A Temperature Monitoring Method and System for a Vertical Buried Pipe Ground Source Heat Pump

Abstract

The present invention provides a temperature monitoring method and system for a vertical buried pipe ground source heat pump, belonging to the technical field of temperature measurement. The method and system of the present invention first collect original temperature data through a distributed optical fiber sensor and construct a temperature fluctuation matrix, then perform time-domain decomposition to obtain temperature fluctuation characteristic quantities, calculate temperature anomaly parameters based on this and construct a temperature anomaly matrix. The temperature anomaly matrix is input into a pre-trained temperature error prediction model to obtain an error prediction value, and a temperature compensation matrix is generated accordingly. Subsequently, a three-level compensation strategy is adopted to achieve primary compensation, secondary compensation, and final correction of temperature data in sequence. The pre-trained model constructs training data through a conditional generative adversarial network embedded with physical equations, ensuring the reliability of the compensation effect. It solves the technical problem in the prior art that the temperature field distribution around the vertical buried pipe of the ground source heat pump is difficult to accurately measure, resulting in poor temperature error compensation effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of temperature measurement, and more particularly, relates to a temperature monitoring method and system for a vertical buried pipe ground source heat pump. Background Art

[0002] The ground source heat pump system is an energy-efficient technology that utilizes shallow geothermal energy in the ground. Among them, the vertical buried pipe heat exchange system is the most commonly used underground heat exchange method. In practical applications, accurately measuring and monitoring the temperature field distribution around the vertical buried pipes is of great significance for evaluating system performance, optimizing operating parameters, and predicting system life. Traditional temperature monitoring methods mainly rely on arranging discrete temperature sensors around the vertical buried pipes to obtain temperature distribution information through multi-point temperature measurement. With the development of distributed optical fiber sensing technology, which has the advantages of high spatial resolution, continuous measurement, and electromagnetic interference resistance, it has gradually become the main means for monitoring the temperature field of vertical buried pipes.

[0003] However, the existing temperature monitoring technologies still face many challenges in practical applications. First, the underground environment is complex, and various factors such as soil properties, groundwater flow, and environmental temperature changes jointly affect the temperature field distribution. The coupling effect of these factors leads to large errors in temperature measurement. Second, due to the depth distribution characteristics of the underground temperature field, traditional temperature compensation methods are difficult to obtain sufficient calibration data, and the training data for the compensation model is severely insufficient. Third, the existing temperature error compensation methods are mostly based on simplified models and do not fully consider the dynamic change characteristics of the underground environment, resulting in limited compensation effects. In addition, the uncertainty of groundwater flow and the non-linear variation of soil thermal physical parameters pose severe challenges to the accuracy of temperature field measurement.

[0004] Currently, the main technical means to solve the above problems include optimizing the sensor layout scheme, improving the signal processing algorithm, and establishing a temperature compensation model, etc. However, these methods often only focus on the influence of a single factor and lack a systematic consideration of the multi-factor coupling effect in the underground environment. At the same time, due to the difficulty of large-scale field measurement of the underground temperature field, the existing training data for the compensation model is severely insufficient, and the generalization ability of the model is limited. Therefore, how to accurately measure and effectively compensate the temperature field around the vertical buried pipes under the condition of data scarcity has become a key technical problem to be solved urgently. That is to say, there is a technical problem in the prior art that the temperature field distribution around the vertical buried pipes of the ground source heat pump is difficult to accurately measure, resulting in poor temperature error compensation effect. Summary of the Invention

[0005] In view of this, the present invention provides a temperature monitoring method and system for a vertical buried pipe ground source heat pump, which can solve the technical problem in the prior art that the temperature field distribution around the vertical buried pipes of the ground source heat pump is difficult to accurately measure, resulting in poor temperature error compensation effect.

[0006] The present invention is implemented as follows: In a first aspect of the present invention, a temperature monitoring method for a vertical buried tube ground source heat pump is provided. Raw temperature data sequences of multiple measurement points are collected through a distributed optical fiber sensor to construct a temperature fluctuation matrix. The temperature fluctuation matrix is decomposed in the time domain to extract the fluctuation amplitude, fluctuation frequency, and fluctuation phase of the temperature data, and temperature fluctuation characteristic quantities are obtained. Based on the temperature fluctuation characteristic quantities, the raw temperature data is normalized to generate a standardized temperature data sequence. A temperature anomaly parameter is calculated according to the standardized temperature data sequence to construct a temperature anomaly matrix. The temperature anomaly matrix is input into a pre-trained temperature error prediction model to obtain a temperature error prediction value. A mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix is established to generate a temperature compensation matrix. The temperature compensation matrix is used to perform primary compensation on the real-time collected temperature data to obtain primary corrected temperature data. The steady-state deviation value between the primary corrected temperature data and the historical calibration data is calculated. A temperature correction model is established according to the steady-state deviation value. The temperature correction model is used to perform secondary compensation on the primary corrected temperature data to obtain secondary corrected temperature data. A system dynamic response parameter is calculated. The secondary corrected temperature data is finally corrected by using the system dynamic response parameter, and the corrected temperature data is output. It is characterized in that the pre-trained temperature error prediction model adopts a deep convolutional neural network structure, and the deep convolutional neural network structure is composed of a feature extraction network layer, a feature fusion network layer, and a prediction network layer. The temperature correction model includes a temperature offset compensation term and a reference point correction term. The system dynamic response parameters include a temperature response time, a temperature maximum time, and a temperature adjustment time.

[0007] Among them, the feature extraction network layer adopts a four-layer convolutional layer structure. The number of convolutional kernels in each convolutional layer is 32, 64, 128, and 256 respectively. The convolutional kernel size is 3×3, the stride is 1, and each convolution is followed by a normalization network layer and an activation function layer. The feature fusion network layer adopts a fully connected layer structure with 1024 neurons. The prediction network layer adopts a linear output layer with an output dimension equal to the number of measurement points.

[0008] Among them, the training data set of the pre-trained temperature error prediction model constructs virtual training data of the underground temperature distribution through a conditional generative adversarial network. The conditional generative adversarial network includes a generative network and a discriminative network. The generative network is embedded with a temperature generation equation set to simulate the distribution law of the underground temperature field.

[0009] Among them, the temperature generation equation set includes a heat conduction equation, a water flow influence equation, and a thermal conductivity equation. The heat conduction equation is used to describe the heat conduction process in the soil around the vertical buried pipe. The water flow influence equation is used to simulate the influence of groundwater flow on the temperature field. The thermal conductivity equation is used to calculate the soil thermal conductivity under different depths and different water contents.

[0010] Among them, in the process of performing primary compensation using the temperature compensation matrix, the compensation coefficient includes a correction weight and an offset. The value range of the correction weight is from 0 to 1, and the value range of the offset is plus or minus 5 degrees Celsius. The sliding time window method is used to calculate the steady-state deviation value between the primary corrected temperature data and the historical calibration data. The size of the time window is set to 1 hour, and the window sliding step is 10 minutes.

[0011] Among them, the temperature offset compensation term is calculated using the exponential smoothing method, and the smoothing coefficient is taken as 0.3. The reference point correction term is calculated using the piecewise linear interpolation method, and 5 reference points are evenly selected within the measurement range.

[0012] Among them, the temperature response time is defined as the time required for the temperature change to reach 63.2% of the final steady-state value. The temperature adjustment time is defined as the time required for the temperature to enter the steady-state interval. The range of the steady-state interval is plus or minus 2% of the final steady-state value.

[0013] Among them, the local outlier factor algorithm is used to detect the abnormality degree of the temperature data. The size of the local neighborhood is taken as 10% of the total number of measurement points, and the measurement points with a local outlier factor greater than 2 are marked as abnormal points.

[0014] Among them, the empirical mode decomposition method is used to decompose the temperature fluctuation matrix. The obtained intrinsic mode function sequence is subjected to Hilbert transform to calculate the instantaneous frequency and instantaneous amplitude, and the fluctuation amplitude, fluctuation frequency, and fluctuation phase corresponding to the main frequency components are extracted.

[0015] The second aspect of the present invention provides a temperature monitoring system for a vertical buried pipe ground source heat pump, which has a box body. A vertical plate is fixedly installed at the top of the box body. A gear is rotatably installed at one end of the vertical plate. Tooth plates are movably installed at both ends of the vertical plate. The tooth plates are meshed with the outer surface of the gear. Connecting rods are respectively fixedly installed on the tooth plates. A movable door is fixedly installed at one end of the connecting rod. The movable door includes a left movable door and a right movable door. A roller and a rotating shaft are rotatably installed at the other end of the vertical plate. A belt is movably sleeved on the outer surfaces of the roller and the rotating shaft. One end of the roller penetrates through the vertical plate and is fixedly connected with one end of the gear. A round shaft is fixedly installed at one end of the rotating shaft. A protective box is fixedly installed at one end of the vertical plate. A motor is fixedly installed at one end of the protective box, and the output end of the motor penetrates through the protective box and is fixedly connected with one end of the round shaft.

[0016] Among them, a fixed rod is fixedly installed at one end of the box body. A strip-shaped groove is opened at the top of the fixed rod. A round rod is fixedly installed inside the strip-shaped groove. Both sides of the surface of the round rod are movably sleeved with moving blocks, and the top of the moving block is fixedly connected to the bottom of the movable door.

[0017] Among them, a card slot is opened on one side of the left movable door, a clamping plate is fixedly installed on one side of the right movable door, and the card slot is adapted to the clamping plate.

[0018] Among them, sensing optical fibers are fixedly installed at equal intervals at the bottom of the box body. The top of the sensing optical fiber penetrates the box body and extends to the inner surface of the box body, and sleeve rods are movably sleeved on the surfaces of the sensing optical fibers.

[0019] Among them, sliding grooves are opened at both ends of the bottom of the sleeve rod. Cylinders are fixedly installed inside the sliding grooves. Sliding blocks are movably sleeved on the surfaces of the cylinders. Springs are fixedly installed between the sliding blocks and the sliding grooves. The inner surface of the spring is movably connected to the outer surface of the cylinder, and sealing rods are fixedly installed at the bottoms of the sliding blocks.

[0020] Among them, limiting grooves are opened at both ends of the top of the sleeve rod. Moving rods are movably installed inside the limiting grooves. The bottom of the moving rod is fixedly connected to the top of the sliding block, and clamping rings are fixedly installed at the tops of the moving rods.

[0021] Among them, a temperature detection module and a data processing module are fixedly installed at one end inside the box body, and a data transmission module and a power supply module are fixedly installed at one end inside the box body on the right side of the temperature detection module and the data processing module.

[0022] Among them, a mounting plate is fixedly installed on the top of the box body, and mounting holes are opened at both ends of the mounting plate.

[0023] Among them, heat dissipation grooves are opened at equal intervals on both sides of the box body, and the sizes of the heat dissipation grooves are the same.

[0024] Among them, a display screen is fixedly installed at one end of the left movable door, and a PLC controller is fixedly installed at one end of the right movable door.

[0025] Among them, the data processing module uses a single-chip microcomputer. A storage medium is arranged inside the data processing module. Program codes are stored in the storage medium. When the single-chip microcomputer executes the program codes, it is used to execute the above-mentioned temperature monitoring method for the vertical buried pipe ground source heat pump.

[0026] During the daily use of the system, the operator starts the motor. The operation of the motor causes the circular shaft to rotate, and then the circular shaft drives the rotating shaft to rotate. Subsequently, the rotating shaft drives the belt to rotate, and then the belt drives the roller to rotate. At this time, the roller drives the gear to rotate, and then the gear drives the toothed plate to slide. Subsequently, the toothed plate drives the connecting rod to slide, and at the same time, the connecting rod drives the movable door to move towards each other. Then, the movable door slides on the inner surface of the strip-shaped groove and the surface of the round rod until the clamping plate is placed inside the clamping groove, and the box can be automatically closed. Conversely, it can be opened, which facilitates the maintenance of multiple modules inside the box.

[0027] During the daily use of the system, when the sensing optical fiber is connected to the vertically buried pipe, the sealing rod is pulled. When the sealing rod slides, it drives the slider to slide on the inner surface of the sliding groove and the surface of the cylinder. Subsequently, the slider squeezes and compresses the spring. At this time, the slider drives the moving rod to slide inside the limiting groove. Then, the moving rod drives the clamping ring to slide. Subsequently, the sliding sleeve rod is adjusted until the sealing rod is placed at the connection between the sensing optical fiber and the vertically buried pipe. At the same time, the sealing rod is released, and then the clamping ring clamps and fixes the sensing optical fiber. Subsequently, the connection between the sensing optical fiber and the vertically buried pipe can be assisted and fixed by the sealing rod to make the connection more tight.

[0028] Compared with the prior art, a temperature monitoring method and system for a vertical buried pipe ground source heat pump provided by the present invention realizes the generation of virtual data of the underground temperature field distribution by constructing a conditional generative adversarial network based on a physical model, and innovatively solves the problem of lack of training data. This method integrates physical processes such as the basic principle of heat conduction, the influence of groundwater flow, and the change of soil thermal conductivity characteristics into the generative network to ensure the physical rationality of the generated data. At the same time, through the adversarial training of the discriminative network, the quality of the generated data is continuously optimized, and the reliability of the virtual training data is improved.

[0029] On this basis, the present invention designs a multi-level temperature error compensation strategy. First, the spatio-temporal change characteristics of the temperature field are captured through the temperature fluctuation matrix, and a temperature anomaly detection mechanism is established. Secondly, the precise prediction of the temperature error is realized by using a pre-trained deep convolutional neural network model. Thirdly, by establishing the mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix, a dynamic temperature compensation matrix is generated. Finally, a multi-level compensation strategy is adopted to realize the steady-state error compensation, dynamic error correction, and system response characteristic compensation of the temperature data in sequence, significantly improving the accuracy of temperature measurement.

[0030] The present invention effectively solves the technical problem in the prior art that it is difficult to accurately measure the temperature field distribution around the vertical buried pipe of the ground source heat pump, resulting in poor temperature error compensation effect. By combining the physical model with the deep learning method, it not only ensures the physical interpretability of the model but also improves the reliability of the compensation effect. At the same time, it innovatively uses the conditional generative adversarial network to construct training data, overcomes the limitation of the lack of measured data in the underground environment, and provides a new technical approach for improving the measurement accuracy of the temperature field. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is the front view of the present invention;

[0032] Figure 2 is the vertical plate cross-sectional view of the present invention;

[0033] Figure 3 is the front cross-sectional view of the present invention;

[0034] Figure 4 is the side cross-sectional view of the present invention;

[0035] Figure 5 is of the present invention Figure 4 partial enlarged view at A in;

[0036] Figure 6 is of the present invention Figure 4 partial enlarged view at B in;

[0037] Figure 7 is the schematic diagram of the internal structure of the box of the present invention;

[0038] Figure 8 is of the present invention Figure 7 partial enlarged view at C in;

[0039] Figure 9 is the schematic diagram of the top structure of the box of the present invention;

[0040] Figure 10 is the schematic diagram of the bottom structure of the box of the present invention.

[0041] Figure 11 is the flowchart of the method of the present invention.

[0042] In the attached drawings: 1. Box body; 2. Vertical plate; 3. Gear; 4. Tooth plate; 5. Connecting rod; 61. Left movable door; 62. Right movable door; 7. Roller; 8. Rotating shaft; 9. Belt; 10. Round shaft; 11. Protection box; 12. Motor; 13. Fixed rod; 14. Strip-shaped groove; 15. Round rod; 16. Moving block; 17. Card slot; 18. Card plate; 19. Sensing optical fiber; 20. Sleeve rod; 21. Slide groove; 22. Cylinder; 23. Slide block; 24. Spring; 25. Sealing rod; 26. Limit groove; 27. Moving rod; 28. Snap ring; 29. Temperature detection module; 30. Data processing module; 31. Data transmission module; 32. Power supply module; 33. Mounting plate; 34. Mounting hole; 35. Heat dissipation groove; 36. Display screen; 37. PLC controller. Detailed implementation mode

[0043] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0044] As Figure 11 shown, it is a flowchart of a temperature monitoring method for a vertical buried pipe ground source heat pump provided by the present invention. This method includes the following steps:

[0045] S01. Collect the original temperature data sequences of multiple measuring points at preset time intervals through a distributed optical fiber sensor, and construct a temperature fluctuation matrix according to the trend of temperature values changing with time in the original temperature data sequences;

[0046] S02. Perform time-domain decomposition on the temperature fluctuation matrix, extract the fluctuation amplitude, fluctuation frequency and fluctuation phase of the temperature data, and obtain temperature fluctuation characteristic quantities;

[0047] S03. Perform data normalization processing on the original temperature data based on the temperature fluctuation characteristic quantities to generate a standardized temperature data sequence;

[0048] S04. Calculate temperature anomaly parameters according to the standardized temperature data sequence, and construct a temperature anomaly matrix according to the corresponding relationship between the temperature anomaly parameters in time series and spatial positions;

[0049] S05. Input the temperature anomaly matrix into a pre-trained temperature error prediction model to obtain a temperature error prediction value;

[0050] S06. Establish a mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix according to the temperature error prediction value to generate a temperature compensation matrix;

[0051] S07. Perform primary compensation on the real-time collected temperature data using the compensation coefficients at the corresponding positions in the temperature compensation matrix to obtain the primary corrected temperature data;

[0052] S08. Calculate the steady-state deviation value between the primary corrected temperature data and the historical calibration data;

[0053] S09. Establish a temperature correction model based on the steady-state deviation value. The temperature correction model includes a temperature offset compensation term and a reference point correction term;

[0054] S10. Perform secondary compensation on the primary corrected temperature data using the temperature correction model to obtain the secondary corrected temperature data;

[0055] S11. Calculate the system dynamic response parameters based on the secondary corrected temperature data, including the temperature response time, the temperature maximum time, and the temperature adjustment time;

[0056] S12. Perform final correction on the secondary corrected temperature data using the system dynamic response parameters and output the corrected temperature data;

[0057] The pre-trained temperature error prediction model adopts a deep convolutional neural network structure. The deep convolutional neural network structure consists of a feature extraction network layer, a feature fusion network layer, and a prediction network layer. The feature extraction network layer adopts a four-layer convolutional layer structure. The number of convolutional kernels in each convolutional layer is 32, 64, 128, and 256 respectively. The size of the convolutional kernel is 3×3, and the stride is 1. After each convolution, a normalization network layer and an activation function layer are connected. The feature fusion network layer adopts a fully connected layer structure with 1024 neurons. The prediction network layer adopts a linear output layer, and the output dimension is the number of measurement points;

[0058] The training dataset establishment step of the pre-trained temperature error prediction model is to construct virtual training data of the underground temperature distribution through a conditional generative adversarial network. The conditional generative adversarial network includes a generative network and a discriminative network. The generative network is embedded with a temperature generation equation set to simulate the distribution law of the underground temperature field;

[0059] The temperature generation equation set includes:

[0060] The heat conduction equation is used to describe the heat conduction process in the soil around the vertical buried pipe. The inputs include the soil thermal conductivity, the soil mass density, the soil specific heat at constant pressure, the initial soil temperature distribution, and the soil boundary temperature. The output is the temperature field distribution values at different depth positions in the vertical direction. The soil thermal conductivity, the soil mass density, and the soil specific heat at constant pressure are obtained through soil sample experiments. The initial soil temperature distribution and the soil boundary temperature are measured through temperature sensors;

[0061] The water flow influence equation is used to simulate the influence of groundwater flow on the temperature field. The inputs include groundwater flow velocity, groundwater temperature, soil permeability, soil porosity, and water flow angle, and the output is the corrected temperature field value considering groundwater convective heat transfer. The groundwater flow velocity and the groundwater temperature are obtained through groundwater monitoring equipment, the soil permeability and the soil porosity are obtained through soil permeability experiments, and the water flow angle is obtained through a water flow detector;

[0062] The thermal conductivity equation is used to calculate the soil thermal conductivity under different depths and different water contents. The inputs include soil apparent density, soil water content, soil mineral mass ratio, soil organic matter mass ratio, and soil temperature value, and the output is the soil thermal conductivity value at the corresponding position. The soil apparent density, the soil water content, the soil mineral mass ratio, and the soil organic matter mass ratio are obtained through soil composition experiments, and the soil temperature value is measured through a temperature sensor;

[0063] Among them, the temperature fluctuation matrix refers to a multi-dimensional data matrix formed by arranging the collected temperature data according to the corresponding relationship between time series and spatial position;

[0064] The temperature anomaly matrix refers to a characteristic representation matrix obtained by performing anomaly detection on temperature data, which is used to represent the deviation degree of temperature data;

[0065] The temperature compensation matrix refers to a calibration coefficient matrix used to correct temperature measurement errors, which includes temperature compensation coefficients and correction weight coefficients.

[0066] The following describes the specific implementation manners of the above steps in detail.

[0067] The specific implementation manner of step S01 is to collect temperature data through a distributed optical fiber sensor and construct a temperature fluctuation matrix. First, a distributed Brillouin scattering optical fiber temperature measurement system is selected as the data collection device. The optical fiber sensor is spirally wound and installed along the surface of the vertical buried pipe. The measurement point spacing is set to 0.5 meters, the sampling frequency is set to 1 Hz, and the continuous collection duration is not less than 24 hours. The collected original temperature data includes time stamps, spatial position coordinates, and corresponding temperature values. The original data is preprocessed, including outlier removal, data smoothing, and time synchronization. The outlier removal uses the three-standard-deviation principle, and the sliding average method is used for data smoothing. The time window size is set to 60 seconds. Subsequently, the preprocessed temperature data is used to construct a temperature fluctuation matrix according to the time series and depth positions. The rows of the matrix represent different moments, and the columns represent the measurement point positions at different depths. The purpose of this step is to obtain an accurate and reliable original temperature data sequence to provide a data basis for subsequent analysis.

[0068] The specific implementation of step S02 is to perform time-domain decomposition on the temperature fluctuation matrix to extract characteristic quantities. The empirical mode decomposition method is used to decompose the temperature fluctuation matrix. First, the local maximum and minimum points of the temperature data are determined, and the upper and lower envelopes are obtained through cubic spline interpolation, and the mean envelope is calculated. The original data is subtracted from the mean envelope to obtain the first intrinsic mode function, and the above process is repeated until the remaining signal becomes a monotonic function. The Hilbert transform is performed on the obtained sequence of intrinsic mode functions to calculate the instantaneous frequency and instantaneous amplitude, and the fluctuation amplitude, fluctuation frequency, and fluctuation phase corresponding to the main frequency components are extracted. The fluctuation amplitude characterizes the severity of temperature changes, the fluctuation frequency reflects the speed of temperature changes, and the fluctuation phase reflects the lead or lag relationship of temperature changes. Through time-domain decomposition, complex temperature fluctuation signals can be decomposed into several components with obvious characteristics, which is conducive to in-depth analysis of temperature change laws.

[0069] The specific implementation of step S03 is to perform data normalization based on the temperature fluctuation characteristic quantities. First, the mean and standard deviation of the fluctuation amplitude are calculated, and the amplitude data is standardized to a zero-mean unit-variance distribution. The minimum-maximum normalization is performed on the fluctuation frequency to map the frequency data to the interval from 0 to 1. The periodic normalization is performed on the fluctuation phase to convert the phase angle to the range from -π to π. Then, the original temperature data is weighted and normalized according to the standardized characteristic quantities, and the weight coefficient is determined by the proportion of temperature fluctuation energy. The greater the fluctuation energy of a characteristic quantity, the greater its weight. Finally, a standardized temperature data sequence is obtained, which eliminates the scale difference between different measuring points and makes the data comparable. The role of this step is to convert temperature data with different dimensions to a unified scale space for subsequent analysis and modeling.

[0070] The specific implementation of step S04 is to calculate temperature anomaly parameters to construct a temperature anomaly matrix. The local outlier factor algorithm is used to detect the anomaly degree of temperature data. First, the size of the local neighborhood is determined, which is 10% of the total number of measuring points. The distance between each measuring point and its neighborhood points is calculated, and the Euclidean distance is selected as the distance metric. The local reachability density of each measuring point is statistically calculated, and the ratio of the local reachability density of each measuring point to that of its neighborhood points is used to obtain the local outlier factor. The measuring points with a local outlier factor greater than 2 are marked as outlier points, and the anomaly degree is represented by the outlier factor value. Then, the outlier factors are used to construct a temperature anomaly matrix according to the correspondence relationship between the time series and the spatial position. The larger the value in the matrix, the higher the anomaly degree of the temperature data at that position. The purpose of this step is to identify the anomaly patterns in temperature data and provide a basis for subsequent error prediction.

[0071] The specific implementation of step S05 is to predict the temperature error using a pre-trained deep convolutional neural network. This network consists of three functional network layers: feature extraction, feature fusion, and prediction. The feature extraction network adopts a four-layer convolutional structure, and the activation function selects the rectified linear unit function. In the feature extraction network, the first layer has 32 convolutional kernels of size 3×3 to extract local temperature change features; the second layer has 64 convolutional kernels of size 3×3 to extract temperature gradient features; the third layer has 128 convolutional kernels of size 3×3 to extract temperature curvature features; the fourth layer has 256 convolutional kernels of size 3×3 to extract high-order temperature features. The feature fusion network uses a fully connected layer with 1024 neurons to combine multi-scale features. The prediction network uses a linear output layer, and the output dimension is the same as the number of measurement points. This step predicts the temperature measurement error through deep learning methods, providing a benchmark for temperature data correction.

[0072] The specific implementation of step S06 is to establish the mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix. The mapping model is constructed using the multiple regression analysis method, with the independent variable being the temperature fluctuation feature quantity and the dependent variable being the temperature anomaly parameter. First, feature selection is performed by calculating the correlation coefficient between the feature quantity and the anomaly parameter, and the feature quantity with an absolute value of the correlation coefficient greater than 0.3 is selected as the effective feature. Then, a multiple linear regression equation is established, and the regression coefficients are estimated using the least squares method. A significance test is performed on the regression equation. If the P-value is less than 0.05, it indicates that the regression relationship is significant. Finally, a temperature compensation matrix is generated based on the regression coefficients, and the values in the matrix represent the temperature compensation coefficients at the corresponding positions. The role of this step is to quantify the relationship between temperature fluctuation and temperature anomaly, providing a basis for temperature data correction.

[0073] The specific implementation of step S07 is to perform primary compensation using the temperature compensation matrix. When collecting temperature data in real time, first obtain the compensation coefficient at the corresponding position of the current measurement point in the temperature compensation matrix. The compensation coefficient includes two parts: the correction weight and the offset. The real-time temperature data is linearly corrected, and the correction formula is the original temperature value plus the offset multiplied by the correction weight. The value range of the correction weight is from 0 to 1, and the value range of the offset is plus or minus 5 degrees Celsius. Different compensation coefficients are used for measurement points at different depths. The correction weight of the shallow measurement points is larger, and the correction weight of the deep measurement points is smaller. The compensated temperature data is called the primary corrected temperature data, which eliminates the systematic error in temperature measurement. The role of this step is to preliminarily correct the temperature data through the compensation matrix, improving the accuracy of temperature measurement.

[0074] The specific implementation of step S08 is to calculate the steady-state deviation value between the primary corrected temperature data and the historical calibration data. First, a historical calibration database is established, which contains standard temperature values under different working conditions. The standard temperature values are obtained by calibrating with high-precision temperature sensors. The primary corrected temperature data is matched with the historical calibration data, and the data under the same working conditions is selected for comparison. The sliding time window method is used to calculate the steady-state deviation value. The size of the time window is set to 1 hour, and the window sliding step is 10 minutes. Within each time window, the root mean square error between the corrected temperature data and the calibration data is calculated as the steady-state deviation value. The purpose of this step is to evaluate the systematic deviation between the temperature data after primary correction and the standard value, providing a basis for secondary compensation.

[0075] The specific implementation of step S09 is to establish a temperature correction model. This model consists of two parts: a temperature offset compensation term and a reference point correction term. The temperature offset compensation term is used to correct the zero drift of temperature measurement, and the reference point correction term is used to correct the linearity error of temperature measurement. The temperature offset compensation term is calculated using the exponential smoothing method, and the smoothing coefficient is set to 0.3, considering the cumulative effect of temperature drift. The reference point correction term is calculated using the piecewise linear interpolation method. Five reference points are evenly selected within the measurement range, and the reference point temperature values are determined through on-site calibration. For any measurement point, the reference point interval where it is located is determined according to its temperature value, and the correction coefficient is calculated using linear interpolation. The temperature correction model established in this step can effectively compensate for the non-linear error in temperature measurement.

[0076] The specific implementation of step S10 is to perform secondary compensation using the temperature correction model. First, the offset of the primary corrected temperature data is calculated, and the zero-point correction result is obtained by subtracting the offset compensation value from the temperature data. Then, the reference point interval where the temperature value is located is determined, and the linear correction coefficient within this interval is calculated. The zero-point correction result is multiplied by the linear correction coefficient to obtain the secondary corrected temperature data. Secondary correction takes into account the non-linear characteristics of temperature measurement and can more accurately reflect the actual temperature value. The role of this step is to further improve the accuracy of temperature measurement and make the corrected temperature data closer to the true value.

[0077] The specific implementation of step S11 is to calculate the system dynamic response parameters. The temperature response time is defined as the time required for the temperature change to reach 63.2% of the final steady-state value, which is calculated by performing exponential fitting on the secondary corrected temperature data. The temperature maximum time is the moment when the temperature reaches the peak, which is determined by finding the local maximum of the temperature data. The temperature regulation time is defined as the time required for the temperature to enter the steady-state interval. The range of the steady-state interval is plus or minus 2% of the final steady-state value, which is determined by judging the temperature fluctuation amplitude. These dynamic response parameters reflect the dynamic characteristics of the temperature measurement system and can be used to evaluate the control performance of the system.

[0078] The specific implementation of step S12 is to make a final correction according to the system dynamic response parameters. First, a dynamic compensation model is established. The inputs of the model are the temperature response time, the temperature maximum time, and the temperature regulation time, and the output is the dynamic correction coefficient. The fuzzy control method is used to design the dynamic compensation rules, and the correction coefficient is adjusted according to the magnitude of the dynamic response parameters. When the response time is long, the correction coefficient is increased to accelerate the response speed; when the regulation time is long, the correction coefficient is decreased to suppress the temperature fluctuation. The secondary corrected temperature data is multiplied by the dynamic correction coefficient to obtain the final correction result. The purpose of this step is to optimize the dynamic characteristics of temperature measurement and improve the control accuracy of the system. The finally corrected temperature data has high accuracy and good dynamic characteristics, and reliably reflects the temperature distribution around the vertical buried pipe.

[0079] The calculation process involved in the present invention is described in detail as follows.

[0080] 1. The construction process of the temperature fluctuation matrix is specifically expressed as follows:

[0081] ;

[0082] In the formula, is the temperature fluctuation matrix; represents the temperature value of the th moment at the th measuring point; is the number of sampling time points; is the number of measuring points.

[0083] Calculation process of matrix elements:

[0084] ;

[0085] In the formula, is the reference temperature value, obtained through on-site calibration; is the temperature fluctuation amount, obtained by measurement; is the measurement error, obeying the normal distribution . The construction steps of the temperature fluctuation matrix are as follows: First, preprocess the temperature measurement data, including outlier removal and data smoothing; then arrange the processed data in time series and spatial position; finally, form a -dimensional matrix. This matrix can reflect the spatio-temporal distribution characteristics of the temperature field.

[0086] 2. The mathematical expression of the empirical mode decomposition process is as follows:

[0087] ;

[0088] In the formula, is the original temperature signal; is the Intrinsic mode functions; is the residual signal; is the decomposition level.

[0089] The extraction process of the intrinsic mode function is as follows:

[0090] ;

[0091] ;

[0092] In the formula, is the signal obtained by the th screening; is the mean of the upper and lower envelope lines. The screening termination condition is:

[0093] ;

[0094] In the formula, is the standard deviation; is the threshold, and the value is 0.2. This method can adaptively decompose non - linear and non - stationary signals.

[0095] 3. The calculation process of the Hilbert transform is as follows:

[0096] ;

[0097] ;

[0098] In the formula, is the Hilbert transform; is the analytic signal; is the instantaneous amplitude; is the instantaneous phase; is the imaginary unit.

[0099] 4. The calculation formula for data normalization is as follows:

[0100] ;

[0101] In the formula, is the normalized data; is the original data; is the mean; is the standard deviation.

[0102] 5. The formula for the local outlier factor is as follows:

[0103] ;

[0104] ;

[0105] In the formula, is the point Local reachability density; For point of k-nearest neighbor set; is the reachable distance; is the local outlier factor.

[0106] 6. The expression of the heat conduction equation is as follows:

[0107] ;

[0108] In the formula, is the soil density, with the unit of kg / m³; is the specific heat capacity, with the unit of J / (kg·K); is the temperature, with the unit of K; is the time, with the unit of s; is the thermal conductivity, with the unit of W / (m·K); is the heat source term, with the unit of W / m³.

[0109] 7. The expression of the water flow influence equation is as follows:

[0110] ;

[0111] In the formula, is the water flow velocity component, with the unit of m / s; is the temperature diffusion coefficient, with the unit of m² / s.

[0112] 8. The expression of the thermal conductivity equation is as follows:

[0113] ;

[0114] In the formula, is the dry soil thermal conductivity, with the unit of W / (m·K); is the moisture content; is the water density; is the specific heat capacity of water; is the volumetric moisture content; is the saturated moisture content; is the empirical coefficient, with the value range of 0.5 - 0.8; is the thermal conductivity enhancement coefficient.

[0115] 9. The calculation formula of the temperature compensation coefficient is as follows:

[0116] ;

[0117] In the formula, is the compensation coefficient; is the reference compensation coefficient; is the temperature coefficient; is the temperature deviation.

[0118] 10. The exponential smoothing calculation formula is as follows:

[0119] ;

[0120] In the formula, is the smoothed value at time is the observed value at time is the smoothing coefficient, with a value of 0.3.

[0121] 11. The expression of the dynamic compensation model is as follows:

[0122] ;

[0123] In the formula, is the dynamic correction coefficient; is the temperature response time; is the temperature maximum time; is the temperature regulation time; is the corresponding reference time value; is the weight coefficient, and satisfies .

[0124] 12. The expression of the temperature correction model is as follows:

[0125] ;

[0126] In the formula, is the corrected temperature value; is the measured temperature value; is the offset compensation coefficient; is the temperature offset; is the reference point correction coefficient; is the reference point temperature value.

[0127] Among them, the offset compensation term:

[0128] ;

[0129] In the formula, is the initial compensation coefficient; is the attenuation coefficient. The reference point correction term:

[0130] ;

[0131] In the formula, is the correction coefficient, obtained by least squares fitting. This model takes into account the non-linear characteristics of temperature measurement and the time drift effect.

[0132] 13. The formula for the steady-state deviation value is as follows:

[0133] ;

[0134] In the formula, is the root mean square error; is the number of data points within the time window; is the corrected temperature value; is the calibrated temperature value.

[0135] 14. The temperature anomaly matrix is expressed as follows:

[0136] ;

[0137] In the formula, is the anomaly factor value of the th moment at the th measurement point. The calculation formula has been given above. The construction of the anomaly matrix takes into account the local density characteristics of temperature data and can effectively identify abnormal measurement points.

[0138] When used as the input of the deep convolutional neural network, the expression is:

[0139] ;

[0140] In the formula, is the output of the first layer of convolutional network; is the convolutional kernel weight; represents the convolutional operation; is the bias term; is the activation function. This matrix is used to characterize the abnormal characteristics of the temperature field and helps predict temperature measurement errors.

[0141] 15. Dynamic compensation coefficient vector:

[0142] ;

[0143] The dynamic compensation coefficient vector is used in the temperature correction process:

[0144] ;

[0145] In the formula, is the final corrected temperature value; is the secondary corrected temperature value; is the dynamic characteristic parameter vector, which includes the temperature response time, the temperature maximum time, and the temperature regulation time. This vector is used to adjust the dynamic response characteristics of temperature.

[0146] Dynamic compensation coefficient matrix:

[0147] ;

[0148] In the formula, is an element of the dynamic compensation coefficient matrix, representing the influence coefficient of the th measurement point on the th measurement point. The calculation of dynamic compensation is:

[0149] ;

[0150] In the formula, is the temperature vector after compensation; is the measured temperature vector. This compensation method takes into account the mutual influence between measurement points.

[0151] The dynamic compensation coefficient matrix is used in the final temperature correction:

[0152] ;

[0153] In the formula, is the final corrected temperature vector; is the secondary corrected temperature vector; is the correction error vector. This matrix takes into account the spatial correlation between measurement points and is used to optimize the overall distribution of the temperature field.

[0154] Specifically, the principle of the present invention is: The technical principle of the present invention is based on a deep learning framework driven by a physical model. First, the heat conduction equation, the water flow influence equation, and the thermal conductivity equation are embedded in the conditional generative adversarial network. These three core equations respectively describe the heat conduction process, the influence of groundwater flow, and the change of soil thermal properties. In this way, it is ensured that the generated data satisfies the constraints of physical laws. Among them, the heat conduction equation depicts the diffusion characteristics of the temperature field, the water flow influence equation describes the influence of convective heat transfer, and the thermal conductivity equation reflects the dynamic change of soil thermal physical parameters. The coupled solution of these three equations realizes the accurate simulation of the evolution of the temperature field in a complex underground environment.

[0155] On this basis, the present invention uses a deep convolutional neural network to construct a temperature error prediction model. This network extracts the spatio-temporal features of temperature data through a multi-layer convolutional structure, uses a feature fusion network layer to effectively integrate multi-scale features, and finally outputs the temperature error prediction value through a prediction network layer. This network structure design fully considers the spatial correlation and time continuity of the temperature field distribution and can effectively capture the change law of temperature error. At the same time, the present invention innovatively proposes a multi-level compensation strategy, which realizes the comprehensive compensation from steady-state error to dynamic response characteristics through the synergistic action of the temperature fluctuation matrix, the temperature anomaly matrix, and the temperature compensation matrix.

[0156] A specific embodiment 1 of the method of the present invention is provided below. The specific implementation of each step in this embodiment 1 is described in detail as follows.

[0157] The specific implementation of step S01 is to collect temperature data through a distributed Brillouin scattering optical fiber temperature measurement system and construct a temperature fluctuation matrix. This system uses a pulsed light source to emit a laser with a wavelength of 1550 nm. The optical signal is coupled into the sensing optical fiber through an optical fiber coupler. The optical signal interacts with the medium during transmission to generate Brillouin scattering. A single-mode optical fiber is selected as the sensing optical fiber, which is helically wound along the surface of the vertical buried pipe. The winding pitch is 0.1 m, the measurement point spacing is set to 0.5 m, the sampling frequency is 1 Hz, and the continuous acquisition duration is not less than 24 hours. The collected original temperature data includes time stamps, spatial position coordinates, and corresponding temperature values. First, data preprocessing is performed, including outlier removal, data smoothing, and time synchronization. Outlier removal adopts the three-standard-deviation principle, calculating the mean and standard deviation of the data sequence, and marking and removing the data that deviates from the mean by more than . Data smoothing adopts the moving average method, with the time window size set to 60 seconds, and calculating the arithmetic mean of the data within each window as the smoothing result. Time synchronization uses the linear interpolation method to unify the sampling moments of different measurement points. Then, the preprocessed temperature data is used to construct a temperature fluctuation matrix according to the time series and depth position . The calculation formula for the matrix element is , where is the reference temperature value obtained through on-site calibration, is the temperature fluctuation amount obtained by measurement, and is the measurement error, which follows a normal distribution . The purpose of this step is to obtain an accurate and reliable original temperature data sequence to provide a data basis for subsequent analysis.

[0158] The specific implementation of step S02 is to perform time-domain decomposition on the temperature fluctuation matrix to extract characteristic quantities. The empirical mode decomposition method is used to decompose the temperature fluctuation matrix. This method can adaptively decompose non-linear and non-stationary signals. The basic principle of empirical mode decomposition is to decompose a complex signal into a finite number of intrinsic mode functions and a residual term. The decomposition formula is , where is the original temperature signal, is the th intrinsic mode function, is the residual signal, is the decomposition level. The extraction process of the intrinsic mode function adopts the iterative screening method. First, calculate the local maximum and minimum points of the signal, obtain the upper and lower envelope lines through cubic spline interpolation, and calculate the mean envelope line. Subtract the mean envelope line from the original data to obtain the candidate intrinsic mode function, and repeat the above process until the termination condition is met. The mathematical expression of the iterative process is , , where is the signal obtained by the -th screening, is the mean of the upper and lower envelope lines. The screening termination condition is that the standard deviation is less than the threshold , and the calculation formula is , where takes the value of 0.2. Perform the Hilbert transform on the obtained intrinsic mode function sequence, and the calculation formula is , , where is the Hilbert transform, is the analytic signal, is the instantaneous amplitude, is the instantaneous phase, is the imaginary unit. Extract the fluctuation amplitude, fluctuation frequency, and fluctuation phase corresponding to the main frequency components through the Hilbert transform. The fluctuation amplitude characterizes the severity of temperature changes, the fluctuation frequency reflects the speed of temperature changes, and the fluctuation phase reflects the leading or lagging relationship of temperature changes.

[0159] The specific implementation of step S03 is to perform data normalization based on the temperature fluctuation characteristic quantities. First, calculate the mean and standard deviation of the fluctuation amplitude, and use the standardization method to convert the amplitude data to a zero-mean unit-variance distribution. The calculation formula is , where is the normalized data, is the original data, is the mean, is the standard deviation. Perform min-max normalization on the fluctuation frequency to map the frequency data to the interval from 0 to 1. Perform periodic normalization on the fluctuation phase to convert the phase angle to the range from -π to π. Then, perform weighted normalization on the original temperature data according to the standardized characteristic quantities, and the weight coefficient is determined by the proportion of temperature fluctuation energy. The greater the fluctuation energy of the characteristic quantity, the greater the weight. Finally, obtain the standardized temperature data sequence, which eliminates the scale difference between different measurement points and makes the data comparable. The role of this step is to convert temperature data with different dimensions to a unified scale space for subsequent analysis and modeling.

[0160] The specific implementation of step S04 is to calculate the temperature anomaly parameter to construct a temperature anomaly matrix. The local outlier factor algorithm is used to detect the anomaly degree of temperature data. First, determine the size of the local neighborhood, which is 10% of the total number of measurement points. Calculate the distance between each measurement point and its neighborhood points, and the Euclidean distance is selected as the distance metric. Then, calculate the local reachability density of each measurement point. The calculation formula is , where is the local reachability density of point , is the nearest neighbor set of point , is the reachability distance. Then, calculate the local outlier factor. The formula is , where is the local outlier factor. Mark the measurement points with a local outlier factor greater than 2 as abnormal points, and the anomaly degree is represented by the outlier factor value. Construct a temperature anomaly matrix based on the calculated outlier factors . The matrix element represents the outlier factor value of the th moment and the th measurement point. The purpose of this step is to identify the abnormal patterns in the temperature data and provide a basis for subsequent error prediction.

[0161] The specific implementation of step S05 is to use a pre-trained deep convolutional neural network to predict the temperature error. This network consists of three functional network layers: feature extraction, feature fusion, and prediction. Each layer uses a specific structure and parameter settings. The feature extraction network uses a four-layer convolutional structure. After each convolution, a normalization network layer and an activation function layer are connected. The first layer has 32 convolutional kernels of size 3×3 to extract local temperature change features; the second layer has 64 convolutional kernels of size 3×3 to extract temperature gradient features; the third layer has 128 convolutional kernels of size 3×3 to extract temperature curvature features; the fourth layer has 256 convolutional kernels of size 3×3 to extract high-order temperature features. The feature fusion network uses a fully connected layer with 1024 neurons to combine multi-scale features. The prediction network uses a linear output layer, and the output dimension is the same as the number of measurement points. When the temperature anomaly matrix is used as the network input, the output expression of the first layer convolutional network is , where is the output of the first layer convolutional network, is the convolutional kernel weight, represents the convolution operation, is the bias term, As the activation function, the rectified linear unit function is selected. The output of this layer is processed by subsequent network layers, and finally the predicted value of the temperature error is obtained. The network is trained using the backpropagation algorithm. The loss function is selected as the mean squared error, the optimizer is selected as the adaptive moment estimation algorithm, the initial value of the learning rate is set to 0.001, and the number of training epochs is 1000. This step predicts the temperature measurement error through deep learning methods, providing a benchmark for temperature data correction.

[0162] The specific implementation of step S06 is to establish the mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix. The mapping model is constructed using the multiple regression analysis method. The independent variable is the temperature fluctuation characteristic quantity, and the dependent variable is the temperature anomaly parameter. First, feature selection is performed. The correlation coefficient between the characteristic quantity and the anomaly parameter is calculated, and the characteristic quantity with the absolute value of the correlation coefficient greater than 0.3 is selected as the effective feature. Then, a multiple linear regression equation is established, and the regression coefficients are estimated using the least squares method. A significance test is performed on the regression equation. If the P-value is less than 0.05, it indicates that the regression relationship is significant. The temperature compensation matrix is generated according to the regression coefficients, and the values in the matrix represent the temperature compensation coefficients at the corresponding positions. The calculation formula for the compensation coefficient is , where is the compensation coefficient, is the reference compensation coefficient, is the temperature coefficient, is the temperature deviation. The role of this step is to quantify the relationship between temperature fluctuations and temperature anomalies, providing a basis for temperature data correction.

[0163] The specific implementation of step S07 is to perform primary compensation using the temperature compensation matrix. When collecting temperature data in real time, first obtain the compensation coefficient at the corresponding position of the current measurement point in the temperature compensation matrix. The compensation coefficient includes two parts: the correction weight and the offset. The real-time temperature data is linearly corrected, and the correction formula is the original temperature value plus the offset multiplied by the correction weight. The value range of the correction weight is from 0 to 1, and the value range of the offset is plus or minus 5 degrees Celsius. Different compensation coefficients are used for measurement points at different depths. The correction weight of the shallow measurement points is larger, and the correction weight of the deep measurement points is smaller. The compensated temperature data is called the primary corrected temperature data, and this data eliminates the systematic error in temperature measurement. The calculation process of the primary correction can be expressed as , where is the compensated temperature vector, is the dynamic compensation coefficient matrix, is the measured temperature vector. The role of this step is to perform preliminary correction on the temperature data through the compensation matrix, improving the accuracy of temperature measurement.

[0164] The specific implementation of step S08 is to calculate the steady-state deviation value between the primary corrected temperature data and the historical calibration data. First, establish a historical calibration database containing standard temperature values under different working conditions, which are obtained by calibrating with a high-precision temperature sensor. Match the primary corrected temperature data with the historical calibration data, and select the data under the same working conditions for comparison. Use the sliding time window method to calculate the steady-state deviation value. The size of the time window is set to 1 hour, and the window sliding step is 10 minutes. Within each time window, calculate the root mean square error between the corrected temperature data and the calibration data. The calculation formula is , where is the root mean square error, is the number of data points within the time window, is the corrected temperature value, is the calibrated temperature value. The steady-state deviation value reflects the systematic error of temperature correction and provides a basis for secondary compensation. The purpose of this step is to evaluate the systematic deviation between the temperature data after primary correction and the standard value to ensure the reliability of temperature correction.

[0165] The specific implementation of step S09 is to establish a temperature correction model. This model consists of two parts: a temperature offset compensation term and a reference point correction term. The temperature offset compensation term is used to correct the zero drift of temperature measurement, and the reference point correction term is used to correct the linearity error of temperature measurement. The expression of the temperature correction model is , where is the corrected temperature value, is the measured temperature value, is the offset compensation coefficient, is the temperature offset, is the reference point correction coefficient, is the reference point temperature value. The temperature offset compensation term is calculated using the exponential smoothing method, and the smoothing coefficient is taken as 0.3. The calculation formula is , where is the smoothed value at time , is the observed value at time is the smoothing coefficient. The reference point correction term is calculated using the piecewise linear interpolation method. Five reference points are evenly selected within the measurement range, and the reference point temperature values are determined by on-site calibration. For any measurement point, determine the reference point interval where its temperature value is located, and calculate the correction coefficient using linear interpolation. The temperature correction model established in this step can effectively compensate for the nonlinear error in temperature measurement and improve the accuracy of temperature measurement.

[0166] The specific implementation of step S10 is to perform secondary compensation using a temperature correction model. First, calculate the offset of the primary corrected temperature data, and subtract the offset compensation value from the temperature data to obtain the zero-point correction result. The offset compensation value is calculated using the exponential smoothing method, which takes into account the cumulative effect of temperature drift. Then, determine the reference point interval where the temperature value is located, and calculate the linear correction coefficient within this interval. The linear correction coefficient is obtained through interpolation, and the calculation formula is , where is the correction coefficient, obtained by least squares fitting. Multiply the zero-point correction result by the linear correction coefficient to obtain the secondary corrected temperature data. The secondary correction takes into account the non-linear characteristics of temperature measurement and can more accurately reflect the actual temperature value. The role of this step is to further improve the accuracy of temperature measurement and make the corrected temperature data closer to the true value.

[0167] The specific implementation of step S11 is to calculate the system dynamic response parameters. The temperature response time is defined as the time required for the temperature change to reach 63.2% of the final steady-state value, and is obtained by performing exponential fitting on the secondary corrected temperature data. The temperature maximum time is the moment when the temperature reaches the peak, determined by finding the local maximum of the temperature data. The temperature regulation time is defined as the time required for the temperature to enter the steady-state interval, and the range of the steady-state interval is plus or minus 2% of the final steady-state value, determined by judging the temperature fluctuation amplitude. The expression of the dynamic compensation model is , where is the dynamic correction coefficient, is the temperature response time, is the temperature maximum time, is the temperature regulation time, is the corresponding reference time value, is the weight coefficient, and satisfies . These dynamic response parameters reflect the dynamic characteristics of the temperature measurement system and can be used to evaluate the control performance of the system.

[0168] The specific implementation of step S12 is to perform the final correction based on the system dynamic response parameters. First, establish a dynamic compensation model. The inputs of the model are the temperature response time, the temperature maximum time, and the temperature regulation time, and the output is the dynamic correction coefficient. The calculation expression for the final temperature correction is , where is the final corrected temperature vector, is the secondary corrected temperature vector, is the correction error vector. The elements of the dynamic compensation coefficient matrix represent the th measurement point for the ​The influence coefficient of each measuring point. The fuzzy control method is used to design dynamic compensation rules, and the correction coefficient is adjusted according to the size of the dynamic response parameter. When the response time is long, the correction coefficient is increased to speed up the response; when the adjustment time is long, the correction coefficient is reduced to suppress temperature fluctuations. The final correction result comprehensively considers the static and dynamic characteristics of temperature measurement and can accurately reflect the temperature distribution around the vertical buried pipe. The purpose of this step is to optimize the dynamic characteristics of temperature measurement and improve the control accuracy of the system.

[0169] In order to better understand and implement the present invention, Example 2 of a specific application scenario of the method of the present invention is provided below: A research team applied the temperature monitoring method of the present invention in an actual engineering project of a ground source heat pump system. The system includes 10 vertical buried pipes with a burial depth of 100 meters. First, a distributed optical fiber temperature sensing system is installed on one of the typical buried pipes. A single-mode optical fiber is used as the sensing element. It is installed along the pipe wall in a spiral winding manner. The winding spacing is 0.1 meters, the measuring point spacing is 0.5 meters, and there are a total of 200 measuring points. The sampling frequency is set to 1 Hz, and the temperature data is continuously collected for 48 hours. The initial collected temperature data is shown in Table 1:

[0170] Table 1 Example of raw temperature data (partial)

[0171] Depth (m) Temperature at 0 moment (℃) Temperature at 1 moment (℃) Temperature at 2 moment (℃) Temperature at 3 moment (℃) 0.5 15.32 15.45 15.67 15.89 1.0 15.28 15.36 15.52 15.71 1.5 15.25 15.31 15.43 15.58 2.0 15.23 15.27 15.35 15.46 2.5 15.21 15.24 15.29 15.37

[0172] The original data was preprocessed, and the triple standard deviation principle was used to eliminate outliers, and a total of 15 abnormal data points were identified. The sliding average method with a 60-second time window was used for data smoothing. The processed temperature data was constructed into a temperature fluctuation matrix with a matrix dimension of 172800×200.

[0173] The temperature fluctuation matrix is ​​decomposed by the empirical mode decomposition method, the standard deviation threshold is set to 0.2, and four intrinsic mode functions are obtained by iterative calculation. The first intrinsic mode function reflects the short-term temperature fluctuation characteristics with a period of about 1 hour; the second intrinsic mode function reflects the medium-term temperature change characteristics with a period of about 6 hours; the third and fourth intrinsic mode functions reflect the long-term temperature change trend. The energy distribution of each intrinsic mode function is shown in Table 2:

[0174] Table 2 Energy distribution of eigenmode function

[0175] Modal function number Energy proportion (%) Main frequency (Hz) Average amplitude (℃) 1 45.6 <![CDATA[2.78×10⁻ 4 > 0.42 2 32.3 <![CDATA[4.63×10⁻ 5 > 0.35 3 15.8 <![CDATA[7.72×10⁻ 6 > 0.28 4 6.3 <![CDATA[1.29×10⁻ 6 > 0.15

[0176] Perform Hilbert transform on the decomposed intrinsic mode functions to extract the wave characteristic quantities. Then, perform data normalization processing to calculate the standardized temperature data of each measurement point. The local outlier factor algorithm is used to detect temperature anomalies. The local neighborhood size is set to 20 measurement points. The calculation results show that there are 32 measurement points with abnormal conditions, mainly concentrated near the ground surface and the bottom area of the pipe. The anomaly detection results are shown in Table 3 as follows:

[0177] Table 3 Temperature Anomaly Detection Results Table (Partial)

[0178] Measuring point depth (m) Local anomaly factor Anomaly degree Main influencing factors 0.5 2.45 Moderate anomaly Surface temperature disturbance 1.0 2.32 Moderate anomaly Surface temperature disturbance 98.5 2.68 Relatively serious anomaly Groundwater influence 99.0 2.73 Relatively serious anomaly Groundwater influence 99.5 2.81 Relatively serious anomaly Groundwater influence

[0179] Build a deep convolutional neural network for temperature error prediction. The network structure includes 4 convolutional layers, 1 fully connected layer, and an output layer. Use the on-site calibration data as the training set. After 1000 rounds of training, the prediction accuracy of the network on the test set reaches 0.15°C. The comparison between the prediction results and the actual errors is shown in Table 4 as follows:

[0180] Table 4 Comparison Table of Temperature Error Prediction Results (Partial)

[0181] Measuring point depth (m) Prediction error (℃) Actual error (℃) Relative error (%) 10.0 0.23 0.25 8.0 20.0 0.18 0.19 5.3 30.0 0.15 0.16 6.2 40.0 0.12 0.13 7.7 50.0 0.11 0.12 8.3

[0182] Based on the prediction results, establish a temperature compensation matrix to perform primary compensation on the real-time temperature data. During the compensation process, the correction weight of the shallow measurement points (0 - 20 meters) is set to 0.8, the correction weight of the middle measurement points (20 - 80 meters) is set to 0.6, and the correction weight of the deep measurement points (80 - 100 meters) is set to 0.4. The root mean square error between the temperature data after primary compensation and the calibration data is reduced to 0.12°C.

[0183] Use the sliding time window method to calculate the steady-state deviation value and perform secondary compensation on the primary corrected data. In the compensation model, the temperature offset compensation term is calculated using the exponential smoothing method, and the smoothing coefficient is taken as 0.3; the reference point correction term selects 5 reference points evenly within the measurement range for correction. The temperature measurement accuracy after secondary compensation is further improved, and the root mean square error is reduced to 0.08°C.

[0184] Finally, calculate the system dynamic response parameters, including the temperature response time, the temperature maximum time, and the temperature regulation time. The test results show that the average temperature response time of the system is 185 seconds, the temperature maximum time is 486 seconds, and the temperature regulation time is 823 seconds. Based on these parameters, establish a dynamic compensation model to achieve the final temperature correction. The system performance parameters after the final correction are shown in Table 5 as follows:

[0185] Table 5 System Performance Parameter Table

[0186] Performance index Original value Value after correction Improvement amplitude (%) Measurement accuracy (℃) 0.25 0.05 80.0 Response time (s) 185 142 23.2 Adjustment time (s) 823 675 18.0 Temperature fluctuation (℃) 0.18 0.08 55.6 System stability (%) 85.6 94.8 10.7

[0187] The traditional ground-coupled pipe temperature monitoring method mainly has the following problems: First, the single-point temperature measurement method is adopted, with low spatial resolution and unable to accurately reflect the temperature field distribution; second, the non-linear characteristics of measurement errors are not considered, resulting in poor compensation effect; third, the lack of dynamic characteristic analysis affects the system control effect. The present invention adopts the distributed optical fiber temperature measurement technology to achieve high-spatial-resolution temperature field monitoring; predicts temperature errors through deep learning methods and establishes a multi-level temperature compensation mechanism; introduces dynamic response parameter analysis to optimize the system control performance. The implementation results show that compared with the traditional method, the measurement accuracy of the present invention is increased by 80%, the system response speed is increased by 23.2%, and the operation stability is increased by 10.7%, significantly improving the operation effect of the ground source heat pump system.

[0188] A specific Embodiment 3 of the system of the present invention is provided below: Please refer to Figure 1 - Figure 10 , a vertical ground-coupled pipe ground source heat pump temperature monitoring system based on distributed optical fiber, having a box body 1. A vertical plate 2 is fixedly installed at the top of the box body 1. A gear 3 is rotatably installed at one end of the vertical plate 2. Tooth plates 4 are movably installed at both ends of the vertical plate 2. The number of tooth plates 4 is two, and the sizes of the two tooth plates 4 are the same as that of the box body. The tooth plates 4 are meshed with the outer surface of the gear 3. When the gear 3 rotates, it will drive the tooth plates 4 to move towards or away from each other. Connecting rods 5 are respectively fixedly installed on the tooth plates 4. When the tooth plates 4 slide, they will drive the connecting rods 5 to slide. One end of the connecting rod 5 is fixedly installed with a movable door, including a left movable door 61 and a right movable door 62. When the connecting rod 5 slides, it will drive the movable door to slide. The sizes of the two movable doors are the same. A roller 7 and a rotating shaft 8 are rotatably installed at the other end of the vertical plate 2. A belt 9 is movably sleeved on the outer surfaces of the roller 7 and the rotating shaft 8. When the rotating shaft 8 rotates, it will drive the belt 9 to rotate. Then the belt 9 will drive the roller 7 to rotate. One end of the roller 7 penetrates through the vertical plate 2 and is fixedly connected to one end of the gear 3. When the roller 7 rotates, it will drive the gear 3 to rotate. A circular shaft 10 is fixedly installed at one end of the rotating shaft 8. When the circular shaft 10 rotates, it will drive the rotating shaft 8 to rotate. A protective box 11 is fixedly installed at one end of the vertical plate 2. The protective box 11 can protect the roller 7, the rotating shaft 8, the belt 9 and the circular shaft 10 from being collided. A motor 12 is fixedly installed at one end of the protective box 11, and the output end of the motor 12 penetrates through the protective box 11 and is fixedly connected to one end of the circular shaft 10. When the motor 12 operates, it will cause the circular shaft 10 to rotate.

[0189] In the present invention, when it is necessary to open and close the box body 1, the operation of the motor 12 will cause the circular shaft 10 to rotate. Subsequently, the circular shaft 10 will drive the rotating shaft 8 to rotate. Then, the rotating shaft 8 will drive the belt 9 to rotate. Further, the belt 9 will drive the roller 7 to rotate. At this time, the roller 7 will drive the gear 3 to rotate. Subsequently, the gear 3 will drive the toothed plate 4 to slide. Then, the toothed plate 4 will drive the connecting rod 5 to slide. At the same time, the connecting rod 5 will drive the movable door to move towards each other, so as to automatically close the box body 1. Conversely, it can be opened, thus facilitating the maintenance of multiple modules inside the box body 1.

[0190] The following provides a specific Embodiment 4 of the system of the present invention: Please refer to Figure 1 - Figure 10 , a vertical buried pipe ground source heat pump temperature monitoring system based on distributed optical fiber. One end of the box body 1 is fixedly installed with a fixed rod 13. A strip-shaped groove 14 is opened at the top of the fixed rod 13. A round rod 15 is fixedly installed inside the strip-shaped groove 14. Both sides of the surface of the round rod 15 are movably sleeved with moving blocks 16. The inner surface of the moving block 16 and the outer surface of the round rod 15 are both smooth, which can make the moving block 16 slide more smoothly on the surface of the round rod 15, reducing the occurrence of jamming. And the top of the moving block 16 is fixedly connected to the bottom of the movable door. When the movable door slides, it will drive the moving block 16 to slide inside the strip-shaped groove 14 and on the surface of the round rod 15. Due to the design of the round rod 15 and the moving block 16, the sliding of the movable door can be made more stable. A card slot 17 is opened on one side of the left movable door 61. A clamping plate 18 is fixedly installed on one side of the right movable door 62. And the card slot 17 is adapted to the clamping plate 18. The inner surface of the card slot 17 and the outer surface of the clamping plate 18 are both rough. When the clamping plate 18 is placed inside the card slot 17, the connection between the two can be made more tight, thereby improving the stability of the movable door when it is closed.

[0191] In the present invention, when the movable door slides, it will drive the moving block 16 to slide inside the strip-shaped groove 14 and on the surface of the round rod 15. Due to the design of the round rod 15 and the moving block 16, the sliding of the movable door can be made more stable. When the clamping plate 18 is placed inside the card slot 17, the two movable doors will close the box body 1. When the clamping plate 18 slides out of the card slot 17, the movable doors will move away from each other, so that the box body 1 is in an open state.

[0192] The following provides a specific Embodiment 5 of the system of the present invention: Please refer to Figure 1 - Figure 10, a vertical buried pipe ground source heat pump temperature monitoring system based on distributed optical fiber. Sensing optical fibers 19 are fixedly installed at equal distances at the bottom of the box body 1. The sensing optical fibers 19 adopt specially designed fast heat-conducting optical cables, which have the characteristics of high tensile strength, bending resistance, pressure resistance, waterproofness, corrosion resistance, etc. They can effectively protect the optical fibers and quickly transfer external heat. The top of the sensing optical fiber 19 penetrates through the box body 1 and extends to the inner surface of the box body 1. The sensing optical fibers 19 have the same size. The sensing optical fibers 19 can be distributedly connected to the vertical buried pipes. And sleeve rods 20 are movably sleeved on the surfaces of the sensing optical fibers 19. The inner surface of the sleeve rod 20 and the outer surface of the sensing optical fiber 19 are both smooth. The position of the sliding sealing rod 25 can be adjusted through the sleeve rod 20 to assist in fixing the connection between the sensing optical fiber 19 and the vertical buried pipe. Chutes 21 are opened at both ends of the bottom of the sleeve rod 20. Cylinders 22 are fixedly installed inside the chutes 21. Sliders 23 are movably sleeved on the surfaces of the cylinders 22. The inner surface of the slider 23 and the outer surface of the cylinder 22 are both smooth, which can make the slider 23 slide more smoothly on the surface of the cylinder 22 and reduce the occurrence of jamming. Springs 24 are fixedly installed between the sliders 23 and the chutes 21. The inner surface of the spring 24 is movably connected to the outer surface of the cylinder 22. When the slider 23 slides inside the chute 21 and on the surface of the cylinder 22, the spring 24 will be squeezed and compressed. And sealing rods 25 are fixedly installed at the bottoms of the sliders 23. When the sealing rod 25 slides, it will drive the slider 23 to slide. At the same time, the connection between the sensing optical fiber 19 and the vertical buried pipe can be assisted in fixing through the sealing rod 25. Limit grooves 26 are opened at both ends of the top of the sleeve rod 20. Moving rods 27 are movably installed inside the limit grooves 26. The inner surface of the limit groove 26 and the outer surface of the moving rod 27 are both smooth, which can make the moving rod 27 slide more smoothly inside the limit groove 26 and reduce the occurrence of jamming. The bottom of the moving rod 27 is fixedly connected to the top of the slider 23. When the slider 23 slides, it will drive the moving rod 27 to slide inside the limit groove 26. And clamping rings 28 are fixedly installed at the tops of the moving rods 27. When the moving rod 27 slides, it will drive the clamping ring 28 to slide. The clamping ring 28 can fix the surface of the sensing optical fiber 19. At the same time, the clamping ring 28 can be made of soft material.

[0193] In the present invention, when the sensing optical fiber 19 is connected to the vertically buried pipe, the sealing rod 25 is pulled accordingly. When the sealing rod 25 slides, it will drive the slider 23 to slide inside the chute 21 and on the surface of the cylinder 22. Subsequently, the slider 23 will squeeze and compress the spring 24. At this time, the slider 23 will drive the moving rod 27 to slide inside the limiting groove 26. Subsequently, the moving rod 27 will drive the snap ring 28 to slide. Then, slide the sleeve rod 20 until the sealing rod 25 is placed at the connection between the sensing optical fiber 19 and the vertically buried pipe. At the same time, release the sealing rod 25. Subsequently, the snap ring 28 will clamp and fix the sensing optical fiber 19. Then, the connection between the sensing optical fiber 19 and the vertically buried pipe can be assisted and fixed by the sealing rod 25 to make the connection tighter.

[0194] A specific embodiment 6 of the system of the present invention is provided below: Please refer to Figure 1 - Figure 10 , a vertically buried pipe ground source heat pump temperature monitoring system based on distributed optical fiber. At one end inside the box body 1, a temperature detection module 29 and a data processing module 30 are fixedly installed. The temperature detection module 29 can monitor the temperature and process the monitored data through the data processing module 30. And at one end inside the box body 1, a data transmission module 31 and a power supply module 32 are fixedly installed on the right side of the temperature detection module 29 and the data processing module 30. The data transmission module 31 can transmit the processed data and can provide power support for the temperature detection module 29, the data processing module 30, and the data transmission module 31 through the power supply module 32 to enable them to work for a longer time. On the top of the box body 1, a mounting plate 33 is fixedly installed, and mounting holes 34 are provided at both ends of the mounting plate 33. Due to the design of the mounting plate 33 and the mounting holes 34, it is convenient to install the box body 1.

[0195] In the present invention, the operator connects the temperature detection module 29, the data processing module 30, the data transmission module 31, and the power supply module 32 to the clamping plate 18 through wires or connecting lines. At the same time, the temperature detection module 29 can monitor the temperature, the data processing module 30 can process the monitored data, and then transmit the processed data through the data transmission module 31. Subsequently, the power supply module 32 can provide power support for the temperature detection module 29, the data processing module 30, and the data transmission module 31 to enable them to work for a longer time.

[0196] A specific embodiment 7 of the system of the present invention is provided below: Please refer to Figure 1 - Figure 10, a vertical buried tube ground source heat pump temperature monitoring system based on distributed optical fiber. Heat dissipation slots 35 are evenly arranged on both sides of the box body 1 at equal distances, and the sizes of the heat dissipation slots 35 are the same. The temperature detection module 29, data processing module 30, data transmission module 31, and power supply module 32 generate heat during operation. If the heat is not dissipated in time, it may affect the normal monitoring work. Subsequently, the heat can be dissipated through the heat dissipation slots 35. One end of the left movable door 61 is fixedly installed with a display screen 36, and one end of the right movable door 62 is fixedly installed with a PLC controller 37. The PLC controller 37 is a digital operation electronic system specifically designed for application in industrial environments. It uses a programmable memory to store instructions for performing operations such as logical operations, sequential control, timing, counting, and arithmetic operations inside it. It controls various types of mechanical equipment or production processes through digital or analog inputs and outputs. It adopts modern large-scale integrated circuit technology. The PLC controller 37 takes various measures in both hardware and software to improve its reliability. In terms of hardware, the PLC controller 37 shields the main components such as the power transformer, CPU, and programmer to prevent external interference, uses a filter network for the power supply system and input lines to eliminate high-frequency interference, and uses a multi-stage filter and regulator to adjust the power supply required by the CPU to adapt to power grid fluctuations. In terms of software, the PLC controller 37 regularly detects the external environment through a monitoring program, promptly processes faults, and sets a watchdog timer to prevent the program from entering an infinite loop, thereby improving the degree of intelligence.

[0197] In the present invention, the operator connects the display screen 36 and the PLC controller 37 to the motor 12, sensing optical fiber 19, temperature detection module 29, data processing module 30, data transmission module 31, and power supply module 32 through wires. The heat dissipation slots 35 can dissipate the heat generated by the temperature detection module 29, data processing module 30, data transmission module 31, and power supply module 32 to prevent them from overheating and affecting the normal monitoring work. At the same time, the display screen 36 can display the monitored data, making it convenient for the operator to observe, and the automation degree of the device can also be achieved through the PLC controller 37.

[0198] It should be noted that the detailed explanations of the variables involved in the present invention are shown in Table 6 below.

[0199] Table 6 Variable Explanation Table

[0200]

[0201] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A temperature monitoring method for a vertical buried pipe ground source heat pump, comprising the following steps: The original temperature data sequence of multiple measuring points is collected by distributed optical fiber sensors to construct a temperature fluctuation matrix; Decomposing the temperature fluctuation matrix in the time domain, extracting the fluctuation amplitude, fluctuation frequency and fluctuation phase of the temperature data, and obtaining the temperature fluctuation characteristic quantity; Based on the temperature fluctuation characteristic quantity, the original temperature data is normalized to generate a standardized temperature data sequence; temperature anomaly parameters are calculated according to the standardized temperature data sequence to construct a temperature anomaly matrix; Inputting the temperature anomaly matrix into a pre-trained temperature error prediction model to obtain a temperature error prediction value; Establishing a mapping relationship between the temperature fluctuation matrix and the temperature anomaly matrix to generate a temperature compensation matrix; using the temperature compensation matrix to perform primary compensation on the temperature data collected in real time to obtain primary corrected temperature data; Calculating a steady-state deviation value between the primary corrected temperature data and the historical calibration data; Establishing a temperature correction model according to the steady-state deviation value; performing secondary compensation on the primary corrected temperature data using the temperature correction model to obtain secondary corrected temperature data; Calculate system dynamic response parameters; The secondary corrected temperature data is finally corrected by using the system dynamic response parameters, and the corrected temperature data is output; characterized in that the pre-trained temperature error prediction model adopts a deep convolutional neural network structure, and the deep convolutional neural network structure is composed of a feature extraction network layer, a feature fusion network layer and a prediction network layer; the temperature correction model includes a temperature offset compensation term and a reference point correction term; The system dynamic response parameters include temperature response time, temperature maximum value time and temperature adjustment time.

2. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 1, characterized in that: The feature extraction network layer adopts a four-layer convolution layer structure. The number of convolution kernels in each convolution layer is 32, 64, 128, and 256 respectively. The convolution kernel size is 3×3, and the step size is 1. Each convolution layer is followed by a normalization network layer and an activation function layer. The feature fusion network layer adopts a fully connected layer structure with 1024 neurons. The prediction network layer adopts a linear output layer with an output dimension of the number of measurement points.

3. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 2, characterized in that: The training data set of the pre-trained temperature error prediction model constructs virtual training data of underground temperature distribution through a conditional generative adversarial network. The conditional generative adversarial network includes a generative network and a discriminative network. The generative network has an embedded temperature generation equation group for simulating the distribution law of the underground temperature field.

4. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 3, characterized in that: The temperature generation equation group includes a heat conduction equation, a water flow influence equation and a thermal conductivity equation. The heat conduction equation is used to describe the heat conduction process in the soil around the vertical buried pipe. The water flow influence equation is used to simulate the influence of groundwater flow on the temperature field. The thermal conductivity equation is used to calculate the thermal conductivity of the soil under different depths and different water contents.

5. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 4, characterized in that: In the process of performing primary compensation using the temperature compensation matrix, the compensation coefficient includes a correction weight and an offset, the correction weight ranges from 0 to 1, and the offset ranges from plus or minus 5 degrees Celsius; The steady-state deviation value between the first-level corrected temperature data and the historical calibration data is calculated using a sliding time window method, with the time window size set to 1 hour and the window sliding step size set to 10 minutes.

6. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 5, characterized in that: The temperature offset compensation term is calculated using an exponential smoothing method, with a smoothing coefficient of 0.3; the reference point correction term is calculated using a piecewise linear interpolation method, and 5 reference points are evenly selected within the measurement range.

7. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 6, characterized in that: The temperature response time is defined as the time required for the temperature change to reach 63.2% of the final steady-state value, and the temperature adjustment time is defined as the time required for the temperature to enter the steady-state interval, and the range of the steady-state interval is plus or minus 2% of the final steady-state value.

8. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 7, characterized in that: The local anomaly factor algorithm is used to detect the degree of anomaly of temperature data. The size of the local neighborhood is taken as 10% of the total number of measuring points, and the measuring points with a local anomaly factor greater than 2 are marked as abnormal points.

9. The temperature monitoring method of a vertical buried pipe ground source heat pump according to claim 8, characterized in that: The empirical mode decomposition method is used to decompose the temperature fluctuation matrix, and the obtained intrinsic mode function sequence is subjected to Hilbert transform to calculate the instantaneous frequency and instantaneous amplitude, and extract the fluctuation amplitude, fluctuation frequency and fluctuation phase corresponding to the main frequency components.

10. A temperature monitoring system for a vertical buried pipe ground source heat pump, comprising a box, characterized in that: A vertical plate is fixedly installed on the top of the box body, a gear is rotatably installed on one end of the vertical plate, and toothed plates are movably installed on both ends of the vertical plate, the toothed plates are meshed and connected with the outer surface of the gear, and connecting rods are fixedly installed on the toothed plates respectively, and a movable door is fixedly installed on one end of the connecting rods, and a roller and a rotating shaft are rotatably installed on the other end of the vertical plate, and a belt is movably sleeved on the outer surfaces of the roller and the rotating shaft, one end of the roller passes through the vertical plate and is fixedly connected to one end of the gear, one end of the rotating shaft is fixedly installed with a round shaft, and one end of the vertical plate is fixedly installed with a protective box, and the protective box A motor is fixedly installed at one end, and the output end of the motor passes through the protective box and is fixedly connected to one end of the circular shaft; a fixed rod is fixedly installed at one end of the box body, a strip groove is provided on the top of the fixed rod, a round rod is fixedly installed inside the strip groove, and moving blocks are movably sleeved on both sides of the surface of the round rod, and the top of the moving block is fixedly connected to the bottom of the movable door; the movable door includes a left movable door and a right movable door, a card slot is provided on one side of the left movable door, and a card plate is fixedly installed on one side of the right movable door, and the card slot is adapted to the card plate; the bottom of the box body is fixedly installed at equal distances A sensing optical fiber is fixedly installed, the top of the sensing optical fiber passes through the box body and extends to the inner surface of the box body, and the surface of the sensing optical fiber is movably sleeved with a sleeve rod; both ends of the bottom of the sleeve rod are provided with a slide groove, the inside of the slide groove is fixedly installed with a cylinder, the surface of the cylinder is movably sleeved with a slider, a spring is fixedly installed between the slider and the slide groove, the inner surface of the spring is movably connected to the outer surface of the cylinder, and a sealing rod is fixedly installed at the bottom of the slider; both ends of the top of the sleeve rod are provided with a limit groove, the inside of the limit groove is movably installed with a moving rod, and the bottom of the moving rod The box body is fixedly connected to the top of the slider, and the top of the moving rod is fixedly installed with a clamping ring; a temperature detection module and a data processing module are fixedly installed at one end of the interior of the box body, and a data transmission module and a power supply module located on the right side of the temperature detection module and the data processing module are fixedly installed at one end of the interior of the box body; the data processing module adopts a single-chip microcomputer, and a storage medium is provided in the data processing module, and a program code is stored in the storage medium. When the single-chip microcomputer executes the program code, it is used to execute the temperature monitoring method of the vertical buried pipe ground source heat pump described in any one of claims 1-9.

Images