Method and device for monitoring abnormity of suspension clamp

Abstract

The invention discloses a suspension clamp abnormity monitoring method and equipment, and the method comprises the steps: obtaining a vibration data sequence and a temperature data sequence, carrying out the filtering of the vibration data sequence through employing a self-adaptive Kalman filtering algorithm, obtaining a vibration prediction value sequence, carrying out the filtering of the temperature data sequence through employing a self-adaptive mean value filtering algorithm, and obtaining a vibration prediction value sequence; according to the method, the suspension clamp is monitored in real time from the vibration mode and the temperature mode, the vibration data is processed through the self-adaptive Kalman filtering algorithm, the temperature prediction value sequence is obtained, and when the vibration prediction value is larger than a first preset value or the temperature prediction value is larger than a second preset value, it is judged that the suspension clamp is abnormal, and an abnormal alarm is given out. The influence of the change of the noise level of the vibration data on the monitoring result can be reduced, the monitoring data is processed by adopting the adaptive mean filtering algorithm, different fluctuations of the temperature data can be adapted, and the anomaly monitoring accuracy is improved.

Description

Technical Field

[0001] The invention relates to a power fault monitoring technology, and in particular to a method and a device for monitoring abnormality of a suspension wire clamp. Background Art

[0002] Suspension clamps are used to fix conductors on the insulator strings of straight pole towers, or to hang lightning arresters on straight pole towers. They can also be used to support transposed conductors on transposed pole towers and fix jumpers on tension angle pole towers.

[0003] The suspension clamps of power lines face problems such as abnormal temperature, vibration and wear. If they cannot be monitored in time, maintenance personnel will not be able to handle them in time, which will cause line failures and affect the stable operation of the power system. Summary of the invention

[0004] The invention provides a method and a device for monitoring abnormality of a suspension wire clamp, so as to improve the accuracy of abnormality monitoring.

[0005] In a first aspect, the present invention provides a method for monitoring abnormality of a suspension clamp, comprising:

[0006] Acquire a vibration data sequence and a temperature data sequence, wherein the vibration data sequence includes a plurality of vibration observation values ​​arranged in time sequence within an observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in time sequence within the observation period;

[0007] Adopting an adaptive Kalman filter algorithm to filter the vibration data sequence to obtain a vibration prediction value sequence;

[0008] Adopting an adaptive mean filtering algorithm to filter the temperature data sequence to obtain a temperature prediction value sequence;

[0009] When the vibration prediction value is greater than the first preset value, or the temperature prediction value is greater than the second preset value, it is determined that the suspension wire clamp is abnormal, and an abnormal alarm is issued.

[0010] Optionally, an adaptive Kalman filter algorithm is used to filter the vibration data sequence to obtain a vibration prediction value sequence, including:

[0011] The first vibration observation value in the vibration data sequence is taken as the initial vibration observation value Z 0 , and set the initial error covariance P 0 , initial process noise covariance Q 0 , initial observation noise covariance R 0 , a first smoothing coefficient β for updating the observation noise covariance and a second smoothing coefficient γ for updating the process noise covariance;

[0012] The i-th vibration prediction value is used as the initial value X of the i+1-th vibration prediction value corresponding to the i+1-th vibration observation value. i+1|i ;

[0013] Based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i ;

[0014] Based on the initial value P of the i+1th error covariance i+1|i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 ;

[0015] Initial value X based on the i+1th vibration prediction value i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1|i , get the i+1th vibration prediction value X i+1 ;

[0016] Based on the initial value P of the i+1th error covariance i+1|i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1|i , and get the i+1th error covariance P i+1 ;

[0017] Based on the i-th observation noise covariance R i , the initial value X of the i+1th vibration prediction value i+1|i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1 ;

[0018] Based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1|i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 , where i is a natural number.

[0019] Optionally, based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i The calculation formula is:

[0020] P i+1|i =Pi +Q i

[0021] Among them, P i is the i-th error covariance, Q i is the noise covariance of the ith process.

[0022] Optionally, based on the initial value P of the i+1th error covariance i+1｜i Calculate the i+1th Kalman gain K with the i-th observation noise covariance Ri i+1 The calculation formula is:

[0023]

[0024] Among them, R i is the noise covariance of the ith observation, K i+1 is the i+1th Kalman gain.

[0025] Optionally, the initial value X based on the i+1th vibration prediction value i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1|i , get the i+1th vibration prediction value X i+1 The calculation formula is:

[0026] X i+1 =X i+1|i +K i+1 ×(Z i+1 -X i+1|i )

[0027] Among them, X i+1|i is the predicted value of the i+1th vibration, X i+1|i is the initial value of the i+1th vibration prediction value, K i+1 is the i+1th Kalman gain, Z i+1 is the i+1th vibration observation value.

[0028] Optionally, based on the initial value P of the i+1th error covariance i+1|i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1|i , and get the i+1th error covariance P i+1 The calculation formula is:

[0029] P i+1 =(1-K i+1 )×P i+1|i

[0030] Among them, K i+1is the i+1th Kalman gain, P i+1|i is the initial value of the i+1th error covariance.

[0031] Optionally, based on the noise covariance R of the ith observation i , the initial value X of the i+1th vibration prediction value i+1|i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance Ri + The calculation formula for 1 is:

[0032] R i+1 =β×R i +(1-β)×(Z i+1 -X i+1|i ) 2

[0033] Among them, Z i+1 is the i-th vibration observation value, R i is the noise covariance of the ith observation, X i+1|i is the initial value of the i+1th vibration prediction value.

[0034] Optionally, based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1|i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i The calculation formula for +1 is:

[0035] Q i+1 =γ×Q i +(1-γ)×X i+1|i 2

[0036] Among them, Q i is the noise covariance of the ith process, X i+1|i is the initial value of the i+1th vibration prediction value.

[0037] Optionally, an adaptive mean filtering algorithm is used to filter the temperature data sequence to obtain a temperature prediction value sequence, including:

[0038] Set the window value of the sampling window;

[0039] Using the initial window to start sampling from the first temperature observation value of the temperature data sequence, and calculating the average value of multiple temperature observation values ​​within the initial window;

[0040] Determine whether the average value is greater than a threshold;

[0041] If yes, then reduce the window value of the sampling window, and return to execute the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence;

[0042] If not, the window value of the sampling window is increased, and the process returns to the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence.

[0043] In a second aspect, the present invention further provides an electronic device, comprising:

[0044] one or more processors;

[0045] A storage device for storing one or more programs;

[0046] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for monitoring abnormalities of a suspension wire clamp as provided in the first aspect of the present invention.

[0047] The method for monitoring abnormalities of a suspension wire clamp provided by the present invention obtains a vibration data sequence and a temperature data sequence, wherein the vibration data sequence includes a plurality of vibration observation values ​​arranged in chronological order within an observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in chronological order within an observation period, and an adaptive Kalman filtering algorithm is used to filter the vibration data sequence to obtain a vibration prediction value sequence, and an adaptive mean filtering algorithm is used to filter the temperature data sequence to obtain a temperature prediction value sequence. When the vibration prediction value is greater than a first preset value, or the temperature prediction value is greater than a second preset value, the suspension wire clamp is determined to be abnormal, and an abnormal alarm is issued. The present invention monitors the suspension wire clamp in real time from two modes, vibration and temperature, and uses an adaptive Kalman filtering algorithm to process the vibration data, thereby reducing the influence of changes in the noise level of the vibration data on the monitoring results. The adaptive mean filtering algorithm is used to process the monitoring data, thereby adapting to different fluctuations in the temperature data and improving the accuracy of abnormal monitoring.

[0048] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] 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.

[0050] Figure 1 A flow chart of a method for monitoring abnormality of a suspension wire clamp provided by the present invention;

[0051] Figure 2 A schematic structural diagram of a suspension wire clamp abnormality monitoring device provided by the present invention;

[0052] Figure 3 The present invention provides a schematic structural diagram of an electronic device.

[0053] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0054] 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.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0056] The present invention provides a suspension wire clamp abnormality monitoring system, including multiple monitoring terminals and at least one processing terminal. The outer shell of the monitoring terminal is cylindrical in shape to provide strength and sealing to protect the internal electronic components from the external environment (such as moisture, dust, mechanical shock, etc.). The monitoring terminal is internally provided with 1) a temperature sensor module for real-time monitoring of the temperature change of the suspension wire clamp. When the temperature exceeds the set threshold, the temperature sensor module sends the temperature data to the embedded control module. 2) A vibration sensor module for detecting the vibration of the suspension wire clamp. By analyzing the vibration frequency and intensity, possible wear or looseness can be identified.

[0057] The monitoring terminal adopts an open-close connection for easy installation and disassembly. This connection device is located at one end of the monitoring terminal, allowing the monitoring terminal to be quickly connected and disconnected. This design is used to facilitate cable maintenance or replacement of the monitoring terminal, which can save a lot of time.

[0058] The monitoring end adopts a modular design, and the internal components of the equipment (such as RS485 module, single-chip module, etc.) are installed modularly, which means that each module can be removed or replaced individually. This design is mechanically realized through rails, screws or buckles, which is convenient for equipment maintenance and upgrading.

[0059] The battery of the monitoring terminal is fixed inside the monitoring terminal by a bracket or support to ensure that the battery will not come loose when the monitoring terminal is moved or vibrated. The battery bracket has elastic elements or fixing clips to facilitate the installation and replacement of the battery.

[0060] The monitoring terminal adopts a cable threading design, and the cable passes through the sealed interface or threading hole of the monitoring terminal shell. These interfaces are waterproof and dustproof, and are equipped with sealing rings or other sealing devices to ensure the overall sealing of the monitoring terminal.

[0061] The shell of the processing terminal is a cube, made of aluminum alloy, with the characteristics of light weight and easy installation. The terminal contains a solar controller inside, which is responsible for managing the power collected from the solar panel. It can adjust the current and voltage, prevent the battery from overcharging or over-discharging, and ensure the stable operation of the entire system. The USR-LG200 main control device is used, which is a vibration and temperature data collector. Its main function is to process and store vibration and temperature data, and connect to the background data record.

[0062] Vibration sensor module, select input level: 5V~36V, communication mode: RS485. Thermocouple temperature sensor module: Connect PT100 to convert the temperature value into TTL signal. PT100 module: Input level: 3.3V, communication protocol: serial communication. STM32 main control board: Select input level: 3.3V, process the received temperature and vibration values, and send them to the monitoring terminal (LORA101) in real time. Terminal (USR-LG220) selects input level: 5V~36V, communication protocol: LORA communication, and sends the received temperature and vibration values ​​to the cloud background server in real time. Users can view the vibration and temperature values ​​in real time. If the set temperature and vibration thresholds are exceeded, a text message will be automatically sent to the corresponding person in charge for warning.

[0063] The monitoring end (LORA101) and the processing terminal (USR-LG220) are separated. The monitoring end is placed at a height of several tens of meters. The processing terminal is placed 3 meters above the ground. Multiple monitoring ends correspond to one processing terminal, that is, multiple LORA101s correspond to one USR-LG220.

[0064] One processing terminal (processing terminal, i.e. USR-LG220) is placed on one iron, which can collect data of multiple pre-twisted wires (monitoring terminal, i.e. LORA 101), many to one.

[0065] The processing terminal (terminal, i.e. USR-LG220) is an iron box, photovoltaic-powered, installed on an iron platform (3 meters above the ground).

[0066] The system operation process is:

[0067] (1) System initialization. When the system starts, perform the following initialization steps to ensure the normal operation of the system. Hardware configuration: Set the system clock to ensure that the microcontroller starts correctly. Peripheral configuration: Configure GPIO, UART and other peripherals to prepare for data input and output. (2) Whether the temperature value is received: This is a decision node used to determine whether the system has received the temperature value. If it has been received, the process continues; if it has not been received, it jumps to the process of determining whether the vibration value has been received. (3) Send temperature value to monitoring terminal 2 (LORA 101): Once the temperature value is received, the system sends the temperature value to monitoring terminal 2 (LORA 101) (4) Whether the vibration value is received: This is another decision node used to determine whether the system has received the vibration value. If it has been received, the process continues; if it has not been received, the process ends. (5) Send temperature value to monitoring terminal 1 (LORA 101): Once the vibration value is received, the system sends the vibration value to monitoring terminal 1 (LORA101) (6) End: The process ends here. The program will repeat this process continuously, continuously detecting and sending vibration and temperature data.

[0068] Figure 1 This is a flow chart of a method for monitoring abnormality of a suspension clamp provided by the present invention. This embodiment can be used to monitor abnormal vibration and temperature of a suspension clamp. The method can be performed by a device for monitoring abnormality of a suspension clamp provided by the present invention. The device can be implemented by software and / or hardware and is usually configured in an electronic device, such as Figure 1 As shown, the method for monitoring abnormality of the suspension clamp specifically includes the following steps:

[0069] S101. Obtain a vibration data sequence and a temperature data sequence.

[0070] In an embodiment of the present invention, a vibration data sequence and a temperature data sequence are obtained within an observation period. The vibration data sequence includes a plurality of vibration observation values ​​arranged in time order within the observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in time order within the observation period. The observation value is the value collected by the sensor.

[0071] S102: Filter the vibration data sequence using an adaptive Kalman filter algorithm to obtain a vibration prediction value sequence.

[0072] In the standard Kalman filter, the process noise covariance and the observation noise covariance are usually set to fixed values. However, the noise level of the actual vibration data may change over time, which leads to poor accuracy of the abnormal monitoring results obtained by the standard Kalman filter algorithm. In the embodiment of the present invention, in order to improve the accuracy of the vibration warning of the suspension wire clamp, some enhancement and variant algorithms are applied on the basis of the existing Kalman filter. These improvements can effectively improve the accuracy of the filter, adapt to the dynamically changing environmental noise, and thus improve the accuracy of abnormal monitoring.

[0073] In some embodiments of the present invention, the process of the adaptive Kalman filter algorithm is as follows:

[0074] 1. Take the first vibration observation value in the vibration data sequence as the initial vibration observation value Z 0 , and set the initial error covariance P 0 , initial process noise covariance Q 0 , initial observation noise covariance R 0 , a first smoothing coefficient β for updating the observation noise covariance and a second smoothing coefficient γ for updating the process noise covariance.

[0075] 2. Set the i-th vibration prediction value X i The initial value X of the i+1th vibration prediction value corresponding to the i+1th vibration observation value i+1|i . Let X i+1|i =X i .

[0076] 3. Based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i .

[0077] For example, the initial value P of the i+1th error covariance is i+1|i The calculation formula is as follows:

[0078] P i+1|i =P i +Q i

[0079] 4. Initial value P based on the i+1th error covariance i+1|i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 .

[0080] For example, the i+1th Kalman gain K i+1 The calculation formula is as follows:

[0081]

[0082] 5. Initial value X based on the i+1th vibration prediction value i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1｜i , get the i+1th vibration prediction value X i+1 .

[0083] For example, the i+1th vibration prediction value X i+1 The calculation formula is as follows:

[0084] X i+1 =X i+1|i +K i+1 ×(Z i+1 -X i+1|i )

[0085] 6. Initial value P based on the i+1th error covariance i+1｜i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1｜i , and get the i+1th error covariance P i+1 .

[0086] For example, the i+1th error covariance P i+1 The calculation formula is as follows:

[0087] P i+1 =(1-K i+1 )×P i+1|i

[0088] 7. Based on the i-th observation noise covariance R i , the initial value X of the i+1th vibration prediction value i+1｜i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1 .

[0089] For example, the i+1th observation noise covariance R i+1 The calculation formula is as follows:

[0090] R i+1 =β×R i +(1-β)×(Z i+1 -X i+1|i ) 2

[0091] 8. Based on the noise covariance Q of the i-th process i , the initial value X of the i+1th vibration prediction value i+1｜i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 , where i is a natural number.

[0092] For example, the i+1th process noise covariance Q i+1 The calculation formula is as follows:

[0093] Q i+1 =γ×Q i +(1-γ)×X i+1|i 2

[0094] For example, the vibration data sequence is [42, 44, 47, 68, 71, 91, 74, 50, 66, 69, 103, 110, 100], and the unit is decibel. 0 =42, and set the initial value of the first vibration prediction value to Z 0 , set the initial error covariance P 0 =1, initial process noise covariance Q 0 =1, initial observation noise covariance R 0 =4, the first smoothing coefficient β = 0.8, the second smoothing coefficient γ = 0.8. Initial error covariance P 0 Reflects the uncertainty of the initial state estimate (i.e. 42). The default setting is 1, indicating that there is some confidence in the initial estimate of the first vibration prediction value, but there is still some uncertainty. Initial process noise covariance Q 0 Reflects the uncertainty of the change of the system state. It is usually set to 1 by default, indicating that the system state has certain fluctuations. Setting it to 1 can ensure that the filter can track the real changes of the system without being disturbed by small fluctuations. Initial observation noise covariance R 0 It is usually set according to the accuracy of the sensor. The standard deviation of the sensor noise in this experiment is about 2, so the initial observation noise covariance R 0=4. In the absence of specific sensor information, setting a moderate initial observation noise covariance can help the filter balance the weight between observed data and predicted data. (It can be adjusted according to the noise variance of the sensor or experiment. If the observed data is noisy, use a larger initial observation noise covariance; if the observed data is more accurate, the initial observation noise covariance can be reduced). Smoothing coefficients β = 0.8 and γ = 0.8 are used to update the observation noise covariance and process noise covariance. Such smoothing coefficients are usually set to 0.8-0.95. The larger the value, the smoother the noise update and the more stable the filter; the smaller the value means more sensitivity to noise changes. Generally, it is adjusted to the value with the best filtering effect through experiments. If the data changes relatively smoothly, a higher smoothing coefficient can be selected; if the data fluctuates greatly, a smaller smoothing coefficient can be selected to make the filter adapt to data changes faster.

[0095] X 0 =X 1｜0 =Z 0 =42;

[0096] The initial value P of the first error covariance 1|0 =P 0 +Q 0 =2;

[0097] First Kalman Gain

[0098] The first vibration prediction value X 1 =X 1|0 +k 1 ×(Z 1 -X 1|0 )=42.67;

[0099] The first error covariance P 1 =(1-k 1 )×P 1|0 =1.33;

[0100] The first observation noise covariance R 1 =β×R 0 +(1-β)×(Z 1 -X 1|0 ) 2 =4;

[0101] The first process noise covariance Q 1 =γ×Q 0 +(1-γ)×X 1|0 2 =0.8.

[0102] In this way, according to the above process, the vibration prediction value corresponding to the last vibration observation value is calculated, and the vibration prediction value sequence composed of the vibration prediction values ​​is obtained: [42, 42.67, 44.06, 51.45, 57.33, 66.89, 69.43, 65.21, 66.12, 67.05, 82.76, 93.28, 95.83].

[0103] After the adaptive Kalman filter processing, the data sequence is smoothed, and the influence of outliers (such as 103 and 110) on the final result is greatly reduced, which improves the monitoring accuracy.

[0104] S103, using an adaptive mean filtering algorithm to filter the temperature data sequence to obtain a temperature prediction value sequence.

[0105] In the embodiment of the present invention, the adaptive mean filter automatically adjusts the size of the filter window according to the amplitude of the data change, so as to adapt to the different fluctuations of the data. When the data changes drastically, it will reduce the window to improve the response speed to the change; when the data changes more steadily, it will expand the window to enhance the smoothing effect.

[0106] Specifically, the process of the adaptive mean filtering algorithm is:

[0107] 1. Set the window value of the sampling window.

[0108] 2. Use an initial window to start sampling from the first temperature observation value of the temperature data sequence, and calculate the average value of multiple temperature observation values ​​in the initial window as the first temperature prediction value.

[0109] 3. Determine whether the average value is greater than the threshold.

[0110] 4. If so, reduce the window value of the sampling window and return to execute the step of sampling from the first temperature observation value of the temperature data sequence using the initial window.

[0111] 5. If not, increase the window value of the sampling window and return to execute the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence.

[0112] Exemplarily, the temperature data sequence is: [25.0, 25.1, 25.2, 26.0, 25.3, 25.2, 25.1, 25.0] as an example, the unit is Celsius. Set the initial value of the window value of the sampling window to 3, then the data sampled by the sampling window is [25.0, 25.1, 25.2], and the mean of the data in the window is calculated to be 25.1 as the first temperature prediction value. In the embodiment of the present invention, the threshold value T=60, and the mean of the data in the window is less than the threshold value T, then the window value of the sampling window is increased to 4, and then the data sampled by the sampling window is [25.0, 25.1, 25.2, 26.0], and then repeat the above process to obtain the last temperature prediction value. All temperature prediction values ​​constitute a temperature prediction value sequence: [25.1, 25.325, 25.32, 25.3, 25.271, 25.2375]. It should be noted that, in the embodiment of the present invention, since the threshold T is relatively large, the average value will not be greater than the threshold, and therefore, the window value of the sampling window will continue to increase.

[0113] S104. When the vibration prediction value is greater than the first preset value, or the temperature prediction value is greater than the second preset value, it is determined that the suspension clamp is abnormal, and an abnormal alarm is issued.

[0114] In an embodiment of the present invention, each vibration prediction value is compared with a first preset value, and each temperature prediction value is compared with a second preset value. If the vibration prediction value is greater than the first preset value, or the temperature prediction value is greater than the second preset value, the suspension clamp is determined to be abnormal and an abnormal alarm is issued.

[0115] The method for monitoring abnormalities of a suspension wire clamp provided by the present invention obtains a vibration data sequence and a temperature data sequence, wherein the vibration data sequence includes a plurality of vibration observation values ​​arranged in chronological order within an observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in chronological order within an observation period, and an adaptive Kalman filtering algorithm is used to filter the vibration data sequence to obtain a vibration prediction value sequence, and an adaptive mean filtering algorithm is used to filter the temperature data sequence to obtain a temperature prediction value sequence. When the vibration prediction value is greater than a first preset value, or the temperature prediction value is greater than a second preset value, the suspension wire clamp is determined to be abnormal, and an abnormal alarm is issued. The present invention monitors the suspension wire clamp in real time from two modes, vibration and temperature, and uses an adaptive Kalman filtering algorithm to process the vibration data, thereby reducing the influence of changes in the noise level of the vibration data on the monitoring results. The adaptive mean filtering algorithm is used to process the monitoring data, thereby adapting to different fluctuations in the temperature data and improving the accuracy of abnormal monitoring.

[0116] Figure 2 A schematic diagram of the structure of a suspension clamp abnormality monitoring device provided by the present invention, such as Figure 2As shown, the abnormal monitoring device for the suspension clamp includes:

[0117] A data acquisition module 201 is used to acquire a vibration data sequence and a temperature data sequence, wherein the vibration data sequence includes a plurality of vibration observation values ​​arranged in time sequence within an observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in time sequence within the observation period;

[0118] A Kalman filter module 202 is used to filter the vibration data sequence using an adaptive Kalman filter algorithm to obtain a vibration prediction value sequence;

[0119] A mean filtering module 203 is used to filter the temperature data sequence using an adaptive mean filtering algorithm to obtain a temperature prediction value sequence;

[0120] The abnormal alarm module 204 is used to determine that the suspension clamp is abnormal and issue an abnormal alarm when the vibration prediction value is greater than a first preset value or the temperature prediction value is greater than a second preset value.

[0121] In some embodiments of the present invention, the Kalman filter module 202 includes:

[0122] Initialization submodule, used to take the first vibration observation value in the vibration data sequence as the initial vibration observation value Z 0 , and set the initial error covariance P 0 , initial process noise covariance Q 0 , initial observation noise covariance R 0 , a first smoothing coefficient β for updating the observation noise covariance and a second smoothing coefficient γ for updating the process noise covariance;

[0123] The vibration prediction value initial value determination submodule is used to use the i-th vibration prediction value as the initial value X of the i+1-th vibration prediction value corresponding to the i+1-th vibration observation value. i+1|i ;

[0124] The error covariance initial value determination submodule is used to determine the initial value of the error covariance based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i ;

[0125] Kalman gain determination submodule, used for initial value P based on the i+1th error covariance i+1|i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 ;

[0126] The vibration prediction value determination submodule is used to determine the initial value X of the i+1th vibration prediction value. i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1|i , get the i+1th vibration prediction value X i+1 ;

[0127] The error covariance determination submodule is used to determine the initial value P of the error covariance based on the i+1th error i+1|i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1|i , and get the i+1th error covariance P i+1 ;

[0128] The observation noise covariance determination submodule is used to determine the noise covariance R of the ith observation noise based on the i , the initial value X of the i+1th vibration prediction value i+1|i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1 ;

[0129] The process noise covariance determination submodule is used to determine the process noise covariance Q based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1｜i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 , where i is a natural number.

[0130] In some embodiments of the present invention, based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1｜i The calculation formula is:

[0131] P i+1|i =P i +Q i

[0132] Among them, P i is the i-th error covariance, Q i is the noise covariance of the ith process.

[0133] In some embodiments of the present invention, based on the initial value P of the i+1th error covariance i+1｜i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 The calculation formula is:

[0134]

[0135] Among them, R i is the noise covariance of the ith observation, K i+1 is the i+1th Kalman gain.

[0136] In some embodiments of the present invention, based on the initial value X of the i+1th vibration prediction value i+1｜i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1｜i , get the i+1th vibration prediction value X i+1 The calculation formula is:

[0137] X i+1 =X i+1|i +K i+1 ×(Z i+1 -X i+1|i )

[0138] Among them, X i+1|i is the predicted value of the i+1th vibration, X i+1|i is the initial value of the i+1th vibration prediction value, K i+1 is the i+1th Kalman gain, Z i+1 is the i+1th vibration observation value.

[0139] In some embodiments of the present invention, based on the initial value P of the i+1th error covariance i+1｜i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1｜i , and get the i+1th error covariance P i+1 The calculation formula is:

[0140] P i+1 =(1-K i+1 )×P i+1|i

[0141] Among them, K i+1 is the i+1th Kalman gain, P i+1|i is the initial value of the i+1th error covariance.

[0142] In some embodiments of the present invention, based on the i-th observation noise covariance R i , the initial value X of the i+1th vibration prediction value i+1｜i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1The calculation formula is:

[0143] R i+1 =β×R i +(1-β)×(Z i+1 -X i+1|i ) 2

[0144] Among them, Z i+1 is the i-th vibration observation value, R i is the noise covariance of the ith observation, X i+1|i is the initial value of the i+1th vibration prediction value.

[0145] In some embodiments of the present invention, based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1｜i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 The calculation formula is:

[0146] Q i+1 =γ×Q i +(1-γ)×X i+1|i 2

[0147] Among them, Q i is the noise covariance of the ith process, X i+1|i is the initial value of the i+1th vibration prediction value.

[0148] In some embodiments of the present invention, the mean filter module 203 includes:

[0149] The window value initialization submodule is used to set the window value of the sampling window;

[0150] a temperature prediction value determination submodule, configured to adopt the initial window to start sampling from the first temperature observation value of the temperature data sequence, and calculate an average value of a plurality of temperature observation values ​​within the initial window as a first temperature prediction value;

[0151] A judging submodule, used to judge whether the average value is greater than a threshold;

[0152] a window value reduction submodule, for reducing the window value of the sampling window if yes, and returning to execute the step of sampling from the first temperature observation value of the temperature data sequence using the initial window;

[0153] The window value increasing submodule is used to increase the window value of the sampling window if not, and return to execute the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence.

[0154] The above-mentioned suspension wire clamp abnormality monitoring device can execute the suspension wire clamp abnormality monitoring method provided by the above-mentioned embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the suspension wire clamp abnormality monitoring method.

[0155] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0156] like Figure 3 As shown, the electronic device includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0157] A number of components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0158] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for monitoring abnormality of the suspension wire clamp.

[0159] In some embodiments, the suspension wire clamp abnormality monitoring method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the suspension wire clamp abnormality monitoring method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the suspension wire clamp abnormality monitoring method in any other appropriate manner (for example, by means of firmware).

[0160] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0162] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0163] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0165] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0166] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for monitoring abnormalities of a suspension wire clamp as provided in any embodiment of the present application.

[0167] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0168] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0169] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring abnormality of a suspension clamp, characterized in that: include: Acquire a vibration data sequence and a temperature data sequence, wherein the vibration data sequence includes a plurality of vibration observation values ​​arranged in time sequence within an observation period, and the temperature data sequence includes a plurality of temperature observation values ​​arranged in time sequence within the observation period; Adopting an adaptive Kalman filter algorithm to filter the vibration data sequence to obtain a vibration prediction value sequence; Adopting an adaptive mean filtering algorithm to filter the temperature data sequence to obtain a temperature prediction value sequence; When the vibration prediction value is greater than the first preset value, or the temperature prediction value is greater than the second preset value, it is determined that the suspension wire clamp is abnormal, and an abnormal alarm is issued.

2. The method for monitoring abnormality of a suspension clamp according to claim 1, characterized in that: The vibration data sequence is filtered using an adaptive Kalman filter algorithm to obtain a vibration prediction value sequence, including: The first vibration observation value in the vibration data sequence is used as the initial vibration observation value Z0, and an initial error covariance P0, an initial process noise covariance Q0, an initial observation noise covariance R0, a first smoothing coefficient β for updating the observation noise covariance, and a second smoothing coefficient γ for updating the process noise covariance are set; The i-th vibration prediction value is used as the initial value X of the i+1-th vibration prediction value corresponding to the i+1-th vibration observation value. i+1|i ; Based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i ; Based on the initial value P of the i+1th error covariance i+1|i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 ; Initial value X based on the i+1th vibration prediction value i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1|i , get the i+1th vibration prediction value X i+1 ; Based on the initial value P of the i+1th error covariance i+1|i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1|i , and get the i+1th error covariance P i+1 ; Based on the i-th observation noise covariance R i , the initial value X of the i+1th vibration prediction value i+1|i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1 ; Based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1|i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 , where i is a natural number.

3. The method for monitoring abnormality of a suspension clamp according to claim 2, characterized in that: Based on the i-th error covariance P i and the i-th process noise covariance Q i The sum of the error covariances is calculated to calculate the initial value P of the i+1th error covariance. i+1|i The calculation formula is: P i+1|i =P i +Q i Among them, P i is the i-th error covariance, Q i is the noise covariance of the ith process.

4. The method for monitoring abnormality of a suspension clamp according to claim 2, characterized in that: Based on the initial value P of the i+1th error covariance i+1|i and the i-th observation noise covariance R i Calculate the i+1th Kalman gain K i+1 The calculation formula is: Among them, R i is the noise covariance of the ith observation, K i+1 is the i+1th Kalman gain.

5. The method for monitoring abnormality of a suspension wire clamp according to claim 2, characterized in that: Initial value X based on the i+1th vibration prediction value i+1|i 、i+1th Kalman gain K i+1 、i+1th vibration observation value Z i+1 Update the initial value X of the i+1th vibration prediction value i+1|i , get the i+1th vibration prediction value X i+1 The calculation formula is: X i+1 =X i+1|i +K i+1 ×(Z i+1 -X i+1|i ) Among them, X i+1|i is the predicted value of the i+1th vibration, X i+1|i is the initial value of the i+1th vibration prediction value, K i+1 is the i+1th Kalman gain, Z i+1 is the i+1th vibration observation value.

6. The method for monitoring abnormality of a suspension clamp according to claim 2, characterized in that: Based on the initial value P of the i+1th error covariance i+1|i and the i+1th Kalman gain K i+1 Update the initial value P of the i+1th error covariance i+1|i , and get the i+1th error covariance P i+1 The calculation formula is: P i+1 =(1-K i+1 )×P i+1|i Among them, K i+1 is the i+1th Kalman gain, P i+1|i is the initial value of the i+1th error covariance.

7. The method for monitoring abnormality of a suspension clamp according to claim 2, characterized in that: Based on the i-th observation noise covariance R i , the initial value X of the i+1th vibration prediction value i+1|i , the i-th vibration observation value Z i+1 Update the observation noise covariance with the first smoothing coefficient β to obtain the i+1th observation noise covariance R i+1 The calculation formula is: R i+1 =β×R i +(1-β)×(Z i+1 -X i+1|i ) 2 Among them, Z i+1 is the i-th vibration observation value, R i is the noise covariance of the ith observation, X i+1|i is the initial value of the i+1th vibration prediction value.

8. The method for monitoring abnormality of a suspension clamp according to claim 2, characterized in that: Based on the i-th process noise covariance Q i , the initial value X of the i+1th vibration prediction value i+1|i The process noise covariance is updated with the second smoothing coefficient γ to obtain the i+1th process noise covariance Q i+1 The calculation formula is: Q i+1 =γ×Q i +(1-γ)×X i+1|i 2 Among them, Q i is the noise covariance of the ith process, X i+1|i is the initial value of the i+1th vibration prediction value.

9. The method for monitoring abnormality of a suspension clamp according to any one of claims 1 to 8, characterized in that: The temperature data sequence is filtered using an adaptive mean filtering algorithm to obtain a temperature prediction value sequence, including: Set the window value of the sampling window; Using the initial window to start sampling from the first temperature observation value of the temperature data sequence, and calculating the average value of multiple temperature observation values ​​in the initial window as the first temperature prediction value; Determine whether the average value is greater than a threshold; If yes, then reduce the window value of the sampling window, and return to execute the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence; If not, the window value of the sampling window is increased, and the process returns to the step of using the initial window to start sampling from the first temperature observation value of the temperature data sequence.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for monitoring abnormalities of a suspension wire clamp as described in any one of claims 1-9.

Images