Meteorological temperature measuring method and system based on optical fiber sensor

Abstract

The invention relates to the field of meteorological temperature measurement, in particular to a meteorological temperature measurement method and system based on an optical fiber sensor, and the method comprises the steps: collecting data information in an environment through the optical fiber sensor, carrying out the preprocessing of the obtained different parameter information, and providing a data basis for the meteorological temperature measurement method; establishing a meteorological temperature prediction neural network model according to the preprocessed data information, and predicting the meteorological temperature; the meteorological temperature measurement process is improved according to the requirements of different meteorological environments and the prediction result of the meteorological temperature; and evaluating the improvement result of the specific process of meteorological temperature measurement, establishing a temperature measurement evaluation model, and evaluating the effect of the temperature measurement result in practical application. High-precision temperature measurement is provided, meteorological temperature data can be monitored in real time through manual intervention, the change condition of the meteorological temperature is reflected in time, and the whole measurement process has high reliability and stability.

Description

Technical Field

[0001] The present invention relates to the field of meteorological temperature measurement, and in particular to a meteorological temperature measurement method and system based on an optical fiber sensor. Background Art

[0002] With the development of fiber optic sensing technology, fiber optic sensors have become an advanced sensing technology widely used in various fields, with advantages such as high precision, remote monitoring and anti-interference. Fiber optic sensors have broad application prospects in meteorological temperature measurement due to their high sensitivity, easy deployment and remote transmission. At the same time, meteorological temperature is an important parameter in meteorology, which is of great significance to many fields such as weather forecasting, climate research and environmental monitoring, industrial development, etc., and traditional meteorological temperature measurement methods have some limitations, such as low accuracy, limited measurement range, inconvenient automatic reading, and inability to remotely monitor.

[0003] However, there are still some problems with the current methods of applying fiber optic sensors to meteorological temperature measurement: it is impossible to conduct multi-dimensional comprehensive modeling and analysis of temperature prediction based on historical data, and it is impossible to improve the accuracy and stability of measurement; the measurement process is not further optimized based on the obtained meteorological temperature prediction results, resulting in excessive uniformity and lack of strategic deployment; and how to evaluate the meteorological temperature measurement results for the variable measurement process is always ignored, which cannot improve the performance of the measurement method.

[0004] Therefore, a method and system for measuring meteorological temperature based on optical fiber sensors are needed. Summary of the invention

[0005] The present invention provides a meteorological temperature measurement method and system based on an optical fiber sensor, the purpose of which is to provide high-precision temperature measurement and realize remote monitoring. The meteorological temperature data can be monitored in real time without human intervention, and the changes in meteorological temperature can be reflected in time, so that the entire measurement process has high reliability and stability.

[0006] The technical solution of the present invention is specifically as follows: A method for measuring meteorological temperature based on an optical fiber sensor comprises the following steps: Step S1. Collect data information in the environment through the optical fiber sensor, pre-process the acquired different parameter information, and provide a data basis for the meteorological temperature measurement method; Step S2. Establish a weather temperature prediction neural network model based on the preprocessed data information to predict the weather temperature; Step S3. Improve the meteorological temperature measurement process according to the needs of different meteorological environments and the forecast results of meteorological temperature; Step S4. Based on the evaluation results of the improvement of the specific process of meteorological temperature measurement, a temperature measurement evaluation model is established to evaluate the effect of the temperature measurement results in practical applications.

[0007] Further, step S2 specifically includes: The historical parameter data obtained after preprocessing is used as training samples and as input data for the meteorological temperature prediction neural network model. The meteorological temperature prediction neural network model includes an input layer, a comprehensive analysis layer, an optimization prediction layer, a dynamic adjustment layer, and an output layer.

[0008] Furthermore, in step S2, the features extracted from the comprehensive analysis layer are processed in the optimization prediction layer. The specific process is as follows: in, Represents the input of the optimized prediction layer; Represents the connection weight between the comprehensive analysis layer and the optimized prediction layer; Represents the output value of the input layer; Represents the bias of the optimized prediction layer; Represents the output of the optimized prediction layer; The sensitivity coefficient representing the control difference; Indicates the variance difference, which is used to measure the degree of data variation; Parameters that represent the impact of the degree of variation; Represents the correction parameters in the optimization prediction process; It represents the difference between the actual sensor device delay time and the expected delay time during the prediction process; represents the prediction validation coefficient; Represents the constraint value in temperature prediction; represents a constant adjustment parameter; Indicates the amount of heat gained at the current temperature; Indicates the amount of heat gained at a reference temperature.

[0009] Furthermore, in step S2, a feedback mechanism is introduced in the dynamic adjustment layer, so that the model can dynamically adjust the parameters of the network according to the output and error conditions. The specific process is as follows: in, Represents the input of the dynamic adjustment layer; Represents the connection weight between the optimized prediction layer and the dynamic adjustment layer; Indicates the bias of the dynamic adjustment layer; Represents the output of the dynamic adjustment layer; represents the adjustment factor; represents the proportionality coefficient; represents the gain coefficient; Indicates the temperature comparison data under the historical standard state, which is used to verify with the real-time temperature data; represents the error signal; Indicates The temperature change between the actual temperature data and the reference value. ; Indicates The temperature change between the predicted temperature value and the reference value.

[0010] Further, step S3 specifically includes: in, represents the output of the improved meteorological temperature measurement process; Represents the output of the meteorological temperature prediction neural network model; Indicates the offset parameter; Indicates the stability coefficient during the improvement process; Represents the historical parameter data obtained by the sensor after preprocessing; represents the sensitivity coefficient; Indicates the adaptability of the feature task after extraction to different meteorological environment requirements; Indicates the improvement optimization coefficient; Indicates The weight of the feature task, ; Indicated in Time The basic resources obtained from each feature task.

[0011] Further, step S4 specifically includes: in, represents the output result of the temperature measurement evaluation model; A label representing the model; Indicates the total number of tags; Indicated in the feature Application of predicted temperature The probability of Indicates feature labels; The predicted temperature The number of applications, that is, the number of times it is applied and executed; Indicated in The output value of the improved meteorological temperature measurement process.

[0012] Further, step S4 specifically includes: Defining Thresholds ,if , it means that the meteorological temperature measurement is inaccurate or does not meet the standards required by the business; if , it means that the meteorological temperature measurement is accurate or meets the standards required by the business.

[0013] A meteorological temperature measurement system based on optical fiber sensor, comprising the following contents: Parameter information acquisition module, information preprocessing module, meteorological temperature prediction module, temperature dynamic adjustment module, measurement process improvement module, temperature measurement evaluation module; The parameter information acquisition module monitors various parameters in the meteorological environment in real time through optical fiber sensors and transmits the collected data information to the information preprocessing module; The information preprocessing module performs preliminary processing on the collected parameter information, including data cleaning, denoising, outlier detection and data format conversion operations, and transmits the preprocessed data information to the meteorological temperature prediction module, the temperature dynamic adjustment module and the measurement process improvement module to ensure the accuracy and reliability of the data; The meteorological temperature prediction module uses the collected parameter information and historical data to establish a meteorological temperature prediction neural network model, predict the future meteorological temperature, and pass the prediction results to the temperature dynamic module; The temperature dynamic adjustment module performs a dynamic adjustment layer in the meteorological temperature prediction neural network model, introduces a feedback mechanism, continuously adjusts the model according to actual conditions, and transmits the adjusted data information to the measurement improvement module; The measurement process improvement module improves the meteorological temperature measurement process according to the requirements of different meteorological environments and the forecast results of meteorological temperature, and transmits the improved data information to the temperature measurement module; The temperature measurement evaluation module evaluates the improvement results of the specific process of meteorological temperature measurement, establishes a temperature measurement evaluation model, and evaluates the accuracy and reliability of the system. Beneficial Effects

[0014] 1. The present invention can perform multi-dimensional analysis on pre-processed data, including historical data, environmental factors, etc., through the meteorological temperature prediction neural network model, to achieve real-time prediction of meteorological temperature, timely reflect the changes in meteorological temperature, and help to respond and adjust in time. Through accurate meteorological temperature prediction, resource utilization can be better planned, waste of resources and unnecessary losses can be avoided, and resource utilization efficiency can be improved. At the same time, through the structural design of the comprehensive analysis layer, optimization prediction layer, and dynamic adjustment layer, the prediction accuracy, dynamic adjustment capability, real-time performance, and flexibility can be effectively improved, and the stability of the model and the ability to continuously optimize and improve can be maintained.

[0015] 2. The present invention improves the measurement process through the meteorological temperature prediction results, which can improve the accuracy of the measurement and make the measurement results more reliable and accurate; combined with the meteorological prediction results, it can realize real-time adjustment of the measurement process, and perform corresponding measurement optimization according to the predicted meteorological temperature change trend to maintain the timeliness and accuracy of the measurement. By optimizing the measurement process in combination with the meteorological temperature prediction results, the efficiency of the measurement process can be improved and the manpower and time costs can be reduced; at the same time, according to the different meteorological environment requirements and prediction results, the measurement methods and strategies are continuously improved, so that the measurement process is continuously optimized and can adapt to the measurement requirements under different meteorological conditions.

[0016] 3. By establishing a temperature measurement evaluation model, the present invention can evaluate the sensitivity of the improved measurement method to temperature changes, ensuring that temperature changes can be accurately reflected in different temperature ranges; as well as the real-time performance of the measurement method, that is, the response speed and delay of the measurement results, to help determine whether the improvement has improved the real-time performance. In addition, the temperature measurement evaluation model can evaluate the reliability of the improved measurement method, including the stability and failure rate of the system, to help determine whether the improvement has enhanced the reliability of the system; provide guidance for future improvements, help determine the next optimization direction and focus, and continuously improve the performance of the measurement method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a meteorological temperature measurement method based on an optical fiber sensor of the present invention; Figure 2 This is a module diagram of a meteorological temperature measurement system based on an optical fiber sensor of the present invention. DETAILED DESCRIPTION

[0018] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] Refer to the attached Figure 1 This embodiment provides a method for measuring meteorological temperature based on an optical fiber sensor, comprising the following steps: S1. Deploy the fiber optic sensor in the meteorological environment that needs to be monitored, such as a weather station, farmland, etc.; collect the optical signal data information in the environment through the fiber optic sensor, and convert the optical signal into a digital signal, including temperature value, refractive index, wavelength, propagation speed, timestamp, location information, environmental conditions, etc.; wherein the location information is the location information of each measurement recorded when the sensor is placed in different positions, and the environmental conditions are humidity, air pressure, wind speed, wind direction, sunshine intensity, surface temperature, dew point temperature, ultraviolet index and other data information; the relevant data information is transmitted to the data storage unit to ensure the accuracy and integrity of the data.

[0020] The obtained different parameter information is preprocessed, and the noise is removed by using a digital filter and normalized. The specific process is as follows: in, Represents the normalized value; represents the value before normalization; Indicates the minimum value of parameter information; Indicates the maximum value of parameter information.

[0021] Specifically, after removing the outliers, the fitting algorithm is used for fitting, and the filter function determined by the fitting function is used to estimate the true value of the signal and filter out the noise, thereby achieving optimized processing of the collected data.

[0022] The present invention can realize real-time monitoring of meteorological temperature through optical fiber sensors, and timely obtain changes in ambient temperature, which is helpful for better understanding and prediction of climate change; and can realize simultaneous monitoring of temperatures at multiple locations, which is of great help in accurately measuring meteorological temperature.

[0023] S2. Based on the preprocessed sensor data information, a meteorological temperature prediction neural network model is established to predict the meteorological temperature.

[0024] In an embodiment of the present invention, a meteorological temperature prediction neural network model is established, and the historical parameter data obtained after preprocessing is used as a training sample and as input data of the meteorological temperature prediction neural network model. The model is trained through deep learning, wherein the meteorological temperature prediction neural network model includes an input layer, a comprehensive analysis layer, an optimization prediction layer, a dynamic adjustment layer, and an output layer.

[0025] The training samples are composed of historical parameter data obtained by sensors after data preprocessing. , Represents sensor data information collected at different timestamps, where: , Indicates the number of different timestamps recorded. data information, expressed as ,in Represents the input of the meteorological temperature prediction neural network model. There are neurons; in the input layer, Passed to the comprehensive analysis layer of the weather forecast neural network, the specific process is as follows: in, Represents the input of the comprehensive analysis layer; Represents the connection weight between the input layer and the comprehensive analysis layer; Represents the output value of the input layer; represents the bias of the first hidden layer.

[0026] In the comprehensive analysis layer, the input data is processed and analyzed to capture key patterns and information in the data. The specific process is as follows: in, Represents the output of the comprehensive analysis layer; represents the attenuation coefficient; Indicates the moment when the recording process is terminated; represents the learning factor; Indicates the reference temperature under standard conditions; Indicates the average temperature during the recording time; , denote the corresponding coefficients of refractive index and propagation velocity at reference temperature respectively; Indicates The refractive index of light collected by the sensor at the corresponding time, ; Indicates The speed of light propagation collected by the sensor at the corresponding time; It represents the refractive index at standard temperature; Indicates the propagation speed at standard temperature; Parameter indicating the effect of humidity on temperature change; Parameter indicating the effect of air pressure on temperature change; Indicates the parameter value of the effect of sunlight intensity on temperature change; Indicates the parameter value of the effect of wind speed on temperature change; Time domain function representing humidity parameter information; A time domain function representing information on air pressure parameters; A time domain function representing information on solar radiation intensity parameters; A time domain function representing wind speed parameter information; , , , They represent the collection frequencies of humidity parameters, air pressure parameters, sunshine intensity parameters, and wind speed parameters respectively; Indicates the response time of the sensor to temperature changes.

[0027] In the optimization prediction layer, the features extracted from the comprehensive analysis layer are further processed to better predict the meteorological temperature. The specific process is as follows: in, Represents the input of the optimized prediction layer; Represents the connection weight between the comprehensive analysis layer and the optimized prediction layer; Represents the output value of the input layer; Represents the bias of the optimized prediction layer; Represents the output of the optimized prediction layer; The sensitivity coefficient representing the control difference; Indicates the variance difference, which is used to measure the degree of data variation; Parameters that represent the impact of the degree of variation; Represents the correction parameters in the optimization prediction process; It represents the difference between the actual sensor device delay time and the expected delay time during the prediction process; represents the prediction validation coefficient; Represents the constraint value in temperature prediction; represents a constant adjustment parameter; Indicates the amount of heat gained at the current temperature; Indicates the amount of heat gained at a reference temperature.

[0028] In the dynamic adjustment layer, a feedback mechanism is introduced so that the model can dynamically adjust the parameters of the network according to the output and error conditions. The specific process is as follows: in, Represents the input of the dynamic adjustment layer; Represents the connection weight between the optimized prediction layer and the dynamic adjustment layer; Indicates the bias of the dynamic adjustment layer; Represents the output of the dynamic adjustment layer; represents the adjustment factor; represents the proportionality coefficient; represents the gain coefficient; Indicates the temperature comparison data under the historical standard state, which is used to verify with the real-time temperature data; represents the error signal; Indicates The temperature change between the actual temperature data and the reference value. ; Indicates The temperature change between the predicted temperature value and the reference value.

[0029] Finally, the dynamic adjustment layer passes the adjusted predicted meteorological temperature to the output layer, and outputs the output result of the meteorological temperature prediction application network model in the output layer. The specific process is as follows: in, represents the output result of the output layer, represents the connection weight between the dynamic adjustment layer and the output layer, Represents the bias of the output layer.

[0030] The present invention can perform multi-dimensional analysis on pre-processed data, including historical data, environmental factors, etc., through the meteorological temperature prediction neural network model, realize real-time prediction of meteorological temperature, timely reflect the changes in meteorological temperature, and help to respond and adjust in time. Through accurate meteorological temperature prediction, resource utilization can be better planned, waste of resources and unnecessary losses can be avoided, and resource utilization efficiency can be improved. At the same time, through the structural design of the comprehensive analysis layer, the optimization prediction layer, and the dynamic adjustment layer, the prediction accuracy, dynamic adjustment capability, real-time performance and flexibility can be effectively improved, and the stability of the model and the ability of continuous optimization and improvement can be maintained.

[0031] S3. According to the requirements of different meteorological environments and the forecast results of meteorological temperature, the meteorological temperature measurement process is improved to facilitate flexible deployment and adjustment of the monitoring system.

[0032] Specifically, when improving the meteorological temperature measurement process, the content includes but is not limited to the location deployment of sensors, the calibration frequency of related equipment, the response time of sensors in different environments, and energy consumption, etc. At the same time, the requirements for different meteorological environments include but are not limited to accuracy requirements, stability requirements, cost requirements, adaptability requirements, etc.; key features and key tasks are extracted through existing technologies.

[0033] in, represents the output of the improved meteorological temperature measurement process; Represents the output of the meteorological temperature prediction neural network model; Represents the offset parameter; Indicates the stability coefficient during the improvement process; Represents the historical parameter data obtained by the sensor after preprocessing; represents the sensitivity coefficient; Indicates the adaptability of the feature task after extraction to different meteorological environment requirements; Indicates the improvement optimization coefficient; Indicates The weight of the feature task, ; Indicated in Time The basic resources obtained from each feature task.

[0034] The present invention improves the measurement process through the meteorological temperature prediction results, which can improve the accuracy of the measurement and make the measurement results more reliable and accurate; combined with the meteorological prediction results, the real-time adjustment of the measurement process can be realized, and the corresponding measurement optimization is performed according to the predicted meteorological temperature change trend to maintain the timeliness and accuracy of the measurement. By optimizing the measurement process in combination with the meteorological temperature prediction results, the efficiency of the measurement process can be improved and the manpower and time costs can be reduced; at the same time, according to different meteorological environment requirements and prediction results, the measurement methods and strategies are continuously improved, so that the measurement process is continuously optimized and can adapt to the measurement requirements under different meteorological conditions.

[0035] S4. Based on the evaluation results of the improvement of the specific process of meteorological temperature measurement, a temperature measurement evaluation model is established to evaluate the effect of temperature measurement results in real applications and the accuracy and reliability of the evaluation system.

[0036] Based on the improvement results of the specific process of meteorological temperature measurement, an evaluation model for temperature measurement is established to evaluate the effect of temperature measurement results in real applications, such as the accuracy requirements for meteorological temperature and the impact of measurement results on business decisions. The specific process is as follows: in, represents the output result of the temperature measurement evaluation model; A label representing the model; Indicates the total number of tags; Indicated in the feature Application of predicted temperature The probability of Indicates feature labels; The predicted temperature The number of applications, that is, the number of times it is applied and executed; Indicated in The output value of the improved meteorological temperature measurement process.

[0037] Specifically, the threshold is set based on a large number of experiments and expert experience. ,if , it means that the meteorological temperature measurement is inaccurate or does not meet the standards required by the business; if , it means that the meteorological temperature measurement is accurate or meets the standards required by the business.

[0038] By establishing a temperature measurement evaluation model, the present invention can evaluate the sensitivity of the improved measurement method to temperature changes, ensuring that temperature changes can be accurately reflected in different temperature ranges; as well as the real-time performance of the measurement method, that is, the response speed and delay of the measurement results, to help determine whether the improvement has improved the real-time performance. In addition, the temperature measurement evaluation model can evaluate the reliability of the improved measurement method, including the stability and failure rate of the system, to help determine whether the improvement has enhanced the reliability of the system; provide guidance for future improvements, help determine the next optimization direction and focus, and continuously improve the performance of the measurement method.

[0039] Refer to the attached Figure 2 , this embodiment provides a meteorological temperature measurement system based on an optical fiber sensor, including the following contents: Parameter information acquisition module, information preprocessing module, meteorological temperature prediction module, temperature dynamic adjustment module, measurement process improvement module, temperature measurement evaluation module; The parameter information acquisition module monitors various parameters in the meteorological environment in real time through optical fiber sensors, including temperature, humidity, wind speed, air pressure, etc., and transmits the collected data information to the information preprocessing module; The information preprocessing module performs preliminary processing on the collected parameter information, including data cleaning, denoising, outlier detection and data format conversion, and transmits the preprocessed data information to the meteorological temperature prediction module, the temperature dynamic adjustment module and the measurement process improvement module to ensure the accuracy and reliability of the data; The meteorological temperature prediction module uses the collected parameter information and historical data to establish a meteorological temperature prediction neural network model, predict the future meteorological temperature, and pass the prediction results to the temperature dynamic module; The temperature dynamic adjustment module performs a dynamic adjustment layer in the meteorological temperature prediction neural network model, introduces a feedback mechanism, continuously adjusts the model according to actual conditions, improves the accuracy and reliability of the prediction, and transmits the adjusted data information to the measurement improvement module; The measurement process improvement module improves the meteorological temperature measurement process according to the requirements of different meteorological environments and the forecast results of meteorological temperature, and transmits the improved data information to the temperature measurement module; The temperature measurement evaluation module evaluates the improvement results of the specific process of meteorological temperature measurement, establishes a temperature measurement evaluation model, and evaluates the accuracy and reliability of the system.

[0040] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0041] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0043] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0044] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A meteorological temperature measurement method based on an optical fiber sensor, characterized in that: The following steps are involved: Step S1. Collect data information in the environment through the optical fiber sensor, pre-process the acquired different parameter information, and provide a data basis for the meteorological temperature measurement method; Step S2. Establish a weather temperature prediction neural network model based on the preprocessed data information to predict the weather temperature; Step S3. Improve the meteorological temperature measurement process according to the needs of different meteorological environments and the forecast results of meteorological temperature; Step S4. Based on the evaluation results of the improvement of the specific process of meteorological temperature measurement, a temperature measurement evaluation model is established to evaluate the effect of the temperature measurement results in practical applications.

2. A meteorological temperature measurement method based on an optical fiber sensor according to claim 1, characterized in that: The step S2 specifically includes: The historical parameter data obtained after preprocessing is used as training samples and as input data for the meteorological temperature prediction neural network model. The meteorological temperature prediction neural network model includes an input layer, a comprehensive analysis layer, an optimization prediction layer, a dynamic adjustment layer, and an output layer.

3. A meteorological temperature measurement method based on an optical fiber sensor according to claim 1, characterized in that: In the step S2 optimization prediction layer, the features extracted from the comprehensive analysis layer are processed. The specific process is as follows: in, Represents the input of the optimized prediction layer; Represents the connection weight between the comprehensive analysis layer and the optimized prediction layer; Represents the output value of the input layer; Represents the bias of the optimized prediction layer; Represents the output of the optimized prediction layer; The sensitivity coefficient representing the control difference; Indicates the variance difference, which is used to measure the degree of data variation; Parameters that represent the impact of the degree of variation; Represents the correction parameters in the optimization prediction process; It represents the difference between the actual sensor device delay time and the expected delay time during the prediction process; represents the prediction validation coefficient; Represents the constraint value in temperature prediction; represents a constant adjustment parameter; Indicates the amount of heat gained at the current temperature; Indicates the amount of heat gained at a reference temperature.

4. A method for measuring meteorological temperature based on an optical fiber sensor according to claim 3, characterized in that: In the step S2 dynamic adjustment layer, a feedback mechanism is introduced so that the model can dynamically adjust the parameters of the network according to the output and error conditions. The specific process is as follows: in, Represents the input of the dynamic adjustment layer; Represents the connection weight between the optimized prediction layer and the dynamic adjustment layer; Indicates the bias of the dynamic adjustment layer; Represents the output of the dynamic adjustment layer; represents the adjustment factor; represents the proportionality coefficient; represents the gain coefficient; Indicates the temperature comparison data under the historical standard state, which is used to verify with the real-time temperature data; represents the error signal; Indicates The temperature change between the actual temperature data and the reference value. ; Indicates The temperature change between the predicted temperature value and the reference value.

5. The method for measuring meteorological temperature based on an optical fiber sensor according to claim 1, characterized in that: The step S3 specifically includes: in, represents the output of the improved meteorological temperature measurement process; Represents the output of the meteorological temperature prediction neural network model; Represents the offset parameter; Indicates the stability coefficient during the improvement process; Represents the historical parameter data obtained by the sensor after preprocessing; represents the sensitivity coefficient; Indicates the adaptability of the feature task after extraction to different meteorological environment requirements; Indicates the improvement optimization coefficient; Indicates The weight of the feature task, ; Indicated in Time The basic resources obtained from each feature task.

6. A method for measuring meteorological temperature based on an optical fiber sensor according to claim 1, characterized in that: The step S4 specifically includes: in, represents the output result of the temperature measurement evaluation model; A label representing the model; Indicates the total number of tags; Indicated in the feature Application of predicted temperature probability; Indicates feature labels; The predicted temperature The number of applications, that is, the number of times it is applied and executed; Indicated in The output value of the improved meteorological temperature measurement process.

7. A method for measuring meteorological temperature based on an optical fiber sensor according to claim 6, characterized in that: The step S4 specifically includes: Defining Thresholds ,if , it means that the meteorological temperature measurement is inaccurate or does not meet the standards required by the business; if , it means that the meteorological temperature measurement is accurate or meets the standards required by the business.

8. A meteorological temperature measurement system based on an optical fiber sensor, using the meteorological temperature measurement method based on an optical fiber sensor according to claim 1, characterized in that: Includes the following: Parameter information acquisition module, information preprocessing module, meteorological temperature prediction module, temperature dynamic adjustment module, measurement process improvement module, temperature measurement evaluation module; The parameter information acquisition module monitors various parameters in the meteorological environment in real time through optical fiber sensors and transmits the collected data information to the information preprocessing module; The information preprocessing module performs preliminary processing on the collected parameter information, including data cleaning, denoising, outlier detection and data format conversion operations, and transmits the preprocessed data information to the meteorological temperature prediction module, the temperature dynamic adjustment module and the measurement process improvement module to ensure the accuracy and reliability of the data; The meteorological temperature prediction module uses the collected parameter information and historical data to establish a meteorological temperature prediction neural network model, predicts the future meteorological temperature, and transmits the prediction results to the temperature dynamic module; The temperature dynamic adjustment module performs a dynamic adjustment layer in the meteorological temperature prediction neural network model, introduces a feedback mechanism, continuously adjusts the model according to actual conditions, and transmits the adjusted data information to the measurement improvement module; The measurement process improvement module improves the meteorological temperature measurement process according to the requirements of different meteorological environments and the forecast results of meteorological temperature, and transmits the improved data information to the temperature measurement module; The temperature measurement evaluation module evaluates the improved results of the specific process of meteorological temperature measurement, establishes a temperature measurement evaluation model, and evaluates the accuracy and reliability of the system.

Images