Port communication optical cable route detection method and system based on digital twinning

Abstract

The invention provides a port communication optical cable route detection method and system based on digital twinning. Wherein a high-precision digital twinning model of a port environment and communication optical cable distribution is constructed, consistency is ensured, and a high-precision digital twinning environment is generated; based on the high-precision digital twin environment, predicting performance reduction or fault conditions of the communication optical cable by adopting a long short-term memory network, and generating a potential fault prediction report; based on the potential fault prediction report, searching an optimal inspection path in the high-precision digital twin environment by applying an ant colony algorithm, and generating an optimized inspection path and an inspection task list; and on the basis of the optimized inspection path and the inspection task list, guiding actual inspection and evaluating prediction precision so as to improve operation and maintenance efficiency and system reliability. According to the technical scheme provided by the invention, the communication optical cable state can be monitored, accurately predicted and effectively managed in real time, so that the reliability and the operation and maintenance efficiency of a port communication system are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart port technology, and in particular to a port communication optical cable routing detection method and system based on digital twins. Background Art

[0002] With the rapid development of global trade, ports, as important nodes of international trade, have a level of information construction that is directly related to logistics efficiency and service quality. As a key infrastructure for information transmission, the stability and reliability of port communication optical cables are crucial. However, due to the complex and changeable port environment, including the influence of climate conditions, marine erosion and other factors, communication optical cables are prone to aging and damage, resulting in communication interruptions, which seriously affects port operation efficiency.

[0003] The operation and maintenance of existing port communication optical cables mainly rely on regular manual inspections and simple online monitoring systems. Although manual inspections can find some obvious problems, they have disadvantages such as long inspection cycles, limited coverage, and low efficiency. Although the existing online monitoring system can monitor some key parameters in real time, it lacks comprehensive consideration of environmental factors and cannot accurately predict future failures, resulting in insufficient preventive maintenance and difficulty in responding to emergencies in a timely manner.

[0004] Manual inspection relies on the experience and judgment of inspectors, which is not only time-consuming and laborious, but also easy to miss hidden fault points and cannot achieve comprehensive coverage; the existing online monitoring system mainly focuses on the basic parameters of communication optical cables, such as signal strength, temperature, etc., and lacks comprehensive analysis of environmental factors (such as humidity, salt spray corrosion, etc.), resulting in inaccurate fault prediction; the existing solution lacks intelligent fault prediction and path optimization tools, and cannot dynamically adjust the inspection plan according to actual conditions, making it difficult to achieve refined management, resulting in unstable operation of the port communication system and frequent failures, affecting the normal operation of the port. Summary of the invention

[0005] The embodiments of the present application provide a port communication optical cable routing detection method and system based on digital twins to solve the problem of poor inspection effect of port communication optical cables in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a port communication optical cable routing detection method based on digital twin, comprising:

[0007] Build a high-precision digital twin model of the port environment and communication cable distribution to synchronize the status information of the port communication cable with environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment;

[0008] Based on the high-precision digital twin environment, historical environmental data and communication optical cable performance data are analyzed, and a long short-term memory network is used to predict the performance degradation or failure of the communication optical cable under specific environmental conditions, and a potential fault prediction report is generated;

[0009] Based on the potential fault prediction report, an ant colony algorithm is used to automatically search for an optimal inspection path in the high-precision digital twin environment, monitor and record key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list;

[0010] Based on the optimized inspection path and inspection task list, the actual inspection work is guided, the actual inspection results are compared with the predicted data in the high-precision digital twin model, and the prediction accuracy is evaluated and optimized to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

[0011] In a second aspect, an embodiment of the present application provides a port communication optical cable routing detection system based on digital twins, including:

[0012] Building modules to construct a high-precision digital twin model of the port environment and communication cable distribution, so as to synchronize the status information of the port communication cable with environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment;

[0013] An analysis module, based on the high-precision digital twin environment, analyzes historical environmental data and communication optical cable performance data, uses a long short-term memory network to predict performance degradation or failure of the communication optical cable under specific environmental conditions, and generates a potential failure prediction report;

[0014] A monitoring module, based on the potential fault prediction report, applies an ant colony algorithm to automatically search for an optimal inspection path in the high-precision digital twin environment, monitors and records key performance indicators of the communication optical cable, and generates an optimized inspection path and inspection task list;

[0015] The optimization module guides the actual inspection work based on the optimized inspection path and inspection task list, compares the actual inspection results with the predicted data in the high-precision digital twin model, evaluates and optimizes the prediction accuracy, so as to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

[0016] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the port communication optical cable routing detection method based on digital twins as described in any one of the first aspects.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements the port communication optical cable routing detection method based on digital twin as described in the first aspect.

[0018] In an embodiment of the present application, a high-precision digital twin model of the port environment and the distribution of communication optical cables is constructed to synchronize the status information of the port communication optical cables with the environmental variables in real time, ensure the consistency of the model with the actual environment, and generate a high-precision digital twin environment; based on the high-precision digital twin environment, historical environmental data and communication optical cable performance data are analyzed, and a long short-term memory network is used to predict the performance degradation or failure of the communication optical cable under specific environmental conditions, and a potential fault prediction report is generated; based on the potential fault prediction report, an ant colony algorithm is used to automatically search for the optimal inspection path in the high-precision digital twin environment, monitor and record the key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list; based on the optimized inspection path and inspection task list, the actual inspection work is guided, the actual inspection results are compared with the predicted data in the high-precision digital twin model, and the prediction accuracy is evaluated and optimized to improve the operation and maintenance efficiency and system reliability of the port communication optical cable. By building a high-precision digital twin model, real-time monitoring and dynamic management of port communication optical cables and their environment can be achieved, reducing the workload of manual inspections and improving operation and maintenance efficiency. By using long-short-term memory networks to analyze historical data, it is possible to predict possible future failures, allowing maintenance personnel to take preventive measures before failures occur, thereby reducing failure rates and maintenance costs. The ant colony algorithm is used to automatically search for the optimal inspection path in the digital twin environment, ensuring the efficiency and comprehensiveness of the inspection work while reducing the uncertainty and risk in the inspection process. By comparing and analyzing the actual inspection results with the predicted data in the digital twin model, it is possible to continuously optimize The accuracy of the prediction model is improved, thereby improving the reliability and stability of the entire port communication system; based on the high-precision digital twin environment and optimized inspection paths, it provides detailed data support for port managers, which helps to make more scientific and reasonable operation and maintenance decisions and improve management levels; through accurate predictions and optimized inspection strategies, unnecessary on-site operations are reduced, energy consumption and environmental pollution are reduced, which is in line with the principle of sustainable development; this method integrates a variety of advanced technologies such as digital twins, big data analysis, AI prediction and optimization algorithms, which not only solves practical problems in the operation and maintenance of port communication optical cables, but also provides new ideas and directions for technological progress and development in related fields.

[0019] Collect and preprocess historical port environmental data and communication cable performance data to generate a structured data set, organize the data in chronological order and input it into the time series prediction model for training, and obtain a training model that learns the relationship between environmental factors and communication cable performance. Based on this model, a long short-term memory network is used to predict performance degradation or failure under specific environmental conditions, generate preliminary fault prediction data, analyze the scope of fault impact, and generate a fault risk assessment report based on the actual layout. Finally, targeted preventive measures and suggestions are formulated to generate a potential fault prediction report. Through the collection and preprocessing of historical data, the relationship between environmental factors and the performance of communication optical cables can be learned using long-term and short-term memory networks, which can more accurately predict fault conditions under specific environmental conditions; the generated fault risk assessment report and potential fault prediction report provide scientific decision-making support for port managers, help them formulate targeted preventive measures, and improve the efficiency of operation and maintenance management; by predicting and preventing faults in advance, timely maintenance of communication optical cables is ensured, the reliability and stability of the port communication system are improved, and the normal operation of the port is guaranteed; through intelligent fault prediction and optimized inspection path planning, the workload and frequency of manual inspections are reduced, and the operation and maintenance costs are reduced; detailed data support and scientific decision-making basis are provided for port managers, helping them make more reasonable and efficient operation and maintenance decisions, and improving management level and operation efficiency. Through data-driven decision-making methods, the scientificity and foresight of management are improved; by predicting potential faults in advance, preventive measures can be taken in time, and emergency response capabilities are improved. Intervention before the fault occurs reduces the impact of sudden faults on port operations and ensures business continuity and stability.

[0020] Based on the structured data set, the data is sorted in time series to ensure the temporal continuity and logic of the data and generate an ordered data sequence; the ordered data sequence is normalized to reduce the impact of data magnitude differences and generate standardized data input; the standardized data input is used to input the time series prediction model for training, learn the relationship between environmental factors and communication optical cable performance, and generate a preliminary training model; the model is evaluated and parameters are optimized through cross-validation to improve the generalization ability and prediction accuracy of the model and generate an optimized training model; the optimized training model is used to test new environmental condition data to verify the model prediction effect and generate the final training model for learning the relationship between environmental factors and communication optical cable performance. By sorting the data in time series, the temporal continuity and logic of the data are ensured, and an ordered data sequence is generated, providing a high-quality data foundation for subsequent model training; the ordered data sequence is normalized to reduce the impact of data magnitude differences and generate standardized data input, making model training more stable and accurate; standardized data input is used to input the time series prediction model for training, and the model is evaluated and parameter optimized by cross-validation, which improves the generalization ability and prediction accuracy of the model and ensures the applicability of the model under different environmental conditions; the optimized training model is used to test new environmental condition data, verify the model prediction effect, and generate the final training model for the relationship between learning environmental factors and communication optical cable performance, ensuring the reliability and stability of the model and improving the accuracy of fault prediction; the generated training model provides scientific decision-making support for port managers, helping them to better understand and predict the performance changes of communication optical cables under different environmental conditions, formulate effective preventive measures, and improve the efficiency and effectiveness of operation and maintenance management; by predicting and preventing faults in advance, timely maintenance of communication optical cables is ensured, the reliability and stability of the port communication system is improved, the normal operation of the port is guaranteed, and the business losses caused by communication interruptions are reduced.

[0021] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A flow chart of a port communication optical cable routing detection method based on digital twins provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the structure of a port communication optical cable routing detection system based on digital twins provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0027] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0029] Figure 1 A flow chart of a port communication optical cable routing detection method based on digital twin is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0030] 101. Build a high-precision digital twin model of the port environment and communication optical cable distribution to synchronize the status information of the port communication optical cable with environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment;

[0031] Create a virtual model that is highly consistent with the actual port environment and communication cable distribution, which can reflect the status information and environmental variables in the real world in real time; collect environmental data such as the port's geographic information, building layout, and climate conditions; obtain technical parameters such as the physical location, connection method, and service life of the communication cable; use 3D modeling software and GIS technology to build a digital twin model; implement data interfaces so that the model can receive real-time data updates from sensors and other monitoring equipment.

[0032] 102. Based on the high-precision digital twin environment, analyze historical environmental data and communication optical cable performance data, use a long short-term memory network to predict performance degradation or failure of the communication optical cable under specific environmental conditions, and generate a potential fault prediction report;

[0033] Based on historical data analysis, predict possible performance degradation or failure in the future to provide a basis for preventive maintenance; integrate historical environmental data and communication optical cable performance data; use time series prediction model training such as long short-term memory networks to learn the relationship between environmental factors and optical cable performance; input expected environmental conditions, predict the performance of optical cables in specific environments, and generate potential fault prediction reports.

[0034] Optionally, in step 102, based on the high-precision digital twin environment, historical environmental data and communication optical cable performance data are analyzed, and a long short-term memory network is used to predict the performance degradation or failure of the communication optical cable under specific environmental conditions, and a potential fault prediction report is generated, which specifically includes the following steps:

[0035] Based on the historical port environment data and communication cable performance data, the data is collected and preprocessed to generate a structured data set;

[0036] Based on the structured data set, the data is organized in chronological order and input into a time series prediction model for training to obtain a training model for learning the relationship between environmental factors and communication optical cable performance;

[0037] Based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under specific environmental conditions is predicted using a long short-term memory network to generate preliminary fault prediction data;

[0038] Based on the preliminary fault prediction data, analyze the fault impact range and generate a fault risk assessment report in combination with the actual layout of the port communication optical cable;

[0039] Based on the fault risk assessment report, targeted preventive measures and suggestions are formulated to support the operation and maintenance management of port communication optical cables and generate potential fault prediction reports.

[0040] Suppose a port needs to predict the performance degradation or failure of its communication optical cables in the next month;

[0041] Obtain environmental data such as temperature, humidity, wind speed, etc. for the past year from the weather station, and obtain performance data such as transmission rate, signal attenuation, bit error rate, etc. in the same time period from the optical cable monitoring system; clean the data, remove outliers and missing values, format the data into a unified structure, and generate a structured data set; arrange the structured data set in chronological order to ensure the temporal continuity and logic of the data; input the organized data into the long short-term memory network model, train the model to learn the relationship between environmental factors and communication optical cable performance, and generate a training model; analyze and process the data under expected environmental conditions: input the expected environmental condition data (such as weather forecast data) for the next month The trained long short-term memory network model predicts the performance of communication optical cables under specific environmental conditions and generates preliminary fault prediction data; the model output results show that on certain dates and times, optical cables in specific areas may experience signal attenuation and increased bit error rates; based on the preliminary fault prediction data, the scope of possible impact of these faults is analyzed, and a fault risk assessment report is generated in combination with the actual layout of the optical cables; based on the fault risk assessment report, specific preventive maintenance measures are formulated, such as increasing the inspection frequency during predicted high-incidence periods of faults, replacing optical cable sections that may have problems in advance, and generating potential fault prediction reports to support the operation and maintenance management of port communication optical cables.

[0042] Through this series of steps, port management departments can take measures in advance to avoid or reduce the failure of communication optical cables and improve the operational efficiency and reliability of the port.

[0043] This application considers that the formula is mainly used to build and train a prediction model based on long short-term memory network to predict the performance degradation or failure of communication optical cables under specific environmental conditions. These formulas and models are designed to solve practical problems in the operation and maintenance of communication optical cables, and accurately predict the performance of optical cables by using historical data and current environmental conditions, thereby improving operation and maintenance efficiency and system reliability.

[0044] Optionally, based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under the specific environmental conditions is predicted by using a long short-term memory network to generate preliminary fault prediction data, including:

[0045] Initialize the weight matrix to ensure that the initial values ​​of the weights are reasonably distributed and accelerate model convergence;

[0046] Define an exponentially decaying learning rate strategy with periodic restarts, dynamically adjust the learning rate, and improve the model training effect;

[0047] Initialize the weight matrix W using the following calculation formula:

[0048]

[0049] Where U[a, b] is a random number uniformly distributed from the interval [a, b]; n in and n out are the number of neurons in the input layer and the output layer respectively; α is a regularization coefficient used to adjust the initial distribution range of the weights, usually taking a small positive value; β is a bias term used to further adjust the initial value of the weights, usually taking a small positive value or zero;

[0050] The exponential decay learning rate strategy with periodic restarts is calculated using the following formula:

[0051] η t =η0·e -λ(t-kT) ·(1+sin(2π(t-kT) / T))

[0052] Among them, η t is the learning rate at time step t; η0 is the initial learning rate; λ is the learning rate decay coefficient, usually a small positive number; t is the current training iteration number; T is the learning rate restart cycle; k is the index of the current cycle, satisfying kT≤t<(k+1)T;

[0053] Based on the initialization weights and the exponential decay learning rate strategy with periodic restarts, the nonlinear expression ability and prediction performance of the model are enhanced. The long short-term memory network is calculated by the following calculation formula:

[0054] i t =g(W ix x t +W ih h t-1 +b i )

[0055] f t =g(W fx x t +W fh h t-1 +b f )

[0056] o t =g(W ox x t +W oh h t-1 +b o )

[0057]

[0058] ht =o t tanh(C t )

[0059] Among them, x t is the input data at time step t, including environmental variables and communication cable performance data under specific environmental conditions; h t-1 is the hidden state at time step t-1; i t , f t , o t are the activation values ​​of the input gate, forget gate, and output gate at time step t, respectively; g(x) is the LeakyReLU activation function, g(x) = max(0.01x, x); W ix , W ih , W fx , W fh , W ox , W oh , W cx , W ch is the weight matrix used to calculate the linear combination of input gate, forget gate, output gate and cell state; b i , b f , b o , b c is a bias term that adjusts the result of the linear combination; tanh is a hyperbolic tangent activation function that converts the input into a value between -1 and 1 for updating the cell state; represents the new cell state candidate value at time step t; C t is the cell state at time step t; h t is the hidden state at time step t;

[0060] Based on the hidden state h t ,The performance degradation is predicted through the output layer, the fault conditions of the communication optical cable under specific environmental conditions are evaluated, and preliminary fault prediction data are generated.

[0061] Assume that a port needs to predict the performance degradation or failure of its communication optical cable in the next month; the number of neurons in the input layer is n in =10 (assuming the input data includes 10 features such as temperature, humidity, wind speed, etc.); the number of neurons in the output layer n out =1; regularization coefficient α = 0.01; bias term β = 0.01

[0062] The weight matrix is ​​calculated as

[0063]

[0064] W=U[-0.721,0.721]+0.01

[0065] The exponential decay learning rate strategy with periodic restart is defined as follows: initial learning rate η0 = 0.01, learning rate decay coefficient λ = 0.001, learning rate restart period T = 1000, current training iteration number t = 500, current period index k = 0; the learning rate is calculated as

[0066]

[0067] η t =0.01·e -0.5 ·(1+sin(2π·0.5))

[0068] η t =0.01·0.6065·(1+0)

[0069] η t =0.006065

[0070] Input x t =[15.2,78,3.5,0.05,0.001,0.1,0.02,0.03,0.04,0.06];h t -1=[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]; W ix , W ih , W fx , W fh , W ox , W oh , W cx , W ch is the weight matrix after initialization; b i , b f , b o , b c is the bias term

[0071] The activation value of each gate is calculated as

[0072] i t =g(W ix x t +W ih h t-1 +b i )

[0073] f t =g(W fx x t +W fh h t-1 +b f )

[0074] o t =g(W ox x t +Woh h t-1 +b o )

[0075]

[0076] h t =o t tanh(C t )

[0077] x t is the input data at time step t, including environmental variables and communication cable performance data under specific environmental conditions; h t-1 is the hidden state at time step t-1; i t , f t , o t are the activation values ​​of the input gate, forget gate, and output gate at time step t, respectively; g(x) is the LeakyReLU activation function, g(x) = max(0.01x, x); W ix , W ih , W fx , W fh , W ox , W oh , W cx , W ch is the weight matrix used to calculate the linear combination of input gate, forget gate, output gate and cell state; b i , b f , b o , b c is a bias term that adjusts the result of the linear combination; tanh is a hyperbolic tangent activation function that converts the input into a value between -1 and 1 for updating the cell state; represents the new cell state candidate value at time step t; C t is the cell state at time step t; h t is the hidden state at time step t; the hidden state h is transformed into t Mapped to specific performance indicators (such as signal attenuation and bit error rate); based on the prediction results of the output layer, evaluate the fault conditions of the communication optical cable under specific environmental conditions and generate preliminary fault prediction data.

[0078] Through this series of steps, port management departments can accurately predict the performance degradation or failure of communication optical cables under specific environmental conditions, take measures in advance to avoid or reduce the failure of communication optical cables, and improve the operational efficiency and reliability of the port.

[0079] Optionally, based on the structured data set, the data is organized in chronological order, input into a time series prediction model for training, and a training model for learning the relationship between environmental factors and communication optical cable performance is obtained, specifically comprising the following steps:

[0080] Based on the structured data set, the data is sorted in time series to ensure the time continuity and logic of the data and obtain an ordered data sequence;

[0081] Based on the ordered data sequence, normalizing the data to reduce the impact of data magnitude differences and generate standardized data input;

[0082] Using the standardized data input, inputting the time series prediction model for training to learn the relationship between environmental factors and communication optical cable performance, and generating a preliminary training model;

[0083] According to the preliminary training model, the model is evaluated and parameters are optimized by cross-validation to improve the generalization ability and prediction accuracy of the model, and an optimized training model is generated;

[0084] The optimized training model is used to test new environmental condition data, verify the model prediction effect, and generate a training model for learning the relationship between environmental factors and communication optical cable performance.

[0085] Suppose a large seaport uses advanced digital twin technology and machine learning algorithms to predict and prevent potential failures of communication cables in order to improve the stability and reliability of its communication network;

[0086] Environmental data and communication optical cable performance data (including signal attenuation, transmission rate, bit error rate, etc.) from the past ten years were collected. After data cleaning, denoising and format conversion, a structured data set was generated. During the data cleaning process, records with too many missing values ​​were deleted and outliers were smoothed. Data format conversion ensured that all data could be input into subsequent analysis models in a unified format. The structured data set was sorted in chronological order to ensure the temporal continuity and logic of the data. Subsequently, data of different magnitudes were converted into a unified standard range to reduce the impact of data magnitude differences on model training. Using standardized data input, a long short-term memory network was selected to handle long-term dependency problems in sequence data for predicting performance changes of communication optical cables. During the training process, the parameters of the model, such as the learning rate and the number of hidden layers, were continuously adjusted to learn the relationship between environmental factors and the performance of communication optical cables. After the initial training was completed, the model was evaluated using the K-fold cross-validation method. The parameters of the model were optimized through multiple iterations to improve the generalization ability and prediction accuracy of the model.

[0087] Through the above steps, the port can enhance the stability and reliability of its communication network, accurately predict and effectively prevent potential failures that communication optical cables may encounter.

[0088] Optionally, based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under specific environmental conditions is predicted by using a long short-term memory network to generate preliminary fault prediction data, which specifically includes the following steps:

[0089] Based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed to ensure that the time series characteristics of the input data are consistent with the training data, and the formatted input data is generated;

[0090] Based on the formatted input data, using the training model for learning the relationship between environmental factors and communication optical cable performance, predicting the performance change trend of the communication optical cable under specific environmental conditions to generate a preliminary prediction result;

[0091] Based on the preliminary prediction results, evaluating the performance degradation or failure of the communication optical cable under specific environmental conditions to generate preliminary fault assessment data;

[0092] Based on the preliminary fault assessment data, combined with the actual layout of the port communication optical cable and historical fault data, the fault impact range is analyzed to generate an impact range analysis report;

[0093] Based on the impact range analysis report, the preliminary fault assessment data is corrected and optimized to ensure the accuracy and practicality of the prediction, and preliminary fault prediction data is generated.

[0094] Suppose a port wants to use a long short-term memory network to predict the performance degradation of its communication cables under specific weather conditions;

[0095] Environmental data and communication cable performance data from the past five years were collected from the port's historical database. The data were cleaned, denoised, and normalized to generate a structured data set. The structured data set was organized in chronological order and input into the long short-term memory network for training. During the training process, the model learns the relationship between environmental factors and the performance of communication optical cables; assuming that the current prediction is the performance of communication optical cables within the next week, the expected environmental condition data within this week is formatted to ensure that it is consistent with the time series characteristics of the training data; the trained model is used to predict the formatted input data to obtain the performance change trend of the communication optical cable within the next week; based on the prediction results, the performance degradation of the communication optical cable under specific environmental conditions is evaluated, and preliminary fault assessment data is generated; combined with the actual layout of the port communication optical cable and historical fault data, the scope of possible impact of the fault is analyzed, and an impact range analysis report is generated; based on the impact range analysis report, the preliminary fault assessment data is corrected and optimized to ensure the accuracy and practicality of the prediction; based on the preliminary fault prediction data, a fault risk assessment report is generated to evaluate the risk of communication optical cable failure within the next week; based on the fault risk assessment report, targeted preventive measures and suggestions are formulated, such as strengthening optical cable maintenance, adjusting optical cable layout, etc., to support the operation and maintenance management of port communication optical cables.

[0096] The port can not only accurately predict the performance degradation or failure of communication optical cables under specific environmental conditions in the future, but also conduct effective risk management and formulate response measures based on this.

[0097] 103. Based on the potential fault prediction report, an ant colony algorithm is used to automatically search for the optimal inspection path in the high-precision digital twin environment, monitor and record key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list;

[0098] Use algorithms to automatically plan the most effective inspection routes to ensure the efficiency and comprehensiveness of the inspection work; determine the areas and optical cable sections that need to be inspected based on potential fault prediction reports; use optimization algorithms such as ant colony algorithms to find the inspection paths with the lowest cost, shortest time and covering all key points in the digital twin environment; record the key performance indicators of the optical cable during the inspection process, such as signal strength, temperature changes, etc., and form an inspection report.

[0099] Optionally, based on the potential fault prediction report, the ant colony algorithm is applied in the high-precision digital twin environment to automatically search for the optimal inspection path, monitor and record the key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list, which specifically includes the following steps:

[0100] Based on the potential fault prediction report, the potential fault points and priorities of the communication optical cable are analyzed and processed to generate a fault point list;

[0101] Based on the fault point list, an ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length, and generate a preliminary inspection path plan;

[0102] Based on the preliminary inspection path plan, the inspection process is simulated in the high-precision digital twin environment, key performance indicators of the communication optical cable are monitored and recorded, and inspection data records are generated;

[0103] Based on the inspection data records, combined with actual inspection requirements and resource constraints, the preliminary inspection path plan is optimized, the inspection sequence and time schedule are adjusted, the inspection efficiency and quality are ensured, and an optimized inspection path is generated;

[0104] Based on the optimized inspection path, a detailed inspection task list is compiled to guide the actual inspection work and generate an optimized inspection path and inspection task list.

[0105] Assume that a port needs to automatically search for the optimal inspection path in a high-precision digital twin environment based on a potential fault prediction report using an ant colony algorithm; identify potential fault points and their priorities for the communication optical cable in the next month based on the potential fault prediction report. For example, fault points A, B, and C are located at Pier 1, Pier 3, and Pier 5, respectively, with high, medium, and low priorities; organize these fault points and their priorities into a list as the basis for subsequent inspection path optimization; based on the fault point list, apply the ant colony algorithm in a high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time, and path length. The ant colony algorithm simulates the foraging behavior of ants to find the optimal path from the starting point to all fault points and then back to the starting point; the algorithm outputs a preliminary inspection path plan, for example: starting point->Pier 1->Pier 3->Pier 5->Starting point; based on the preliminary inspection path plan, simulate the inspection process in a high-precision digital twin environment. During the simulation, record the key performance indicators of the communication optical cable, such as signal strength, temperature change, etc.; organize the data recorded during the simulation into inspection data records for subsequent path optimization; optimize the preliminary inspection path plan based on the inspection data records, combined with actual inspection needs and resource constraints. For example, adjust the inspection order to ensure that high-priority fault points are inspected first, while minimizing inspection time and cost; the optimized inspection path may be: starting point->Pier 1->Pier 5->Pier 3->Starting point; Based on the optimized inspection path, prepare a detailed inspection task list. The task list should include information such as the specific location of each fault point, inspection time, required tools and personnel configuration to guide the actual inspection work; organize the optimized inspection path and task list into a report and submit it to port management personnel to ensure the efficiency and comprehensiveness of the inspection work.

[0106] Through the above steps, the port management department can use potential fault prediction reports and advanced optimization algorithms to automatically generate the optimal inspection path and task list to ensure the efficiency and comprehensiveness of the inspection work and improve the maintenance level of port communication optical cables.

[0107] This application considers that the formula is used to construct a multi-objective optimization model for the inspection path, integrating multiple optimization objectives through a comprehensive objective function, including minimizing the path length, minimizing the inspection cost, maximizing the inspection efficiency, maximizing the safety, and optimizing the dynamic factors. Each objective function has its own specific expression, which is combined into a comprehensive objective function through a weighted sum;

[0108] Optionally, an ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length to generate a preliminary inspection path plan, including:

[0109] Update pheromones to provide the latest reference values ​​for path selection and accelerate the optimal path discovery;

[0110] Set the transition probability formula to dynamically guide movement decisions to improve the efficiency and accuracy of path search;

[0111] Update pheromones using the following calculation formula:

[0112] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t)

[0113] Among them, τ ij (t) represents the pheromone concentration on the path (i, j) at time step t; ρ is the pheromone evaporation rate, which is usually a positive number less than 1; Δτ ij (t) represents the concentration of the newly added pheromone on the path (i, j) at time step t, m is the number of ants, represents the contribution of the kth ant to the path (i, j) at time step t; Q is a constant representing the total amount of pheromone; L k is the total length of the path taken by the kth ant:

[0114] The transition probability is calculated using the following formula:

[0115]

[0116] in, represents the probability that the kth ant moves from node i to node j at time step t; α is the pheromone importance factor; β is the heuristic information importance factor; ηij Represents heuristic information, usually the reciprocal distance of path (i, j), η ij =1 / d ij , d ij is the distance between node i and node j; N k (i) represents the set of next nodes that the kth ant can choose when it is at node i;

[0117] Based on the update pheromone and transition probability, the multi-factor comprehensive nonlinear relationship is introduced, and the comprehensive path evaluation is calculated through the following calculation formula:

[0118]

[0119] in, is the comprehensive evaluation score of the kth ant moving from node i to node j at time step t; ω1, ω2, ω3, ω4, ω5 are the weight factors of reliability, efficiency, safety, cost and dynamic factors respectively; ij (t) is the reliability of path (i, j) at time step t, failure_rate ij (t) is the failure rate of path (i, j) at time step t, λ is a tuning parameter; Efficiency ij (t) is the efficiency of path (i, j) at time step t, d ij is the distance between node i and node j, μ is a small positive number to prevent division by zero error; Safety ij (t) is the safety of path (i, j) at time step t, risk ij (t) is the risk value of path (i, j) at time step t, σ is a standard deviation parameter used to control the weight attenuation of risk; Cost ij (t) represents the cost of path (i, j) at time step t, cost ij (t) is the actual cost of path (i, j) at time step t, ∈ is a small positive number to prevent division by zero error; Dynamic_Factor ij (t) represents the dynamic factor of path (i, j) at time step t, dynamic_impact ij (t) is the dynamic influencing factor of path (i, j) at time step t, and τ is an adjustment parameter used to control the weight of the dynamic factor;

[0120] Dynamically adjust the pheromone concentration on the path, repeatedly calculate the transfer probability, and select the optimal path in the high-precision digital twin environment;

[0121] Through multiple rounds of iterations, a preliminary inspection path plan is generated.

[0122] Assuming that a port has five docks (nodes), numbered 1 to 5, the ant colony algorithm is used to generate a preliminary inspection path plan in a high-precision digital twin environment;

[0123] The initialization parameters are: number of ants m = 5; pheromone evaporation rate ρ = 0.5; total pheromone amount Q = 100; pheromone importance factor α = 1.0; heuristic information importance factor β = 1.0; initial pheromone concentration τ ij (0) = 1 (all paths); the distances between nodes are: the distance from node 1 to node 2 is 2 km, the distance from node 1 to node 3 is 3 km, the distance from node 1 to node 4 is 4 km, the distance from node 1 to node 5 is 5 km, the distance from node 2 to node 3 is 2 km, the distance from node 2 to node 4 is 3 km, the distance from node 2 to node 5 is 4 km, the distance from node 3 to node 4 is 2 km, the distance from node 3 to node 5 is 3 km, and the distance from node 4 to node 5 is 2 km; suppose that 5 ants choose The following paths are obtained: Ant 1 is 1->2->3->4->5->1, with a total path length of L1 = 13; Ant 2 is 1->3->2->4->5->1, with a total path length of L2 = 14; Ant 3 is 1->4->2->3->5->1, with a total path length of L3 = 15; Ant 4 is 1->5->2->3->4->1, with a total path length of L4 = 16; Ant 5 is 1->2->4->3->5->1, with a total path length of L5 = 14; the concentration of newly added pheromones on each path is calculated as follows: Where Q = 100; for each path, the concentration of the newly added pheromone is Update pheromone concentration to τ ij (1) = (1-ρ)·τ ij (0)+Δτ ij (0), where ρ = 0.5. For each path, the pheromone concentration is τ 12 (1)=(1-0.5)·1+(7.69+7.14)=0.5+14.83=15.33,τ 23 (1)=(1-0.5)·1+(7.69+6.67+6.25+7.14)=0.5+27.75=28.25,τ 34 (1)=(1-0.5)·1+(7.69+6.25+7.14)=0.5+21.08=21.58,τ45 (1)=(1-0.5)·1+(7.69+7.14+7.14)=0.5+21.97=22.47,τ 51 (1)=(1-0.5)·1+(7.69+7.14+6.67+7.14+7.14)=0.5+35.78=36.28, τ 13 (1)=(1-0.5)·1+7.14=0.5+7.14=7.64,τ 32 (1)=(1-0.5)·1+7.14=0.5+7.14=7.64,τ 24 (1)=(1-0.5)·1+(7.14+7.14+7.14)=0.5+21.42=21.92,τ 42 (1)=(1-0.5)·1+6.67=0.5+6.67=7.17,τ 35 (1)=(1-0.5)·1+(6.67+7.14+7.14)=0.5+20.95=21.45,τ 52 (1)=(1-0.5)·1+6.25=0.5+6.25=6.75,τ 41 (1)=(1-0.5)·1+6.25=0.5+6.25=6.75,τ 14 (1)=(1-0.5)·1+6.67=0.5+6.67=7.17,τ 43 (1)=(1-0.5)·1+7.14=0.5+7.14=7.64,τ 15 (1)=(1-0.5)·1+6.25=0.5+6.25=6.75,τ 53 (1) = (1-0.5) · 1 + 7.14 = 0.5 + 7.14 = 7.64; Assume that in the second iteration, the next node set that the first ant can choose when it is at node 1 is {2, 3, 4, 5}; Heuristic information therefore Assume that the first ant chooses path 1-2, calculate the comprehensive evaluation score of path 1-2: The comprehensive evaluation score is

[0124] Through the above steps, the ant colony algorithm generates a preliminary inspection path plan in a high-precision digital twin environment. Through multiple iterations, the pheromone concentration will be gradually updated, the transfer probability will be dynamically adjusted, and finally the optimal inspection path will be selected.

[0125] Optionally, based on the fault point list, an ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length to generate a preliminary inspection path plan, specifically including the following steps:

[0126] Based on the fault point list, the location information and priority of each fault point are analyzed and processed to generate detailed information of the fault point;

[0127] Based on the detailed information of the fault point, combined with the inspection cost, time and path length, the parameters of the ant colony algorithm are set and processed to generate algorithm parameters suitable for port optical cable inspection;

[0128] By using the algorithm parameters adapted to the inspection of the port optical cable, in the high-precision digital twin environment, an ant colony algorithm is applied to search and process possible paths from the starting point to each fault point, simulating the pheromone release and perception behavior of ants, and generating multiple candidate inspection paths;

[0129] Based on the multiple candidate inspection paths, the pheromone concentration on the path is updated to converge to a better solution and generate an optimized candidate inspection path;

[0130] Based on the optimized candidate inspection paths, the best path is selected and a preliminary inspection path plan is generated by combining inspection efficiency, cost and path safety.

[0131] Suppose a port needs to conduct regular inspections on communication optical cables to ensure their normal operation. The following are the steps to implement the solution; based on historical data and prediction models, generate a prediction report containing potential fault points and their priorities of the communication optical cables; extract the location information and priority of each fault point from the prediction report, and generate a detailed list of fault points; set the parameters of the ant colony algorithm according to the detailed information of the fault point, inspection cost, time, and path length. For example, set the pheromone volatility coefficient to 0.5, the pheromone intensity to 10, the number of ants to 50, etc.; in a high-precision digital twin environment, apply the ant colony algorithm to search for possible paths from the starting point to each fault point. Simulate the pheromone release and perception behavior of ants to generate multiple candidate inspection paths; update the pheromone concentration on the path according to the quality of the candidate inspection path (such as path length, inspection time, etc.). Make the better path have a higher pheromone concentration, so as to guide the ants to converge to a better solution; based on the optimized candidate inspection path, combined with factors such as inspection efficiency, cost and path security, select an optimal path as the preliminary inspection path plan; simulate the inspection process in the digital twin environment, conduct inspections according to the preliminary plan, and monitor and record the key performance indicators of the communication optical cable (such as transmission rate, bit error rate, etc.); optimize the preliminary inspection path plan according to actual inspection needs and resource constraints (such as the number of inspection personnel, inspection time window, etc.). Adjust the inspection sequence and time schedule to ensure inspection efficiency and quality; compile a detailed inspection task list based on the optimized inspection path plan. The list includes information such as the division of labor of inspection personnel, inspection time, inspection location, and key performance indicators that need to be monitored.

[0132] Through the above steps, the port can realize automatic planning and optimization of the inspection path of communication optical cables, improve inspection efficiency and quality, and reduce inspection costs.

[0133] 104. Based on the optimized inspection path and inspection task list, guide the actual inspection work, compare the actual inspection results with the predicted data in the high-precision digital twin model, evaluate and optimize the prediction accuracy, so as to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

[0134] By comparing the actual inspection results with the prediction model, the accuracy of the prediction model is continuously optimized and the operation and maintenance efficiency is improved; the data collected in the actual inspection is compared with the predicted data in the digital twin model; the differences between the two are analyzed to identify the deviations in the model prediction; the model parameters are adjusted according to the analysis results and the prediction algorithm is optimized; the digital twin model is updated regularly to ensure that it can better reflect the actual situation and improve the accuracy of fault prediction and the reliability of the system.

[0135] Optionally, in step 104, based on the optimized inspection path and inspection task list, actual inspection work is guided, actual inspection results are compared with the predicted data in the high-precision digital twin model, and the prediction accuracy is evaluated and optimized to improve the operation and maintenance efficiency and system reliability of the port communication optical cable, which specifically includes the following steps:

[0136] Based on the optimized inspection route and inspection task list, plan and guide the actual inspection work, execute the inspection tasks, and generate actual inspection records;

[0137] Based on the actual inspection records, the performance changes and fault conditions of the communication optical cables during the inspection process are collected, and the inspection results are sorted, analyzed and processed to generate actual inspection results;

[0138] Based on the actual inspection results, the predicted data in the high-precision digital twin model are compared to evaluate the accuracy of the predicted data, identify prediction deviations, and generate a prediction accuracy evaluation report;

[0139] Based on the forecast accuracy assessment report, analyze the major forecast deviations, identify the causes of the deviations, propose improvement measures, and generate a forecast model optimization plan;

[0140] Based on the prediction model optimization scheme, the high-precision digital twin model is updated and optimized, the prediction accuracy of the model is improved, and an optimized digital twin model is generated to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

[0141] Assume that a port management department needs to guide the actual inspection work according to the optimized inspection path and inspection task list, and evaluate and optimize the prediction accuracy by comparing the actual inspection results with the predicted data in the high-precision digital twin model; plan and execute the actual inspection tasks based on the optimized inspection path and inspection task list. For example, the inspection personnel check the communication optical cables of Pier 1 and Pier 3 in turn according to the predetermined path and task list, record the inspection time, location, detection indicators, etc., and generate actual inspection records; collect the performance changes and fault conditions of the communication optical cables during the inspection, organize and analyze the inspection results, and generate actual inspection results. For example, record the performance indicators such as signal strength and temperature changes of the optical cable at Pier 1, as well as whether there is a fault; compare the actual inspection results with the predicted data in the high-precision digital twin model, evaluate the accuracy of the predicted data, and generate a prediction accuracy evaluation report. For example, compare the actual signal strength of the optical cable at Pier 1 with the predicted signal strength to evaluate the accuracy of the prediction; based on the prediction accuracy evaluation report, analyze the large part of the prediction deviation, identify the cause of the deviation, propose improvement measures, and generate a prediction model optimization plan. For example, if the signal strength prediction error of the optical cable at Pier 1 is found to be large, analysis may be due to the model not fully considering the impact of environmental factors, and improvement measures such as increasing the weight of environmental factors are proposed; according to the prediction model optimization plan, the high-precision digital twin model is updated and optimized to improve the prediction accuracy of the model and generate an optimized digital twin model. For example, the model parameters are adjusted, the weight of the impact of environmental factors is increased, and the model is retrained to improve the accuracy of the prediction.

[0142] Through the above steps, port management departments can continuously optimize the accuracy of the prediction model, improve the efficiency of inspection work and the operation and maintenance level of communication optical cables, and ensure the reliability and stability of the port communication system.

[0143] Figure 2 A structural diagram of a port communication optical cable routing detection system based on digital twin is provided for the embodiment of the present application, such as Figure 2 As shown, the device comprises:

[0144] Building module 21, building a high-precision digital twin model of the port environment and communication optical cable distribution, so as to synchronize the status information of the port communication optical cable with the environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment;

[0145] The analysis module 22 analyzes historical environmental data and communication optical cable performance data based on the high-precision digital twin environment, uses a long short-term memory network to predict performance degradation or failure of the communication optical cable under specific environmental conditions, and generates a potential fault prediction report;

[0146] The monitoring module 23, based on the potential fault prediction report, applies an ant colony algorithm to automatically search for an optimal inspection path in the high-precision digital twin environment, monitors and records key performance indicators of the communication optical cable, and generates an optimized inspection path and inspection task list;

[0147] The optimization module 24 guides the actual inspection work based on the optimized inspection path and inspection task list, compares the actual inspection results with the predicted data in the high-precision digital twin model, evaluates and optimizes the prediction accuracy, so as to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

[0148] Figure 2 The port communication optical cable routing detection system based on digital twin can perform Figure 1 The implementation principle and technical effect of the port communication optical cable routing detection method based on digital twin described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the port communication optical cable routing detection system based on digital twin in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0149] In one possible design, Figure 2 The port communication optical cable routing detection system based on digital twin of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0150] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0151] The processing component 32 is used to: construct a high-precision digital twin model of the port environment and the distribution of communication optical cables to synchronize the status information of the port communication optical cables with environmental variables in real time, ensure the consistency of the model with the actual environment, and generate a high-precision digital twin environment; based on the high-precision digital twin environment, analyze historical environmental data and communication optical cable performance data, use long and short-term memory networks to predict the performance degradation or failure of communication optical cables under specific environmental conditions, and generate a potential fault prediction report; based on the potential fault prediction report, use an ant colony algorithm to automatically search for the optimal inspection path in the high-precision digital twin environment, monitor and record the key performance indicators of the communication optical cables, and generate an optimized inspection path and inspection task list; based on the optimized inspection path and inspection task list, guide the actual inspection work, compare the actual inspection results with the predicted data in the high-precision digital twin model, evaluate and optimize the prediction accuracy, so as to improve the operation and maintenance efficiency and system reliability of the port communication optical cables.

[0152] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0153] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0154] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0155] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0156] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0157] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0158] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a port communication optical cable routing detection method based on digital twin.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0161] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A port communication optical cable routing detection method based on digital twins, characterized in that: include: Build a high-precision digital twin model of the port environment and communication cable distribution to synchronize the status information of the port communication cable with environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment; Based on the high-precision digital twin environment, historical environmental data and communication optical cable performance data are analyzed, and a long short-term memory network is used to predict the performance degradation or failure of the communication optical cable under specific environmental conditions, and a potential fault prediction report is generated; Based on the potential fault prediction report, an ant colony algorithm is used to automatically search for an optimal inspection path in the high-precision digital twin environment, monitor and record key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list; Based on the optimized inspection path and inspection task list, the actual inspection work is guided, the actual inspection results are compared with the predicted data in the high-precision digital twin model, and the prediction accuracy is evaluated and optimized to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

2. The port communication optical cable routing detection method based on digital twin according to claim 1 is characterized in that: Based on the high-precision digital twin environment, historical environmental data and communication optical cable performance data are analyzed, and a long short-term memory network is used to predict the performance degradation or failure of the communication optical cable under specific environmental conditions, and a potential fault prediction report is generated, which specifically includes the following steps: Based on the historical port environment data and communication cable performance data, the data is collected and preprocessed to generate a structured data set; Based on the structured data set, the data is organized in chronological order and input into a time series prediction model for training to obtain a training model for learning the relationship between environmental factors and communication optical cable performance; Based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under specific environmental conditions is predicted using a long short-term memory network to generate preliminary fault prediction data; Based on the preliminary fault prediction data, analyze the fault impact range and generate a fault risk assessment report in combination with the actual layout of the port communication optical cable; Based on the fault risk assessment report, formulate targeted preventive measures and suggestions to support the operation and maintenance management of port communication optical cables and generate potential fault prediction reports; Among them, based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under specific environmental conditions is predicted by using a long short-term memory network to generate preliminary fault prediction data, including: Initialize the weight matrix to ensure that the initial values ​​of the weights are reasonably distributed and accelerate model convergence; Define an exponentially decaying learning rate strategy with periodic restarts, dynamically adjust the learning rate, and improve the model training effect; Initialize the weight matrix W using the following calculation formula: Among them, U[a,b] is a random number uniformly distributed from the interval [a,b]; n in and n out are the number of neurons in the input layer and the output layer respectively; α is a regularization coefficient used to adjust the initial distribution range of the weights, usually taking a small positive value; β is a bias term used to further adjust the initial value of the weights, usually taking a small positive value or zero; The exponential decay learning rate strategy with periodic restarts is calculated using the following formula: or t =η0·e -λ(t-kT) ·(1+sin(2π(t-kT) / T)) Among them, η t is the learning rate at time step t; η0 is the initial learning rate; λ is the learning rate decay coefficient, which is usually a small positive number; t is the current number of training iterations; T is the period of learning rate restart; k is the index of the current period, satisfying kT≤t<(k+1)T; Based on the initialization weights and the exponential decay learning rate strategy with periodic restarts, the nonlinear expression ability and prediction performance of the model are enhanced. The long short-term memory network is calculated by the following calculation formula: i t =g(W ix x t +W ih h t-1 +b i ) f t =g(W fx x t +W fh h t-1 +b f ) o t =g(W ox x t +W oh h t-1 +b o ) h t =o t fishy(C) t ) Among them, x t is the input data at time step t, including environmental variables and communication cable performance data under specific environmental conditions; h t-1 is the hidden state at time step t-1; i t ,f t ,o t are the activation values ​​of the input gate, forget gate, and output gate at time step t, respectively; g(x) is the LeakyReLU activation function, g(x) = max(0.01x, x); W ix ,W ih ,W fx ,W fh ,W ox ,W oh ,W cx ,W ch is the weight matrix used to calculate the linear combination of input gate, forget gate, output gate and cell state; b i ,b f ,b o ,b c is a bias term that adjusts the result of the linear combination; tanh is a hyperbolic tangent activation function that converts the input into a value between -1 and 1 for updating the cell state; represents the new cell state candidate value at time step t; C t is the cell state at time step t; h t is the hidden state at time step t; Based on the hidden state h t ,The performance degradation is predicted through the output layer, the fault conditions of the communication optical cable under specific environmental conditions are evaluated, and preliminary fault prediction data are generated.

3. The port communication optical cable routing detection method based on digital twin according to claim 2 is characterized in that: Based on the structured data set, the data is organized in chronological order, input into the time series prediction model for training, and a training model for learning the relationship between environmental factors and communication optical cable performance is obtained, which specifically includes the following steps: Based on the structured data set, the data is sorted in time series to ensure the time continuity and logic of the data and obtain an ordered data sequence; Based on the ordered data sequence, normalizing the data to reduce the impact of data magnitude differences and generate standardized data input; Using the standardized data input, inputting the time series prediction model for training to learn the relationship between environmental factors and communication optical cable performance, and generating a preliminary training model; According to the preliminary training model, the model is evaluated and parameters are optimized by cross-validation to improve the generalization ability and prediction accuracy of the model, and an optimized training model is generated; The optimized training model is used to test new environmental condition data, verify the model prediction effect, and generate a training model for learning the relationship between environmental factors and communication optical cable performance.

4. The port communication optical cable routing detection method based on digital twin according to claim 2 is characterized in that: Based on the training model of the relationship between the learning environment factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed, and the performance degradation or failure of the communication optical cable under specific environmental conditions is predicted by using a long short-term memory network to generate preliminary fault prediction data, which specifically includes the following steps: Based on the training model of the relationship between the learning environmental factors and the performance of the communication optical cable, the data under the expected environmental conditions are analyzed and processed to ensure that the time series characteristics of the input data are consistent with the training data, and the formatted input data is generated; Based on the formatted input data, using the training model for learning the relationship between environmental factors and communication optical cable performance, predicting the performance change trend of the communication optical cable under specific environmental conditions to generate a preliminary prediction result; Based on the preliminary prediction results, evaluating the performance degradation or failure of the communication optical cable under specific environmental conditions to generate preliminary fault assessment data; Based on the preliminary fault assessment data, combined with the actual layout of the port communication optical cable and historical fault data, the fault impact range is analyzed to generate an impact range analysis report; Based on the impact range analysis report, the preliminary fault assessment data is corrected and optimized to ensure the accuracy and practicality of the prediction, and preliminary fault prediction data is generated.

5. The port communication optical cable routing detection method based on digital twin according to claim 1 is characterized in that: Based on the potential fault prediction report, the ant colony algorithm is used to automatically search for the optimal inspection path in the high-precision digital twin environment, monitor and record the key performance indicators of the communication optical cable, and generate an optimized inspection path and inspection task list, which specifically includes the following steps: Based on the potential fault prediction report, the potential fault points and priorities of the communication optical cable are analyzed and processed to generate a fault point list; Based on the fault point list, an ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length, and generate a preliminary inspection path plan; Based on the preliminary inspection path plan, the inspection process is simulated in the high-precision digital twin environment, key performance indicators of the communication optical cable are monitored and recorded, and inspection data records are generated; Based on the inspection data records, combined with actual inspection requirements and resource constraints, the preliminary inspection path plan is optimized, the inspection sequence and time schedule are adjusted, the inspection efficiency and quality are ensured, and an optimized inspection path is generated; Based on the optimized inspection path, a detailed inspection task list is compiled to guide the actual inspection work and generate an optimized inspection path and inspection task list; Among them, the ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length, and generate a preliminary inspection path plan, including: Update pheromones to provide the latest reference values ​​for path selection and accelerate the optimal path discovery; Set the transition probability formula to dynamically guide movement decisions to improve the efficiency and accuracy of path search; Update pheromones using the following calculation formula: t ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij (t) Among them, τ ij (t) represents the pheromone concentration on the path (i, j) at time step t; ρ is the pheromone evaporation rate, which is usually a positive number less than 1; Δτ ij (t) represents the concentration of pheromone added on path (i, j) at time step t, m is the number of ants, represents the contribution of the kth ant to the path (i, j) at time step t; Q is a constant representing the total amount of pheromone; l k is the total length of the path taken by the kth ant; The transition probability is calculated using the following formula: in, represents the probability that the kth ant moves from node i to node j at time step t; α is the pheromone importance factor; β is the heuristic information importance factor; η ij Represents heuristic information, usually the reciprocal distance of path (i, j), η ij =1 / d ij , d ij is the distance between node i and node j; N k (i) represents the set of next nodes that the kth ant can choose when it is at node i; Based on the update pheromone and transition probability, the multi-factor comprehensive nonlinear relationship is introduced, and the comprehensive path evaluation is calculated through the following calculation formula: in, is the comprehensive evaluation score of the kth ant moving from node i to node j at time step t; ω1, ω2, ω3, ω4, ω5 are the weight factors of reliability, efficiency, safety, cost and dynamic factors respectively; ij (t) is the reliability of path (i, j) at time step t, failure_rate ij (t) is the failure rate of path (i, j) at time step t, λ is a tuning parameter; Efficiency ij (t) is the efficiency of path (i, j) at time step t, d ij is the distance between node i and node j, μ is a small positive number to prevent division by zero error; Safety ij (t) is the safety of path (i,j) at time step t, risk ij (t) is the risk value of path (i, j) at time step t, σ is a standard deviation parameter used to control the weight attenuation of risk; Cost ij (t) represents the cost of path (i, j) at time step t, cost ij (t) is the actual cost of path (i, j) at time step t, ∈ is a small positive number to prevent division by zero error; Dynamic_Factor ij (t) represents the dynamic factors of path (i, j) at time step t, dynamic_impact ij (t) is the dynamic influencing factor of path (i, j) at time step t, and τ is an adjustment parameter used to control the weight of the dynamic factor; Dynamically adjust the pheromone concentration on the path, repeatedly calculate the transfer probability, and select the optimal path in the high-precision digital twin environment; Through multiple rounds of iterations, a preliminary inspection path plan is generated.

6. The port communication optical cable routing detection method based on digital twin according to claim 5 is characterized in that: Based on the fault point list, the ant colony algorithm is applied in the high-precision digital twin environment to search and process the inspection path in combination with the inspection cost, time and path length, and generate a preliminary inspection path plan, which specifically includes the following steps: Based on the fault point list, the location information and priority of each fault point are analyzed and processed to generate detailed information of the fault point; Based on the detailed information of the fault point, combined with the inspection cost, time and path length, the parameters of the ant colony algorithm are set and processed to generate algorithm parameters suitable for port optical cable inspection; By using the algorithm parameters adapted to the inspection of the port optical cable, in the high-precision digital twin environment, an ant colony algorithm is applied to search and process possible paths from the starting point to each fault point, simulating the pheromone release and perception behavior of ants, and generating multiple candidate inspection paths; Based on the multiple candidate inspection paths, the pheromone concentration on the path is updated to converge to a better solution and generate an optimized candidate inspection path; Based on the optimized candidate inspection paths, the best path is selected and a preliminary inspection path plan is generated by combining inspection efficiency, cost and path safety.

7. The port communication optical cable routing detection method based on digital twin according to claim 1 is characterized in that: Based on the optimized inspection path and inspection task list, actual inspection work is guided, actual inspection results are compared with the predicted data in the high-precision digital twin model, and the prediction accuracy is evaluated and optimized to improve the operation and maintenance efficiency and system reliability of the port communication optical cable, which specifically includes the following steps: Based on the optimized inspection route and inspection task list, plan and guide the actual inspection work, execute the inspection tasks, and generate actual inspection records; Based on the actual inspection records, the performance changes and fault conditions of the communication optical cables during the inspection process are collected, and the inspection results are sorted, analyzed and processed to generate actual inspection results; Based on the actual inspection results, the predicted data in the high-precision digital twin model are compared to evaluate the accuracy of the predicted data, identify prediction deviations, and generate a prediction accuracy evaluation report; Based on the forecast accuracy assessment report, analyze the major forecast deviations, identify the causes of the deviations, propose improvement measures, and generate a forecast model optimization plan; Based on the prediction model optimization scheme, the high-precision digital twin model is updated and optimized, the prediction accuracy of the model is improved, and an optimized digital twin model is generated to improve the operation and maintenance efficiency and system reliability of the port communication optical cable. 8.Port communication optical cable routing detection system based on digital twin, characterized by: include: Building modules to construct a high-precision digital twin model of the port environment and communication cable distribution, so as to synchronize the status information of the port communication cable with environmental variables in real time, ensure the consistency between the model and the actual environment, and generate a high-precision digital twin environment; An analysis module, based on the high-precision digital twin environment, analyzes historical environmental data and communication optical cable performance data, uses a long short-term memory network to predict performance degradation or failure of the communication optical cable under specific environmental conditions, and generates a potential failure prediction report; A monitoring module, based on the potential fault prediction report, applies an ant colony algorithm to automatically search for an optimal inspection path in the high-precision digital twin environment, monitors and records key performance indicators of the communication optical cable, and generates an optimized inspection path and inspection task list; The optimization module guides the actual inspection work based on the optimized inspection path and inspection task list, compares the actual inspection results with the predicted data in the high-precision digital twin model, evaluates and optimizes the prediction accuracy, so as to improve the operation and maintenance efficiency and system reliability of the port communication optical cable.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the port communication optical cable routing detection method based on digital twins as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the port communication optical cable routing detection method based on digital twins as described in any one of claims 1 to 7 is implemented.

Images