On-operation OPGW optical cable anomaly detection method and system based on multi-modal data

Abstract

The invention provides an in-operation OPGW optical cable anomaly detection method and system based on multi-modal data, and the method comprises the steps: collecting the Brillouin frequency shift parameters of an OPGW optical cable under different operation conditions in actual production, and collecting the state information of the corresponding OPGW optical cable; respectively performing feature extraction on the acquired Brillouin frequency shift parameters of the OPGW optical cable and the state information of the corresponding OPGW optical cable to obtain Brillouin frequency shift parameter features of the OPGW optical cable and state information features of the OPGW optical cable; and carrying out multi-modal fusion on the extracted Brillouin frequency shift parameter characteristics of the OPGW optical cable and the state information characteristics of the OPGW optical cable, and classifying OPGW optical cable faults in combination with an SVM classifier so as to complete fault identification. The health state of the optical cable can be evaluated more comprehensively, and the accuracy and reliability of anomaly detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optical fiber and cable fault diagnosis, and in particular to a method and system for detecting anomalies of an in-service OPGW optical cable based on multimodal data. Background Art

[0002] In modern power and communication systems, optical cables, as an important transmission medium, are widely used in the construction of overhead power lines and communication networks. Among them, optical fiber composite overhead ground wire (OPGW) cables not only have good optical signal transmission characteristics, but also provide additional lightning protection and power transmission capabilities. However, with the influence of various factors such as environmental factors, natural disasters and human activities, OPGW cables may have various anomalies during operation, such as fiber breakage, external force damage, temperature changes, etc. These anomalies will seriously affect the stability and reliability of power and communication. Therefore, it is particularly important to detect anomalies of OPGW cables in a timely and effective manner.

[0003] Traditional anomaly detection methods mostly rely on a single data source, such as fiber optic transmission loss, temperature monitoring or electromechanical sensors, which often cannot fully reflect the operating status of the optical cable, resulting in insufficient detection accuracy and real-time performance. Summary of the invention

[0004] In view of this, the present invention provides an in-service OPGW optical cable anomaly detection method based on multimodal data. By integrating data from different sensors, the health status of the optical cable can be more comprehensively evaluated, thereby improving the accuracy and reliability of anomaly detection.

[0005] To achieve the above object, according to one aspect of the present invention, a method for detecting abnormalities of an in-service OPGW optical cable based on multimodal data is provided, comprising:

[0006] S1. Collecting Brillouin frequency shift parameters of OPGW optical cables under different operating conditions in actual production, and simultaneously collecting status information of corresponding OPGW optical cables, wherein the status information of OPGW optical cables includes: wind speed when collecting Brillouin frequency shift parameters of OPGW optical cables and distance and height difference between towers of corresponding OPGW optical cables;

[0007] S2, respectively extracting features of the collected Brillouin frequency shift parameters of the OPGW optical cable and the corresponding state information of the OPGW optical cable to obtain Brillouin frequency shift parameter features of the OPGW optical cable and state information features of the OPGW optical cable;

[0008] S3, performing multi-modal fusion on the Brillouin frequency shift parameter features of the OPGW optical cable extracted in step S2 and the status information features of the OPGW optical cable, and classifying the OPGW optical cable faults in combination with the SVM classifier, thereby completing fault identification.

[0009] Further, the multimodal fusion in step S3 includes feature layer fusion and decision layer fusion, wherein the feature layer fusion includes fusing and analyzing the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable to obtain a new feature vector; the decision layer fusion includes pre-classifying the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, establishing two binary SVM classifiers, and combining the two set fault states to be identified to construct an identification framework Θ={CL 1 ,CL 2 The two fault states to be identified include a fault state and a normal state, and a DS inference allocation function is established through the output result of the SVM classifier to calculate the probability values ​​(BPA) of the two types of fault states. And the feature fusion of probability values ​​is performed through orthogonal rules to complete the decision-level fusion:

[0010]

[0011] In the formula, the feature vector after multimodal fusion is labeled m(CL 1 ) and m(CL 2 ) form, where m(CL 1 ) represents the confidence level of the fault state, m(CL 2 ) represents the degree of trust in the normal state; the trust function of each type of fault state is marked in the form of Bel(CL), the identification framework is marked Θ, and the measurement and labeling of all B subsets in set A is Bel(A).

[0012] Furthermore, in step S3, the OPGW optical cable fault is classified in combination with the SVM classifier to complete fault identification, which specifically includes: setting a fixed threshold a, if Bel(A) is greater than the set fixed threshold a, it is considered that the OPGW optical cable has a fault, that is, the fault diagnosis is completed.

[0013] Furthermore, a system for detecting abnormality of an in-service OPGW optical cable based on multimodal data is characterized by comprising:

[0014] A data acquisition module is used to collect the Brillouin frequency shift parameters of the OPGW optical cable under different operating conditions in actual production, and to collect the status information of the corresponding OPGW optical cable, wherein the status information of the OPGW optical cable includes: the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cable and the distance and height difference between the towers of the corresponding OPGW optical cable;

[0015] A feature extraction module is used to extract features from the collected Brillouin frequency shift parameters of the OPGW optical cable and the state information of the corresponding OPGW optical cable, respectively, to obtain the Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable;

[0016] The multimodal fusion module is used to perform multimodal fusion on the extracted Brillouin frequency shift parameter characteristics of the OPGW optical cable and the status information characteristics of the OPGW optical cable, and classify the OPGW optical cable faults in combination with the SVM classifier, thereby completing fault identification.

[0017] Further, the multimodal fusion module performs multimodal fusion on the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, specifically including: feature layer fusion and decision layer fusion, wherein the feature layer fusion includes fusing and analyzing the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable to obtain a new feature vector; the decision layer fusion includes pre-classifying the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, establishing two binary SVM classifiers, and combining the two set fault states to be identified to construct an identification framework Θ={CL 1 ,CL 2 The two fault states to be identified include a fault state and a normal state, and a DS inference allocation function is established through the output result of the SVM classifier to calculate the probability values ​​(BPA) of the two types of fault states. And the feature fusion of probability values ​​is performed through orthogonal rules to complete the decision-level fusion:

[0018]

[0019] In the formula, the feature vector after multimodal fusion is labeled m(CL 1 ) and m(CL 2 ) form, where m(CL 1 ) represents the confidence level of the fault state, m(CL 2 ) represents the degree of trust in the normal state; the trust function of each type of fault state is marked in the form of Bel(CL), the identification framework is marked Θ, and the measurement and labeling of all B subsets in set A is Bel(A).

[0020] Furthermore, the multimodal fusion module combines with the SVM classifier to classify the OPGW optical cable fault, thereby completing fault identification, specifically including: setting a fixed threshold a, if Bel(A) is greater than the set fixed threshold a, it is considered that the OPGW optical cable is faulty, that is, the fault diagnosis is completed.

[0021] The present invention can realize real-time monitoring and fault diagnosis by utilizing the Brillouin frequency shift parameters of the OPGW optical cable and the status information parameters of the OPGW optical cable. The innovation of the present invention lies in the selected parameter combination. Compared with other existing multi-mode data fusion schemes, the status information parameters of the OPGW optical cable are added, that is, the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cable and the tower distance and height difference of the corresponding OPGW optical cable are added. This real-time and flexibility enable the system to respond to faults quickly and take appropriate measures to ensure the reliability and stability of the OPGW optical cable. At the same time, predictive maintenance of potential faults can be achieved. By identifying problems in advance and taking measures, the system can reduce maintenance time and cost and extend the life of the OPGW optical cable. By comprehensively utilizing these data, the faults of the OPGW optical cable can be diagnosed more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for detecting abnormality of an in-service OPGW optical cable based on multimodal data provided by an embodiment of the present invention;

[0023] Figure 2 It is a structural schematic diagram of an in-service OPGW optical cable anomaly detection system based on multimodal data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting abnormalities of an in-service OPGW optical cable based on multimodal data, comprising the following steps:

[0026] S1. Collecting Brillouin frequency shift parameters of OPGW optical cables under different operating conditions in actual production and status information of the corresponding OPGW optical cables, wherein the status information of the OPGW optical cables includes: the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cables and the tower distance and height difference of the corresponding OPGW optical cables.

[0027] S2. Perform feature extraction on the two types of data collected above, that is, perform feature extraction on the collected Brillouin frequency shift parameters of the OPGW optical cable and the collected status information of the corresponding OPGW optical cable, to obtain the Brillouin frequency shift parameter characteristics of the OPGW optical cable and the status information characteristics of the OPGW optical cable.

[0028] The step S2 comprises the following sub-steps:

[0029] S21, the Brillouin frequency shift parameters of the OPGW optical cable collected are denoised, normalized, and processed to obtain their characteristic parameters x 1 .

[0030] S22, the collected OPGW optical cable status information is subjected to denoising, normalization and other processing to obtain its characteristic parameter x 2 .

[0031] S3. Use multimodal fusion method combined with SVM classifier to classify OPGW optical cable faults, so as to complete fault identification. First, a multi-layer classification model is established based on SVM classifier, and the acquired features are fused through multimodal fusion method. Finally, the diagnosis of OPGW optical cable faults is completed through the established classification model.

[0032] Among them, S3 can be implemented in the following ways:

[0033] S31, feature layer fusion is as follows:

[0034] The Brillouin frequency shift parameters of the OPGW optical cable obtained above and the collected state information of the corresponding OPGW optical cable are fused and analyzed to obtain a new feature vector, and the process is shown in formula (1);

[0035] y=x 1 ⊙x 2 , (1)

[0036] Where the new eigenvector is labeled y and ⊙ is the Hadamard product.

[0037] S32, the decision layer fusion is as follows:

[0038] Firstly, the acquired Brillouin frequency shift parameter characteristics of the OPGW optical cable and the collected state information characteristics of the corresponding OPGW optical cable are pre-classified, and two binary SVM classifiers are established. The two classifiers will classify the input feature y respectively, and the output results will be used for decision layer fusion. The two set fault states to be identified (fault state and normal state) are combined to construct a recognition framework Θ={CL 1 ,CL 2}(fault state and normal state), and establish the DS inference allocation function through the output of the SVM classifier to calculate the probability values ​​(BPA) of the two types of fault states, (BPA) = m(CL 1 ) s1 ,m(CL 2 ) s1 , Represents the classifier S 1 The probability value of the fault state and the classifier S 1 The probability value of the normal state, classifier S 2 The probability value of the fault state and the classifier S 2 The probability value of the normal state is considered, and the feature fusion of the probability value is performed through the orthogonal rule. The result is shown in formula (2):

[0039]

[0040] In the formula, the feature vector after multimodal fusion is labeled m(CL 1 ) and m(CL 2 ) form, where m(CL 1 ) represents the confidence level of the fault state, m(CL 2 ) represents the degree of trust in the normal state; the trust function of each type of fault state is marked in the form of Bel(CL), the identification framework is marked Θ, the measurement and mark of all B subsets in set A is Bel(A), in this invention, Bel(A) represents the trust function value of the fault, represents the sum of the basic probability distribution functions of all subsets considered to be faulty, and finally sets a fixed threshold a. If Bel(A) is greater than the set fixed threshold a, it is considered that the OPGW optical cable is faulty, that is, the fault diagnosis is completed.

[0041] According to another aspect of the present invention, Figure 2 As shown, a system for detecting abnormalities of an in-service OPGW optical cable based on multimodal data is provided, comprising:

[0042] The data acquisition module is used to collect the Brillouin frequency shift parameters of the OPGW optical cable under different operating conditions in actual production, and at the same time collect the status information of the corresponding OPGW optical cable, wherein the status information of the OPGW optical cable includes: the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cable and the tower distance and height difference of the corresponding OPGW optical cable.

[0043] The feature extraction module is used to extract features from the collected Brillouin frequency shift parameters of the OPGW optical cable and the corresponding state information of the OPGW optical cable, respectively, to obtain the Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable.

[0044] The multimodal fusion module is used to perform multimodal fusion on the extracted Brillouin frequency shift parameter characteristics of the OPGW optical cable and the status information characteristics of the OPGW optical cable, and classify the OPGW optical cable faults in combination with the SVM classifier, thereby completing fault identification.

[0045] The present invention combines a variety of data sources, including the Brillouin frequency shift parameters of the OPGW optical cable and the state information parameters of the OPGW optical cable. Although the wind speed will affect the wind pressure ratio of the optical cable, it is more significant that it easily causes the optical cable to dance and vibrate in the air. This vibration and dancing will not only affect the operating state of the optical cable, but also seriously threaten the normal operation of the transmission line. When the OPGW optical cable of the continuous gear is subjected to the wind force, due to the different gear spacing and height difference angles between the gears, the stress components of the optical cable in the vertical and horizontal directions are also different, so the displacements of each suspension point in different line directions will also be different. Therefore, compared with other existing multi-mode data fusion schemes, the state information parameters of the OPGW optical cable are added, that is, the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cable and the tower distance and height difference of the corresponding OPGW optical cable are added. By incorporating environmental factors such as wind speed into the analysis, the performance of the optical cable under actual operating conditions can be more accurately evaluated. This multi-dimensional data fusion helps to identify potential abnormal situations, thereby reducing false alarms and missed reports. Wind speed and tower information can reflect the dynamic response of optical cables under different environmental conditions, enabling the system to monitor changes in the state of optical cables in a timely manner and issue early warnings to prevent damage or accidents to optical cables caused by factors such as wind. In addition, different wind speeds, tower distances, and height differences can cause changes in stress components of optical cables in different directions. Taking these parameters into consideration, the stress conditions of optical cables can be analyzed more comprehensively, thereby evaluating their safety and reliability.

[0046] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting abnormality of an in-service OPGW optical cable based on multimodal data, characterized in that: include: S1. Collecting Brillouin frequency shift parameters of OPGW optical cables under different operating conditions in actual production, and simultaneously collecting status information of corresponding OPGW optical cables, wherein the status information of OPGW optical cables includes: wind speed when collecting Brillouin frequency shift parameters of OPGW optical cables and distance and height difference between towers of corresponding OPGW optical cables; S2, respectively extracting features of the collected Brillouin frequency shift parameters of the OPGW optical cable and the corresponding state information of the OPGW optical cable to obtain Brillouin frequency shift parameter features of the OPGW optical cable and state information features of the OPGW optical cable; S3, performing multi-modal fusion on the Brillouin frequency shift parameter features of the OPGW optical cable extracted in step S2 and the status information features of the OPGW optical cable, and classifying the OPGW optical cable faults in combination with the SVM classifier, thereby completing fault identification.

2. The method for detecting abnormalities of an in-service OPGW optical cable based on multimodal data according to claim 1, characterized in that: The multimodal fusion in step S3 includes feature layer fusion and decision layer fusion, wherein the feature layer fusion includes fusing and analyzing the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable to obtain a new feature vector; the decision layer fusion includes pre-classifying the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, establishing two binary SVM classifiers, combining the two set fault states to be identified to construct an identification framework Θ={CL1, CL2}, the two fault states to be identified include a fault state and a normal state, and establishing a DS inference allocation function through the output result of the SVM classifier, and calculating the probability values ​​(BPA) of the two types of fault states, And the feature fusion of probability values ​​is performed through orthogonal rules to complete the decision-level fusion: In the formula, the feature vectors after multimodal fusion are marked in the form of m(CL1) and m(CL2), where m(CL1) represents the degree of trust in the fault state and m(CL2) represents the degree of trust in the normal state; the trust function of each type of fault state is marked in the form of Bel(CL), the recognition framework is marked Θ, and the measurement and label of all B subsets in set A is Bel(A).

3. The method for detecting abnormality of an in-service OPGW optical cable based on multimodal data as claimed in claim 2, characterized in that: In step S3, the OPGW optical cable fault is classified in combination with the SVM classifier to complete fault identification, which specifically includes: setting a fixed threshold a, if Bel(A) is greater than the set fixed threshold a, it is considered that the OPGW optical cable has a fault, that is, the fault diagnosis is completed.

4. An in-service OPGW optical cable anomaly detection system based on multimodal data, characterized in that: include: A data acquisition module is used to collect the Brillouin frequency shift parameters of the OPGW optical cable under different operating conditions in actual production, and to collect the status information of the corresponding OPGW optical cable, wherein the status information of the OPGW optical cable includes: the wind speed when collecting the Brillouin frequency shift parameters of the OPGW optical cable and the distance and height difference between the towers of the corresponding OPGW optical cable; A feature extraction module is used to extract features from the collected Brillouin frequency shift parameters of the OPGW optical cable and the state information of the corresponding OPGW optical cable, respectively, to obtain the Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable; The multimodal fusion module is used to perform multimodal fusion on the extracted Brillouin frequency shift parameter characteristics of the OPGW optical cable and the status information characteristics of the OPGW optical cable, and classify the OPGW optical cable faults in combination with the SVM classifier, thereby completing fault identification.

5. The in-service OPGW optical cable anomaly detection system based on multimodal data as claimed in claim 4, characterized in that: The multimodal fusion module performs multimodal fusion on the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, specifically including: feature layer fusion and decision layer fusion, wherein the feature layer fusion includes fusing and analyzing the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable to obtain a new feature vector; the decision layer fusion includes pre-classifying the extracted Brillouin frequency shift parameter features of the OPGW optical cable and the state information features of the OPGW optical cable, establishing two binary SVM classifiers, combining the two set fault states to be identified to construct an identification framework Θ={CL1, CL2}, the two fault states to be identified include a fault state and a normal state, and establishing a DS inference allocation function through the output result of the SVM classifier, and calculating the probability values ​​(BPA) of the two types of fault states, And the feature fusion of probability values ​​is performed through orthogonal rules to complete the decision-level fusion: In the formula, the feature vectors after multimodal fusion are marked in the form of m(CL1) and m(CL2), where m(CL1) represents the degree of trust in the fault state and m(CL2) represents the degree of trust in the normal state; the trust function of each type of fault state is marked in the form of Bel(CL), the recognition framework is marked Θ, and the measurement and label of all B subsets in set A is Bel(A).

6. The in-service OPGW optical cable anomaly detection system based on multimodal data as claimed in claim 5, characterized in that: The multimodal fusion module combines with the SVM classifier to classify the OPGW optical cable fault, thereby completing fault identification, specifically including: setting a fixed threshold a, if Bel(A) is greater than the set fixed threshold a, it is considered that the OPGW optical cable has a fault, that is, the fault diagnosis is completed.

Images