Method for monitoring performance of mid-infrared sensor

Abstract

The invention belongs to the technical field of sensor monitoring, and discloses a mid-infrared sensor performance monitoring method, which comprises the following steps: S100, integrated calibration: integrating an FBG (Fiber Bragg Grating) and an auxiliary sensor to a mid-infrared system, and completing connection and calibration; s200, acquisition and analysis: acquiring data, analyzing wavelength change of the FBG to deduce temperature / deformation, and judging a state; s300, fusion evaluation: fusing multi-source data, carrying out algorithm processing and calculating performance indexes; s400, threshold grading: setting a dynamic threshold, and dividing performance grades; and S500, response adjustment: executing an emergency response, adjusting a strategy after a fault, and restarting monitoring. According to the invention, through integration of various sensors and combination of data fusion and intelligent analysis, comprehensive and accurate monitoring of the performance of the mid-infrared sensor is realized, the monitoring accuracy and real-time performance are improved, the interference of environmental factors is effectively eliminated, and the actual working state of the mid-infrared sensor is reflected more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor monitoring, and particularly to a method for monitoring the performance of a mid-infrared sensor. Background Art

[0002] Mid-infrared sensors have been widely used in many fields due to their unique performance. The stability and accuracy of their working state are crucial for ensuring the normal operation of the system. However, mid-infrared sensors are affected by various environmental factors during operation, such as temperature, humidity, air pressure, as well as electromagnetic interference, chemical erosion, etc. These factors may cause the performance of mid-infrared sensors to decline or malfunction. Therefore, monitoring the performance of mid-infrared sensors and promptly detecting and handling abnormal situations are of great significance for ensuring system stability and security.

[0003] Existing methods for monitoring the performance of mid-infrared sensors usually mainly rely on single sensor data. For example, only by the temperature change or the amount of deformation to judge the working state of the mid-infrared sensor. This method has obvious limitations because single data often cannot comprehensively reflect the actual performance of the mid-infrared sensor. In addition, existing methods also lack sufficient consideration and compensation for environmental factors, resulting in the accuracy and reliability of mid-infrared sensor performance monitoring being seriously affected under complex working conditions. At the same time, existing methods often use static threshold settings and cannot be dynamically adjusted according to the actual application scenario and the change of mid-infrared sensor performance, thus limiting their adaptability and flexibility.

[0004] Therefore, it is necessary to develop a new method for monitoring the performance of mid-infrared sensors to overcome the deficiencies of the prior art. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and provide a method for monitoring the performance of a mid-infrared sensor. This method realizes multi-parameter data acquisition and fusion analysis by integrating fiber Bragg grating (FBG), humidity and air pressure sensors, and can more comprehensively and accurately evaluate the sensor performance and perform dynamic early warning and adjustment.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A method for monitoring the performance of a mid-infrared sensor, the method comprising the following steps: S100, Sensor Integration and Calibration: Research the working principle, usage scenarios, and past fault feedback of mid-infrared sensors, select fiber Bragg gratings (FBGs) suitable for the working environment of the mid-infrared sensors, choose packaging materials according to the structural and operating characteristics of the mid-infrared sensors, attach the FBGs to the mid-infrared sensors, and simultaneously install humidity sensors and barometric pressure sensors near the mid-infrared sensors. Connect all sensors to the central control system via shielded cables, complete the line connection according to the standard communication protocol, and calibrate the zero point and range of each sensor unit; S200, Basic Data Acquisition and Analysis: Set the spectral analyzer to collect the reflection spectra of the FBGs at a preset frequency, and the humidity and barometric pressure monitoring units respectively collect environmental data at their respective preset frequencies. The central control system simultaneously starts all sensors to work, and after verification, transmits the collected data to the central control system. The data processing software built into the central control system extracts the change in the central wavelength of the FBGs from it, and analyzes the current temperature change and deformation of the mid-infrared sensors to determine whether the mid-infrared sensors are in a normal physical state. If it exceeds the normal range, a warning is triggered; S300, Data Fusion and Performance Evaluation: The central control system stores the data collected in real time by the humidity and barometric pressure monitoring units and the temperature and strain data calculated from the FBGs in a dedicated database; collect historical data, and use the big data platform and machine learning algorithms to train the basic correlation functions and , combined with the determined cross-coupling coefficient , substitute it into the preset formula for cross-compensation of each parameter. The formula is: , where represents the final quantified value of the performance index of the mid-infrared sensor, represents the preliminary performance correlation value, and the calculation formula is: , represents the temperature change of the mid-infrared sensor, represents the deformation of the mid-infrared sensor, represents humidity, represents barometric pressure, represents each parameter variable, referring to temperature , strain , humidity , barometric pressure among them, represents and corresponding basic correlation function, and finally outputs the quantified value of the performance index of the mid-infrared sensor ; S400, Threshold Dynamic Setting and Level Division: Collect data on the application scenarios and failure cases of the mid-infrared sensor, calculate the quantified values of the historical mid-infrared sensor performance metrics, determine the boundary values of the four performance levels of safety, mild anomaly, moderate risk, and severe failure based on the quantified values of the historical mid-infrared sensor performance metrics, calculate the real-time collected data and output the risk level; S500, Emergency Response and Strategy Adjustment: The central control system receives the early warning report in real time and takes different early warning treatments for different early warning reports: in case of mild anomaly, record the details in the background, push low-priority prompts and troubleshooting guides; in case of moderate risk, increase the acquisition frequency and pop up a warning on the operation and maintenance interface; in case of severe failure, immediately trigger the audible and visual alarm of the preset decibel, send an emergency text message, and link the surrounding equipment to shut down emergently; after the failure is repaired, dynamically adjust the threshold according to the situation and restart the monitoring process.

[0007] Preferably, in the step S200, in the basic data collection and analysis, the central wavelength change amount is extracted from the FBG reflection spectrum through the following parameter conversion formula, and analyzed in combination with the physical parameters of the mid-infrared sensor: Let the central wavelength change amount of the reflected light of the fiber Bragg grating FBG be , the temperature change amount of the mid-infrared sensor be , the deformation amount be , introduce the temperature sensitivity coefficient and the strain sensitivity coefficient , and the formula is: , where the temperature sensitivity coefficient has a value range of 0.01 - 0.02 nm / °C, and the strain sensitivity coefficient has a value range of 0.78 - 1.2 pm / με, is the environmental comprehensive interference amount, which covers factors such as electromagnetic interference and weak chemical erosion that are difficult to directly measure, is the environmental interference correction factor, and its value range is 0.01 - 0.1.

[0008] Preferably, in the step S200, in the basic data collection and analysis, the method for determining the normal range threshold of the physical state of the mid-infrared sensor is: Let the operating temperature range of the mid-infrared sensor be to , the deformation tolerance range be to , the working condition correction coefficients be and , and their value range is 0.1 - 0.5. The calculation formula for the normal range threshold is: , , , , where , is the amount by which the lower and upper temperature limits need to be adjusted additionally due to operating conditions factors, statistically obtained from historical fault data. is the amount by which the deformation amount needs to be adjusted.

[0009] Preferably, in the step S300, the method for determining the cross-coupling coefficient in data fusion and performance evaluation is as follows: An iterative optimization algorithm based on gradient descent is adopted, combined with the historical monitoring data set , , represents the temperature change amount of the mid-infrared sensor in the m-th monitoring , represents the deformation amount , represents the humidity H, represents the air pressure P, is the corresponding performance index of the mid-infrared sensor, and a loss function is constructed. The formula of the loss function is: , where is the predicted performance index of the mid-infrared sensor based on the current value, calculated by the following formula: , during the iteration process, is updated according to the following formula: ; η is the learning rate, and its value range is 0.001 - 0.1. is the partial derivative of the loss function with respect to , represents the basic correlation function; after each iteration calculation, the performance of the model is verified until the value of the loss function converges to a preset minimum value, and the optimal cross-coupling coefficient is determined.

[0010] Preferably, in the step S300, the calculation methods for the basic correlation functions and in data fusion and performance evaluation are as follows: The polynomial fitting method is adopted to determine the , forms. An example formula is: , , where represents the temperature change amount of the mid-infrared sensor, represents the deformation amount of the mid-infrared sensor, represents the humidity, represents the air pressure. The specific coefficients of the correlation functions , are determined by the least squares method to fit the experimental data.

[0011] Preferably, in the step S300, the method for training the correlation function by combining high-order polynomial fitting and Gaussian process regression in data fusion and performance evaluation is as follows: collect experimental data covering relevant parameters of temperature, strain, humidity, and air pressure; clean the data and perform min-max normalization; then perform high-order polynomial fitting. For the basic correlation functions and , the formula of the high-order polynomial is: , , where represents the temperature change of the mid-infrared sensor, represents the deformation of the mid-infrared sensor, H represents humidity, and P represents air pressure; use the least squares method to solve the coefficients and ; perform Gaussian process regression, select the radial basis function RBF kernel as the kernel function, and the formula of the kernel function is: ; estimate the hyperparameters and by maximizing the marginal likelihood function, and the formula of the marginal likelihood function is: ; use the trained model to predict new data points, and the predicted mean is: , and the variance is: ; combine the results of high-order polynomial fitting and Gaussian process regression with weights to obtain the final basic correlation function.

[0012] Preferably, in the step S400, in the threshold dynamic setting and level division, the warning priority corresponding to the quantization value of the performance index of the mid-infrared sensor is calculated by the following warning priority determination formula: Let the deviation degree of the performance index S of the mid-infrared sensor from the standard value in the safe state be , and the warning priority be . Introduce the risk perception index , and the calculation formula is: , .

[0013] Preferably, in the step S400, in the threshold dynamic setting and level division, the risk perception index r is calculated according to the following risk perception index calculation formula: where is the weight coefficient, and its value range is 0.1 - 1.0 and satisfies , represents the temperature deviation, represents the humidity deviation, represents the air pressure deviation, ρΔL represents the strain change rate, which is the strain of the mid-infrared sensor relative to the normal strain range The degree of change, and the calculation formula is: , is the failure frequency weight, and the calculation formula is: , where is the preset maximum failure frequency, is the scenario risk level.

[0014] Preferably, in the step S400, the threshold is dynamically set and the level is divided according to the value of the warning priority W to determine the boundary values of four performance levels: safe, slightly abnormal, medium risk, and serious failure: When 0 ≤ ≤ 24, it means that the mid-infrared sensor is in a safe state and is set to the safe level; When 25 ≤ ≤ 49, it means that there are some slight abnormalities in the mid-infrared sensor and is set to the slightly abnormal level; When 50 ≤ ≤ 74, it means that there is a medium risk in the mid-infrared sensor and is set to the medium risk level; When 75 ≤ ≤ 100, it means that there is a serious failure in the mid-infrared sensor and is set to the serious failure level.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. By integrating the fiber Bragg grating FBG, humidity sensor and air pressure sensor, and combining the data processing ability of the central control system, the present invention realizes the comprehensive monitoring of the performance of the mid-infrared sensor, not only improves the accuracy and real-time performance of the monitoring, but also can effectively eliminate the interference of environmental factors, such as electromagnetic interference and weak chemical erosion, through the fusion and cross-compensation of multi-parameter data, so as to more accurately reflect the actual working state of the mid-infrared sensor. This comprehensive monitoring method provides strong data support for the fault warning, emergency response and strategy adjustment of the mid-infrared sensor, and helps to improve the reliability and service life of the mid-infrared sensor.

[0016] 2. By collecting the application scenario and fault case data of the mid-infrared sensor, the present invention can dynamically adjust the threshold according to the actual situation, and divide the working state of the mid-infrared sensor into four levels: safe, slightly abnormal, medium risk and serious failure according to the quantitative value of the performance index of the mid-infrared sensor and the risk assessment result. This dynamic and flexible threshold setting method makes the warning, emergency response and strategy adjustment more accurate and efficient, and can take corresponding measures according to different situations, avoiding losses caused by false alarms or missed alarms. At the same time, this performance level division also provides more clear guidance for the maintenance and management of the mid-infrared sensor, and helps to improve the maintenance efficiency and management level of the mid-infrared sensor. Brief Description of the Drawings

[0017] 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 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 also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of a method for monitoring the performance of a mid-infrared sensor of the present invention. Detailed Embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] Refer to Figure 1 , the present invention provides a method for monitoring the performance of a mid-infrared sensor.

[0021] Embodiment 1: Industrial Furnace Temperature Monitoring Scenario In the industrial furnace temperature monitoring scenario, a mid-infrared sensor is used to monitor the temperature change in the furnace in real time. The method of the present invention is applied to this scenario, and the specific steps are as follows: S100, Sensor Integration and Calibration: Through research, it is determined that the mid-infrared sensor works in this high-temperature and complex electromagnetic environment. Select fiber Bragg gratings (FBGs) with high temperature resistance and electromagnetic interference resistance, select ceramics as the packaging material, attach the FBG to the sensor, install a humidity sensor and a pressure sensor near the mid-infrared sensor, and connect each sensor to the central control system through a shielded cable according to the standard communication protocol, and calibrate the zero point and range.

[0022] S200, Basic Data Acquisition and Analysis: According to the characteristics of the sensor and the environment, set the spectral analyzer to collect the FBG reflection spectrum 10 times per second, and the humidity and pressure monitoring units collect at frequencies of 3 minutes and 5 minutes. After the central control system starts the work of each sensor and the collected data is transmitted, extract the change amount of the central wavelength , analyze the temperature change amount and the strain amount of the mid-infrared sensor according to the parameter conversion formula. The formula is: , is the temperature sensitivity coefficient, is the strain sensitivity coefficient, is the comprehensive environmental interference amount,[[]]END]] is the environmental interference correction factor; and according to the working condition correction coefficient , and the working temperature range to , the deformation tolerance range to to determine the normal range threshold for judgment, and the threshold formula is: , , , , where is the temperature adjustment amount, is the deformation adjustment amount; and judge the physical state of the sensor, and trigger an alarm when the range is exceeded.

[0023] S300, data fusion and performance evaluation: The central control system sets up a dedicated database to fuse humidity, air pressure data with temperature and strain data converted by FBG; use the iterative optimization algorithm based on gradient descent to determine the cross-coupling coefficient , construct the loss function , is the actual performance index, is the predicted performance index, and update the coefficient iteratively according to the formula: , is the learning rate, until the loss function converges to obtain the optimal ; use the polynomial fitting method to determine the correlation function: , ; substitute it into the compensation formula to calculate the quantified value of the performance index , and the formula is: where: .

[0024] S400, threshold dynamic setting and level division: Collect the fault case data of the industrial furnace temperature monitoring scenario, calculate the historical S value, and calculate the deviation degree according to the formula , where is the safety standard value; combined with the risk perception index , and the formula is: , is the weight coefficient, is the humidity deviation, is the air pressure deviation, is the strain change rate, is the fault frequency weight, is the scenario risk level; and determine the performance boundary value according to the early warning priority formula: , divide the level: 0 ≤ ≤ 24 is safe, 25 ≤ ≤ 49 is slightly abnormal, 50 ≤ ≤74 is a medium risk, 75≤ ≤100 is a severe fault.

[0025] S500, Emergency Response and Strategy Adjustment: The central control system receives the early warning and processes it according to the level: For mild anomalies, record in the background and push prompts for troubleshooting; for medium risks, increase the acquisition frequency and pop up a warning; for severe faults, issue a 120-decibel sound and light alarm, send a text message notification, and link to stop the surrounding equipment; after repair, restart the monitoring according to the adjusted threshold.

[0026] Through the above steps, this embodiment constructs a performance monitoring system for mid-infrared sensors for industrial furnace temperature monitoring. In the sensing integration link, select FBG and packaging materials suitable for high-temperature and strong-interference working conditions, and integrate multiple sensors into the central control for calibration. In the data acquisition and analysis link, set the frequency according to the characteristics, analyze the temperature through the formula, and judge anomalies based on the deformation quantity. In the fusion compensation link, use the algorithm to determine the coefficient and obtain the quantization value through the fitting function. In the dynamic threshold setting link, set the four-level boundary based on the case data to evaluate the performance. In the emergency response link, process according to the warning level progression, repair, adjust the threshold, and restart. Thus, it comprehensively ensures the accuracy and reliability of furnace temperature monitoring, the safety of production without worry, improves the system stability and operation and maintenance efficiency, and consolidates the foundation of industrial temperature control.

[0027] Embodiment 2: Method for Monitoring the Performance of Mid-Infrared Sensors in the Scenario of Industrial Kiln Monitoring In the scenario of industrial kiln temperature and environment monitoring, mid-infrared sensors are used to accurately measure the temperature of key parts inside the kiln, which is crucial for controlling the quality of the production process. The method of the present invention is applied to this scenario, and the specific steps are similar to those of Embodiment 1, but are adaptively adjusted according to the characteristics of the kiln environment: S100, Sensor Integration and Calibration: Based on the working environment of the kiln with high temperature, complex chemical atmosphere and strong electromagnetic interference, deeply study the working principle of mid-infrared sensors, the root causes of past faults and the feedback of various working conditions. After rigorous screening, select fiber Bragg gratings (FBGs) with high temperature resistance, chemical corrosion resistance and high shielding efficiency against electromagnetic interference. According to the structural characteristics, thermal stress distribution and vibration conditions of the kiln, select suitable ceramic packaging materials, firmly attach the FBG to the key sensing area of the mid-infrared sensor to ensure close contact and efficient heat conduction and strain transfer. Accurately install high-precision humidity sensors and pressure sensors near the mid-infrared sensors inside the kiln. Each sensor is connected to the central control system through high-temperature and anti-interference shielded cables according to the standard communication protocol. Use professional calibration equipment and standard temperature, humidity and pressure sources to finely calibrate the zero point and range of each sensor according to the established procedures to ensure the accuracy of the measurement reference and lay a solid foundation for subsequent accurate monitoring.

[0028] S200, Basic Data Acquisition and Analysis: Given the complex and ever-changing conditions of the kiln, the spectral analyzer is set to collect FBG reflection spectra at an appropriate frequency. Meanwhile, the humidity and air pressure monitoring units determine their respective collection frequencies according to the fluctuation characteristics of the kiln environment parameters. The central control system is started to drive the sensors to work together, and the integrity and accuracy of data transmission are verified in real time. After verification, the data is transmitted to the central control system. Based on the built-in advanced data processing software in the central control system, according to the internal relationship between the FBG reflection spectrum and the physical parameters of the mid-infrared sensor, the change amount of the central wavelength is extracted through a rigorous parameter conversion formula. Let the change amount of the central wavelength of the FBG reflected light be Δλ, the change amount of the temperature of the mid-infrared sensor be ΔT, and the deformation amount be ΔL. The precise temperature sensitivity coefficient and strain sensitivity coefficient are introduced, and calculated by the formula: , where α is the environmental interference correction factor and ε is the comprehensive interference amount of electromagnetic and chemical erosion. The working temperature range to of the mid-infrared sensor determined in combination with the kiln design specifications and process requirements, the deformation tolerance range to , and the working condition correction coefficients and obtained through in-depth analysis of the historical failure big data are used to accurately calculate the normal range thresholds by the formula: , , Among them: is the temperature adjustment amount, is the deformation adjustment amount. Analyze the current physical state of the mid-infrared sensor in real time. Once the threshold is exceeded, an alarm is immediately triggered to ensure the safe and stable operation of the kiln.

[0029] S300, Data Fusion and Performance Evaluation: The central control system creates a large-capacity dedicated database to accurately converge the real-time data of humidity and air pressure and the temperature and strain data obtained by FBG conversion, and strictly aligns and matches them according to the time stamp. Widely collect the long-term operation historical data of the kiln, covering various parameter change situations under multiple working conditions. Use the powerful computing power of the big data platform and advanced machine learning algorithms to train the basic correlation functions and based on the massive data. For example, after multiple iterations of optimization and verification, the form is determined (the combination of high-order polynomial fitting and Gaussian process regression can be adopted), and the example formula is: , . Through the gradient descent iterative optimization algorithm, a loss function is constructed in combination with the historical data set: , where is the actual performance index, is the prediction index, and the cross-coupling coefficient is iteratively updated according to the formula., η is the learning rate, until the loss function converges to a minimum value to obtain the optimal coefficients. Substitute into the formula for calculation and output the quantified value of the reliable sensor performance index : Where: .

[0030] S400, Threshold Dynamic Setting and Level Division: Comprehensively collect information on the kiln production scenario and rich fault case data, and deeply explore the variation law of the quantified value of the sensor performance index. According to the deviation degree between the sensor performance index S and the safety state standard value (the formula is: ) and the risk perception index r, comprehensively determine the early warning priority W (the calculation formula is: ), where r is calculated according to the formula: , is the weight coefficient, is the temperature deviation, is the humidity deviation, is the air pressure deviation, is the strain change rate, is the fault frequency weight, is the scenario risk level). Based on this, accurately determine the safety (0 ≤ ≤ 24), mild anomaly (25 ≤ ≤ 49), moderate risk (50 ≤ ≤ 74), severe fault (75 ≤ ≤ 100) four-level performance boundary values, realize the accurate hierarchical evaluation of the kiln sensor status, and efficiently guide the operation and maintenance decision-making.

[0031] S500, Emergency Response and Strategy Adjustment: The central control system receives the early warning report in real time and responds intelligently according to the risk level. In case of mild anomaly, the background records the details in detail, and accurately pushes low-priority prompts and targeted troubleshooting guides to assist the operation and maintenance personnel in accurately locating potential hidden dangers. In case of moderate risk, adaptively increase the data collection frequency, and a prominent pop-up warning appears on the operation and maintenance interface to help personnel closely monitor key parameters. When a severe fault occurs suddenly, immediately trigger a 120-decibel strong sound and light alarm to shock the whole field, send an emergency text message to the person in charge within seconds, and at the same time link to the emergency shutdown of the supporting equipment around the kiln to contain the spread of the fault and ensure the safety of production facilities and personnel. After the fault is repaired, deeply review the fault characteristics and the overall working conditions, dynamically and finely adjust the threshold according to the situation, restart the monitoring process, and continuously optimize the monitoring efficiency to escort the efficient and stable operation of the kiln throughout the process.

[0032] This embodiment has achieved remarkable application results in the industrial furnace monitoring scenario. During the sensor integration and calibration stage, appropriate FBGs and packaging materials are selected according to the harsh working conditions of the furnace, and each sensor is properly placed and accurately calibrated, laying a foundation for accurate monitoring. When collecting and analyzing basic data, the collection frequency is set according to the characteristics of the furnace, and the central control system verifies and processes the data. The change amount and threshold of the central wavelength are calculated using specific formulas, and an alarm is issued when the threshold is exceeded to ensure the safety of the furnace. In the data fusion and evaluation link, the central control system collects multiple data, trains the correlation function and determines the coupling coefficient using algorithms, and substitutes them into the formula to obtain the performance index value, providing key support for furnace evaluation. In the threshold dynamic setting and division link, the boundary value is determined based on the deviation degree and risk index of the indicators calculated from a large amount of data, and a four-level accurate evaluation is carried out. In the emergency response strategy adjustment link, intelligent responses are made according to the alarms, and the threshold is dynamically optimized during fault repair to restart the process. Thus, the stable and efficient operation of the furnace is comprehensively guaranteed, effectively improving production quality and safety, and reducing operation and maintenance risks and costs.

[0033] 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, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A method for monitoring the performance of a mid-infrared sensor, characterized in that, The following steps are involved: S100, sensor integration and calibration: Investigate the working principle, usage scenarios and past fault feedback of the mid-infrared sensor, select the fiber Bragg grating FBG that is suitable for the working environment of the mid-infrared sensor, select the packaging material according to the structure and working characteristics of the mid-infrared sensor, attach the FBG to the mid-infrared sensor, and simultaneously install the humidity sensor and air pressure sensor near the mid-infrared sensor, connect all sensors to the central control system via shielded cables, complete the line connection according to the standard communication protocol, and calibrate the zero point and range of each sensor unit; S200, basic data collection and analysis: The spectrum analyzer is set to collect the reflection spectrum of the FBG at a preset frequency, and the humidity and air pressure monitoring units collect environmental data at their respective preset frequencies. The central control system starts all sensors synchronously, and after verification, the collected data is transmitted to the central control system. The built-in data processing software of the central control system extracts the central wavelength change of the FBG from it, and analyzes the current temperature change and deformation of the mid-infrared sensor to determine whether the mid-infrared sensor is in a normal physical state. If it exceeds the normal range, an early warning is triggered; S300, data fusion and performance evaluation: The central control system stores the data collected in real time by the humidity and air pressure monitoring unit, as well as the temperature and strain data calculated from the FBG, in a dedicated database; collects historical data, and uses a big data platform and machine learning algorithms to train a basic correlation function and , combines with the determined cross-coupling coefficient , and substitutes it into a preset formula for cross-compensation of each parameter. The formula is: , where represents the final quantified value of the mid-infrared sensor performance index, represents the preliminary performance correlation value, and the calculation formula is: , represents the temperature change of the mid-infrared sensor, represents the deformation of the mid-infrared sensor, represents humidity, represents air pressure, represents each parameter variable, referring to temperature , strain , humidity , air pressure in one of them, represents the basic correlation function corresponding to , and finally outputs the quantified value S of the mid-infrared sensor performance index; S400, dynamic threshold setting and classification: Collect data on application scenarios and failure cases of the mid-infrared sensor, calculate the quantified values of historical mid-infrared sensor performance indicators, determine the boundary values of four performance levels of safety, mild abnormality, moderate risk, and severe failure according to the quantified values of historical mid-infrared sensor performance indicators, calculate the real-time collected data and output the risk level; S500, emergency response and strategy adjustment: The central control system receives early warning reports in real time and takes different early warning actions for different early warning reports: in case of minor abnormalities, the background records the details and pushes low-priority prompts and troubleshooting guides; in case of moderate risks, the collection frequency is increased and a pop-up window alert is displayed on the operation and maintenance interface; in case of serious faults, a preset decibel sound and light alarm is immediately triggered, an emergency text message is sent, and surrounding equipment is linked to emergency shutdown; after the fault is repaired, the threshold is dynamically adjusted according to the situation and the monitoring process is restarted.

2. The performance monitoring method of a mid-infrared sensor according to claim 1, characterized in that, In the step S200, in the basic data collection and analysis, the central wavelength change amount is extracted from the FBG reflection spectrum through the following parameter conversion formula, and analyzed in combination with the physical parameters of the mid-infrared sensor: Let the central wavelength change amount of the reflected light of the fiber Bragg grating FBG be , the temperature change amount of the mid-infrared sensor be , the deformation amount be , the temperature sensitivity coefficient and the strain sensitivity coefficient are introduced, and the formula is: , where the value range of the temperature sensitivity coefficient is 0.01 - 0.02 nm / °C, and the value range of the strain sensitivity coefficient is 0.78 - 1.2 pm / με, is the environmental comprehensive interference amount, which covers factors such as electromagnetic interference and weak chemical erosion that are difficult to directly measure, is the environmental interference correction factor, and its value range is 0.01 - 0.

1.

3. The performance monitoring method of a mid-infrared sensor according to claim 1, characterized in that, In the step S200, the method for determining the normal range threshold of the physical state of the mid-infrared sensor in the basic data collection and analysis is as follows: Let the operating temperature range of the mid-infrared sensor be to , the deformation tolerance range be to , the working condition correction coefficient be and , and its value range is 0.1 - 0.

5. The calculation formula for the normal range threshold is: , , , , where , are the amounts of additional adjustments required for the lower and upper temperature limits due to working condition factors statistically obtained from historical failure data, and is the amount of adjustment required for the deformation amount.

4. A method for monitoring the performance of a mid-infrared sensor according to claim 1, characterized in that, In the step S300, the method for determining the cross-coupling coefficient in data fusion and performance evaluation is as follows: An iterative optimization algorithm based on gradient descent is adopted, combined with the historical monitoring data set , , represents the temperature change of the mid-infrared sensor in the th monitoring, , represents the deformation amount , represents the humidity , represents the air pressure , is the corresponding performance index of the mid-infrared sensor, and a loss function is constructed. The formula of the loss function is: , where is the performance index of the mid-infrared sensor predicted based on the current value, and is calculated by the following formula: . During the iteration process, is updated according to the following formula; is the learning rate, and its value range is 0.001 - 0.1, is the partial derivative of the loss function with respect to , represents the basic correlation function; after each iteration calculation, the performance of the model is verified until the value of the loss function converges to a preset minimum value, and the optimal cross-coupling coefficient is determined.

5. A method for monitoring the performance of a mid-infrared sensor according to claim 1 or 4, characterized in that, In the step S300, the basic correlation functions in data fusion and performance evaluation and are calculated as follows: The polynomial fitting method is used to determine the form of and . The example formula is: , , where represents the temperature change of the mid-infrared sensor, represents the deformation of the mid-infrared sensor, represents the humidity, represents the air pressure, and the specific coefficients of the correlation functions and are determined by fitting the experimental data with the least squares method.

6. A performance monitoring method for a mid-infrared sensor according to claim 1 or 4, characterized in that, In the step S300, the method for training the correlation function by combining high-order polynomial fitting and Gaussian process regression in data fusion and performance evaluation is as follows: collect experimental data covering relevant parameters of temperature, strain, humidity, and air pressure; clean the data and perform min-max normalization; then perform high-order polynomial fitting. For the basic correlation functions and , the formula of the high-order polynomial is: , , where represents the temperature change of the mid-infrared sensor, represents the deformation of the mid-infrared sensor, represents humidity, represents air pressure; use the least squares method to solve the coefficients and ; Perform Gaussian process regression, select the radial basis function (RBF) kernel as the kernel function, and the formula of the kernel function is: ; Estimate the hyperparameters and by maximizing the marginal likelihood function, and the formula of the marginal likelihood function is: ; Use the trained model to predict new data points, and the predicted mean is: , and the variance is: ; The results of high-order polynomial fitting and Gaussian process regression are weighted combined to obtain the final basic correlation function.

7. A method for monitoring the performance of a mid-infrared sensor according to claim 1, characterized in that, In the step S400, during the dynamic setting of the threshold and the grading, the warning priority corresponding to the quantization value of the performance index of the mid-infrared sensor is calculated through the following warning priority determination formula: Let the performance index S of the mid-infrared sensor be relative to the standard value in the safe state The degree of deviation is , the warning priority is , introduce the risk perception index , and the calculation formula is: , .

8. A performance monitoring method for a mid-infrared sensor according to claim 7, characterized in that, In the step S400, the risk perception index is calculated according to the following risk perception index calculation formula during the dynamic setting of the threshold and the level division. : , where is the weight coefficient, and its value range is 0.1 - 1.0 and satisfies . represents the temperature deviation. represents the humidity deviation. represents the air pressure deviation. represents the strain change rate, which is the strain of the mid-infrared sensor relative to the normal strain range . The calculation formula is: . is the weight of the failure frequency, and the calculation formula is: , where is the preset maximum failure frequency, is the scene risk level.

9. A method for monitoring the performance of a mid-infrared sensor according to claim 1 or 7, characterized in that, In the step S400, the dynamic setting of the threshold and the level division are based on the warning priority to determine the boundary values of four performance levels: safe, mildly abnormal, moderately risky, and severely faulty When 0 ≤ ≤ 24, it indicates that the mid-infrared sensor is in a safe state and is set to the safe level; When 25 ≤ ≤ 49, it indicates that there are some minor abnormalities in the mid-infrared sensor, which is set to the minor abnormality level; When 50 ≤ ≤ 74, it indicates that there is a medium risk for the mid-infrared sensor, and it is set to the medium risk level; When 75 ≤ ≤ 100, it indicates that the mid-infrared sensor has a serious fault and is set to the serious fault level.

Images