtaining a first change relationship coefficient between any two adjacent time windows in the current monitoring time period according to a difference between pressure change characteristic values ​​corresponding to any two adjacent time windows in the current monitoring time period and a difference in connector temperature mean values ​​between sub-connector temperature data sequences corresponding to the two adjacent time windows; Based on the mean difference in connector temperature between the sub-connector temperature data sequences corresponding to any two adjacent time windows in the current monitoring time period and the mean difference in bolt gasket pressure between the sub-bolt gasket pressure data sequences corresponding to two adjacent time windows, the second change relationship coefficient between any two adjacent time windows in the current monitoring time period is obtained.

4. The sensor-based intelligent monitoring method for bolt tightening status according to claim 3, characterized in that: The method for obtaining the first change relationship coefficient between two adjacent time windows includes: For the i-th time window and the i-1-th time window in the current monitoring time period, i is greater than 1: the difference between the pressure change characteristic value corresponding to the i-th time window and the pressure change characteristic value corresponding to the i-1-th time window is recorded as the pressure change characteristic difference value, and the difference between the mean of the sub-connector temperature data sequence corresponding to the i-th time window and the mean of the sub-connector temperature data sequence corresponding to the i-1-th time window is recorded as the connector temperature mean difference value; the ratio of the pressure change characteristic difference value to the temperature mean difference value is used as the first change relationship coefficient between the i-th time window and the i-1-th time window.

5. The sensor-based intelligent monitoring method for bolt tightening status according to claim 4, characterized in that: The method for obtaining a second change relationship coefficient between two adjacent time windows comprises: For the i-th time window and the i-1-th time window: the difference between the mean of the sub-bolt gasket pressure data sequence corresponding to the i-th time window and the mean of the sub-bolt gasket pressure data sequence corresponding to the i-1-th time window is recorded as the bolt gasket pressure mean difference value, and the ratio of the bolt gasket pressure mean difference value to the connecting part temperature mean difference value is taken as the second change relationship coefficient between the i-th time window and the i-1-th time window.

6. The sensor-based intelligent monitoring method for bolt tightening status according to claim 1, characterized in that: The method for obtaining the bolt abnormality characterization value corresponding to each time window includes: For the i-th time window in the current monitoring time period, i is greater than 1: In the current monitoring time period, a sequence constructed by all time windows located before the i-th time window in time is recorded as a preceding time window sequence corresponding to the i-th time window; According to the first change relationship coefficient between two adjacent time windows in the previous time window sequence, a first difference factor corresponding to the i-th time window is obtained; according to the second change relationship coefficient between two adjacent time windows in the previous time window sequence, a second difference factor corresponding to the i-th time window is obtained, and the method for obtaining the second difference factor corresponding to the i-th time window is the same as the method for obtaining the first difference factor corresponding to the i-th time window; A normalized value of a result obtained by multiplying a first difference factor corresponding to the i-th time window by a second difference factor corresponding to the i-th time window is used as the bolt abnormality characterization value corresponding to the i-th time window.

7. The sensor-based intelligent monitoring method for bolt tightening status according to claim 6, characterized in that: The method for obtaining the first difference factor corresponding to the i-th time window includes: Obtain a preceding first change relationship coefficient sequence and reference weight values ​​of each first change relationship coefficient in the preceding first change relationship coefficient sequence, the first change relationship coefficient between the mth time window and the m-1th time window in the preceding time window sequence is the m-1th first change relationship coefficient in the preceding first change relationship coefficient sequence, m is greater than 1, the reference weight value of the jth first change relationship coefficient in the preceding first change relationship coefficient sequence is M-j+1, and M is the total number of data in the preceding first change relationship coefficient sequence; Recording the cumulative sum of the reference weight values ​​of all first change relationship coefficients in the preceding first change relationship coefficient sequence as a first comprehensive reference weight value, and recording the first change relationship coefficient between the i-th time window and the i-1-th time window as a first eigenvalue; Obtain a first weighted coefficient difference sequence, wherein the jth first weighted coefficient difference in the first weighted coefficient difference sequence is D j ×t j , D j is the absolute value of the difference between the jth first change relationship coefficient in the preceding first change relationship coefficient sequence and the first eigenvalue, t j is the reference weight value of the jth first change relationship coefficient in the preceding first change relationship coefficient sequence; and the ratio of the cumulative sum of all first weighted coefficient differences in the first weighted coefficient difference sequence to the first comprehensive reference weight value is recorded as the first difference factor corresponding to the i-th time window.

8. The sensor-based intelligent monitoring method for bolt tightening status according to claim 1, characterized in that: The method for monitoring the tightening state of the bolt according to the abnormal characterization value of the bolt includes: Record the sequence of bolt abnormality characterization values ​​corresponding to all time windows in the current monitoring time period as a bolt abnormality characterization value sequence, draw a curve corresponding to the bolt abnormality characterization value sequence, and record it as the curve to be analyzed; record the sequence of slopes between adjacent data points on the curve to be analyzed as a slope sequence, and use the mean value of the slope sequence as the abnormal trend indicator value; If the abnormal trend index value is greater than the preset trend threshold or the bolt abnormality characterization value corresponding to the last time window in the current monitoring time period is greater than the preset abnormality threshold, a bolt tightening abnormality alarm is issued at the current monitoring time.

Images