Method and system for generating unit temperature distribution diagram through fiber bragg grating temperature measurement

Abstract

The invention provides a unit temperature distribution diagram generation method and system based on fiber grating temperature measurement, and the method comprises the steps: dividing a target temperature segment into a plurality of sub-temperature segments, and carrying out the pre-training of a temperature calculation model corresponding to each sub-temperature segment; historical data of each temperature measurement point are obtained, multi-dimensional temperature measurement data of the next time point are predicted based on the historical data of the temperature measurement point, and the multi-dimensional temperature measurement data comprise a Bragg wavelength change value and an environment sensor measurement value; calculating a predicted temperature change value based on the multi-dimensional temperature measurement data of the next time point, and selecting a temperature calculation model; building a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point, inputting the temperature measurement matrix into the selected temperature calculation model, and determining the temperature value of the temperature measurement point; and rendering is carried out based on the temperature values of the temperature measurement points of the target unit in the three-dimensional model of the target unit, and a temperature distribution diagram output for the user is determined based on the view cone of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of optical fiber temperature measurement, and particularly to a method and system for generating a temperature distribution map of a unit by optical fiber grating temperature measurement. Background Art

[0002] As a key facility for energy conversion and supply, the stable operation of a power plant is directly related to the security and reliability of the power system, and thus affects all aspects of the stable operation of the social economy and the daily life of the public. In the complex operating environment of a power plant, various devices such as generators, transformers, and switchgear undertake huge tasks of electric energy conversion and transmission. Under the long-term and high-load working conditions, these devices are extremely likely to cause local overheating due to factors such as current overload, insulation aging, and poor contact, which may further lead to equipment failures and even fire accidents, not only causing huge economic losses but also posing a serious threat to personnel safety.

[0003] Therefore, accurate temperature measurement of power plant devices has become an essential part of accident prevention and ensuring safe production. The importance of accurate temperature measurement mainly includes:

[0004] 1. Early fault warning: By regularly or real-time monitoring the device temperature, potential overheating points can be detected in a timely manner. These hot spots are often precursors to device failures. Early detection and taking corresponding measures can effectively avoid the expansion of failures, reduce unplanned downtime, and ensure the continuity of power supply; 2. Extending device life: Accurate temperature measurement helps to understand the working state of the device and reasonably arrange maintenance and repair plans. For parts with abnormally increased temperature, timely cooling measures or replacement of damaged components can delay the aging process of the device, extend the overall service life, and reduce long-term operation costs.

[0005] In summary, in order to ensure accurate temperature measurement at each temperature measurement point, the prior art often adopts the method of optical fiber grating temperature measurement. The principle of optical fiber grating temperature measurement is to measure temperature through the change of the Bragg wavelength. It is difficult to combine the environmental conditions. The power plant environment is relatively complex, and the influence of environmental conditions is relatively important. The prior art is difficult to be applied to the accurate temperature measurement of power plant units.

[0006] In view of this, the present invention is proposed. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and system for generating a temperature distribution map of a unit by optical fiber grating temperature measurement. While considering the change of the Bragg wavelength, this solution incorporates the measured values of environmental sensors and ensures accurate temperature measurement of power plant units through a temperature calculation model preset for each sub-temperature segment.

[0008] The present invention provides a method for generating a temperature distribution map of a unit by optical fiber grating temperature measurement. The steps of the method include:

[0009] Divide the target temperature range into multiple sub - temperature ranges. For each sub - temperature range, construct a training data set and pre - train the temperature calculation model to obtain temperature calculation models corresponding to each sub - temperature range.

[0010] For each temperature measurement point, obtain the historical data of this measurement point. The historical data includes multi - dimensional temperature measurement data at each historical time point. Based on the historical data of the temperature measurement point, predict the multi - dimensional temperature measurement data at the next time point. The multi - dimensional temperature measurement data includes the change value of the Bragg wavelength and the measurement value of the environmental sensor.

[0011] Calculate the predicted temperature change value based on the multi - dimensional temperature measurement data at the next time point, and select the temperature calculation model based on the predicted temperature change value.

[0012] Construct a temperature measurement matrix based on the actually measured multi - dimensional temperature measurement data at the next time point, and input the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point.

[0013] Render the three - dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit, and determine the temperature distribution map output for the user based on the user's viewing frustum.

[0014] Adopting the above - mentioned scheme, this scheme first pre - sets a temperature calculation model for each sub - temperature range. For temperature measurement in a relatively large temperature range, more refined processing can be achieved through the division of sub - temperature ranges. On the other hand, this scheme predicts multi - dimensional temperature measurement data, calculates the predicted temperature change value based on the predicted multi - dimensional temperature measurement data, and then determines the temperature calculation model to be called, without the need to call all temperature calculation models, ensuring the utilization efficiency of computing resources. And in the final temperature measurement process, a temperature measurement vector is constructed through multi - dimensional temperature measurement data to determine the final temperature measurement value. This scheme takes into account the change of the Bragg wavelength, incorporates the measurement value of the environmental sensor, and ensures accurate temperature measurement of the power plant unit through the temperature calculation model pre - set for each sub - temperature range.

[0015] In some embodiments of the present invention, the measurement value of the environmental sensor includes the measurement value of the auxiliary sensor and the pressure measurement value. In the step of calculating the predicted temperature change value based on the multi - dimensional temperature measurement data at the next time point, calculate the predicted temperature change value based on the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, the pressure measurement value, and the noise constant.

[0016] In some embodiments of the present invention, in the step of calculating the predicted temperature change value based on the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, the pressure measurement value, and the noise constant, calculate the predicted temperature change value according to the following formula:

[0017]

[0018] Among them, ΔT represents the predicted temperature change value, and Δλ B represents the change value of the Bragg wavelength, and K ε and K P respectively represent the auxiliary sensor and the pressure coefficient. Δε and ΔP respectively represent the change value of the auxiliary sensor and the change value of the pressure. δ represents the noise constant, and K T represents the temperature coefficient.

[0019] Adopting the above scheme, this scheme is based on the linear compensation relationship of the accurate physical model for the temperature change value, combines the sensor data measured by each external sensor with the change value of the Bragg wavelength of the optical fiber, and supplements and adds the noise constant during the combination process to further compensate the calculation result and ensure the calculation accuracy of the predicted temperature change value.

[0020] In some embodiments of the present invention, in the step of calculating the predicted temperature change value based on the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, the pressure measurement value and the noise constant, the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, and the pressure measurement value adopted are all the values after standardizing the original change value of the Bragg wavelength, the measurement value of the auxiliary sensor, and the pressure measurement value.

[0021] In some embodiments of the present invention, in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point:

[0022] Obtain the multi-dimensional temperature measurement data of the nearest preset time length, and respectively construct a temperature measurement vector from the nearest preset time length and the multi-dimensional temperature measurement data actually measured at the next time point;

[0023] Take each temperature measurement vector as a data row, and arrange the temperature measurement vectors vertically based on the time corresponding to the time point of the temperature measurement vector to obtain the temperature measurement matrix.

[0024] Adopting the above scheme, in the process of actually calculating the temperature of each temperature measurement point, this scheme uses the temperature calculation model for accurate calculation, not only comprehensively considers the measurement value of the environmental sensor and the change value of the Bragg wavelength to ensure the calculation accuracy; but also introduces the time sequence relationship of each time point through the temperature measurement matrix, making the final temperature calculation for each temperature measurement point more accurate.

[0025] In some embodiments of the present invention, the temperature calculation model includes a first processing module and a second processing module. The first processing module uses a 1D-CNN model, and the second processing module uses an LSTM model. The first processing module and the second processing module are connected in sequence to obtain the temperature calculation model.

[0026] In some embodiments of the present invention, there is an overlapping region between at least two adjacent sub-temperature segments. In the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point and selecting the temperature calculation model based on the predicted temperature change value, if it is determined that the temperature calculation model corresponding to the predicted temperature change value is one or more, and if it is one, then in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point, the selected temperature calculation model is used for calculation;

[0027] If there are multiple, then in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point:

[0028] Calculate the intermediate temperature value based on the sub-temperature segment corresponding to each selected temperature calculation model;

[0029] Determine the predicted temperature based on the predicted temperature change value, calculate the temperature difference between the predicted temperature and each intermediate temperature value, and determine the weight value of each selected temperature calculation model based on the temperature difference;

[0030] Perform weighted calculation on the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point.

[0031] With the above solution, first, by setting temperature calculation models corresponding to multiple sub-temperature segments, the calculation of temperature is made more precise. Further, in order to address the poor performance of the temperature calculation model in calculating the temperature at the edges of the sub-temperature segments, an overlapping region is set between at least two adjacent sub-temperature segments. When the predicted temperature is in the overlapping region at the edge, comprehensive calculation is performed through the corresponding multiple temperature calculation models, and the weight value of the calculation is determined based on the temperature difference between the predicted temperature and the intermediate temperature values of each sub-temperature segment. By performing weighted calculation on the outputs of each temperature calculation model, the calculation at the edges of the sub-temperature segments of the temperature calculation model is bridged, further ensuring the calculation accuracy.

[0032] In some embodiments of the present invention, in the step of determining the weight value of each selected temperature calculation model based on the temperature difference, the following formula is used to calculate the weight value of each temperature calculation model:

[0033]

[0034] Among them, τ represents the weight value, and θ represents the temperature difference;

[0035] In the step of calculating the weighted average of the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point, the weighted average of the output values of the selected temperature calculation models is calculated to obtain the temperature value of the temperature measurement point.

[0036] In some embodiments of the present invention, the step of rendering the three-dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit and determining the temperature distribution map output for the user based on the user's viewing frustum includes:

[0037] Render the three-dimensional model block of the area where the temperature measurement point is located in the three-dimensional model based on the pixel value corresponding to the temperature value of the temperature measurement point;

[0038] For the three-dimensional model blocks in the area of the three-dimensional model not covered by the temperature measurement points, calculate the distance value between the three-dimensional model block and the temperature measurement points within the threshold distance range of the three-dimensional model block, and determine the temperature influence weight based on the distance value;

[0039] Based on the temperature influence weight, perform weighted calculation on the temperature values of each temperature measurement point within the threshold distance range of the three-dimensional model block, determine the temperature value of the corresponding three-dimensional model block, and determine the pixel value corresponding to the temperature value, and render the corresponding three-dimensional model block with the pixel value.

[0040] Adopting the above solution, for the area covered by the temperature measurement points in the three-dimensional model of the present solution, it is directly rendered based on the temperature values measured by the temperature measurement points. For the area not covered by the temperature measurement points, first determine the temperature measurement points within the threshold distance range of each three-dimensional model block, determine the temperature influence weight based on the distance from the temperature measurement points, the closer the distance, the greater the temperature influence weight, determine the temperature at this position through weighted calculation, and then determine the pixel value to complete the rendering of the entire three-dimensional model.

[0041] In some embodiments of the present invention, in the step of determining the temperature distribution map output for the user based on the user's viewing frustum, perform an intersection test between the user's viewing frustum and the rendered three-dimensional model, determine the three-dimensional model blocks intersecting with the user's viewing frustum, construct the range surrounded by the three-dimensional model blocks intersecting with the user's viewing frustum as the temperature distribution map, and give feedback.

[0042] On the other hand, the present invention also relates to a system for generating a temperature distribution map of a unit by using an optical fiber grating temperature measurement. The system includes a computer device, the computer device includes a processor and a memory, computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0043] In summary, the present invention has the following beneficial effects:

[0044] 1. In this solution, a temperature calculation model is preset for each sub-temperature segment. For temperature measurement in a relatively large temperature range, more refined processing can be achieved through the division of sub-temperature segments. On the other hand, this solution predicts multi-dimensional temperature measurement data, calculates the predicted temperature change value based on the predicted multi-dimensional temperature measurement data, and then determines the temperature calculation model to be called, without the need to call all temperature calculation models, ensuring the utilization efficiency of computing resources. In the final temperature measurement process, a temperature measurement vector is constructed through multi-dimensional temperature measurement data to determine the final temperature measurement value. This solution takes into account the change in Bragg wavelength and incorporates the measured values of environmental sensors, and through the temperature calculation model preset for each sub-temperature segment, ensures accurate temperature measurement of the power plant unit;

[0045] 2. Based on the linear compensation relationship of the accurate physical model for the temperature change value, this solution combines the sensor data measured by each external sensor with the change value of the Bragg wavelength of the optical fiber, and adds a noise constant during the combination process to further compensate the calculation result and ensure the calculation accuracy of the predicted temperature change value;

[0046] 3. By setting temperature calculation models corresponding to multiple sub-temperature segments, the calculation of temperature is made more refined. Further, in order to address the poor performance of the temperature calculation model in calculating the temperature at the edge of the sub-temperature segment, this solution sets an overlapping area between at least two adjacent sub-temperature segments. When the predicted temperature is in the overlapping area at the edge, comprehensive calculation is performed through the corresponding multiple temperature calculation models, and the calculation weight value is determined based on the temperature difference between the predicted temperature and the temperature median value of each sub-temperature segment. By performing weighted calculation on the outputs of each temperature calculation model, the calculation at the edge of the sub-temperature segment of the temperature calculation model is bridged, further ensuring the calculation accuracy;

[0047] 4. For the area covered by the temperature measurement points in the three-dimensional model of this solution, rendering is directly based on the temperature values measured at the temperature measurement points. For the area not covered by the temperature measurement points, first, the temperature measurement points within the threshold distance range of each three-dimensional model block are determined, the temperature influence weight is determined based on the distance from the temperature measurement points, and the closer the distance, the greater the temperature influence weight. The temperature at this position is determined through weighted calculation, and then the pixel value is determined to complete the rendering of the entire three-dimensional model. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0049] Figure 1 It is a schematic diagram of an implementation manner of the method for generating the unit temperature distribution map by fiber Bragg grating temperature measurement according to the present invention;

[0050] Figure 2 It is a processing schematic diagram when one or more temperature calculation models are selected in the method for generating the unit temperature distribution map by fiber Bragg grating temperature measurement according to the present invention;

[0051] Figure 3 It is a schematic diagram of another implementation manner of the method for generating the unit temperature distribution map by fiber Bragg grating temperature measurement according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present invention. On the contrary, they are only examples of systems and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0053] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0054] As Figure 1 shown, the present invention provides a method for generating a unit temperature distribution map by fiber Bragg grating temperature measurement. The steps of the method include:

[0055] Step S110: Divide the target temperature range into multiple sub-temperature ranges, construct a training data set for each sub-temperature range, and pre-train the temperature calculation model to obtain each temperature calculation model corresponding to each sub-temperature range;

[0056] Specifically, in the step of pre-training the temperature calculation model, each training data group corresponding to each sub-temperature segment is used for pre-training. Specifically, the temperature calculation model is pre-trained by calculating the loss function.

[0057] In the specific implementation process, the temperature calculation model can be an LSTM model or a Transformer model. The LSTM (Long Short-Term Memory) model is a special recurrent neural network (RNN). By introducing memory cells and gating mechanisms such as input gates, forget gates, and output gates, it solves the problems of gradient disappearance and gradient explosion in the processing of long-sequence data by ordinary RNNs, and can capture long-term dependencies in sequences, and is widely used in fields such as natural language processing, time series prediction, and speech recognition. The Transformer model is a deep learning model based on self-attention mechanism, which is specifically used to process sequence data, such as natural language text. Through the encoder-decoder architecture and parallel computing capabilities, it effectively captures long-range dependencies in sequence data, significantly improving the efficiency and accuracy of natural language processing tasks.

[0058] Step S210, for each temperature measurement point, obtain the historical data of this temperature measurement point. The historical data includes multi-dimensional temperature measurement data at each historical time point, and predict the multi-dimensional temperature measurement data at the next time point based on the historical data of the temperature measurement point. The multi-dimensional temperature measurement data includes the change value of the Bragg wavelength and the measurement value of the environmental sensor.

[0059] In the specific implementation process, the environmental sensor includes a temperature sensor, a humidity sensor, a vibration frequency sensor, a loudness sensor, a pressure sensor, and a noise frequency sensor arranged in the environment.

[0060] Step S300, calculate the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, and select a temperature calculation model based on the predicted temperature change value.

[0061] In some embodiments of the present invention, in the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, the relationship between the change value of the Bragg wavelength, the measurement value of the environmental sensor, and the temperature change value in the pre-set physical model of the linear compensation relationship is used to calculate the predicted temperature change value.

[0062] In the specific implementation process, in the step of selecting a temperature calculation model based on the predicted temperature change value, calculate the predicted temperature value based on the temperature value at the previous time point and the predicted temperature change value, and determine the selected temperature calculation model based on the sub-temperature segment where the predicted temperature value is located.

[0063] In the specific implementation process, in the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, the multi-dimensional temperature measurement data in the historical time period is constructed into a vector and predicted through a pre-trained LSTM model to obtain the multi-dimensional temperature measurement data at the predicted next time point.

[0064] Step S400, construct a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point, and input the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point;

[0065] Step S500, render the three-dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit, and determine the temperature distribution map output for the user based on the user's viewing cone.

[0066] In the specific implementation process, determine the pixel value for rendering based on the correspondence between the temperature value and the pixel value in the pre-set look-up table.

[0067] Adopting the above solution, this solution first pre-sets a temperature calculation model for each sub-temperature segment. For temperature measurement in a relatively large temperature range, more refined processing can be achieved through the division of sub-temperature segments. On the other hand, this solution predicts the multi-dimensional temperature measurement data, calculates the predicted temperature change value based on the predicted multi-dimensional temperature measurement data, and then determines the temperature calculation model that needs to be called, without having to call all the temperature calculation models, ensuring the utilization efficiency of computing resources. And in the final temperature measurement process, a temperature measurement vector is constructed through the multi-dimensional temperature measurement data to determine the final temperature measurement value. This solution takes into account the change in the Bragg wavelength while incorporating the environmental sensor measurement values, and through the temperature calculation models pre-set for each sub-temperature segment, ensures accurate temperature measurement of the power plant unit.

[0068] In some embodiments of the present invention, the environmental sensor measurement values include auxiliary sensor measurement values and pressure measurement values. In the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, calculate the predicted temperature change value based on the Bragg wavelength change value, auxiliary sensor measurement values, pressure measurement values, and noise constant.

[0069] In some embodiments of the present invention, in the step of calculating the predicted temperature change value based on the Bragg wavelength change value, auxiliary sensor measurement values, pressure measurement values, and noise constant, calculate the predicted temperature change value based on the following formula:

[0070]

[0071] Where, ΔT represents the predicted temperature change value, Δλ B represents the Bragg wavelength change value, K ε and K Prespectively represent the auxiliary sensor and the pressure coefficient, Δε and ΔP respectively represent the change value of the auxiliary sensor and the change value of the pressure, δ represents the noise constant, and K T represents the temperature coefficient.

[0072] In the specific implementation process, the auxiliary sensor can be any one of a temperature sensor, a humidity sensor, a vibration frequency sensor, a loudness sensor, and a noise frequency sensor.

[0073] Adopting the above scheme, based on the linear compensation relationship of the accurate physical model for the temperature change value, this scheme combines the sensor data measured by each external sensor with the change value of the Bragg wavelength of the optical fiber, and adds a noise constant during the combination process to further compensate the calculation result, ensuring the calculation accuracy of the predicted temperature change value.

[0074] In some embodiments of the present invention, in the step of calculating the predicted temperature change value based on the Bragg wavelength change value, the auxiliary sensor measurement value, the pressure measurement value, and the noise constant, the used Bragg wavelength change value, auxiliary sensor measurement value, and pressure measurement value are all the values after standardizing the original Bragg wavelength change value, auxiliary sensor measurement value, and pressure measurement value.

[0075] In some embodiments of the present invention, in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point:

[0076] Obtain the multi-dimensional temperature measurement data of the nearest preset time length, and respectively construct a temperature measurement vector from the nearest preset time length and the multi-dimensional temperature measurement data actually measured at the next time point;

[0077] Take each temperature measurement vector as a data row, and arrange the temperature measurement vectors vertically based on the time corresponding to the time point of the temperature measurement vector to obtain the temperature measurement matrix.

[0078] Specifically, each row of the temperature measurement matrix corresponds to a time point, and each column corresponds to a certain dimension of temperature measurement data.

[0079] Adopting the above scheme, in the actual temperature measurement calculation process of each temperature measurement point, this scheme uses a temperature calculation model for accurate calculation, not only comprehensively considering the environmental sensor measurement value and the Bragg wavelength change value to ensure the calculation accuracy; but also introducing the time sequence relationship of each time point through the temperature measurement matrix, making the final temperature calculation of each temperature measurement point more accurate.

[0080] In some embodiments of the present invention, the temperature calculation model includes a first processing module and a second processing module. The first processing module uses an ID-CNN model, and the second processing module uses an LSTM model. The first processing module and the second processing module are connected in sequence to obtain the temperature calculation model.

[0081] In the specific implementation process, during the temperature measurement process of this solution, the combined model of ID-CNN and LSTM has the dual advantages of spatial feature extraction and temporal dynamic modeling: ID-CNN efficiently captures the local detailed features of fiber Bragg gratings (FBGs) (such as peak shift, spectral distortion) through convolutional kernels, and effectively extracts the spatial patterns related to temperature; while LSTM models the temporal dependence relationship of temperature changes (such as dynamic thermal gradients, periodic noise) through memory units, suppresses instantaneous interference and predicts trend changes. After the two are combined, the model can not only identify subtle temperature fluctuations from single-spectrum data, but also enhance the anti-interference ability in a dynamic environment through time series analysis, thereby significantly improving the temperature measurement accuracy and robustness in complex scenarios (such as vibration, rapid temperature change).

[0082] As Figure 2 shown, in some embodiments of the present invention, there is an overlapping region between at least two adjacent sub-temperature segments. In the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point and selecting the temperature calculation model based on the predicted temperature change value, if it is determined that the temperature calculation model corresponding to the predicted temperature change value is one or more, if it is one, then in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point, step S410 is performed and calculation is carried out using this temperature calculation model;

[0083] If there are multiple, then in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point, it includes:

[0084] Perform step S421 to calculate the intermediate temperature value based on the sub-temperature segment corresponding to each selected temperature calculation model;

[0085] Perform step S422 to determine the predicted temperature based on the predicted temperature change value, calculate the temperature difference between the predicted temperature and each intermediate temperature value, and determine the weight values of each selected temperature calculation model based on the temperature difference:

[0086] Perform step S423 to perform weighted calculation on the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point.

[0087] In the specific implementation process, adjacent sub-temperature segments can be -10 to 10 °C, -5 to 15 °C, 0 to 20 °C, 5 to 25 °C,..., 40 to 50 °C, 43 to 52 °C, etc. The temperature ranges summarized by each sub-temperature segment can be uneven; specifically, the temperature median of -10 to 10 °C is 0 °C, the temperature median of 5 to 25 °C is 15 °C, and the temperature median of 40 to 50 °C is 45 °C.

[0088] Specifically, in the step of determining the predicted temperature based on the predicted temperature change value, the predicted temperature value is calculated based on the temperature value at the previous time point and the predicted temperature change value.

[0089] With the above solution, first, by setting temperature calculation models corresponding to multiple sub-temperature segments, the calculation of temperature is made more refined. Further, in order to address the poor performance of the temperature calculation model in calculating the temperature at the edges of the sub-temperature segments, this solution sets an overlapping area between at least two adjacent sub-temperature segments. When the predicted temperature is in the overlapping area at the edge, comprehensive calculation is performed through the corresponding multiple temperature calculation models, and the weight value for calculation is determined based on the temperature difference between the predicted temperature and the temperature median of each sub-temperature segment. By performing weighted calculation on the outputs of each temperature calculation model, the calculation at the edges of the sub-temperature segments of the temperature calculation model is bridged, further ensuring the calculation accuracy.

[0090] In some embodiments of the present invention, in the step of determining the weight value of each selected temperature calculation model based on the temperature difference, the following formula is used to calculate the weight value of each temperature calculation model:

[0091]

[0092] where τ represents the weight value and θ represents the temperature difference;

[0093] In the step of performing weighted calculation on the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point, the weighted average value of the output values of each selected temperature calculation model is calculated to obtain the temperature value of the temperature measurement point.

[0094] As Figure 3 shown, in some embodiments of the present invention, the step of rendering the three-dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit and determining the temperature distribution map output for the user based on the user's viewing cone includes:

[0095] Step S511, rendering the three-dimensional model block of the area where the temperature measurement point is located in the three-dimensional model based on the pixel value corresponding to the temperature value of the temperature measurement point;

[0096] Step S512: For the 3D model blocks in the area of the 3D model not covered by the temperature measurement points, calculate the distance value between the 3D model block and the temperature measurement points within the threshold distance range of the 3D model block, and determine the temperature influence weight based on the distance value.

[0097] In the specific implementation process, the unrendered 3D model is a 3D framework constructed according to the structure of the target unit of the power plant, and the 3D framework is composed of stacked 3D model blocks.

[0098] In the specific implementation process, in the step of calculating the distance value between the 3D model block and the temperature measurement points within the threshold distance range of the 3D model block, calculate the cosine distance between the coordinates as the distance value.

[0099] In the specific implementation process, in the step of determining the temperature influence weight based on the distance value, use the following formula to calculate the temperature influence weight:

[0100]

[0101] Where σ represents the temperature influence weight and d represents the distance value.

[0102] Step S513: Based on the temperature influence weight, perform weighted calculation on the temperature values of each temperature measurement point within the threshold distance range of the 3D model block, determine the temperature value of the corresponding 3D model block, and determine the pixel value corresponding to the temperature value, and render the corresponding 3D model block with the pixel value.

[0103] In the step of performing weighted calculation on the temperature values of each temperature measurement point within the threshold distance range of the 3D model block based on the temperature influence weight and determining the temperature value of the corresponding 3D model block, calculate the weighted average as the temperature value.

[0104] Adopting the above solution, for the area of the 3D model covered by the temperature measurement points, the 3D model of this solution is directly rendered based on the temperature values measured by the temperature measurement points. For the area not covered by the temperature measurement points, first determine the temperature measurement points within the threshold distance range of each 3D model block, determine the temperature influence weight based on the distance from the temperature measurement points, the closer the distance, the greater the temperature influence weight, determine the temperature at this position through weighted calculation, and then determine the pixel value to complete the rendering of the entire 3D model.

[0105] In some embodiments of the present invention, in the step of determining the temperature distribution map output for the user based on the user's viewing frustum, it includes step S521: Perform an intersection test between the user's viewing frustum and the rendered 3D model to determine the 3D model blocks that intersect with the user's viewing frustum; step S522: Construct the range enclosed by the 3D model blocks that intersect with the user's viewing frustum as the temperature distribution map and give feedback.

[0106] On the other hand, the present invention also relates to a system for generating a unit temperature distribution map by using fiber Bragg grating temperature measurement. The system includes a computer device, which includes a processor and a memory. Computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0107] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to implement the foregoing method for generating a unit temperature distribution map by using fiber Bragg grating temperature measurement. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium known in the art.

[0108] Those of ordinary skill in the art should understand that the various exemplary components, systems, and methods described in connection with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Specifically, whether to implement in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician may use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention. When implemented in hardware, it may be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment may be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link.

[0109] It should be clear that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0110] In the present invention, the features described and / or illustrated for one embodiment can be used in the same or similar manner in one or more other embodiments, and / or combined with the features of other embodiments or replace the features of other embodiments.

[0111] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for generating a unit temperature distribution map by using fiber Bragg grating temperature measurement, characterized in that, The steps of the method include: Dividing the temperature range of the target into multiple sub-temperature ranges, constructing a training data set for each sub-temperature range, and pre-training the temperature calculation model to obtain temperature calculation models corresponding to each sub-temperature range; Obtaining the historical data of each temperature measurement point, where the historical data includes multi-dimensional temperature measurement data at each historical time point, and predicting the multi-dimensional temperature measurement data at the next time point based on the historical data of the temperature measurement point. The multi-dimensional temperature measurement data includes the change value of the Bragg wavelength and the measurement value of the environmental sensor; Calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, and selecting the temperature calculation model based on the predicted temperature change value; Constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point, and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point; Rendering the three-dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit, and determining the temperature distribution map output to the user based on the user's viewing cone.

2. The method for generating the unit temperature distribution diagram by fiber Bragg grating temperature measurement according to claim 1, characterized in that The measurement value of the environmental sensor includes the measurement value of the auxiliary sensor and the pressure measurement value. In the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point, the predicted temperature change value is calculated based on the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, the pressure measurement value, and the noise constant.

3. The method for generating the unit temperature distribution diagram by fiber Bragg grating temperature measurement according to claim 2, characterized in that, In the step of calculating the predicted temperature change value based on the change value of the Bragg wavelength, the measurement value of the auxiliary sensor, the pressure measurement value, and the noise constant, the predicted temperature change value is calculated based on the following formula: where ΔT represents the predicted temperature change value, and Δλ B represents the change value of the Bragg wavelength, K ε and K P represent the auxiliary sensor and the pressure coefficient respectively, Δε and ΔP represent the change values of the auxiliary sensor and the change value of the pressure respectively, δ represents the noise constant, and K T represents the temperature coefficient.

4. The method for generating the unit temperature distribution diagram by fiber Bragg grating temperature measurement according to claim 1, wherein, In the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point, inputting the temperature measurement matrix into the selected temperature calculation model, and determining the temperature value of the temperature measurement point: Obtaining the multi-dimensional temperature measurement data of the most recent preset time length, and respectively constructing a temperature measurement vector from the most recent preset time length and the multi-dimensional temperature measurement data actually measured at the next time point; Taking each temperature measurement vector as a data row, and arranging the temperature measurement vectors longitudinally based on the time corresponding to the time point of the temperature measurement vector to obtain the temperature measurement matrix.

5. The method for generating the unit temperature distribution diagram by fiber Bragg grating temperature measurement according to claim 1, wherein The temperature calculation model includes a first processing module and a second processing module. The first processing module uses a 1D-CNN model, and the second processing module uses an LSTM model. The first processing module and the second processing module are connected in sequence to obtain the temperature calculation model.

6. The method for generating the unit temperature distribution map by optical fiber grating temperature measurement according to any one of claims 1-5, characterized in that There is an overlapping area between at least two adjacent sub-temperature ranges. In the step of calculating the predicted temperature change value based on the multi-dimensional temperature measurement data at the next time point and selecting the temperature calculation model based on the predicted temperature change value, if it is determined that the temperature calculation model corresponding to the predicted temperature change value is one or more, and if it is one, then in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point, inputting the temperature measurement matrix into the selected temperature calculation model, and determining the temperature value of the temperature measurement point, this temperature calculation model is used for calculation; If there are multiple, in the step of constructing a temperature measurement matrix based on the multi-dimensional temperature measurement data actually measured at the next time point and inputting the temperature measurement matrix into the selected temperature calculation model to determine the temperature value of the temperature measurement point: Calculate the intermediate temperature value based on the sub-temperature segments corresponding to each selected temperature calculation model; Determine the predicted temperature based on the predicted temperature change value, calculate the temperature difference between the predicted temperature and each intermediate temperature value, and determine the weight values of the selected temperature calculation models based on the temperature difference; Perform weighted calculation on the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point.

7. The method for generating the unit temperature distribution diagram by fiber Bragg grating temperature measurement according to claim 6, wherein In the step of determining the weight values of the selected temperature calculation models based on the temperature difference, use the following formula to calculate the weight values of each temperature calculation model: where τ represents the weight value and θ represents the temperature difference; In the step of performing weighted calculation on the output values of the selected temperature calculation models based on the weight values of each temperature calculation model to obtain the temperature value of the temperature measurement point, calculate the weighted average value of the output values of the selected temperature calculation models to obtain the temperature value of the temperature measurement point.

8. The method for generating the unit temperature distribution map by fiber Bragg grating temperature measurement according to claim 1, characterized in that The step of rendering the three-dimensional model of the target unit based on the positions and temperature values of each temperature measurement point distributed in the target unit and determining the temperature distribution map output to the user based on the user's viewing cone includes: Render the three-dimensional model block of the area where the temperature measurement point is located in the three-dimensional model based on the pixel value corresponding to the temperature value of the temperature measurement point; For the three-dimensional model blocks in the area not covered by the temperature measurement points in the three-dimensional model, calculate the distance value between the three-dimensional model block and the temperature measurement points within the threshold distance range of the three-dimensional model block, and determine the temperature influence weight based on the distance value; Perform weighted calculation on the temperature values of each temperature measurement point within the threshold distance range of the three-dimensional model block based on the temperature influence weight, determine the temperature value of the corresponding three-dimensional model block, and determine the pixel value corresponding to the temperature value, and render the corresponding three-dimensional model block with the pixel value.

9. The method for generating the unit temperature distribution diagram by optical fiber grating temperature measurement according to claim 1 or 8, characterized in that, In the step of determining the temperature distribution map output to the user based on the user's viewing cone, perform an intersection test between the user's viewing cone and the rendered three-dimensional model, determine the three-dimensional model blocks intersecting with the user's viewing cone, construct the range surrounded by the three-dimensional model blocks intersecting with the user's viewing cone as the temperature distribution map, and perform feedback.

10. A unit temperature distribution map generation system for temperature measurement by fiber Bragg grating, characterized in that: The system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method according to any one of claims 1-9.

Images