Intelligent fiber grating sensor network monitoring system and method thereof

Abstract

The invention provides an intelligent fiber grating sensor network monitoring system and a method thereof, and relates to the technical field of network monitoring. Comprising a networked sensing module, a remote monitoring module, an intelligent decision-making module and a firmware upgrading module. The networked sensing module is used for acquiring fiber bragg grating sensing data and preprocessing the fiber bragg grating sensing data to obtain preprocessed data; the remote monitoring module is used for carrying out statistical analysis on the preprocessed data to obtain operation data; the intelligent decision-making module makes an intelligent decision corresponding to the abnormal information by adopting an abnormal detection method based on statistical distribution; and the firmware upgrading module is used for performing firmware management and upgrading according to the intelligent decision. According to the method, the monitoring data in the distributed sensor network is subjected to statistical analysis, so that the key indexes reflecting the running state of the system are obtained. By adopting the anomaly detection method based on statistical distribution, the anomaly condition in the distributed sensor network can be automatically found. And the firmware version is tracked in real time, the repair program is updated in time, and the system security is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of network monitoring, and in particular to an intelligent fiber grating sensor network monitoring system and an intelligent fiber grating sensor network monitoring method. Background Art

[0002] Fiber Bragg grating sensor is an advanced sensing technology based on the principle of optical fiber modulation. It has the advantages of small size, light weight, long transmission distance, and anti-electromagnetic interference. It is widely used in structural health monitoring, environmental monitoring and other fields. Compared with traditional electrical sensors, fiber Bragg grating sensors can realize real-time and high-precision monitoring of physical quantities in a wider range. With the development of Internet technology, building fiber Bragg grating sensors into a distributed sensing network can realize comprehensive monitoring of complex structures or environments in a wider range.

[0003] When using fiber grating sensors for network monitoring, there are some significant defects in the anomaly detection of running data and firmware upgrades for abnormal situations. In terms of anomaly detection, due to the complexity of its detection algorithm and its reliance on a large amount of data, the real-time detection may be insufficient and the anomalies that occur instantly may not be captured in time. Moreover, the accuracy of existing algorithms is often affected when facing complex and changeable environmental interference, which is prone to misjudgment or omission. At the same time, for some subtle but critical abnormal changes, it may be difficult to effectively identify them due to the accuracy limitations of the sensor and the limitations of the data processing method. In terms of firmware upgrades, the upgrade process is complex and risky. The upgrade process may be affected by network stability, resulting in upgrade interruption or failure. Moreover, the compatibility issues of different versions of firmware are also prominent, which may cause new failures. In addition, since the upgrade operation requires unified coordination of multiple sensor nodes, if some of the nodes fail or communication is not smooth, it will affect the smooth progress of the entire upgrade plan, and the verification and testing links after the upgrade are not perfect, it is difficult to ensure that the upgraded firmware can effectively solve abnormal situations. Summary of the invention

[0004] Based on the above purpose, the present invention provides an intelligent fiber Bragg grating sensor network monitoring system and method thereof. On the one hand, the present invention provides an intelligent fiber Bragg grating sensor network monitoring system, comprising:

[0005] A networked sensing module is used to construct a distributed sensing network based on fiber grating sensor nodes, obtain fiber grating sensing data, and pre-process the fiber grating sensing data to obtain pre-processed data;

[0006] A remote monitoring module, used for performing statistical analysis on the pre-processed data to obtain operating data, and converting the operating data into visual data display;

[0007] The intelligent decision-making module uses an abnormality detection method based on statistical distribution to determine whether the operating data contains abnormal information, and makes corresponding intelligent decisions if so;

[0008] A firmware upgrade module is used to manage and upgrade the firmware of the fiber grating sensor node according to the intelligent decision.

[0009] According to an intelligent fiber Bragg grating sensor network monitoring system provided by the present invention, the networked sensing module includes a sensor unit and a signal processing unit; the sensor unit is used to collect fiber Bragg grating sensing data in real time; the signal processing unit is used to preprocess the fiber Bragg grating sensing data to obtain preprocessed data.

[0010] According to an intelligent fiber Bragg grating sensor network monitoring system provided by the present invention, the process of preprocessing the fiber Bragg grating sensor data includes:

[0011] Converting the fiber grating sensing data into a digital signal;

[0012] Performing filtering on the digitized signal to obtain a filtered signal;

[0013] Amplifying the filtered signal using a programmable gain amplifier to obtain an amplified signal;

[0014] Performing linear processing on the amplified signal by polynomial fitting to obtain linear data;

[0015] The linear data is format-converted to obtain preprocessed data.

[0016] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the remote monitoring module includes a data receiving unit, a data processing unit and a visualization unit; the data receiving unit is used to receive the pre-processed data in real time; the data processing unit is used to perform statistical analysis on the pre-processed data to obtain operating data; the visualization unit is used to convert the operating data into visual data for display.

[0017] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the process of statistically analyzing the pre-processed data includes:

[0018] Recording the timestamp information of each of the preprocessed data, and combining each of the preprocessed data with its corresponding timestamp information to generate time series data;

[0019] Performing statistical analysis on the time series data to calculate statistical features of the time series data, wherein the statistical features include a mean, a variance, and a correlation of the time series features;

[0020] The statistical features are aggregated using a time window aggregation method, and the aggregated results are used as running data.

[0021] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the intelligent decision-making module includes an anomaly detection unit and a decision execution unit; the anomaly detection unit adopts an anomaly detection method based on statistical distribution to obtain anomaly information according to the operating data; the decision execution unit is used to make corresponding intelligent decisions according to the anomaly information.

[0022] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the process of obtaining the abnormal information includes:

[0023] Collecting fiber grating sensing historical data, and preprocessing the historical data to obtain historical preprocessed data;

[0024] Constructing a normal operating state statistical distribution model based on the historical preprocessed data, setting the univariate data to obey Gaussian distribution, calculating the mean and standard deviation, and calculating the covariance matrix for the multivariate data;

[0025] Input the real-time operation data into the normal operation state statistical distribution model, and if the real-time operation data is a univariate Gaussian distribution, calculate the standard deviation from the mean; if the real-time operation data is a multivariate Gaussian distribution, calculate the Mahalanobis distance from the covariance matrix;

[0026] The standard deviation and the Mahalanobis distance are used as an anomaly score, and the anomaly score is compared with a preset anomaly threshold. If the anomaly score is greater than the anomaly threshold, anomaly information is output.

[0027] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the process of making corresponding intelligent decisions based on the abnormal information includes: setting decision rules according to the application scenarios of the distributed sensor network; collecting the operating data in real time and receiving the abnormal information; and making corresponding intelligent decisions based on the decision rules.

[0028] According to an intelligent fiber grating sensor network monitoring system provided by the present invention, the firmware upgrade module includes a firmware version management unit, a remote upgrade mechanism unit and an upgrade strategy optimization unit; the firmware version management unit is used to set the firmware maintenance program library of the fiber grating sensor node; the remote upgrade mechanism unit is used to build a mechanism to support the remote upgrade of the fiber grating sensor node; the upgrade strategy optimization unit is used to implement the firmware upgrade of the fiber grating sensor node according to the intelligent decision.

[0029] On the other hand, the present invention also provides an intelligent fiber grating sensor network monitoring method, comprising:

[0030] S1. Construct a distributed sensing network based on fiber Bragg grating sensor nodes, obtain fiber Bragg grating sensing data, and preprocess the fiber Bragg grating sensing data to obtain preprocessed data.

[0031] S2. Perform statistical analysis on the preprocessed data to obtain operating data, and convert the operating data into visual data for display.

[0032] S3. Use anomaly detection methods based on statistical distribution to determine whether there is abnormal information in the operating data. If so, make corresponding intelligent decisions to manage and upgrade the firmware of the fiber grating sensor nodes.

[0033] Beneficial effects of the present invention:

[0034] The present invention constructs a distributed sensing network by deploying multiple fiber grating sensor nodes, which can achieve coverage monitoring of a wider area and improve the spatial resolution of overall monitoring. By real-time remote collection of monitoring data in the distributed sensing network and statistical analysis of these data, key indicators reflecting the operating status of the system are obtained. This real-time analysis capability is conducive to quickly discovering abnormal situations and providing a basis for subsequent intelligent decision-making. The abnormal situation in the distributed sensing network can be automatically discovered by adopting an abnormality detection method based on statistical distribution, which is more intelligent and robust, can more accurately identify abnormalities, and is conducive to timely discovering and locating system faults, providing a basis for subsequent intelligent decision-making. After detecting the abnormal situation, the module can make corresponding intelligent decisions, and the decision rules can be flexibly set to meet the needs of different application scenarios, avoid the limitations of manual intervention in decision-making, and improve the automation level of the system. A complete fiber grating sensor node firmware program library is maintained through a firmware upgrade module, which can track the firmware version in real time, update the repair program in time, ensure system security, and support the version rollback function to ensure the reliability of the upgrade process. By building a transmission protocol and upgrade process that supports remote upgrades, node firmware can be upgraded remotely and safely without manual intervention, which improves upgrade efficiency and reduces the impact on network operation. Based on the diagnosis results of the intelligent decision-making module, targeted firmware upgrade strategies can be formulated, and by optimizing parameters such as upgrade timing and upgrade priority, the intelligence of the upgrade can be further improved, minimizing the impact of the upgrade process on system stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a structural schematic diagram of an intelligent fiber grating sensor network monitoring system provided by an embodiment of the present invention;

[0037] Figure 2 The present invention provides an intelligent fiber grating sensor network monitoring method. DETAILED DESCRIPTION

[0038] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0039] like Figure 1 As shown, an embodiment of the present invention provides an intelligent fiber grating sensor network monitoring system and method thereof, the execution subject can be an intelligent fiber grating sensor network monitoring system, including a networked sensing module, a remote monitoring module, an intelligent decision-making module and a remote maintenance module.

[0040] The networked sensing module is used to construct a distributed sensing network based on fiber grating sensor nodes, obtain fiber grating sensing data, and preprocess the fiber grating sensing data to obtain preprocessed data.

[0041] The networked sensing module includes a sensor unit and a signal processing unit. The sensor unit is used to collect fiber Bragg grating sensing data in real time. The signal processing unit is used to pre-process the fiber Bragg grating sensing data to obtain pre-processed data.

[0042] The process of preprocessing fiber Bragg grating sensing data includes:

[0043] Convert fiber grating sensing data into digital signals.

[0044] The digitized signal is filtered to obtain a filtered signal.

[0045] A programmable gain amplifier is used to amplify the filtered signal to obtain an amplified signal.

[0046] The amplified signal is linearized by polynomial fitting to obtain linear data.

[0047] The linear data is formatted and preprocessed data is obtained.

[0048] In this embodiment, the fiber Bragg grating sensing data collected by the sensor unit in real time is an analog signal, which is converted into a digital signal through an A / D converter. The A / D conversion resolution can be selected to be 12 bit or 16 bit, and the conversion frequency is above 1 kHz.

[0049] A digital filtering algorithm is applied to the digital signal using a low pass filter or a median filter. The filtering algorithm uses a finite impulse response or infinite impulse response filter and sets the cutoff frequency of the filter according to the spectral characteristics of the digital signal.

[0050] The filtered signal is amplified using a programmable gain amplifier, and the amplification factor is dynamically adjusted according to the actual digital signal amplitude, thereby improving the signal-to-noise ratio of the filtered signal and obtaining an amplified signal.

[0051] The amplified signal is fitted with a polynomial to realize the linear correction of the sensor and obtain linear data.

[0052] Convert linear data to standard data formats, including IEEE754 floating point and CSV files.

[0053] The networked sensing module builds a distributed sensing network by deploying multiple fiber grating sensor nodes. This networked structure can achieve coverage monitoring of a wider area and improve the spatial resolution of overall monitoring. Compared with a single independent sensor, networked sensing can provide more comprehensive and complete monitoring data.

[0054] Fiber Bragg grating sensors have the characteristics of high sensitivity and high precision. Through the collection and preprocessing of fiber Bragg grating sensing data, the module can obtain high-quality monitoring data, providing a reliable data basis for subsequent data analysis and abnormal diagnosis. The module adopts a low-power sensing node design, which is conducive to the stable operation of the node in long-term deployment, reducing the energy consumption demand of the entire monitoring system and improving the sustainability of the system.

[0055] The remote monitoring module is used to perform statistical analysis on the preprocessed data, obtain the operating data, and convert the operating data into visual data for display.

[0056] The remote monitoring module includes a data receiving unit, a data processing unit and a visualization unit. The data receiving unit is used to receive pre-processed data in real time. The data processing unit is used to perform statistical analysis on the pre-processed data to obtain operating data. The visualization unit is used to convert the operating data into visual data for display.

[0057] The process of statistical analysis of preprocessed data includes:

[0058] The timestamp information of each preprocessed data is recorded, and each preprocessed data is combined with its corresponding timestamp information to generate time series data.

[0059] Perform statistical analysis on time series data and calculate the statistical characteristics of time series data. The statistical characteristics include the mean, variance and correlation of time series characteristics.

[0060] The statistical features are aggregated using the time window aggregation method, and the aggregated results are used as running data.

[0061] In this embodiment, the data receiving unit is responsible for receiving preprocessed data from the networked sensor module in real time. The preprocessed data is usually transmitted in a standard data format (such as CSV, JSON, etc.). The data receiving unit will parse the data format and extract the measurement value of each sensor point and the corresponding timestamp information.

[0062] The data processing unit is responsible for performing statistical analysis on the received pre-processed data. The statistical analysis process includes: combining the measurement value and timestamp information of each sensor point into time series data; calculating the statistical characteristics of these time series data, including mean, variance and autocorrelation coefficient.

[0063] The mean reflects the central trend of the data, and the calculation formula is expressed as:

[0064]

[0065] In the formula, x i is the value of the ith data point, and n is the total number of data points.

[0066] Variance reflects the degree of dispersion of data, and the calculation formula is expressed as:

[0067]

[0068] The autocorrelation coefficient reflects the correlation of the data, and the calculation formula is expressed as:

[0069]

[0070] Where k is the time delay step.

[0071] The time window aggregation method is used to aggregate the above statistical features, eliminate short-term fluctuations, and obtain smooth operating data.

[0072] The aggregation formula is expressed as:

[0073]

[0074] In the formula, w represents the time window size, y i is the statistical characteristic value in the i-th time window.

[0075] The visualization unit is responsible for converting the processed operating data into visual charts and dashboards. The visualization forms include: time series graphs, which show the trend of each sensor point changing over time; heat maps, which show the state distribution of each area in the sensor network; and dashboards, which intuitively display key performance indicators.

[0076] The remote monitoring module can collect monitoring data from the distributed sensor network in real time and perform statistical analysis on the data to obtain key indicators that reflect the system's operating status. This real-time analysis capability is conducive to the rapid discovery of abnormal situations and provides a basis for subsequent intelligent decision-making. The module converts the analyzed operating data into intuitive charts and dashboards. This visual presentation method can help managers intuitively understand the system's operating status, which is conducive to quickly discovering problems, analyzing trends, and supporting timely decision-making and adjustments. At the same time, the entire monitoring process is completed remotely, avoiding the workload of manual inspections, and realizing overall monitoring of the entire network, improving monitoring efficiency and coverage.

[0077] The intelligent decision-making module uses an anomaly detection method based on statistical distribution to determine whether there is abnormal information in the operating data, and makes corresponding intelligent decisions if so.

[0078] The intelligent decision-making module includes an anomaly detection unit and a decision execution unit. The anomaly detection unit adopts an anomaly detection method based on statistical distribution to obtain anomaly information based on operating data. The decision execution unit is used to make corresponding intelligent decisions based on the anomaly information.

[0079] The process of obtaining exception information includes:

[0080] Collect fiber Bragg grating sensing historical data, and pre-process the historical data to obtain historical pre-processed data.

[0081] A statistical distribution model of normal operating status based on historical preprocessed data is constructed, the univariate data is set to obey Gaussian distribution, the mean and standard deviation are calculated, and the covariance matrix is ​​calculated for multivariate data.

[0082] Input the real-time operation data into the normal operation state statistical distribution model. If the real-time operation data is a univariate Gaussian distribution, calculate the standard deviation from the mean. If the real-time operation data is a multivariate Gaussian distribution, calculate the Mahalanobis distance from the covariance matrix.

[0083] The standard deviation and Mahalanobis distance are used as anomaly scores, and the anomaly scores are compared with the preset anomaly threshold. If the anomaly score is greater than the anomaly threshold, the anomaly information is output.

[0084] The process of making corresponding intelligent decisions based on abnormal information includes: setting decision rules according to the application scenarios of the distributed sensor network. Collecting operation data in real time and receiving abnormal information. Making corresponding intelligent decisions based on the decision rules.

[0085] The intelligent decision-making module adopts an anomaly detection method based on statistical distribution, which can automatically discover anomalies in distributed sensor networks. It is more intelligent and robust, can identify anomalies more accurately, and is conducive to timely discovery and location of system faults, providing a basis for subsequent intelligent decision-making.

[0086] After detecting an abnormal situation, the module can make corresponding intelligent decisions. The decision-making rules can be flexibly set to meet the needs of different application scenarios, avoiding the limitations of manual intervention in decision-making and improving the automation level of the system. The module's abnormal detection and decision-making rules can also be continuously optimized through machine learning and other methods. By continuously learning and accumulating new abnormal patterns and decision-making strategies, the system becomes more intelligent and adaptable.

[0087] The firmware upgrade module is used to manage and upgrade the firmware of the fiber grating sensor node.

[0088] The firmware upgrade module includes a firmware version management unit, a remote upgrade mechanism unit and an upgrade strategy optimization unit; the firmware version management unit is used to set the firmware maintenance program library of the fiber grating sensor node; the remote upgrade mechanism unit is used to build a mechanism to support the remote upgrade of the fiber grating sensor node; the upgrade strategy optimization unit is used to realize the firmware upgrade of the fiber grating sensor node according to intelligent decision-making.

[0089] In this embodiment, the firmware version management unit needs to maintain a complete fiber grating sensor node firmware program library, including firmware programs of different hardware models and functional versions, and perform version control. The firmware program needs to undergo rigorous testing and verification to ensure quality and compatibility. The firmware program library includes the firmware version number and update time, applicable hardware models and equipment specifications, main functional features and fixed issues, and verification codes and signature information.

[0090] When new vulnerability fixes or function upgrades are discovered, the firmware library needs to be updated in a timely manner. During the update, the compatibility of the old and new firmware versions needs to be ensured to avoid affecting the existing network nodes. The version upgrade log should be maintained to record the detailed information of each upgrade and provide a version rollback function to deal with upgrade failures or problems.

[0091] The remote upgrade mechanism unit needs to build a firmware transmission protocol that supports remote upgrades. The firmware transmission protocol supports breakpoint resumption, data verification, and retransmission mechanisms, and adopts optimization methods such as compression and block transmission. At the same time, encryption and signing measures are used to ensure transmission security.

[0092] The remote upgrade mechanism unit needs to define a complete firmware remote upgrade process, including firmware package downloading, upgrade preparation, firmware burning, and upgrade result confirmation.

[0093] When designing the firmware remote upgrade process, the FBG sensor node status and network conditions should be considered to ensure the reliability of the upgrade process. At the same time, upgrade progress monitoring and interruption recovery mechanisms should be provided to ensure the continuity of the upgrade task.

[0094] The remote upgrade mechanism unit also needs to support firmware upgrades for nodes with different hardware models and software versions. It can automatically match the appropriate firmware program based on the node information, and provide a backward-compatible upgrade solution to ensure a smooth transition of existing network equipment.

[0095] The upgrade strategy optimization unit includes an intelligent decision-making driving subunit, an upgrade priority management subunit and an adaptive optimization subunit.

[0096] The intelligent decision-making driving subunit can formulate targeted upgrade strategies based on intelligent decisions, which include node failure type and severity, network performance indicators (such as online rate, latency, etc.), and topology changes. Based on this information, combined with firmware version management data, the intelligent decision-making driving subunit can formulate a reasonable upgrade plan.

[0097] The upgrade priority management subunit can determine the upgrade priority based on factors such as node importance and fault impact range, giving priority to upgrading key nodes and nodes with a larger impact range, so as to minimize interference with normal network operation.

[0098] The adaptive optimization subunit introduces machine learning algorithms to achieve automatic learning and optimization of upgrade strategies. Based on actual upgrade results, it continuously optimizes strategy parameters such as upgrade timing and target nodes to improve upgrade efficiency and reduce the impact on network stability.

[0099] The firmware upgrade module maintains a complete fiber Bragg grating sensor node firmware library, which can track the firmware version in real time, update the repair program in time to ensure system security, and support version rollback function to ensure the reliability of the upgrade process.

[0100] This module builds a transmission protocol and upgrade process that supports remote upgrades, which can remotely and securely complete the upgrade of node firmware without human intervention, improving upgrade efficiency and reducing the impact on network operations.

[0101] This module can formulate targeted firmware upgrade strategies based on the diagnosis results of the intelligent decision-making module. By optimizing parameters such as upgrade timing and upgrade priority, it can further improve the intelligence of the upgrade and minimize the impact of the upgrade process on system stability.

[0102] In summary, this embodiment provides an intelligent fiber grating sensor network monitoring system, which integrates functional modules such as networked sensing, remote monitoring, intelligent decision-making and firmware upgrade, and realizes a fully automated process from data collection, abnormal diagnosis to automatic repair, greatly reducing the workload of manual inspection and maintenance, and improving the reliability of the monitoring system. Through the design of each functional module, it has strong adaptability and scalability, and can be flexibly configured according to different application scenarios to meet monitoring systems of different scales and needs. It supports dynamic expansion of the number of sensor nodes to adapt to changes in the monitoring range. The system fully combines advanced statistical analysis, machine learning and other technologies to realize the intelligence of the entire process from data collection, analysis and diagnosis to decision-making execution, greatly improving the automation level and adaptive ability of the system, and reducing manual intervention. The system covers the entire life cycle management from deployment, operation to maintenance, can monitor the system operation status in real time, promptly discover and repair abnormalities, ensure the continuous and stable operation of the entire monitoring system, and minimize the operation and maintenance costs.

[0103] Based on the same general inventive concept, the present invention also protects an intelligent fiber grating sensor network monitoring method. The intelligent fiber grating sensor network monitoring method provided by the present invention is described below. The intelligent fiber grating sensor network monitoring method described below and the intelligent fiber grating sensor network monitoring system described above can correspond to each other.

[0104] FIG. 1 is a flow chart of an intelligent fiber grating sensor network monitoring method provided by an embodiment of the present invention.

[0105] like Figure 2 As shown, the intelligent fiber grating sensor network monitoring method includes:

[0106] S1. Construct a distributed sensing network based on fiber Bragg grating sensor nodes, obtain fiber Bragg grating sensing data, and preprocess the fiber Bragg grating sensing data to obtain preprocessed data.

[0107] S2. Perform statistical analysis on the preprocessed data to obtain operating data, and convert the operating data into visual data for display.

[0108] S3. Use anomaly detection methods based on statistical distribution to determine whether there is abnormal information in the operating data. If so, make corresponding intelligent decisions to manage and upgrade the firmware of the fiber grating sensor nodes.

[0109] In this embodiment, by deploying multiple fiber grating sensor nodes, a distributed sensing network is constructed, which can achieve coverage monitoring of a wider area and improve the spatial resolution of the overall monitoring. By real-time remote collection of monitoring data in the distributed sensing network and statistical analysis of these data, key indicators reflecting the operating status of the system are obtained. This real-time analysis capability is conducive to the rapid discovery of abnormal situations and provides a basis for subsequent intelligent decision-making. The use of anomaly detection methods based on statistical distribution can automatically discover abnormal situations in distributed sensing networks, which is more intelligent and robust, can more accurately identify anomalies, and is conducive to timely discovery and positioning of system faults, providing a basis for subsequent intelligent decision-making. After detecting an abnormal situation, the module can make corresponding intelligent decisions, and the decision rules can be flexibly set to meet the needs of different application scenarios, avoid the limitations of manual intervention in decision-making, and improve the automation level of the system. A complete fiber grating sensor node firmware library is maintained through the firmware upgrade module, which can track the firmware version in real time, update the repair program in time, ensure system security, and support the version rollback function to ensure the reliability of the upgrade process. By building a transmission protocol and upgrade process that supports remote upgrades, node firmware can be upgraded remotely and safely without manual intervention, which improves upgrade efficiency and reduces the impact on network operation. Based on the diagnosis results of the intelligent decision-making module, targeted firmware upgrade strategies can be formulated, and by optimizing parameters such as upgrade timing and upgrade priority, the intelligence of the upgrade can be further improved, minimizing the impact of the upgrade process on system stability.

[0110] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0111] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent fiber grating sensor network monitoring system, characterized in that: include: A networked sensing module is used to construct a distributed sensing network based on fiber grating sensor nodes, obtain fiber grating sensing data, and pre-process the fiber grating sensing data to obtain pre-processed data; A remote monitoring module, used for performing statistical analysis on the pre-processed data to obtain operating data, and converting the operating data into visual data display; The intelligent decision-making module uses an abnormality detection method based on statistical distribution to determine whether the operating data contains abnormal information, and makes corresponding intelligent decisions if so; A firmware upgrade module is used to manage and upgrade the firmware of the fiber grating sensor node according to the intelligent decision.

2. The intelligent fiber grating sensor network monitoring system according to claim 1 is characterized in that: The networked sensing module includes a sensor unit and a signal processing unit; the sensor unit is used to collect fiber Bragg grating sensing data in real time; the signal processing unit is used to pre-process the fiber Bragg grating sensing data to obtain pre-processed data.

3. The intelligent fiber grating sensor network monitoring system according to claim 2 is characterized in that: The process of preprocessing the fiber Bragg grating sensing data includes: Converting the fiber grating sensing data into a digital signal; Performing filtering on the digitized signal to obtain a filtered signal; Amplifying the filtered signal using a programmable gain amplifier to obtain an amplified signal; Performing linear processing on the amplified signal by polynomial fitting to obtain linear data; The linear data is format-converted to obtain preprocessed data.

4. The intelligent fiber grating sensor network monitoring system according to claim 1 is characterized in that: The remote monitoring module includes a data receiving unit, a data processing unit and a visualization unit; the data receiving unit is used to receive the pre-processed data in real time; the data processing unit is used to perform statistical analysis on the pre-processed data to obtain operating data; and the visualization unit is used to convert the operating data into visual data for display.

5. The intelligent fiber grating sensor network monitoring system according to claim 4, characterized in that: The process of performing statistical analysis on the preprocessed data includes: Recording the timestamp information of each of the preprocessed data, and combining each of the preprocessed data with its corresponding timestamp information to generate time series data; Performing statistical analysis on the time series data to calculate statistical features of the time series data, wherein the statistical features include mean, variance and correlation of the time series data; The statistical features are aggregated using a time window aggregation method, and the aggregated results are used as running data.

6. The intelligent fiber grating sensor network monitoring system according to claim 1, characterized in that: The intelligent decision-making module includes an anomaly detection unit and a decision execution unit; the anomaly detection unit adopts an anomaly detection method based on statistical distribution to obtain anomaly information according to the operating data; the decision execution unit is used to make corresponding intelligent decisions according to the anomaly information.

7. The intelligent fiber grating sensor network monitoring system according to claim 6, characterized in that: The process of obtaining the abnormal information includes: Collecting fiber grating sensing historical data, and preprocessing the historical data to obtain historical preprocessed data; Constructing a normal operating state statistical distribution model based on the historical preprocessed data, setting the univariate data to obey Gaussian distribution, calculating the mean and standard deviation, and calculating the covariance matrix for the multivariate data; Input the real-time operation data into the normal operation state statistical distribution model, and if the real-time operation data is a univariate Gaussian distribution, calculate the standard deviation from the mean; if the real-time operation data is a multivariate Gaussian distribution, calculate the Mahalanobis distance from the covariance matrix; The standard deviation and the Mahalanobis distance are used as an anomaly score, and the anomaly score is compared with a preset anomaly threshold. If the anomaly score is greater than the anomaly threshold, anomaly information is output.

8. The intelligent fiber grating sensor network monitoring system according to claim 7, characterized in that: The process of making corresponding intelligent decisions according to the abnormal information includes: setting decision rules according to the application scenario of the distributed sensor network; collecting the operation data in real time and receiving the abnormal information; and making corresponding intelligent decisions according to the decision rules.

9. The intelligent fiber grating sensor network monitoring system according to claim 1, characterized in that: The firmware upgrade module includes a firmware version management unit, a remote upgrade mechanism unit and an upgrade strategy optimization unit; the firmware version management unit is used to set the firmware maintenance program library of the fiber grating sensor node; The remote upgrade mechanism unit is used to construct a mechanism to support the remote upgrade of the fiber Bragg grating sensor node; the upgrade strategy optimization unit is used to implement the firmware upgrade of the fiber Bragg grating sensor node according to the intelligent decision.

10. An intelligent fiber Bragg grating sensor network monitoring method, which adopts the intelligent fiber Bragg grating sensor network monitoring system as claimed in any one of claims 1 to 9, characterized in that: The intelligent fiber grating sensor network monitoring method includes: S1, constructing a distributed sensing network based on fiber Bragg grating sensor nodes, acquiring fiber Bragg grating sensing data, and preprocessing the fiber Bragg grating sensing data to obtain preprocessed data; S2. Statistically analyzing the preprocessed data to obtain operating data, and converting the operating data into visual data for display; S3. Adopting an abnormality detection method based on statistical distribution to determine whether there is abnormal information in the operation data, and making corresponding intelligent decisions if so, to manage and upgrade the firmware of the fiber grating sensor node.

Images