Real-time settlement monitoring and advanced early warning method for temperature-settlement decoupling modeling

Abstract

The invention relates to the technical field of settlement monitoring, in particular to a temperature-settlement decoupling modeling settlement real-time monitoring and advanced early warning method. The method comprises the following steps: obtaining settlement monitoring data by using a magnetostrictive static level gauge, performing abnormal value elimination processing on the settlement monitoring data, and constructing a time sequence data set according to the processed settlement monitoring data; acquiring temperature data of an internal liquid medium in the magnetostrictive hydrostatic level gauge through an intrusive temperature probe; constructing a design matrix and a response variable according to the temperature data and the processed settlement monitoring data; combining the design matrix and the response variable to obtain a regression coefficient, and correcting a settlement value influenced by the temperature according to the regression coefficient; and the future settlement trend is predicted based on the corrected settlement value, and real-time settlement monitoring and early warning are completed. The problem that the settlement measurement accuracy is affected by errors caused by temperature differences is solved, and safe and stable operation of power equipment is ensured.

Description

Technical Field

[0001] The invention relates to the technical field of settlement monitoring, and in particular to a settlement real-time monitoring and advance warning method based on temperature-sedimentation degradation coupling modeling. Background Art

[0002] The settlement of power equipment (such as transformers, transmission towers, etc.) directly affects their safe operation and stability. Settlement may cause equipment tilt, foundation cracking, and even serious accidents. Traditional settlement monitoring methods usually rely on regular manual measurements or simple sensor data collection, but these methods often cannot reflect settlement changes in real time and accurately, especially in environments with large temperature changes. The impact of temperature on sensors and settlement data cannot be ignored.

[0003] Therefore, developing a method for monitoring the settlement of power equipment based on temperature correction and settlement prediction can effectively improve the monitoring accuracy and provide early warning of potential risks, which has important engineering application value. Summary of the invention

[0004] In view of the shortcomings of existing methods and the needs of practical applications, in order to reduce the impact of temperature on sensors and settlement data in an environment with large temperature changes, solve the problem of errors caused by environmental temperature differences affecting the accuracy of settlement measurements, and improve the accuracy and reliability of settlement measurements. The present invention provides a settlement real-time monitoring and advance warning method based on temperature-sedimentation coupled modeling, comprising the following steps: A magnetostrictive static level is used to obtain settlement monitoring data, and outliers are removed from the settlement monitoring data, and a time series data set is constructed based on the processed settlement monitoring data; the temperature data of the internal liquid medium in the magnetostrictive static level is obtained through an invasive temperature probe; a design matrix and a response variable are constructed based on the temperature data and the processed settlement monitoring data; a regression coefficient is obtained by combining the design matrix and the response variable, and the settlement value affected by temperature is corrected according to the regression coefficient; future settlement trends are predicted based on the corrected settlement values, and real-time settlement monitoring and early warning are completed. The present invention solves the problem of errors caused by ambient temperature differences affecting the accuracy of settlement measurements by correcting the settlement values ​​affected by temperature by fitting regression coefficients, realizes real-time correction of settlement values ​​and prediction of future trends, improves the accuracy and reliability of settlement measurements, and is conducive to ensuring the safe and stable operation of power equipment.

[0005] Optionally, the outlier elimination process is performed on the settlement monitoring data to satisfy the following formula:

[0006] The outliers are determined by exceeding the following boundaries: Nether:

[0007] Upper bound:

[0008] in, represents the interquartile range, Represents the value of the third quartile, that is, 75% of the data in the data set is less than or equal to , Indicates that 25% of the data in the data set is less than or equal to .

[0009] Optionally, the design matrix satisfies the following formula:

[0010] in, represents the design matrix, It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the first monitoring in the same monitoring cycle. It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the second monitoring in the same monitoring cycle. Indicates the number of The temperature value of the liquid medium inside the magnetostrictive static level obtained by monitoring.

[0011] The response variable satisfies the following formula:

[0012] in, represents the response variable, It indicates the settlement value obtained from the first monitoring in the same monitoring period. It indicates the settlement value obtained from the second monitoring in the same monitoring cycle. Indicates the number of The present invention is conducive to obtaining the regression coefficient accurately and efficiently by constructing a design matrix and a response variable, thereby improving the accuracy of the present invention.

[0013] Optionally, the regression coefficient obtained by combining the design matrix and the response variable satisfies the following formula:

[0014] in, represents the regression coefficient, represents the design matrix, represents the transposed matrix of the design matrix, represents the response variable, represents the first regressor coefficient, The present invention obtains the regression coefficient by least squares fitting, and the data is objective and accurate, which further improves the accuracy of the present invention.

[0015] Optionally, the step of correcting the sedimentation value affected by temperature according to the regression coefficient comprises the following steps: According to the regression coefficient, the first sedimentation value caused by temperature is calculated; according to the first sedimentation value, the sedimentation value is corrected. The present invention obtains the sedimentation value caused by temperature through the regression coefficient and then performs data correction, thereby improving the monitoring accuracy of the present invention.

[0016] Optionally, the first sedimentation value caused by temperature is calculated based on the regression coefficient, satisfying the following formula:

[0017] in, represents the first sedimentation value, represents the design matrix, represents the regression coefficient.

[0018] Optionally, the sedimentation value is corrected according to the first sedimentation value to satisfy the following formula:

[0019] in, represents the corrected settlement value, represents the settlement value before correction, Indicates the first sedimentation value.

[0020] Optionally, predicting the future settlement trend based on the corrected settlement value to complete the real-time monitoring and early warning of settlement includes the following steps: The data transmission technology is used to transmit the settlement monitoring data and the temperature data to the remote monitoring platform; the settlement value after the correction of the temperature effect and the predicted settlement value are displayed on the remote monitoring platform in the form of a dot-line graph; the settlement threshold is set, and the future settlement value is predicted based on the corrected settlement value, and the settlement real-time monitoring and early warning are completed through the future settlement value and the settlement threshold. The present invention realizes platform monitoring through remote data transmission and improves monitoring efficiency.

[0021] Optionally, the data transmission technology includes GPRS wireless transmission technology. The present invention can accurately and timely transmit data through GPRS wireless transmission technology, thereby improving the monitoring efficiency of the present invention.

[0022] Optionally, the internal liquid medium includes antifreeze, silicone oil, or a mixture of the antifreeze and silicone oil. The present invention is applicable to a variety of internal liquid media, which is beneficial to improving the applicability of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of a method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling provided by an embodiment of the present invention; Figure 2 It is a time-sedimentation value curve diagram before eliminating the temperature effect in the embodiment of the present invention; Figure 3 It is a linear regression analysis diagram of temperature-sedimentation value in an embodiment of the present invention; Figure 4 It is a time-sedimentation value curve diagram after eliminating the temperature effect in the embodiment of the present invention; Figure 5 A framework diagram of a real-time monitoring and advance warning system for settlement based on temperature-sedimentation degradation coupling modeling provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0025] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0026] See also Figure 1 In order to improve the accuracy and reliability of settlement measurement, ensure the safe and stable operation of GIS equipment, and solve the problem of errors caused by ambient temperature differences that affect the accuracy of settlement measurement. The present invention provides a settlement real-time monitoring and advance warning method based on temperature-sedimentation coupled modeling, such as Figure 1 As shown, in one embodiment, the method includes the following steps: S1. Using a magnetostrictive static level, obtaining settlement monitoring data, removing abnormal values ​​from the settlement monitoring data, and constructing a time series data set based on the processed settlement monitoring data.

[0027] In the embodiment, the magnetostrictive static level (also known as a connected liquid level settlement meter) is a high-precision liquid level measuring instrument, which uses the magnetostrictive principle to accurately measure the position, thereby obtaining settlement monitoring data.

[0028] Furthermore, the outlier elimination process is performed on the settlement monitoring data to satisfy the following formula:

[0029] The outliers are determined by exceeding the following boundaries: Nether:

[0030] Upper bound:

[0031] in, represents the interquartile range, Represents the value of the third quartile, that is, 75% of the data in the data set is less than or equal to , Indicates that 25% of the data in the data set is less than or equal to .

[0032] Furthermore, a time series data set is constructed based on the processed settlement monitoring data, including adding a timestamp to the monitoring data, thereby constructing the time series data set.

[0033] S2. Obtaining temperature data of the internal liquid medium in the magnetostrictive static level through an invasive temperature probe.

[0034] In an embodiment, an invasive temperature probe and a temperature transmission chip are added to the existing magnetostrictive static level hardware. The invasive temperature probe is used to monitor the temperature of the liquid medium inside the static level. The temperature transmission chip is used to transmit temperature data, which is synchronously transmitted to the data acquisition device along with the settlement monitoring data through the information transmission device to obtain the temperature data of the internal liquid medium in the magnetostrictive static level.

[0035] Furthermore, the internal liquid medium includes antifreeze, silicone oil, or a mixture of the antifreeze and silicone oil.

[0036] S3. Constructing a design matrix and response variables according to the temperature data and the processed settlement monitoring data.

[0037] In an embodiment, the design matrix satisfies the following formula:

[0038] in, represents the design matrix, It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the first monitoring in the same monitoring cycle. It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the second monitoring in the same monitoring cycle. Indicates the number of The temperature value of the liquid medium inside the magnetostrictive static level obtained by monitoring.

[0039] Furthermore, the response variable satisfies the following formula:

[0040] in, represents the response variable, It indicates the settlement value obtained from the first monitoring in the same monitoring period. It indicates the settlement value obtained from the second monitoring in the same monitoring cycle. Indicates the number of The sedimentation value obtained by monitoring.

[0041] S4. Combining the design matrix and the response variable to obtain a regression coefficient, and correcting the settlement value affected by temperature according to the regression coefficient.

[0042] In an embodiment, the regression coefficient obtained by combining the design matrix and the response variable satisfies the following formula:

[0043] in, represents the regression coefficient, represents the design matrix, represents the transposed matrix of the design matrix, represents the response variable, represents the first regressor coefficient, represents the second regressor coefficient.

[0044] Furthermore, the correction of the sedimentation value affected by temperature according to the regression coefficient comprises the following steps: S41. Calculate the first sedimentation value caused by temperature according to the regression coefficient.

[0045] Specifically, the first sedimentation value caused by temperature is calculated based on the regression coefficient, satisfying the following formula:

[0046] in, represents the first sedimentation value, represents the design matrix, represents the regression coefficient.

[0047] In some other embodiments, the least squares method is used to fit the model to obtain the regression coefficients. and .

[0048]

[0049]

[0050] in, , , and The same monitoring period The settlement monitoring value and the temperature value of the liquid medium inside the static level obtained by monitoring.

[0051] Furthermore, the temperature-affected settlement value of the magnetostrictive static level at a certain monitoring time is calculated using the regression coefficient, satisfying the following formula:

[0052] Indicates the first sedimentation value, that is, the sedimentation value affected by temperature.

[0053] S42. Correct the sedimentation value according to the first sedimentation value.

[0054] Subtract the temperature-affected sedimentation value from the original sedimentation value S , and obtain the real settlement value data.

[0055] Specifically, the sedimentation value is corrected according to the first sedimentation value to satisfy the following formula:

[0056] in, represents the corrected settlement value, represents the settlement value before correction, Indicates the first sedimentation value.

[0057] S5. Predict future settlement trends based on the corrected settlement values ​​and complete real-time settlement monitoring and early warning.

[0058] Specifically, the settlement monitoring data and the temperature data are transmitted to a remote monitoring platform using data transmission technology.

[0059] Furthermore, the data transmission technology includes GPRS wireless transmission technology.

[0060] Furthermore, an LSTM deep learning model was constructed, including an input layer, an LSTM layer with 100 neurons, a fully connected layer, and a regression output layer.

[0061] Specifically, the regression output layer uses the mean square error MSE as the loss function, and the formula is as follows:

[0062] in, is the actual settlement value, is the predicted value.

[0063] In the embodiment, constructing the LSTM deep learning model includes the following steps: Input feature design: Input features include historical sedimentation values ​​and timestamps; Model structure: input layer, accepting multi-dimensional time series data; LSTM layer with 100 neurons, capturing long-term dependencies; fully connected layer, mapping LSTM output to settlement prediction value; regression output layer: outputs settlement values ​​for the next k time steps, using mean square error as loss function.

[0064] Model training: loss function, using mean square error (MSE) as the loss function; optimization algorithm, using Adam optimizer, with an initial learning rate of 0.001; data partitioning, dividing the data set into 70% training, 20% validation, and 10% testing ratios.

[0065] Dynamic correction prediction: Input the real-time temperature-corrected settlement data into the trained LSTM model to predict the future settlement trend; dynamically adjust the regression coefficient according to the deviation between the predicted value and the actual value, and satisfy the following formula: ,in, represents the adjusted regression coefficient, represents the regression coefficient before adjustment, Represents the learning rate.

[0066] Furthermore, the LSTM deep learning model was trained and verified using the time series dataset to predict the sedimentation values, and the sedimentation values ​​after correction for temperature effects and the predicted sedimentation values ​​were displayed on the remote monitoring platform in the form of a dot-line graph.

[0067] Furthermore, a settlement threshold is set, and the future settlement value is predicted based on the corrected settlement value, and the real-time settlement monitoring and early warning are completed through the future settlement value and the settlement threshold. The settlement threshold needs to be set according to the actual situation.

[0068] In one embodiment, according to the monitoring scheme, a magnetostrictive static level with an invasive temperature probe and a temperature transmission chip is used to monitor the settlement. The temperature and settlement data of the magnetostrictive static level at the measuring point 1 for 60 cycles are selected to calculate the settlement value. , , , upper bound , the lower bound , check that there are no data points in the data set that are smaller than the lower bound or larger than the upper bound.

[0069] Furthermore, a point-line graph is drawn, such as Figure 2 The collected data is corrected by the method of the present invention to obtain a fitting curve of the first sedimentation value. The fitting curve obtained by linear regression analysis of temperature-sedimentation value is as follows Figure 3 As shown, the settlement correction value of the measuring point 1 for 60 cycles is obtained by The specific data obtained by calculation are shown in Table 1. The time-sedimentation value curve after eliminating the temperature effect is shown in Figure 4 The settlement values ​​of the three cycles predicted by LSMT are: 0.1951mm, -0.0304mm, -0.0835mm, and the actual settlement values ​​of the three cycles D61, D62, and D63 are -0.08728mm, -0.0876mm, and -0.10792mm, respectively.

[0070]

[0071] Table 1 Temperature and settlement data of magnetostrictive static level at measuring point 1 for 60 cycles The invasive temperature probe and temperature transmission chip can transmit the temperature value of the liquid medium in the static level in real time while transmitting the settlement monitoring value. Further application of the proposed correction method can effectively remove the temperature influence, so as to obtain the real settlement value, significantly reduce the monitoring error, and improve the monitoring accuracy, especially in the operation stage of UHV substations in various regions of the country, for the impact of ambient temperature changes on the monitoring results, provides more reliable data support, and ensures the safe operation and stability of the substation.

[0072] See also Figure 5 In an embodiment, in order to be able to efficiently execute a method for real-time monitoring and advance warning of settlement based on temperature-sedimentation degradation coupling modeling provided by the present invention, the present invention also provides a system for real-time monitoring and advance warning of settlement based on temperature-sedimentation degradation coupling modeling, including: an input device, an output device, a processor, and a memory, wherein the input device, the output device, the processor, and the memory are interconnected, and the memory contains program instructions, and the program instructions are used for the steps of the method for real-time monitoring and advance warning of settlement based on temperature-sedimentation degradation coupling modeling. The system for real-time monitoring and advance warning of settlement based on temperature-sedimentation degradation coupling modeling of the present invention has a compact structure and stable performance, and can stably execute a method for real-time monitoring and advance warning of settlement based on temperature-sedimentation degradation coupling modeling of the present invention, further improving the overall applicability and practical application capabilities of the present invention.

[0073] In an embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. An input device may be used to obtain data information. An output device may be used to output the results obtained by storing program instructions contained in a computer program in a memory provided by the present invention. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory.

[0074] In one possible implementation, the memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, and at least one application required for a function, etc.; the data storage area may store data created during use. In addition, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0075] The embodiment also provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for real-time monitoring and advance warning of sedimentation based on the temperature-sedimentation degradation coupling modeling are implemented.

[0076] The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0077] In summary, the present invention corrects the settlement value affected by temperature by fitting the regression coefficient, solves the problem of errors caused by ambient temperature differences affecting the accuracy of settlement measurement, improves the accuracy and reliability of settlement measurement, and helps ensure the safe and stable operation of GIS equipment. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has a high industrial utilization value.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope recorded in the present invention.

Claims

1. A method for real-time monitoring and early warning of sedimentation based on temperature-sedimentation coupling modeling, characterized in that: The following steps are involved: Using a magnetostrictive static level, settlement monitoring data is obtained, outlier removal is performed on the settlement monitoring data, and a time series data set is constructed according to the processed settlement monitoring data; Obtaining temperature data of the internal liquid medium in the magnetostrictive static level by means of an invasive temperature probe; constructing a design matrix and response variables based on the temperature data and the processed settlement monitoring data; Combining the design matrix and the response variable to obtain a regression coefficient, and correcting the settlement value affected by temperature according to the regression coefficient; Based on the corrected settlement value, the future settlement trend is predicted, and real-time settlement monitoring and early warning are completed.

2. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 1 is characterized in that: The outlier elimination process of the settlement monitoring data satisfies the following formula: ， The outliers are determined by exceeding the following boundaries: Nether: , upper bound: ,in, represents the interquartile range, Represents the value of the third quartile, that is, 75% of the data in the data set is less than or equal to , Indicates that 25% of the data in the data set is less than or equal to .

3. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation coupling modeling according to claim 1 is characterized in that: The design matrix satisfies the following formula: ,in, represents the design matrix, It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the first monitoring in the same monitoring cycle. It indicates the temperature value of the liquid medium inside the magnetostrictive static level obtained by the second monitoring in the same monitoring cycle. Indicates the number of The temperature value of the liquid medium inside the magnetostrictive static level obtained by monitoring; The response variable satisfies the following formula: ,in, represents the response variable, It indicates the settlement value obtained from the first monitoring in the same monitoring period. It indicates the settlement value obtained from the second monitoring in the same monitoring cycle. Indicates the number of The sedimentation value obtained by monitoring.

4. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 1 is characterized in that: The regression coefficient obtained by combining the design matrix and the response variable satisfies the following formula: ,in, represents the regression coefficient, represents the design matrix, represents the transposed matrix of the design matrix, represents the response variable, represents the first regressor coefficient, represents the second regressor coefficient.

5. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation coupling modeling according to claim 1 is characterized in that: The method of correcting the sedimentation value affected by temperature according to the regression coefficient comprises the following steps: Calculating the first sedimentation value caused by temperature according to the regression coefficient; The sedimentation value is corrected according to the first sedimentation value.

6. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 5 is characterized in that: The first settlement value caused by temperature is calculated based on the regression coefficient, satisfying the following formula: ,in, represents the first sedimentation value, represents the design matrix, represents the regression coefficient.

7. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation coupling modeling according to claim 5 is characterized in that: The sedimentation value is corrected according to the first sedimentation value to satisfy the following formula: ,in, represents the corrected settlement value, represents the settlement value before correction, Indicates the first sedimentation value.

8. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 1 is characterized in that: The method of predicting the future settlement trend based on the corrected settlement value and completing the real-time monitoring and early warning of settlement includes the following steps: Using data transmission technology, the settlement monitoring data and the temperature data are transmitted to a remote monitoring platform; The settlement value after correction of temperature influence and the predicted settlement value are displayed on the remote monitoring platform in the form of a point-line graph; A settlement threshold is set, and future settlement values ​​are predicted based on the corrected settlement values. Real-time settlement monitoring and early warning are completed through the future settlement values ​​and the settlement threshold.

9. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 8 is characterized in that: The data transmission technology includes GPRS wireless transmission technology.

10. The method for real-time monitoring and advance warning of sedimentation based on temperature-sedimentation degradation coupling modeling according to claim 1 is characterized in that: The internal liquid medium includes antifreeze liquid, silicone oil or a mixture of the antifreeze liquid and the silicone oil.

Images