Optical cable network automatic monitoring system based on industrial equipment

Abstract

The invention discloses an optical cable network automatic monitoring system based on industrial equipment, which relates to the field of industrial automation and comprises a dynamic monitoring module, an abnormity repairing module, a structure analysis module, a cloud management platform module, an automatic alarm module, a safety guarantee module, an intelligent maintenance module and an expansion compatible module. Wherein the output end of the dynamic monitoring module is connected with the input ends of the abnormity repairing module and the cloud management platform module; the output end of the abnormity repairing module is connected with the input end of the structure analysis module; the output end of the cloud management platform module is connected with the input end of the automatic alarm module; the output end of the automatic alarm module is connected with the input ends of the intelligent maintenance module and the safety guarantee module; the output ends of the safety guarantee module and the intelligent maintenance module are connected with the input ends of the cloud management platform module and the expansion compatibility module; according to the method, the problems that a fault point cannot be predicted, a network topology structure cannot be automatically identified and optimized and the compatibility is poor in a traditional monitoring system are solved.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation, and more particularly to an automatic monitoring system for an optical cable network based on industrial equipment. Background Art

[0002] In today's era, the automatic monitoring system for an optical cable network has important application value in the field of industrial equipment. By real-time monitoring, analyzing and diagnosing the status and performance of the optical cable network, it provides more efficient and reliable operation guarantee for industrial equipment. As the core transmission medium of the industrial communication network, the stability and reliability of the optical cable are crucial for ensuring the production process and data transmission. Therefore, introducing an automatic monitoring system for an optical cable network can greatly improve the maintenance management level of industrial equipment, reduce the failure risk and production cost. The automatic monitoring system for an optical cable network can achieve real-time monitoring of the optical cable network. The traditional manual inspection method requires a large amount of time and manpower and has a long monitoring cycle. The automatic monitoring system for an optical cable network can continuously monitor the physical parameters, signal strength, loss conditions, etc. of the optical cable through sensors and devices arranged at key positions, and generate corresponding alarm information. This enables engineers to timely know the network anomalies and quickly take measures for repair and treatment, greatly improving the efficiency of rapid fault location and elimination. However, there are also some disadvantages in the existing automatic monitoring systems for optical cable networks that need to be considered. First of all, the monitoring system can only provide the current network status and cannot predict potential fault points in advance. This means that engineers cannot take preventive maintenance measures and cannot take timely measures for repair or replacement before the occurrence of a fault, which may lead to more serious consequences such as network interruption or data loss.

[0003] Secondly, the existing monitoring systems often cannot automatically identify and optimize the network topology. Engineers need to adjust and upgrade the network based on experience and professional knowledge, which requires a large amount of time and human resources. Moreover, due to the existence of human factors, there may be misjudgments or unreasonable optimization schemes, thus unable to achieve the best network performance.

[0004] In addition, the traditional systems lack standardized interfaces and protocols, resulting in difficulties in data exchange and communication with devices with poor compatibility. Each device may have different data formats, communication protocols and interface requirements, and customized development and integration need to be carried out again, increasing the complexity and cost of the system.

[0005] Therefore, in order to solve the problems existing in the automatic monitoring system for an optical cable network, namely, the inability to predict potential fault points in advance, the inability to automatically identify and optimize the network topology, and poor compatibility, the present invention discloses an automatic monitoring system for an optical cable network based on industrial equipment. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention discloses an automatic monitoring system for an optical cable network based on industrial equipment. The present invention collects and monitors the physical parameters and performance indicators of the optical cable network in real time through a dynamic monitoring module to detect abnormal situations in a timely manner; conducts intelligent analysis and anomaly detection through a neural network algorithm, combines a fault diagnosis model to locate and diagnose the cause of the fault, provides a repair strategy for maintenance personnel, shortens the fault repair time, and improves the availability of the network; automatically analyzes and optimizes the topological structure of the optical cable network through a structure analysis module, improves the transmission performance of the network, reduces signal attenuation and interference, and enhances the stability and transmission quality of the network; views the status and performance of the optical cable network in real time through a cloud management platform module, facilitates monitoring and management by operation and maintenance personnel, and responds to network problems in real time; improves the response and handling efficiency of faults through an automatic alarm module; generates a maintenance plan and optimizes the network upgrade path through an intelligent maintenance module, improves the maintenance efficiency and reduces the maintenance cost; ensures data integrity and system security through a security guarantee module, and guarantees the safe operation of the network; provides flexible expansion and compatibility through an extended compatibility module to meet diverse requirements.

[0007] To achieve the above technical effects, the present invention adopts the following technical solutions: An automatic monitoring system for an optical cable network based on industrial equipment, the system comprising: A dynamic monitoring module, which collects and monitors the physical parameters and performance indicators of the optical cable network in real time through a sensor network; the physical parameters and performance indicators at least include temperature, humidity, optical signal intensity, loss, displacement, tensile force, vibration, pressure and gas indicators; An anomaly repair module, which conducts intelligent analysis and anomaly detection on the data output by the dynamic monitoring module through a neural network algorithm, and the anomaly repair module locates and diagnoses the cause of the fault through a fault diagnosis model to provide a repair strategy; A structure analysis module, which automatically analyzes and optimizes the topological structure of the optical cable network through a network topology analysis model to improve the reliability and stability of the network; A cloud management platform module, which receives the data of the dynamic monitoring module through a real-time data transmission method to view the status and performance of the optical cable network in real time on the cloud management platform; An automatic alarm module, which realizes an automatic alarm notification function through a rule engine, the automatic alarm module sends an alarm notification to relevant personnel through a message push tool, and the message push tool ensures the response and handling of faults through an integrated method of SMS, email and application push; An intelligent maintenance module that deeply analyzes and mines historical data through a big data statistical analysis model to generate a maintenance plan and optimize the network upgrade path, improving maintenance efficiency and reducing maintenance costs; A security guarantee module that provides security protection through an intrusion detection model to ensure data integrity and system security; An extended compatibility module that integrates and is compatible with communication protocols and network architectures through an interface adaptation unit, an automatic configuration unit, and a modular unit to adapt to industrial devices of different scales and types; Among them, the output end of the dynamic monitoring module is connected to the input ends of the anomaly repair module and the cloud management platform module; the output end of the anomaly repair module is connected to the input end of the structure analysis module; the output end of the cloud management platform module is connected to the input end of the automatic alarm module; the output end of the automatic alarm module is connected to the input ends of the intelligent maintenance module and the security guarantee module; the output ends of the security guarantee module and the intelligent maintenance module are connected to the input ends of the cloud management platform module and the extended compatibility module.

[0008] As a further technical solution of the present invention, the sensor network collects the parameters and index data in the optical cable network by deploying distributed sensor nodes; the distributed sensor nodes include a temperature sensor, a humidity sensor, an optical signal intensity sensor, a loss sensor, a tensile sensor, a vibration sensor, a pressure sensor and a smoke sensor. As a further technical solution of the present invention, the fault diagnosis model includes a feature engineering module, a fault classification prediction module, an anomaly localization module and a repair strategy generation module; the feature engineering module includes a feature extraction unit and a feature selection unit; the feature extraction unit extracts feature data from the data of the dynamic monitoring module through wavelet transform and frequency domain analysis, and the feature selection unit performs a selection operation from the extracted features through the chi-square test method to reduce redundancy and noise; the fault classification prediction module includes a model training unit and a classification unit; the model training unit models and trains the historical fault data through an unsupervised learning algorithm to construct a classification model; the classification unit classifies and predicts the fault data through the trained classification model; after the fault data is classified, the anomaly localization module performs fault localization and analysis; the anomaly localization module includes a location inference unit and a cause analysis unit; the location inference unit performs fault localization through a rule inference method; the cause analysis unit infers and analyzes the fault cause through a fault feature algorithm based on historical data and the device knowledge base; the repair strategy generation module includes a knowledge base unit and a strategy matching unit; the knowledge base unit stores the fault types and repair strategies through a database storage method; the strategy matching unit matches the repair strategy through a rule engine according to the fault diagnosis result and the device characteristics; the output end of the feature engineering module is connected to the input end of the fault classification prediction module; the output end of the fault classification prediction module is connected to the input end of the anomaly localization module; the output end of the anomaly localization module is connected to the input end of the repair strategy generation module.

[0009] As a further technical solution of the present invention, the neural network algorithm performs data analysis through a feature transformation formula, and the feature transformation formula converts the input data into the output of the first layer through a weight matrix and a bias vector, and the feature transformation formula also converts the output through a non-linear activation function to obtain a feature representation; the feature transformation formula is: In formula (1), represents the offset of the data, represents the weight parameter of the data, e represents the base of the natural logarithm, represents pi; after the data analysis is completed, data anomaly detection is performed through the forward propagation formula. The forward propagation formula linearly combines the output of the previous layer through a weight matrix and a bias vector, and is converted into the output of the current layer through a non-linear activation function. By continuously stacking multiple layers of calculations, complex feature representations are learned to achieve anomaly data detection; the forward propagation formula is: In formula (2), i represents the input data, b represents the representation of the hidden layer, and z represents the propagation convergence rate. represents the bias vector, represents the activation function, and w represents the reconstruction error; after the anomaly detection is completed, the prediction error of the sample is calculated through the cross-entropy loss function for effect evaluation, and the gap between the prediction result and the true label is measured through the loss function; the formula expression of the cross-entropy loss function is: In formula (3), P is the true label, S is the expected result, and m is the total number of samples. As a further technical solution of the present invention, the network topology analysis model includes a topology discovery module, a performance evaluation module, a diagnosis and optimization module, and a visualization display module; the topology discovery module automatically scans the optical cable network through a link detection method and obtains the connection information between devices to construct a topology map of the optical cable network; the performance evaluation module analyzes the node degree, connectivity, loops, and bandwidth utilization rate of the optical cable network through network analysis algorithms to evaluate the network performance; the diagnosis and optimization module includes a redundancy elimination unit and a fault tolerance design unit; the redundancy elimination unit removes redundant connections and optimizes the network structure through the minimum spanning tree algorithm to reduce loops and redundant paths; the fault tolerance design unit enhances the reliability of the network through a redundancy mechanism; the visualization display module visualizes the topology map and the analysis results through a visualization method; the output end of the topology discovery module is connected to the input end of the performance evaluation module; the output end of the performance evaluation module is connected to the input end of the diagnosis and optimization module; the output end of the diagnosis and optimization module is connected to the input end of the visualization display module.

[0010] As a further technical solution of the present invention, the working mode of the real-time data transmission method is: S1. Convert the collected analog signal into a digital signal through binary encoding to achieve data processing and transmission; S2. After the data conversion is completed, encapsulate the data into a data packet through the network communication TCP / IP protocol stack to achieve routing and processing during the transmission process; the network communication TCP / IP protocol stack encapsulates the data by adding the source address, target address, and data length to the digital signal. S3. Transmit the data through the network transmission protocol. S4. Improve the data transmission efficiency and speed through data compression algorithms and fiber optic transmission to ensure the real-time nature of data transmission; S5. After the cloud management platform receives the transmitted data, the receiving end, according to the packet format, parses the packet header information through a protocol parsing model and extracts the data; the protocol parsing model includes a syntax analysis unit, a state transition unit, a matching recognition unit, and a physical layer parsing unit; the syntax analysis unit uses regular expressions to parse the data layer by layer to identify and extract protocol headers, fields, and parameters; the state transition unit defines different states and state transition conditions through a rule engine, and the state transition unit updates the state of the received data step by step through a state machine parsing method to restore the original protocol information; the matching recognition unit matches and recognizes the data through a pattern matching algorithm; the physical layer parsing unit parses and restores the data through a hardware parser; the output end of the syntax analysis unit is connected to the input end of the state transition unit; the output end of the state transition unit is connected to the input end of the matching recognition unit; the output end of the matching recognition unit is connected to the input end of the physical layer parsing unit.

[0011] S6. Store the decoded data through a time series database to enable querying, historical analysis, and report generation.

[0012] As a further technical solution of the present invention, the cloud management platform module includes a user management unit, a real-time monitoring unit, a configuration management unit, a fault management unit, a historical data unit, and a user interface unit; the user management unit creates and manages user accounts through two-factor authentication and access control methods, and assigns different permissions and roles; the real-time monitoring unit receives data from the dynamic monitoring module through a real-time data transmission method to monitor and display the status and performance information of the optical cable network; the configuration management unit configures devices and links of the optical cable network through network management protocols, configuration file management, and remote command execution to remotely modify and update device configurations; the fault management unit records and tracks fault events through a fault recorder and an event trigger, and provides fault diagnosis and solutions; the historical data unit stores and analyzes historical data through a storage subunit and an analysis subunit to achieve performance optimization and maintenance; the storage subunit realizes the functions of storing and querying historical data through a time series database, and the analysis subunit performs trend analysis and fault diagnosis on the status of the optical cable network through big data analysis methods; the user interface unit visually displays the content of fault analysis, performance evaluation, and capacity planning through data visualization methods.

[0013] As a further technical solution of the present invention, the intrusion detection model includes a traffic collection module, a traffic analysis module, a threat detection module, an attack response module, a security management module, and a storage management module; the traffic collection module includes a data packet capture unit and a filtering unit; the data packet capture unit captures network traffic data packets by means of network packet capture; the filtering unit preprocesses and filters the collected network traffic by means of data preprocessing to remove redundant data and noise; the traffic analysis module includes a deep packet inspection unit, a session analysis unit, and a statistical feature analysis unit; the deep packet inspection unit extracts protocol header, field, and parameter information by means of protocol parsing; the session analysis unit combines and analyzes the captured network traffic data packets by means of session management to implement the restoration operation of communication sessions; the statistical feature analysis unit analyzes the features and behavior patterns of network traffic by means of statistical methods to detect potential attack behaviors; the threat detection module includes a meshing detection unit and a security detection unit; the meshing detection unit compares and matches the traffic data based on network threat intelligence and a rule library through a matching algorithm and a rule engine to identify threats and attack behaviors; the security detection unit scans the files and data in the network traffic through a threat detection engine to identify risk data and viruses; the attack response module includes a firewall unit and a penetration defense unit; the firewall unit filters and monitors the network traffic by means of an access control list to prevent unauthorized access and attacks; the penetration defense unit monitors and analyzes the network traffic in real time through an intrusion detection algorithm, and the penetration defense unit performs a blocking operation through a blocking strategy; the blocking strategy includes IP blocking, port shielding, enhanced access control, protocol filtering, session and connection disconnection, and network isolation operations; the security management module includes an access control unit, an identity authentication unit, a key management unit, and a log auditing unit; the access control unit realizes the authorization and permission management of system resources and functions through an access control policy and an authentication and authorization protocol to ensure the security of the system; the identity authentication unit verifies the legality and authenticity of the user identity through an identity authentication protocol; the key management unit generates, stores, and manages encrypted keys through a key generation algorithm and a key negotiation protocol to ensure the confidentiality and integrity of communication; the log auditing unit records system operations and events through a logger to implement auditing and tracing; the storage management module stores and manages network traffic, threat information, and security rule data through a relational database.

[0014] As a further technical solution of the present invention, the interface adaptation unit identifies and converts the communication protocol into the same interface format through a protocol conversion method to achieve the adaptation of communication interfaces between different devices; the automatic configuration unit selects the communication protocol and network architecture through a network definition method to achieve customized configuration of the communication protocol and network architecture; the modular unit realizes the independence of functional modules through a microservices architecture to meet the needs of different industrial devices.

[0015] Positive and beneficial effects: The present invention collects and monitors the physical parameters and performance indicators of the optical cable network in real time through a dynamic monitoring module to detect abnormal situations in a timely manner; conducts intelligent analysis and anomaly detection through a neural network algorithm, combines a fault diagnosis model to locate and diagnose the cause of the fault, provides repair strategies for maintenance personnel, shortens the fault repair time, and improves the availability of the network; automatically analyzes and optimizes the topological structure of the optical cable network through a structure analysis module, improves the transmission performance of the network, reduces signal attenuation and interference, and enhances the stability and transmission quality of the network; views the status and performance of the optical cable network in real time through a cloud management platform module, facilitates monitoring and management by operation and maintenance personnel, and responds to network problems in real time; improves the response and handling efficiency of faults through an automatic alarm module; generates a maintenance plan and optimizes the network upgrade path through an intelligent maintenance module, improves the maintenance efficiency and reduces the maintenance cost; ensures data integrity and system security through a security guarantee module, and guarantees the safe operation of the network; provides flexible expansion and compatibility through an extended compatibility module to meet diverse requirements. Description of the Drawings

[0016] Figure 1 It is a schematic diagram of the overall module process of an optical cable network automatic monitoring system based on industrial equipment of the present invention; Figure 2 It is a step flowchart of the real-time data transmission method in an optical cable network automatic monitoring system based on industrial equipment of the present invention; Figure 3 It is a schematic diagram of the implementation principle of the intrusion detection model in an optical cable network automatic monitoring system based on industrial equipment of the present invention; Figure 4 It is a schematic diagram of the working principle of the cloud management platform module in an optical cable network automatic monitoring system based on industrial equipment of the present invention; Figure 5 It is a step diagram of the working principle of the neural network algorithm in an optical cable network automatic monitoring system based on industrial equipment of the present invention; Detailed Embodiments

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] As Figures 1-5 shown, an automatic monitoring system for an optical cable network based on industrial equipment, the system includes: A dynamic monitoring module, which collects and monitors the physical parameters and performance indicators of the optical cable network in real time through a sensor network; the physical parameters and performance indicators at least include temperature, humidity, optical signal intensity, loss, displacement, tension, vibration, pressure and gas indicators; An anomaly repair module, which intelligently analyzes and detects anomalies in the output data of the dynamic monitoring module through a neural network algorithm, and the anomaly repair module locates and diagnoses the cause of the failure through a fault diagnosis model to provide a repair strategy; A structure analysis module, which automatically analyzes and optimizes the topology of the optical cable network through a network topology analysis model to improve the reliability and stability of the network; A cloud management platform module, which receives the data of the dynamic monitoring module through a real-time data transmission method to realize real-time viewing of the status and performance of the optical cable network on the cloud management platform; An automatic alarm module, which realizes the automatic alarm notification function through a rule engine, the automatic alarm module sends alarm notifications to relevant personnel through a message push tool, and the message push tool ensures the response and handling of faults through the integration of SMS, email and application push; An intelligent maintenance module, which deeply analyzes and mines historical data through a big data statistical analysis model to generate a maintenance plan and optimize the network upgrade path, improve the maintenance efficiency and reduce the maintenance cost; A security guarantee module, which performs security protection through an intrusion detection model to ensure data integrity and system security; An expansion compatibility module, which integrates and is compatible with communication protocols and network architectures through an interface adaptation unit, an automatic configuration unit and a modular unit to adapt to industrial equipment of different scales and types; Among them, the output end of the dynamic monitoring module is connected to the input ends of the anomaly repair module and the cloud management platform module; the output end of the anomaly repair module is connected to the input end of the structure analysis module; the output end of the cloud management platform module is connected to the input end of the automatic alarm module; the output end of the automatic alarm module is connected to the input ends of the intelligent maintenance module and the security guarantee module; the output ends of the security guarantee module and the intelligent maintenance module are connected to the input ends of the cloud management platform module and the extended compatibility module.

[0019] In the above embodiment, the sensor network collects the parameters and index data in the optical cable network by deploying distributed sensor nodes; the distributed sensor nodes include temperature sensors, humidity sensors, optical signal strength sensors, loss sensors, tensile sensors, vibration sensors, pressure sensors, and smoke sensors.

[0020] In a specific embodiment, the sensor network distributes various types of sensor nodes at key positions in the optical cable network, such as connection points between nodes, corners, hot spots, etc. The sensor nodes can communicate with the central control unit by wired or wireless means. In addition, each sensor node is responsible for collecting data on specific parameters and indexes, such as temperature, humidity, optical signal strength, loss, tensile force, vibration, pressure, and smoke. The sensor nodes convert the collected data into digital signals through analog-to-digital conversion methods and transmit the data to the central control unit through wireless communication means. Then, the central control unit receives the data sent by the sensor nodes and performs data processing and analysis. Machine learning and data mining techniques can be used to perform real-time analysis and anomaly detection on the data to judge the health status and possible faults of the optical cable network. According to the data analysis results, the central control unit can judge whether there are abnormal situations or potential faults and generate corresponding alarm notifications. By setting appropriate thresholds and rules, the system can automatically issue alarms and notify relevant personnel for fault diagnosis and handling.

[0021] In specific implementation, the temperature change in the optical cable network is monitored by a temperature sensor. It is based on the principle of a thermosensitive element or a thermocouple, and converts the sensed temperature change in the surrounding environment into an electrical signal. The temperature sensor can detect high or low temperature conditions in a timely manner, prevent potential faults caused by overheating or overcooling of the optical cable, and provide temperature history data, which can help analyze the working state and operating characteristics of the system.

[0022] The humidity level in the optical cable network is measured by a humidity sensor. It is usually based on the principle of capacitance or resistance, detects the humidity in the air, and converts it into a corresponding electrical signal. The humidity sensor can avoid faults caused by the optical cable being affected by moisture or being overly wet, protect the equipment from humidity damage, and can also assist in judging the impact of climate conditions and environmental changes on the optical cable network, optimizing the network design and deployment.

[0023] The optical signal intensity in the optical cable is measured by an optical signal intensity sensor. Based on the photoelectric conversion principle, it monitors the intensity of the optical signal in the optical cable and converts it into an electrical signal. By using the optical signal intensity sensor, the change of the optical signal intensity in the optical cable is monitored in real time to detect problems such as optical attenuation or signal interruption. In addition, it can assist in identifying the fault points in the optical cable, providing positioning and rapid response.

[0024] The optical signal loss in the optical cable is measured by a loss sensor. Based on the principles of scattering, reflection or insertion loss, it detects the loss of the optical signal during transmission and converts it into an electrical signal to timely detect the signal loss in the optical cable and discover problems such as poor fiber connection or degraded fiber quality.

[0025] The stress on the optical cable is measured by a tensile sensor. Based on the strain principle, it monitors the stress level in the optical cable and converts it into an electrical signal to prevent breakage or damage caused by exceeding the load-bearing capacity of the optical cable.

[0026] The vibration in the optical cable network is detected by a vibration sensor. Based on the principles of acceleration or displacement, it senses the vibration around the optical cable and converts it into an electrical signal to timely detect the abnormal vibration around the optical cable and discover the risks caused by transportation, construction or external forces.

[0027] The pressure on the optical cable is measured by a pressure sensor. Based on the piezoresistive or piezoelectric principle, it monitors the pressure on the optical cable and converts it into an electrical signal to detect the pressure change in the environment where the optical cable is located and prevent damage caused by external pressure. The pressure sensor is used to assist in the optical cable routing and engineering design to ensure that the optical cable works within an appropriate pressure range.

[0028] The smoke or fire in the optical cable network is detected by a smoke sensor. Based on the principles of light scattering, ionization or photoelectric conversion, it senses the smoke or flame in the surrounding air and converts it into an electrical signal to monitor the smoke situation around the optical cable in real time, warn of the fire risk and handle it in a timely manner. The smoke sensor provides historical smoke data to assist in the post-event analysis of fire accidents and response strategies.

[0029] In specific implementation, the sensor network can collect various parameters and index data in the optical cable network in real time, detect abnormal situations in a timely manner, and remind the operation and maintenance personnel to conduct fault troubleshooting and repair through instant alarms, improving the reliability and stability of the network. In addition, through the various parameter and index data provided by the sensor network, the fault location can be more accurately located, and the fault cause diagnosis and repair strategy can be provided for the maintenance personnel, saving the fault troubleshooting time and improving the fault handling efficiency. At the same time, the sensor network can provide historical data of various parameters and indexes of the optical cable network. By deeply analyzing and mining these data, preventive maintenance plans and optimization strategies can be formulated, the equipment life can be extended, and the system performance can be improved. Secondly, the sensor network can automatically collect data and process and analyze it through intelligent algorithms, reducing manual intervention and operation errors, and providing more accurate and reliable data support; in specific implementation, the relevant data collected by using different sensors in the optical cable network automatic monitoring system are shown in Table 1: In the above embodiment, the fault diagnosis model includes a feature engineering module, a fault classification and prediction module, an anomaly location module, and a repair strategy generation module; the feature engineering module includes a feature extraction unit and a feature selection unit; the feature extraction unit extracts feature data from the data of the dynamic monitoring module through wavelet transform and frequency domain analysis, and the feature selection unit performs a selection operation from the extracted features through the chi-square test method to reduce redundancy and noise; the fault classification and prediction module includes a model training unit and a classification unit; the model training unit models and trains the historical fault data through an unsupervised learning algorithm to construct a classification model; the classification unit classifies and predicts the fault data through the trained classification model; after the fault data is classified, fault location and analysis are performed through the anomaly location module; the anomaly location module includes a location inference unit and a cause analysis unit; the location inference unit performs fault location through a rule inference method; the cause analysis unit infers and analyzes the fault cause through a fault feature algorithm based on historical data and the equipment knowledge base; the repair strategy generation module includes a knowledge base unit and a strategy matching unit; the knowledge base unit stores the fault types and repair strategies through a database storage method; the strategy matching unit matches the repair strategy through a rule engine according to the fault diagnosis result and the equipment characteristics; the output end of the feature engineering module is connected to the input end of the fault classification and prediction module; the output end of the fault classification and prediction module is connected to the input end of the anomaly location module; the output end of the anomaly location module is connected to the input end of the repair strategy generation module.

[0030] In a specific embodiment, the fault diagnosis model processes and transforms the raw data collected by the sensor nodes through a feature engineering module to extract feature information related to faults. These features may include temperature change patterns, humidity fluctuation levels, vibration frequencies, etc.; the model is trained by a fault classification and prediction module to classify and predict the features. It can classify faults into different types, such as optical cable breakage, connection faults, etc. This module can be trained with historical fault data to improve accuracy and reliability; the abnormal location module uses the data collected by multiple sensor nodes and combines the results of fault classification and prediction to locate the fault position. By analyzing the differences and change trends between different sensor nodes, the specific location where the fault occurs can be accurately located. This module can help maintenance personnel quickly locate the fault point, reducing maintenance time and costs. The repair strategy generation module provides repair suggestions and strategies for different fault types based on the fault location results and the previous fault case library. This includes relevant information such as repair methods, required resources, time plans, etc., to assist maintenance personnel in carrying out fault repair work. This module can improve maintenance efficiency and accuracy and reduce human errors during the repair process.

[0031] In a specific implementation, the fault diagnosis model can automatically diagnose faults occurring in the optical cable network, classify and predict them according to specific fault types, and locate them. This greatly improves the speed and accuracy of fault diagnosis. Through the abnormal location module, the fault diagnosis model can quickly locate the specific location where the fault occurs, helping maintenance personnel accurately find the fault point and improving maintenance efficiency. At the same time, the fault diagnosis model can generate repair strategies and suggestions based on the fault location results and the previous fault case library. This helps maintenance personnel formulate reasonable repair plans and schemes, improving the success rate of repair. In addition, the fault diagnosis model can provide preventive maintenance suggestions by analyzing historical data and prediction models. This helps to detect potential fault risks in advance and take measures for prevention to avoid the occurrence of faults.

[0032] In summary, the fault diagnosis model plays an important role in the optical cable network automatic monitoring system. By automating fault diagnosis, quickly locating faults, providing repair strategies, and preventive maintenance, it improves the reliability, stability, and maintenance efficiency of the optical cable network.

[0033] In the above embodiment, the neural network algorithm performs data analysis through a feature transformation formula. The feature transformation formula converts the input data into the output of the first layer through a weight matrix and a bias vector, and the feature transformation formula also converts the output through a non-linear activation function to obtain a feature representation; the feature transformation formula is: In formula (1), represents the offset of the data, The weight parameter representing the data, and \(e\) represents the base of the natural logarithm. \(\pi\) represents pi; after the data analysis is completed, data anomaly detection is performed through the forward propagation formula. The forward propagation formula linearly combines the output of the previous layer through a weight matrix and a bias vector, and the forward propagation formula is converted into the output of the current layer through a non-linear activation function. By continuously stacking multiple layers of calculations, complex feature representations are learned to achieve anomaly data detection; the forward propagation formula is: In formula (2), \(i\) represents the input data, \(b\) represents the representation of the hidden layer, and \(z\) represents the propagation convergence rate. represents the bias vector. \(\sigma\) represents the activation function, and \(w\) represents the reconstruction error; after the anomaly detection is completed, the prediction error of the sample is calculated through the cross-entropy loss function for effect evaluation, and the loss function is used to measure the gap between the prediction result and the true label; the formula expression of the cross-entropy loss function is: In formula (3), \(P\) is the true label, \(S\) is the expected result, and \(m\) is the total number of samples. In a specific embodiment, the feature transformation formula can translate the output value after feature transformation by adjusting the offset. The offset enables the model to better fit the overall bias of the data. In addition, the offset allows the model to have a non-zero output value even without input features.

[0034] Through the weight parameter, the input data can be linearly combined to obtain the result after feature transformation. Different weight parameters can assign different importance to different input features, thus affecting the learning and representation ability of the model. In the neural network algorithm, the weight parameter plays a role in regulating the mutual influence between different features.

[0035] In the feature transformation formula, the base of the natural logarithm and pi are mathematical constants used for calculating and transforming features. They provide a mathematical basis and operation tools to help the model appropriately transform and represent the data.

[0036] In the forward propagation formula, the propagation convergence rate represents that the output of the previous layer passes through a non-linear activation function to obtain the output of the current layer. It controls the propagation speed and change degree of the signal and is crucial for constructing a neural network with non-linear mapping ability.

[0037] The activation function then performs a non-linear transformation on the result of the linear combination to introduce non-linear attributes and mapping ability, thereby realizing the expression ability of the model. In the neural network algorithm, the reconstruction error measures the performance and representation ability of the model by comparing the difference between the input and the output. By minimizing the reconstruction error, the model can learn better data representations, thereby improving the effect of problem-solving.

[0038] In a specific embodiment, the working principle steps of the neural network algorithm are as follows: 1. First, collect and organize the data generated by the optical cable network sensors. These data may include indicators in multiple aspects such as temperature, humidity, optical signal intensity, loss, tensile force, vibration, pressure, etc. Then, perform preprocessing operations such as normalization, filtering, and denoising on the collected raw data to improve the quality and reliability of the data.

[0039] 2. Design the structure of the neural network. Generally, a neural network consists of an input layer, a hidden layer, and an output layer. The input layer receives the preprocessed data, the hidden layer performs calculations and feature extraction through a series of connected neurons, and the output layer gives corresponding classification, prediction, or anomaly detection results.

[0040] 3. Divide the preprocessed data into a training set and a validation set, where the training set is used to train the neural network model, and the validation set is used to evaluate the performance of the model. Through optimization methods such as backpropagation algorithm and gradient descent, continuously adjust the connection weights between neurons so that the neural network can gradually learn and fit the patterns and rules of the input data.

[0041] 4. Use the validation set to evaluate the performance of the model, such as indicators like accuracy, precision, recall, etc. According to the evaluation results, optimize the model, for example, adjust the network structure, change hyperparameters, increase the training sample size, etc., to improve the generalization ability and robustness of the model.

[0042] 5. Apply the trained neural network model to the optical cable network automatic monitoring system. The system inputs the sensor data collected in real time into the trained model, and through the inference and judgment of the model, performs anomaly detection, classification, or prediction analysis on the data. For example, when there is an anomaly or the data exceeds the preset threshold for a certain sensor, the system can promptly issue an alarm or take corresponding measures to handle the problem.

[0043] In a specific implementation, the intelligent analysis and anomaly detection data table of temperature, humidity, and optical signal intensity by the neural network model is shown in Table 2: In specific implementations, the neural network model can learn and fit a large amount of input data, thus possessing strong intelligent analysis capabilities. It can discover potential patterns, regularities, and anomalies in the data, assisting operation and maintenance personnel in making more accurate fault diagnoses and judgments. Through the neural network algorithm, the optical cable network automatic monitoring system can monitor and analyze sensor data in real time, promptly detecting potential problems or anomalies. This helps improve the speed of fault discovery, enabling the early adoption of necessary maintenance and repair measures to minimize system downtime to the greatest extent. Additionally, the neural network model has an adaptive learning ability and can continuously update and optimize the model based on the actual operating conditions and new data. Over time, the model can adapt to the changes and evolutions of the optical cable network, enhancing the data analysis effect in different scenarios.

[0044] Therefore, data intelligent analysis and anomaly detection based on the neural network algorithm play an important role in the optical cable network automatic monitoring system, providing intelligent monitoring and analysis capabilities and effectively ensuring the stability and reliability of the optical cable network.

[0045] In the above embodiment, the network topology analysis model includes a topology discovery module, a performance evaluation module, a diagnosis and optimization module, and a visualization display module; the topology discovery module automatically scans the optical cable network through a link detection method and obtains the connection information between devices to construct a topology map of the optical cable network; the performance evaluation module analyzes the node degree, connectivity, loops, and bandwidth utilization rate of the optical cable network through a network analysis algorithm to evaluate the network performance; the diagnosis and optimization module includes a redundancy elimination unit and a fault tolerance design unit; the redundancy elimination unit removes redundant connections and optimizes the network structure through a minimum spanning tree algorithm to reduce loops and redundant paths; the fault tolerance design unit enhances the reliability of the network through a redundancy mechanism; the visualization display module visually displays the topology map and analysis results through a visualization method; the output end of the topology discovery module is connected to the input end of the performance evaluation module; the output end of the performance evaluation module is connected to the input end of the diagnosis and optimization module; the output end of the diagnosis and optimization module is connected to the input end of the visualization display module.

[0046] In a specific embodiment, the network topology analysis model detects nodes and links in the optical cable network through the topology discovery module and constructs an initial network topology structure. It can establish the network topology by scanning network devices or relying on the network management protocol SNMP to obtain data such as device configuration information and link status. The performance of the optical cable network is evaluated through the performance evaluation module, including key performance indicators such as bandwidth utilization, latency, and packet loss rate. By collecting and analyzing real-time network traffic data, link status information, etc., a quantitative evaluation of the network performance is carried out. The diagnosis and optimization module identifies and locates the fault points or bottlenecks in the topology and provides corresponding optimization strategies. It can analyze problems such as bottleneck nodes and short-circuit links in the network topology structure, and based on the results of topology discovery and performance evaluation, infer possible fault causes and provide repair and optimization suggestions. Through the visualization display module, information such as the network topology structure, performance indicators, fault points, and optimization results is displayed to the user in a visual manner. In this way, users can intuitively understand the status and change trends of the entire optical cable network, quickly locate problems, and make corresponding optimization decisions.

[0047] In a specific implementation, through the network topology analysis model, it can help automatically monitor the optical cable system to optimize the network topology structure, thereby improving the performance of the entire system and reducing potential fault points. At the same time, the network topology analysis model can calculate network parameters, find problems such as bottleneck nodes and transmission delays in the network, and accordingly propose targeted optimization suggestions to improve network performance, data transmission speed, and stability. In addition, the network topology analysis model can automatically monitor the optical cable network, timely detect and solve faults, and after optimizing the network structure, reduce maintenance costs and the possibility of failures. Finally, by automatically optimizing the topology structure of the optical cable network, the network topology analysis model can improve the reliability of the entire system, thus ensuring the normal operation of the enterprise. In the above embodiment, the working mode of the real-time data transmission method is as follows: S1. Convert the collected analog signal into a digital signal through binary encoding to realize data processing and transmission; S2. After the data conversion is completed, encapsulate the data into data packets through the network communication TCP / IP protocol stack to realize routing and processing during the transmission process; the network communication TCP / IP protocol stack encapsulates the data by adding the source address, destination address, and data length to the digital signal. S3. Transmit the data through the network transmission protocol; S4. Improve the data transmission efficiency and speed through data compression algorithms and fiber optic transmission to ensure the real-time nature of data transmission; S5. After the cloud management platform receives the transmitted data, the receiving end parses the packet header information of the data packet according to the packet format through a protocol parsing model and extracts the data. The protocol parsing model includes a syntax analysis unit, a state transition unit, a matching and recognition unit, and a physical layer parsing unit. The syntax analysis unit parses the data layer by layer through regular expressions to identify and extract the protocol header, fields, and parameters. The state transition unit defines different states and state transition conditions through a rule engine, and the state transition unit performs step-by-step state update operations on the received data through a state machine parsing method to restore the original protocol information. The matching and recognition unit matches and recognizes the data through a pattern matching algorithm. The physical layer parsing unit parses and restores the data through a hardware parser. The output end of the syntax analysis unit is connected to the input end of the state transition unit. The output end of the state transition unit is connected to the input end of the matching and recognition unit. The output end of the matching and recognition unit is connected to the input end of the physical layer parsing unit.

[0048] S6. Store the decoded data through a time series database to achieve query, historical analysis, and report generation.

[0049] In a specific embodiment, in the optical cable network automatic monitoring system, the real-time data transmission method is used to receive real-time data from the dynamic monitoring module. First, the dynamic monitoring module will collect data in the optical cable network in real time, such as temperature, humidity, optical signal intensity, etc. These data collections can be achieved through devices such as sensors and monitoring instruments. The collected real-time data needs to be encoded so that it can be effectively transmitted and parsed during the transmission process. Common encoding methods include binary encoding, compression encoding, etc. After that, the encoded data is transmitted through the real-time data transmission method. Common real-time data transmission methods are as follows: Use the Ethernet protocol for data transmission, and real-time data transmission can be carried out through a local area network or a wide area network.

[0050] Transmit the data to the receiving end through a serial interface, such as an RS-232 interface or an RS-485 interface, which is suitable for short-distance real-time data transmission.

[0051] Utilize wireless communication technologies, such as Wi-Fi, Bluetooth, or the wireless network protocol Zigbee, etc., for real-time data transmission, which is suitable for data transmission between remote or mobile devices.

[0052] Use optical fiber communication technology for data transmission, which has advantages such as high bandwidth, low latency, and anti-interference, and performs well in long-distance transmission and high-speed data transmission.

[0053] After the receiving end receives the transmitted real-time data, it needs to be parsed and processed. The parsing process includes steps such as data decoding and data verification to ensure the accuracy of the received data.

[0054] Through real-time data transmission, the system can immediately receive the monitoring data in the optical cable network, realizing the real-time monitoring and tracking of the status of the optical cable network. At the same time, real-time data transmission can enable data to be transmitted remotely, facilitating remote operation and management. The operation and maintenance personnel can view and manage the monitoring data of the optical cable network in real time through the cloud platform or network access. In addition, timely transmission of real-time data can help the system detect abnormal situations in the optical cable network, such as too high temperature, abnormal humidity, etc., so as to realize fault warning and rapid response, effectively avoiding the expansion of potential problems. Secondly, real-time data transmission provides a basis for subsequent data analysis and optimization. By analyzing and mining the real-time data, the working status and performance indicators of the optical cable network can be understood, providing a basis for the optimization and improvement of the system.

[0055] In summary, the real-time data transmission method plays a key role in the optical cable network automatic monitoring system, which can realize the real-time collection, transmission and processing of data, thereby improving the monitoring efficiency and reliability of the optical cable network. In the above embodiments, the cloud management platform module includes a user management unit, a real-time monitoring unit, a configuration management unit, a fault management unit, a historical data unit and a user interface unit; the user management unit creates and manages user accounts through two-factor authentication and access control methods, and assigns different permissions and roles; the real-time monitoring unit receives the data of the dynamic monitoring module through the real-time data transmission method to monitor and display the status and performance information of the optical cable network; the configuration management unit configures the equipment and links of the optical cable network through network management protocols, configuration file management and remote command execution to realize remote modification and update of equipment configuration; the fault management unit records and tracks fault events through a fault recorder and an event trigger, and provides fault diagnosis and solutions; the historical data unit stores and analyzes historical data through a storage subunit and an analysis subunit to realize performance optimization and maintenance; the storage subunit realizes the functions of storing and querying historical data through a time series database, and the analysis subunit conducts trend analysis and fault diagnosis on the status of the optical cable network through big data analysis methods; the user interface unit visualizes the content of fault analysis, performance evaluation and capacity planning through data visualization methods.

[0056] In a specific embodiment, the cloud management platform module realizes functions such as registration, login, permission management, and role management of system users through the user management unit, ensuring that only authorized users can access the system. The real-time monitoring unit realizes the real-time monitoring and display of the monitoring data of the optical cable network. Through the real-time monitoring unit, operation and maintenance personnel can immediately obtain the monitoring data of the optical cable network, such as information on temperature, humidity, optical signal intensity, etc., and make timely processing and response according to the changes in the monitoring data. The configuration management unit provides flexible management of the system configuration. For example, it configures the sampling frequency of the monitoring module, sets the alarm threshold, configures the transmission mode, etc., to ensure the normal operation of the system. The fault management unit realizes the rapid discovery and location of optical cable network faults. When an abnormal situation occurs in the system, this module will automatically issue an alarm and notify relevant personnel for processing in a timely manner. The historical data unit records the historical records and analysis of the monitoring data of the optical cable network. Relevant personnel can query the historical monitoring data through this module for data analysis and processing. The user interface unit provides a friendly user interface, making the system operation more convenient and easy to use.

[0057] In a specific implementation, the test data of the optical cable network automatic monitoring system through the cloud management platform is shown in Table 3: Remote access is realized through the cloud management platform module. Operation and maintenance personnel can monitor and manage the optical cable network without having to go to the monitoring site in person, improving work efficiency. At the same time, the cloud management platform module can realize the real-time monitoring and surveillance of the optical cable network. Operation and maintenance personnel can timely master the monitoring data, discover and handle problems in a timely manner. In addition, the cloud management platform module can issue an alarm and notify relevant personnel, quickly warning and responding to abnormal situations of the optical cable network to avoid the expansion of faults. Secondly, the historical data unit can record the historical monitoring data of the optical cable network, providing a basis for subsequent data analysis and optimization. In addition, the user interface unit provides an intuitive and friendly user interface, making the system operation more convenient and easy to use.

[0058] In the above embodiments, the intrusion detection model includes a traffic collection module, a traffic analysis module, a threat detection module, an attack response module, a security management module, and a storage management module; the traffic collection module includes a data packet capture unit and a filtering unit; the data packet capture unit captures network traffic data packets through network packet capture methods; the filtering unit preprocesses and filters the collected network traffic through data preprocessing methods to remove redundant data and noise; the traffic analysis module includes a deep packet inspection unit, a session analysis unit, and a statistical feature analysis unit; the deep packet inspection unit extracts protocol headers, fields, and parameter information through protocol parsing methods; the session analysis unit combines and analyzes the captured network traffic data packets through session management methods to implement the restoration operation of communication sessions; the statistical feature analysis unit analyzes the characteristics and behavior patterns of network traffic through statistical methods to detect potential attack behaviors; the threat detection module includes a meshing detection unit and a security detection unit; the meshing detection unit, based on network threat intelligence and a rule library, compares and matches traffic data through matching algorithms and rule engines to identify threats and attack behaviors; the security detection unit scans files and data in network traffic through a threat detection engine to identify risk data and viruses; the attack response module includes a firewall unit and a penetration defense unit; the firewall unit filters and monitors network traffic through access control list methods to prevent unauthorized access and attacks; the penetration defense unit monitors and analyzes network traffic in real time through intrusion detection algorithms, and the penetration defense unit performs blocking operations through blocking policies; the blocking policies include IP blocking, port shielding, enhanced access control, protocol filtering, session and connection disconnection, and network isolation operations; the security management module includes an access control unit, an identity authentication unit, a key management unit, and a log auditing unit; the access control unit realizes the authorization and permission management of system resources and functions through access control policies and authentication and authorization protocols to ensure system security; the identity authentication unit verifies the legality and authenticity of user identities through identity authentication protocols; the key management unit generates, stores, and manages encrypted keys through key generation algorithms and key negotiation protocols to ensure the confidentiality and integrity of communications; the log auditing unit records system operations and events through a logger to achieve auditing and tracking; the storage management module stores and manages network traffic, threat information, and security rule data through a relational database. In a specific embodiment, the intrusion detection model monitors the traffic in the optical cable network through the traffic collection module and collects the traffic data into the intrusion detection system. The traffic can be network traffic, communication traffic, or other related traffic. The collected traffic data is analyzed and processed by the traffic analysis module. It can identify normal traffic patterns and abnormal traffic patterns and extract corresponding features. The traffic characteristics are analyzed and compared by the threat detection module to detect potential intrusion threats.It can determine whether there are abnormal or malicious activities by comparing with known attack patterns and behaviors. Once the threat detection module detects a potential intrusion threat, the attack response module will immediately take corresponding measures for response and prevention. For example, it can perform real-time alarming, block the threat source, start the backup system, etc. Configure and manage the intrusion detection model through the security management module. It can set detection rules, update the threat library, manage user permissions, etc., to ensure the efficient operation and security of the intrusion detection system. Store and manage the traffic data, logs, event records, etc. generated by the intrusion detection system through the storage management module. These data can be used for subsequent data analysis, event tracing, security auditing, etc. In specific implementation, through the analysis and comparison of traffic characteristics, the intrusion detection model can accurately identify potential intrusion threats, helping to prevent network attacks and data leakage. In addition, once a threat is detected, the intrusion detection model can immediately take corresponding measures for real-time response, effectively reducing potential losses and risks. Secondly, the intrusion detection model can predict possible threats by analyzing known attack patterns and behaviors, and thus take corresponding preventive measures to improve the security of the system. Finally, the intrusion detection model is equipped with security management and storage management modules, which can perform functions such as configuration management, log recording, and event tracing, facilitating the management and auditing of the system security.

[0059] In summary, the intrusion detection model in the automatic monitoring system of the optical cable network based on industrial equipment provides an effective intrusion detection and defense mechanism through functions such as traffic collection, analysis, threat detection, attack response, security management, and storage management, to ensure the security and stability of the system. In specific implementation, the performance test data of the automatic monitoring system of the optical cable network based on industrial equipment is shown in Table 4: In Data Table 4, MTBF represents the mean time between failures, and MTTR represents the mean time to repair.

[0060] In the above embodiments, the interface adaptation unit realizes the interface coordination and connection between different devices through a protocol conversion model to ensure communication and data exchange between devices; the protocol conversion model includes a signal intercommunication module, an interface coordination module, a format switching module, and a data communication adaptation module; the signal intercommunication module converts the output signal level through a signal level converter device to ensure signal intercommunication and compatibility between different devices; the interface coordination module converts the device interface type through an interface conversion module to realize data transmission between devices; the format switching module converts the data format output by the device through a protocol converter to realize lossless data transmission and compatibility; the data communication adaptation module mutually converts the communication protocols used by the devices through a protocol adapter to realize communication protocol compatibility between different devices; the automatic configuration unit selects communication protocols and network architectures through a network definition model to realize customized configuration of communication protocols and network architectures; the network definition model includes a network address allocation unit and an automatic parameter allocation unit; the network address allocation unit automatically allocates network addresses through the Dynamic Host Configuration Protocol for communication and management; the automatic parameter allocation unit automatically sets communication rate, transmission protocol, and data format parameters through a parameter configuration strategy to ensure communication and operation of the devices in the system; the modular unit realizes the independence of functional modules through a microservices architecture to meet the needs of different industrial devices.

[0061] In a specific embodiment, the extended compatibility module realizes the conversion and adaptation between different communication protocols through the interface adaptation unit. It can analyze the data formats of different protocols and convert them into a unified data format within the system to ensure the normal interaction of each device and component. For example, when different network communication protocols are involved, the interface adaptation unit will convert them into a format that the system can understand to achieve seamless communication between devices. Through the automatic configuration unit, users can customize and adjust the system according to actual needs and environmental characteristics. It can include functions such as setting different monitoring parameters, adjusting alarm thresholds, and configuring automation tasks to meet the needs in different usage scenarios. By dividing the system functions into independent modules through the modular unit, each module can be developed, maintained, and upgraded independently. The design of the modular unit improves the scalability and maintainability of the system. If new functions need to be added or a certain module needs to be updated, only the corresponding module needs to be modified without making large-scale changes to the entire system.

[0062] In specific implementations, through the interface adaptation and automatic configuration unit, the system can adapt to and support more different communication protocols and network architectures, thereby meeting the requirements of different industrial devices. At the same time, the modular design enables the system to conveniently add new functions and perform module-level upgrades. Secondly, the extended compatibility module can achieve smooth communication between different devices and components, enabling the entire system to work in coordination. In this way, engineers can seamlessly integrate various devices into the system, improving the overall performance and efficiency of the system. Additionally, the automatic configuration unit allows users to customize and configure the system according to actual needs, meeting specific requirements in different industrial environments. Users can flexibly adjust monitoring parameters, alarm thresholds, etc. according to their own needs, improving the adaptability and practicality of the system.

[0063] In summary, the extended compatibility module plays a role in integrating different communication protocols and network architectures in the automatic monitoring system of the fiber optic cable network based on industrial devices. Through interface adaptation, configurability, and modular design, it improves the flexibility, scalability, and personalized configuration ability of the system, enabling the system to better meet the needs of industrial device monitoring.

[0064] Although the specific implementation manners of the present invention have been described above, those skilled in the art should understand that these specific implementation manners are merely illustrative. Without departing from the principles and essence of the present invention, those skilled in the art can make various omissions, substitutions, and changes to the details of the above methods and systems. For example, combining the above method steps so as to perform substantially the same function in a substantially the same manner to achieve substantially the same result falls within the scope of the present invention. Therefore, the scope of the present invention is only defined by the appended claims.

Claims

1. An automatic monitoring system for an optical cable network based on industrial equipment, characterized in that: The system includes: A dynamic monitoring module that collects and monitors the physical parameters and performance indicators of the optical cable network in real time through a sensor network; the physical parameters and performance indicators at least include temperature, humidity, optical signal intensity, loss, displacement, tensile force, vibration, pressure, and gas indicators; An anomaly repair module that performs intelligent analysis and anomaly detection on the output data of the dynamic monitoring module through a neural network algorithm, and the anomaly repair module locates and diagnoses the cause of the fault through a fault diagnosis model to provide a repair strategy; A structure analysis module that automatically analyzes and optimizes the topology of the optical cable network through a network topology analysis model to improve network reliability and stability; A cloud management platform module that receives the data of the dynamic monitoring module through a real-time data transmission method to realize real-time viewing of the status and performance of the optical cable network on the cloud management platform; An automatic alarm module that realizes the automatic alarm notification function through a rule engine, and the automatic alarm module sends alarm notifications to relevant personnel through a message push tool, and the message push tool ensures the response and handling of faults through the integration of SMS, email, and application push; An intelligent maintenance module that deeply analyzes and mines historical data through a big data statistical analysis model to generate a maintenance plan and optimize the network upgrade path, improving maintenance efficiency and reducing maintenance costs; A security guarantee module that performs security protection through an intrusion detection model to ensure data integrity and system security; An extended compatibility module that integrates and is compatible with communication protocols and network architectures through an interface adaptation unit, an automatic configuration unit, and a modular unit to adapt to industrial equipment of different scales and types; Among them, the output end of the dynamic monitoring module is connected to the input ends of the anomaly repair module and the cloud management platform module; the output end of the anomaly repair module is connected to the input end of the structure analysis module; the output end of the cloud management platform module is connected to the input end of the automatic alarm module; the output end of the automatic alarm module is connected to the input ends of the intelligent maintenance module and the security guarantee module; the output ends of the security guarantee module and the intelligent maintenance module are connected to the input ends of the cloud management platform module and the extended compatibility module.

2. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, wherein: The sensor network collects parameter and index data in the optical cable network by deploying distributed sensor nodes; the distributed sensor nodes include temperature sensors, humidity sensors, optical signal intensity sensors, loss sensors, tensile force sensors, vibration sensors, pressure sensors, and smoke sensors.

3. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, wherein: The fault diagnosis model includes a feature engineering module, a fault classification and prediction module, an anomaly location module, and a repair strategy generation module; the feature engineering module includes a feature extraction unit and a feature selection unit; The feature extraction unit extracts feature data from the data of the dynamic monitoring module through wavelet transform and frequency domain analysis. The feature selection unit selects from the extracted features through the chi-square test method to reduce redundancy and noise. The fault classification and prediction module includes a model training unit and a classification unit. The model training unit models and trains the historical fault data through unsupervised learning algorithms to construct a classification model. The classification unit classifies and predicts the fault data through the trained classification model. After the fault data is classified, fault location and analysis are performed through the anomaly location module. The anomaly location module includes a location inference unit and a cause analysis unit. The location inference unit locates the fault through the rule inference method. The cause analysis unit infers and analyzes the fault cause through the fault feature algorithm based on historical data and the device knowledge base. The repair strategy generation module includes a knowledge base unit and a strategy matching unit. The knowledge base unit stores the fault types and repair strategies through the database storage method. The strategy matching unit matches the repair strategy through the rule engine according to the fault diagnosis result and device characteristics. The output end of the feature engineering module is connected to the input end of the fault classification and prediction module. The output end of the fault classification and prediction module is connected to the input end of the anomaly location module. The output end of the anomaly location module is connected to the input end of the repair strategy generation module.

4. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, wherein: The neural network algorithm performs data analysis through a feature transformation formula. The feature transformation formula converts the input data into the output of the first layer through a weight matrix and a bias vector, and the feature transformation formula also converts the output through a non-linear activation function to obtain a feature representation. The feature transformation formula is: In formula (1), represents the offset of the data, represents the weight parameter of the data, and e represents the base of the natural logarithm, represents pi; After the data analysis is completed, data anomaly detection is performed through the forward propagation formula. The forward propagation formula linearly combines the output of the previous layer through a weight matrix and a bias vector, and the forward propagation formula is also converted into the output of the current layer through a non-linear activation function. By continuously stacking the calculations of multiple layers, complex feature representations are learned to achieve anomaly data detection. The forward propagation formula is: In formula (2), i represents the input data, b represents the representation of the hidden layer, z represents the propagation convergence rate, represents the bias vector, represents the activation function, and w represents the reconstruction error; after anomaly detection, the prediction error of the sample is calculated through the cross-entropy loss function to evaluate the effect, and the gap between the prediction result and the true label is measured through the loss function; the formula expression of the cross-entropy loss function is: In formula (3), P is the true label, S is the expected result, and m is the total number of samples.

5. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 4, wherein: The network topology analysis model includes a topology discovery module, a performance evaluation module, a diagnosis and optimization module, and a visualization display module; the topology discovery module automatically scans the optical cable network through a link detection method and obtains the connection information between devices to construct a topology map of the optical cable network; the performance evaluation module analyzes the node degree, connectivity, loops, and bandwidth utilization rate of the optical cable network through network analysis algorithms to evaluate the network performance; the diagnosis and optimization module includes a redundancy elimination unit and a fault tolerance design unit; the redundancy elimination unit removes redundant connections and optimizes the network structure through a minimum spanning tree algorithm to reduce loops and redundant paths; the fault tolerance design unit enhances the reliability of the network through a redundancy mechanism; the visualization display module visually displays the topology map and analysis results through a visualization method; the output end of the topology discovery module is connected to the input end of the performance evaluation module; the output end of the performance evaluation module is connected to the input end of the diagnosis and optimization module; the output end of the diagnosis and optimization module is connected to the input end of the visualization display module.

6. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, characterized in that: The working mode of the real-time data transmission method is as follows: S1. Convert the collected analog signal into a digital signal through binary coding to realize data processing and transmission; S2. After the data conversion is completed, encapsulate the data into data packets through the network communication TCP / IP protocol stack to realize routing and processing during the transmission process; the network communication TCP / IP protocol stack encapsulates the data by adding the source address, destination address, and data length to the digital signal. S3. Transmit the data through the network transmission protocol. S4. Improve the data transmission efficiency and speed through data compression algorithms and optical fiber transmission to ensure the real-time nature of data transmission. S5. After the cloud management platform receives the transmitted data, the receiving end parses the data packet header information and extracts the data according to the packet format through a protocol parsing model; the protocol parsing model includes a syntax analysis unit, a state transition unit, a matching recognition unit, and a physical layer parsing unit. The syntax analysis unit gradually parses the data through regular expressions to identify and extract the protocol header, fields, and parameters. The state transition unit defines different states and state transition conditions through a rule engine, and the state transition unit gradually updates the state of the received data through a state machine parsing method to restore the original protocol information; the matching recognition unit matches and recognizes the data through a pattern matching algorithm; the physical layer parsing unit parses and restores the data through a hardware parser; the output end of the syntax analysis unit is connected to the input end of the state transition unit; the output end of the state transition unit is connected to the input end of the matching recognition unit; the output end of the matching recognition unit is connected to the input end of the physical layer parsing unit. S6. Store the decoded data through a time series database to realize query, historical analysis, and report generation.

7. An automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, characterized in that: The cloud management platform module includes a user management unit, a real-time monitoring unit, a configuration management unit, a fault management unit, a historical data unit, and a user interface unit; the user management unit creates and manages user accounts through two-factor authentication and access control methods, and assigns different permissions and roles; The real-time monitoring unit receives data from the dynamic monitoring module through real-time data transmission methods to monitor and display the status and performance information of the optical cable network; The configuration management unit performs device configuration and link configuration on the optical cable network through network management protocols, configuration file management, and remote command execution to remotely modify and update device configurations; The fault management unit records and tracks fault events through a fault recorder and event triggers, and provides fault diagnosis and solutions; the historical data unit stores and analyzes historical data through a storage subunit and an analysis subunit to achieve performance optimization and maintenance; The storage subunit realizes the functions of storing and querying historical data through a time series database, and the analysis subunit performs trend analysis and fault diagnosis on the status of the optical cable network through big data analysis methods; the user interface unit visually displays the content of fault analysis, performance evaluation, and capacity planning through data visualization methods.

8. An automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, characterized in that: The intrusion detection model includes a traffic collection module, a traffic analysis module, a threat detection module, an attack response module, a security management module, and a storage management module; the traffic collection module includes a data packet capture unit and a filtering unit; the data packet capture unit captures network traffic data packets through network packet capture methods; The filtering unit preprocesses and filters the collected network traffic through data preprocessing methods to remove redundant data and noise; The traffic analysis module includes a deep packet inspection unit, a session analysis unit, and a statistical feature analysis unit; the deep packet inspection unit extracts protocol headers, fields, and parameter information through protocol parsing methods; the session analysis unit combines and analyzes the captured network traffic data packets through session management methods to achieve the restoration operation of communication sessions; the statistical feature analysis unit analyzes the characteristics and behavior patterns of network traffic through statistical methods to detect potential attack behaviors; the threat detection module includes a meshing detection unit and a security detection unit; the meshing detection unit, based on network threat intelligence and a rule library, compares and matches traffic data through a matching algorithm and a rule engine to identify threats and attack behaviors; the security detection unit scans files and data in network traffic through a threat detection engine to identify risk data and viruses; the attack response module includes a firewall unit and a penetration defense unit; the firewall unit filters and monitors network traffic through access control list methods to prevent unauthorized access and attacks; the penetration defense unit real-time monitors and analyzes network traffic through intrusion detection algorithms, and the penetration defense unit performs blocking operations through blocking policies; the blocking policies include IP blocking, port shielding, enhanced access control, protocol filtering, session and connection disconnection, and network isolation operations; the security management module includes an access control unit, an identity authentication unit, a key management unit, and a log audit unit; the access control unit realizes the authorization and permission management of system resources and functions through access control policies and authentication and authorization protocols to ensure system security; the identity authentication unit verifies the legality and authenticity of user identities through identity authentication protocols; The key management unit generates, stores, and manages encrypted keys through key generation algorithms and key negotiation protocols to ensure the confidentiality and integrity of communications; The log audit unit records system operations and events through a logger to achieve auditing and tracing; the storage management module stores and manages network traffic, threat information, and security rule data through a relational database.

9. The automatic monitoring system for an optical cable network based on industrial equipment according to claim 1, wherein: The interface adaptation unit realizes the interface coordination and connection between different devices through a protocol conversion model to ensure communication and data exchange between devices; the protocol conversion model includes a signal intercommunication module, an interface coordination module, a format switching module, and a data communication adaptation module; the signal intercommunication module converts the output signal level through a signal level converter device to ensure signal intercommunication and compatibility between different devices; the interface coordination module converts the device interface type through an interface conversion module to achieve data transmission between devices; the format switching module converts the data format output by the device through a protocol converter to achieve lossless data transmission and compatibility; the data communication adaptation module mutually converts the communication protocols used by the devices through a protocol adapter to achieve communication protocol compatibility between different devices; the automatic configuration unit selects communication protocols and network architectures through a network definition model to achieve customized configuration of communication protocols and network architectures; the network definition model includes a network address allocation unit and an automatic parameter allocation unit; the network address allocation unit automatically allocates network addresses through the Dynamic Host Configuration Protocol for communication and management; the automatic parameter allocation unit automatically sets communication rate, transmission protocol, and data format parameters through a parameter configuration strategy to ensure communication and operation of the devices in the system; the modular unit realizes the independence of functional modules through a microservices architecture to meet the needs of different industrial devices.

Images