An AI intelligent inspection control system

Abstract

The present invention relates to the field of AI intelligent inspection technology, and specifically to an AI intelligent inspection control system, including: an optical fiber break monitoring module: monitoring the operating status data of the optical fiber link in the wavelength division optical transmission system, and using the AI ​​anomaly detection model to determine the optical fiber break position and break degree; an optical power safety control module: according to the optical fiber break position and break degree, and based on the optical power dynamic control algorithm, automatically reducing the luminous power to a safe level; a link recovery detection module: determining whether the optical fiber link has been repaired; monitoring the transmission performance parameters of the optical fiber; a communication control module: controlling the switching of the communication state according to the fault alarm information of the optical fiber break monitoring module and the recovery confirmation signal of the link recovery detection module; and an inspection recording module. In the present invention, through this automated recovery mechanism, the response speed of the system after the break is repaired is greatly improved, reducing manual intervention and enhancing the overall self-healing ability.

Description

Technical Field

[0001] The present invention relates to the field of AI intelligent inspection technology, and in particular to an AI intelligent inspection control system. Background Art

[0002] With the development of optical fiber communication technology, wavelength division multiplexing (WDM) transmission systems have been widely used in modern communication networks due to their high bandwidth and high efficiency. However, as the core transmission medium, optical fiber faces a variety of uncontrollable external threats, such as fiber breakage caused by construction excavation, natural disasters or equipment aging. These breakage events will not only lead to communication interruptions, but may also cause safety hazards to human eyes and the environment due to exposed high-power laser signals. Therefore, when an optical fiber break occurs, quickly detecting the break location, determining the degree of breakage and implementing safe power regulation are the key to ensuring the safety and stability of the wavelength division multiplexing transmission system.

[0003] In the existing technology, most of the equipment such as optical time domain reflectometer (OTDR) is used to perform physical measurement of fiber breaks. However, such methods mainly rely on single modal data and are greatly affected by factors such as signal noise, environmental interference and insufficient reflection intensity, which are prone to positioning errors or failure to detect. In addition, traditional break detection and control systems usually only provide fixed power adjustment strategies, which makes it difficult to flexibly reduce the luminous power according to the specific situation of the break. There is a problem of too high or too low power, which affects the system security and the efficiency of subsequent link detection.

[0004] In terms of fiber optic link repair, traditional methods usually require manual intervention to determine the link recovery status and manually reinitialize communication functions, which has the disadvantages of slow response and low recovery efficiency. Summary of the invention

[0005] The present invention provides an AI intelligent inspection control system.

[0006] An AI intelligent inspection control system, comprising:

[0007] Fiber break monitoring module: monitors the operating status data of the optical fiber link in the wavelength division optical transmission system, including optical power fluctuation, reflected light intensity and link attenuation; uses a multimodal data fusion algorithm to analyze the operating status data, and combines the AI ​​anomaly detection model to determine the location and degree of fiber breakage; when a fiber breakage event occurs, generates fault alarm information including the location and degree of fiber breakage and notifies the communication control module;

[0008] Optical power safety control module: According to the optical fiber break position and break degree, and based on the optical power dynamic control algorithm, the luminous power is automatically reduced to a safe level to ensure that the power output does not exceed the specified threshold of international safety standards;

[0009] Link recovery detection module: performs periodic detection on the broken optical fiber link to determine whether the optical fiber link has been repaired; monitors the transmission performance parameters of the optical fiber in real time through low-power detection optical signals, and generates a recovery confirmation signal and notifies the communication control module when the optical fiber link returns to normal;

[0010] Communication control module: controls the switching of communication status according to the fault alarm information of the optical fiber break monitoring module and the recovery confirmation signal of the link recovery detection module;

[0011] Inspection record module: records and analyzes the entire process of fiber breakage and link recovery, and generates historical inspection reports.

[0012] Optionally, the monitoring of the operating status data specifically includes:

[0013] Optical power fluctuation monitoring: The optical power monitoring devices installed at both ends of the optical fiber link collect the input optical power and output optical power of the signal transmitted in the optical fiber in real time and calculate the power attenuation value;

[0014] Reflected light intensity monitoring: Use a reflectometer (such as optical time domain reflectometer, OTDR) to periodically measure the intensity of reflected light in the optical fiber link and analyze the time delay and intensity change of the reflected light;

[0015] Link loss monitoring: By comparing the optical signal loss at the input and output ends, the link loss value is calculated in combination with the optical fiber characteristic parameters.

[0016] Optionally, the use of a multimodal data fusion algorithm to analyze the operating status data and combining the AI ​​anomaly detection model to determine the optical fiber break position and break degree specifically includes:

[0017] Multimodal data fusion: The collected optical power fluctuation data, reflected light intensity data and link loss data are standardized and processed to construct single-modal feature vectors respectively. , use weighted fusion to fuse each single-modal feature vector to generate a multi-modal feature vector : ,in, The weight is dynamically assigned;

[0018] The AI ​​anomaly detection model is built on a multi-layer perceptron to fused multimodal feature vectors. Perform high-dimensional feature extraction and mapping to output two target values:

[0019] Fiber break location : Indicates the exact location of the break in the optical fiber link;

[0020] Fiber breakage degree : Indicates the severity of the degradation of optical fiber transmission performance caused by the break;

[0021] AI anomaly detection model input is multimodal fusion features , the output is the target value .

[0022] Optionally, the network structure of the AI ​​anomaly detection model includes:

[0023] Input layer: input fused multimodal feature vector , each input node corresponds to a feature;

[0024] Multi-layer hidden layer (23 layers): Each layer is a fully connected layer, and the activation function uses ReLU to capture nonlinear features. The output of the hidden layer is expressed as: ,in, It is The output features of the layer, They are The weight matrix and bias vector of the layer, Activation function;

[0025] Output layer: The number of output nodes is 2, corresponding to ;

[0026] Use an adapted activation function:

[0027] Location : Linear activation, ensuring that the output is a continuous value.

[0028] degree : Sigmoid activation, normalized to the range [0,1], indicating the probability of the severity of the fracture.

[0029] Optionally, the optical fiber break position : Based on the high-dimensional features extracted by the hidden layer, they are mapped to the link position through the fully connected layer: ,in, are the weights and biases of the position output, and the output is a continuous value within the link length range, indicating the specific location of the fracture;

[0030] The degree of fiber breakage : Classify the extracted high-dimensional features into probability maps to represent the normalized severity of the fracture degree: ,in, , are the weight and bias of the fracture degree output, It is the Sigmoid activation function, and the output value range is [0,1].

[0031] Optionally, the AI ​​anomaly detection model also includes a dynamic weight adjustment mechanism to improve the adaptability to feature importance, specifically including:

[0032] Dynamic weight design: for each input feature Add a learnable weight parameter , dynamically adjust the influence of each feature on the final output: , It is a dynamic weight learned through an additional network (attention mechanism) to represent the feature The importance of The update is expressed as:

[0033] ,in, is a learnable scalar consisting of the features The contextual relationship is calculated;

[0034] Dynamic weights re-weight the feature vectors at the input layer:

[0035] .

[0036] Optionally, the optical power safety control module specifically includes:

[0037] According to the location of the fiber break The distance information is used to calculate the power transmission loss of the optical fiber segment where the break point is located. : ,in, is the total length of the optical fiber, is the total link power loss;

[0038] According to the degree of fracture and , determine the power reduction target that needs to be adjusted .

[0039] Optionally, the power reduction target Calculated as: ,

[0040] in, is the luminous power under normal working conditions;

[0041] After a break event is detected, the luminous power is reduced to a preliminary safe level:

[0042] ,in, is the preset safety power threshold.

[0043] Optionally, the link recovery detection module analyzes the optical fiber operation signal returned by low-power detection to obtain transmission performance parameters:

[0044] Optical signal loss ,in, Indicates the low-power detection signal power input to the optical fiber link, Indicates the optical signal power detected by the receiving end after passing through the optical fiber link;

[0045] Bit Error Rate :The bit error rate of the digital data transmission of the detection signal is calculated by comparing the number of bit errors in the sent and received data: ;

[0046] Recovery judgment criteria: If the monitored transmission performance parameters meet the following criteria, the optical fiber link is judged to be loss-free;

[0047] Bit Error Rate ,in is the set bit error rate tolerance.

[0048] Beneficial effects of the present invention:

[0049] The present invention realizes accurate judgment of the position and degree of optical fiber breakage through the combination of optical fiber breakage monitoring module, multimodal data fusion algorithm and AI anomaly detection model. The multimodal data fusion algorithm can integrate multidimensional data such as optical power fluctuation, reflected light intensity, link attenuation, etc., thereby improving the reliability and anti-interference ability of detection. At the same time, the optical power safety control module uses the optical power dynamic control algorithm based on the breakage position and breakage degree to quickly reduce the luminous power to a safe level, avoiding damage to human eyes caused by strong light exposure. It not only ensures the safety of the system, but also meets the strict requirements of safety standards and improves the intelligent management capabilities of optical fiber networks.

[0050] In the present invention, the link recovery detection module detects optical signals at low power periodically, monitors the performance parameters such as optical signal loss and bit error rate in real time, and thus accurately determines the repair status of the optical fiber link. Combined with multi-level judgment criteria, it can effectively identify the stable state after the link is restored, generate a recovery confirmation signal and notify the communication control module. The communication control module quickly completes the reinitialization of the communication channel based on the signal, so that the link can seamlessly switch to a normal working state after recovery. Through this automated recovery mechanism, the response speed of the system after the break is repaired is greatly improved, reducing manual intervention and enhancing the overall self-healing ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A schematic diagram of functional modules of a control system according to an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of an AI anomaly detection model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0055] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0056] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0057] like Figure 1-Figure 2 As shown, an AI intelligent inspection control system includes:

[0058] Fiber break monitoring module: monitors the operating status data of the optical fiber link in the wavelength division optical transmission system, including optical power fluctuation, reflected light intensity and link attenuation; uses a multimodal data fusion algorithm to analyze the operating status data, and combines the AI ​​anomaly detection model to determine the location and degree of fiber breakage; when a fiber breakage event occurs, generates fault alarm information including the location and degree of fiber breakage and notifies the communication control module;

[0059] Optical power safety control module: According to the optical fiber break position and break degree, and based on the optical power dynamic control algorithm, the luminous power is automatically reduced to a safe level to ensure that the power output does not exceed the specified threshold of international safety standards;

[0060] Link recovery detection module: performs periodic detection on the broken optical fiber link to determine whether the optical fiber link has been repaired; monitors the transmission performance parameters of the optical fiber in real time through low-power detection optical signals, and generates a recovery confirmation signal and notifies the communication control module when the optical fiber link returns to normal;

[0061] Communication control module: controls the switching of communication status according to the fault alarm information of the optical fiber break monitoring module and the recovery confirmation signal of the link recovery detection module;

[0062] When the optical fiber is broken, the communication is interrupted to avoid the system from transmitting data incorrectly and causing waste of resources;

[0063] After the link is restored, the communication channel is reinitialized according to the communication protocol, and the normal communication function of the link is restored synchronously.

[0064] Inspection record module: records and analyzes the entire process of fiber breakage and link recovery, and generates historical inspection reports.

[0065] The monitoring of operation status data specifically includes:

[0066] Optical power fluctuation monitoring: The optical power monitoring devices installed at both ends of the optical fiber link collect the input optical power and output optical power of the signal transmitted in the optical fiber in real time, calculate the power attenuation value, and record and report the abnormal status if the power fluctuation exceeds the preset threshold;

[0067] The optical power fluctuation is calculated by comparing the optical power difference between the input and output ends of the link, using the following formula:

[0068] ,in, is the optical power fluctuation, which indicates the difference between the input optical power and the output optical power. is the optical power at the input end of the fiber link, is the optical power at the output end of the optical fiber link. Judgment conditions: When the optical power fluctuates When the preset threshold is exceeded, the exception is recorded;

[0069] Reflected light intensity monitoring: Use a reflectometer (such as optical time domain reflectometer, OTDR) to periodically measure the intensity of reflected light in the optical fiber link and analyze the time delay and intensity change of the reflected light;

[0070] The reflected light intensity and reflection point position are measured by an optical time domain reflectometer (OTDR). The formula is as follows:

[0071] ,in, is the distance to the initial fiber break or abnormal point under standard conditions, is the speed of light in the optical fiber, calculated as: , is the speed of light, is the refractive index of the optical fiber, is the time delay of the reflected light, measured by the OTDR equipment;

[0072] Link loss monitoring: By comparing the optical signal loss at the input and output ends, the link loss value is calculated in combination with the fiber characteristic parameters. When the loss value reaches or exceeds the set threshold, an alarm signal is generated and the location of the loss point is marked. The formula is as follows: ,in, is the link loss, is the optical power at the input end of the fiber link, is the optical power at the output end of the fiber link.

[0073] The multimodal data fusion algorithm is used to analyze the operation status data, and the AI ​​anomaly detection model is used to determine the location and degree of fiber breakage. Specifically, the following are included:

[0074] Multimodal data fusion: The collected optical power fluctuation data, reflected light intensity data and link loss data are standardized and processed to construct single-modal feature vectors respectively. , use weighted fusion to fuse each single-modal feature vector to generate a multi-modal feature vector : ,in, The weight is dynamically assigned;

[0075] The AI ​​anomaly detection model is built on a multi-layer perceptron to fused multimodal feature vectors. Perform high-dimensional feature extraction and mapping to output two target values:

[0076] Fiber break location : Indicates the exact location of the break in the optical fiber link;

[0077] Fiber breakage degree : Indicates the severity of the degradation of optical fiber transmission performance caused by the break;

[0078] AI anomaly detection model input is multimodal fusion features , the output is the target value ;

[0079] (1) Optical power fluctuation characteristic vector ( ): ,in, is the mean value of the optical power fluctuation, is the standard deviation of the optical power fluctuation, indicating the degree of dispersion of the fluctuation. It is the maximum value of optical power fluctuation and is used to capture sudden anomalies;

[0080] (2) Reflected light intensity feature vector (F2): ,in, is the mean value of the reflected light intensity, which is used to capture the overall reflectivity level of the link. is the standard deviation of the reflected light intensity, which indicates the distribution characteristics of the reflected light intensity. are the locations of the first and last major reflection points, indicating the starting point of the link and the end point of the possible anomaly range, respectively. is the sharp drop in reflected light intensity at the link break: , and are the light intensities before and after the fracture, respectively;

[0081] (3) Link loss characteristic vector ( ): ,in, is the mean value of link loss, indicating the average performance of the entire link. is the gradient of the attenuation distribution in the link, calculated using multi-point sampling power values: , is the power loss per unit distance, is the link distance, It is the maximum value of local loss in the link, identifying high-loss areas.

[0082] The network structure of the AI ​​anomaly detection model includes:

[0083] Input layer: input fused multimodal feature vector , each input node corresponds to a feature;

[0084] Multi-layer hidden layer (23 layers): Each layer is a fully connected layer, and the activation function uses ReLU to capture nonlinear features. The output of the hidden layer is expressed as: ,in, It is The output features of the layer, They are The weight matrix and bias vector of the layer, Activation function;

[0085] Output layer: The number of output nodes is 2, corresponding to ;

[0086] Use an adapted activation function:

[0087] Location : Linear activation, ensuring that the output is a continuous value.

[0088] degree : Sigmoid activation, normalized to the range [0,1], indicating the probability of the severity of the fracture.

[0089] Fiber break location : Based on the high-dimensional features extracted by the hidden layer, they are mapped to the link position through the fully connected layer: ,in, are the weights and biases of the position output, and the output is a continuous value within the link length range, indicating the specific location of the fracture;

[0090] Fiber breakage degree : Classify the extracted high-dimensional features into probability maps to represent the normalized severity of the fracture degree: ,in, , are the weight and bias of the fracture degree output, It is the Sigmoid activation function, and the output value range is [0,1].

[0091] The AI ​​anomaly detection model also includes a dynamic weight adjustment mechanism to improve the ability to adapt to the importance of features, including:

[0092] Dynamic weight design: for each input feature Add a learnable weight parameter , dynamically adjust the influence of each feature on the final output: , It is a dynamic weight learned through an additional network (attention mechanism) to represent the feature The importance of The update is expressed as:

[0093] ,in, is a learnable scalar consisting of the features The contextual relationship is calculated;

[0094] Dynamic weights re-weight the feature vectors at the input layer:

[0095] The dynamic weight adjustment mechanism can optimize the weights of input features in real time according to the importance of features during training, avoiding the impact of redundant features on model performance. It is particularly suitable for scenarios of multimodal feature fusion, because features of different modalities may have different importance in different situations.

[0096] The optical power safety control module specifically includes:

[0097] According to the location of the fiber break The distance information is used to calculate the power transmission loss of the optical fiber segment where the break point is located. : ,in, is the total length of the optical fiber, is the total link power loss;

[0098] According to the degree of fracture and , determine the power reduction target that needs to be adjusted .

[0099] Power reduction target Calculated as: ,in, is the luminous power under normal working conditions;

[0100] After a break event is detected, the luminous power is reduced to a preliminary safe level:

[0101] ,in, is the preset safety power threshold.

[0102] The link recovery detection module analyzes the optical fiber operation signal returned by low-power detection to obtain transmission performance parameters:

[0103] Optical signal loss ,in, Indicates the low-power detection signal power input to the optical fiber link, Indicates the optical signal power detected by the receiving end after passing through the optical fiber link;

[0104] Bit Error Rate :The bit error rate of the digital data transmission of the detection signal is calculated by comparing the number of bit errors in the sent and received data: ;

[0105] Restoration judgment criteria: If the monitored transmission performance parameters meet the following criteria, the optical fiber link is judged to have been repaired:

[0106] Optical signal loss ,in is the maximum allowable loss under normal working conditions;

[0107] Bit Error Rate ,in is the set bit error rate tolerance.

[0108] After detecting that the link has returned to normal, a recovery confirmation signal is generated, which includes the link status, transmission performance parameters and repair completion time. The recovery confirmation signal is sent to the communication control module to reinitialize the communication channel and restore normal communication functions.

[0109] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0110] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An AI intelligent inspection control system, characterized in that: include: Optical fiber break monitoring module: monitors the operating status data of the optical fiber link in the wavelength division optical transmission system, including optical power fluctuation, reflected light intensity and link attenuation; uses a multimodal data fusion algorithm to analyze the operating status data, and combines the AI ​​anomaly detection model to determine the location and degree of optical fiber breakage; When an optical fiber break event occurs, fault alarm information including the optical fiber break position and break degree is generated and notified to the communication control module; The use of a multimodal data fusion algorithm to analyze the operating status data and combining the AI ​​anomaly detection model to determine the optical fiber break location and break degree specifically includes: Multimodal data fusion: The collected optical power fluctuation data, reflected light intensity data and link loss data are standardized and processed to construct single-modal feature vectors respectively. , use weighted fusion to fuse each single-modal feature vector to generate a multi-modal feature vector : ,in, is the weight assigned dynamically; The AI ​​anomaly detection model is built on a multi-layer perceptron to fused multimodal feature vectors. Perform high-dimensional feature extraction and mapping to output two target values: Fiber break location : Indicates the exact location of the break in the optical fiber link; Fiber breakage degree : Indicates the severity of the degradation of optical fiber transmission performance caused by the break; AI anomaly detection model input is a multimodal feature vector Output is the target value ; The network structure of the AI ​​anomaly detection model includes: Input layer: input fused multimodal feature vector , each input node corresponds to a feature; Multi-layer hidden layer: Each layer is a fully connected layer, and the activation function uses ReLU to capture nonlinear features. The output of the hidden layer is expressed as: ,in, It is The output features of the layer, They are The weight matrix and bias vector of the layer, , is the activation function; Output layer: The number of output nodes is 2, corresponding to ; Fiber break location Use a linear activation function to ensure that the output is a continuous value; Fiber breakage degree Use the Sigmoid activation function, normalized to the range of [0,1], to represent the probability of fracture severity; Optical power safety control module: automatically reduces the luminous power to a safe level based on the optical power dynamic control algorithm according to the optical fiber break position and break degree; Link recovery detection module: performs periodic detection on the broken optical fiber link to determine whether the optical fiber link has been repaired; monitors the transmission performance parameters of the optical fiber in real time through low-power detection optical signals, and generates a recovery confirmation signal and notifies the communication control module when the optical fiber link returns to normal; Communication control module: controls the switching of communication status according to the fault alarm information of the optical fiber break monitoring module and the recovery confirmation signal of the link recovery detection module; Inspection record module: records and analyzes the entire process of fiber breakage and link recovery, and generates historical inspection reports.

2. The AI ​​intelligent inspection control system according to claim 1 is characterized in that: The monitoring of the operating status data specifically includes: Optical power fluctuation monitoring: The optical power monitoring devices installed at both ends of the optical fiber link collect the input optical power and output optical power of the signal transmitted in the optical fiber in real time and calculate the power attenuation value; Reflected light intensity monitoring: Use a reflectometer to periodically measure the intensity of reflected light in the optical fiber link and analyze the time delay and intensity change of the reflected light; Link loss monitoring: By comparing the optical signal loss at the input and output ends, the link loss value is calculated in combination with the optical fiber characteristic parameters.

3. The AI ​​intelligent inspection control system according to claim 1 is characterized in that: The optical fiber break position : Based on the high-dimensional features extracted by the hidden layer, they are mapped to the link position through the fully connected layer: ,in, are the weights and biases of the position output, and the output is a continuous value within the link length range, indicating the specific location of the fracture; The degree of fiber breakage : Classify the extracted high-dimensional features into probability maps to represent the normalized severity of the fracture degree: ,in, are the weight and bias of the fracture degree output, It is the Sigmoid activation function, and the output value range is [0,1].

4. The AI ​​intelligent inspection control system according to claim 3 is characterized in that: The AI ​​anomaly detection model also includes a dynamic weight adjustment mechanism to improve the adaptability to feature importance, including: Dynamic weight design: for each input feature Add a learnable weight parameter , dynamically adjust the influence of each feature on the final output: , is a dynamic weight learned through an additional network, representing the feature The importance of The update is expressed as: ,in, is a learnable scalar consisting of the features The contextual relationship is calculated; Dynamic weights re-weight the feature vectors at the input layer: .

5. The AI ​​intelligent inspection control system according to claim 1 is characterized in that: The optical power safety control module specifically includes: According to the location of the fiber break The distance information is used to calculate the power transmission loss of the optical fiber segment where the break point is located. ,in, is the total length of the optical fiber, is the total link power loss; According to the degree of fracture and , determine the power reduction target that needs to be adjusted .

6. The AI ​​intelligent inspection control system according to claim 5 is characterized in that: The power reduction target Calculated as: ,in, is the luminous power under normal working conditions; After a break event is detected, the luminous power is reduced to a preliminary safe level: ,in, is the preset safety power threshold.

7. The AI ​​intelligent inspection control system according to claim 1 is characterized in that: The link recovery detection module analyzes the optical fiber operation signal returned by low-power detection to obtain transmission performance parameters: Optical signal loss ,in, Indicates the low-power detection signal power input to the optical fiber link, Indicates the optical signal power detected by the receiving end after passing through the optical fiber link; Bit Error Rate :The bit error rate of the digital data transmission of the detection signal is calculated by comparing the number of bit errors in the sent and received data: ; Restoration judgment criteria: If the monitored transmission performance parameters meet the following criteria, the optical fiber link is judged to have been repaired: Optical signal loss ,in is the maximum allowable loss under normal working conditions; Bit Error Rate ,in is the set bit error rate tolerance.

Images