Power optical cable laying output optimization method based on BP neural network

Abstract

The invention relates to the technical field of power optical cable output control, in particular to a power optical cable laying output optimization method based on a BP neural network. The method comprises the following steps: collecting data related to overhead, pipeline and in-well scenes of power optical cable laying, considering ADSS multi-model optical cables, and optimizing the power optical cable to be optimized according to an aging output interval, first output average performance, second output average performance and initial performance of the power optical cable to be optimized; calculating and obtaining an aging output attribute parameter set of the offline durability test and the online pipeline durability cycle test; all indexes of the aging output attribute parameter set are correspondingly added and averaged to obtain a final attribute parameter combination, then adding and averaging are carried out to obtain final attribute parameters, and the model, the size, the length and the laying environment of the optical cable are input; the optimal output interval of the optical cable laying machine can be automatically output, optical cables are prevented from being damaged, and laying quality is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power optical cable output control, and in particular to a method for optimizing the laying output of power optical cables based on a BP neural network. Background Art

[0002] At present, the control of optical cable electric fields mainly includes output limit control, smoothing control, climbing rate control and automatic power generation control. The control of optical cable electric fields in my country mainly adopts the output limit mode. The dispatching center issues an upper limit on the output to the optical cable electric field. The optical cable electric field only needs to control the output of the optical cable electric field to operate below the upper limit. This method enables the optical cable electric field to participate in system dispatching to a certain extent. However, it fails to give full play to the control potential of the optical cable electric field, so that the output of the optical cable electric field with good wind speed conditions and control performance is limited, which is not conducive to improving the output characteristics of the optical cable electric field.

[0003] A Chinese patent with announcement number CN115549210A discloses a reliability index value calculation method and device for offshore wind farm grid connection, the method comprising: statistically analyzing the output probability parameters of the wind turbine, the output probability parameters comprising several output probability values ​​of the wind turbine in a fault state and a non-fault state, each output probability value corresponding to a set of output intervals of the wind turbine; based on the output probability parameters, respectively calculating the available output values ​​corresponding to the cable in several different operating states to obtain several available output values; using several available output values ​​to calculate the annual average available output value of the wind turbine, and using the annual average available output value to calculate the reliability index value. The above method measures the output interval through the output probability, and there is a certain error. Therefore, it is urgent for those skilled in the art to solve the above technical problems. Summary of the invention

[0004] The technical problem to be solved by the present invention is that the above-mentioned prior art cannot provide an accurate output range and the optical cable laying efficiency is low.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for optimizing the laying output of power optical cables based on BP neural network, comprising:

[0007] Acquiring the power optical cable to be optimized and the initial performance of the power optical cable to be optimized;

[0008] Loading the power optical cable to be optimized into multiple test output scenarios with equal power and size;

[0009] According to the set actual laying working conditions, a durable aging output pipeline cycle test is performed on each test output scenario, and the cycle test time of each test output scenario is recorded;

[0010] After the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out for performance testing to obtain the first output average performance of the power optical cables to be optimized at this time;

[0011] Perform an offline durability test on the power optical cable to be optimized, and record the offline durability test time; after the test, collect the second output average performance of the power optical cable to be optimized after the offline durability test;

[0012] According to the second output average performance and initial performance of the power optical cable to be optimized, calculating and obtaining the aging output range of the power optical cable to be optimized after the pipeline durability cycle of each test output scenario;

[0013] According to the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized, an aging output attribute parameter set of an offline durability test and an online pipeline durability cycle test is calculated;

[0014] The final attribute parameter combination is obtained by adding and averaging the corresponding indices of the aging output attribute parameter set, and then the final attribute parameter is obtained by adding and averaging.

[0015] By adopting the above technical solution, the aging output range of the optical cable can be accurately calculated, which can avoid damage to the optical cable due to excessive tension or pressure during the laying process, thereby improving the safety of construction. The method can automatically output the best output suggestion according to the actual laying conditions, which helps to ensure the stable performance of the optical cable during the laying process and reduce quality problems caused by improper operation. The data after the durable aging test provides valuable information for the design and use of the optical cable, which can help identify those parameters that are sensitive to environmental factors, and then take measures to mitigate the impact of these factors and extend the overall life of the optical cable. Accurate output control reduces the need for rework due to improper laying, reduces material waste and labor costs, and reduces the cost of later maintenance and replacement by predicting and preventing potential problems. The application of BP neural network makes the entire optimization process more automated and intelligent. It can learn and predict future situations based on historical data, provide reliable decision-making basis for engineering personnel, enhance the manageability and controllability of the project, take into account ADSS optical cables of different models, sizes and lengths, and combine a variety of laying environments (such as overhead, pipeline, well), so that this method has high versatility and adaptability, and is suitable for optical cable laying in various complex scenarios.

[0016] Furthermore, the obtaining of the power optical cable to be optimized and the initial performance of the power optical cable to be optimized further includes:

[0017] The test indicators of the power optical cable to be optimized include the optical cable model score H, size T, length R, contact angle C, air density E in the well, and pipeline laying depth P;

[0018] The initial performance of the power optical cable to be optimized is recorded as X;

[0019] X = [H, T, R, C, E, P] (1);

[0020] The performance of the power optical cable to be optimized after aging output is set to X′;

[0021] X′=[H′,T′,R′,C′,E′,P′] (2);

[0022] At this time, the OPGW aging output range λ is:

[0023] λ=[λ1,λ2,λ3······];

[0024]

[0025] By adopting the above technical solutions, detailed measurement and recording of multiple key parameters can achieve refined management of the optical cable status, accurately grasp the specific situation of each optical cable, and provide a reliable data basis for subsequent analysis. The accurate collection of initial performance data is the basis for all subsequent calculations and analyses. Detailed initial performance information ensures the accuracy of the calculation of the aging output range, thereby improving the effectiveness of the entire optimization method. The use of a unified standard to measure different types of optical cables makes it possible to compare the performance of different optical cables. This is conducive to selecting the type of optical cable that is most suitable for a specific application environment. By setting the performance indicators after aging treatment and comparing them with the initial performance, the performance change trend of the optical cable under different use conditions can be predicted. According to the test results, the designer can understand which factors have the greatest impact on the performance of the optical cable, and then adjust the design to improve these aspects of performance. By calculating the aging output range, potential risk points can be identified in advance.

[0026] Furthermore, the power optical cable to be optimized is loaded into a plurality of test output scenarios of equal power and size, and further includes:

[0027] The number of the battery stack is recorded as N;

[0028] N=[N 1 ,N 2 ,N 3 ……] (4);

[0029] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0030] By adopting the above technical solutions, using multiple test scenarios of equal power and size can ensure that each test is carried out under the same conditions, which helps to eliminate variables caused by different test conditions, thereby improving the reliability and comparability of test results. By testing in different stacks, data can be collected from multiple locations. This multi-point data collection can more comprehensively reflect the various situations that optical cables may encounter during actual laying, including the impact of different installation locations. Different stacks represent different laying environments or working conditions. For example, N1, N2, and N3 may represent three different laying methods: overhead, pipeline, and well. This ensures that the test results have a wide range of application value and are suitable for a variety of actual application scenarios. Testing in multiple stacks at the same time can speed up the overall testing process and save time. This is especially important for large-scale engineering projects because more test cases can be completed in a shorter period of time. If performance degradation or other problems are found in a particular stack, the specific cause of the problem can be determined by comparing the data of other stacks.

[0031] Furthermore, the method of performing a durable aging output pipeline cycle test on each test output scenario according to the set actual laying working conditions, and recording the cycle test time of each test output scenario, further includes:

[0032] The time of each stack cycle test is recorded as T;

[0033] T=[T 1 , T 2 , T 3 ……] (5).

[0034] By adopting the above technical solution and setting the actual laying working conditions for testing, the actual application of optical cables can be simulated more realistically, ensuring that the test results are highly correlated with the actual situation, thereby improving the effectiveness and practicality of the optimization method. Different cycle test times (T1, T2, T3, etc.) can be used to evaluate the performance changes of optical cables under different usage times. In this way, the aging characteristics of optical cables can be fully understood, providing reliable data support for long-term use. By disassembling and performing performance tests on optical cables piece by piece after different cycle test times, a series of dynamic performance data can be obtained. These data reflect the specific performance of optical cables at different aging stages, which helps to predict their service life more accurately. Through multiple tests and performance tests, the first output average performance (XN) of optical cables in each test output scenario can be calculated. The calculation of this average value reduces the impact of single measurement errors and improves the reliability of the results. By comparing the test results of different stacks (N1, N2, N3, etc.), it is possible to identify which factors have a significant impact on the performance of optical cables.

[0035] Further, after the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out and performance tested to obtain the first output average performance of the power optical cables to be optimized at this time, further comprising:

[0036] The first output average performance X of the power optical cable to be optimized after the pipeline durability cycle of multiple test output scenarios N They are:

[0037]

[0038] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0039] By adopting the above technical solution, detailed performance tests are performed on the aged optical cables in each stack after different cycle test times, and specific performance data can be obtained. This helps to fully understand the performance of the optical cable under different usage conditions. The data collected from multiple stacks (N1, N2, N3, etc.) provide a wider data set that can reflect the performance changes of optical cables in different locations and environments, thereby improving the representativeness and reliability of the analysis results. By calculating the average performance of the first output (XN), a comprehensive performance indicator can be obtained. This average value reduces the impact of single measurement errors and provides a more stable and reliable performance reference.

[0040] Further, the step of calculating and obtaining the aging output range of the power optical cable to be optimized after the pipeline durability cycle of each test output scenario based on the first output average performance and the initial performance of the power optical cable to be optimized also includes:

[0041] The aging output range of OPGW after multiple stack pipeline durability cycles is:

[0042]

[0043] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0044] By adopting the above technical solution and comparing the average performance of the first output with the initial performance, the performance degradation of the optical cable under different test conditions can be quantified. This helps to accurately evaluate the aging state of the optical cable, thereby better predicting its service life. The calculated aging output range provides clear operational guidance for construction personnel. Understanding the safe output range of the optical cable at different aging stages can help avoid damage caused by excessive stretching or improper operation and improve construction safety. A clear aging output range can help to formulate a more reasonable maintenance and replacement plan. According to the actual aging condition of the optical cable, inspection and maintenance work can be arranged in advance to extend the service life of the optical cable and reduce the risk of sudden failures. Based on the analysis results of the aging output range, the design of the optical cable can be optimized.

[0045] Furthermore, the method further comprises:

[0046] The second output average performance X of the power optical cable to be optimized after the offline durability test L for

[0047] X L =[H′ L ,T L ′,R′ L ,C′ L ,E′ L ,P L ′] (8)

[0048] At the same time, the aging output range of the power optical cable to be optimized obtained by offline durability test is:

[0049]

[0050] By adopting the above technical solutions, the online pipeline durability cycle test and the offline durability test are combined to provide multi-dimensional data verification. The online test simulates the stress conditions in the actual working environment, while the offline test performs more rigorous tests in a more controlled environment. The two complement each other and improve the reliability and comprehensiveness of the data. By comparing the first output average performance (XN) and the second output average performance (XL), the comprehensive performance of the optical cable under different test conditions can be obtained. This helps to fully understand the stability and reliability of the optical cable under various conditions of use. The offline durability test can be carried out under more extreme or accelerated conditions to quickly obtain the aging information of the optical cable. This test method can help identify potential problems of the optical cable after long-term use, so as to take preventive measures in advance. Combining the results of online and offline tests can reduce the errors that may be caused by a single test method. The combination of multiple test methods makes data analysis more accurate and improves the grasp of the performance trend of the optical cable.

[0051] Further, the aging output attribute parameter set of the offline durability test and the online pipeline durability cycle test is calculated and obtained according to the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized, and further includes:

[0052] By dividing the difference between each variable and the initial performance in formula (8) by the difference between each variable and the initial performance in formula (6), the aging output attribute parameter set θ for the offline durability test and the online pipeline durability cycle test is obtained:

[0053]

[0054] By adopting the above technical solution, the performance changes of optical cables under different use conditions can be comprehensively evaluated by comprehensively considering the aging output range, the first output average performance, the second output average performance and the initial performance. This helps to more accurately understand the performance of optical cables throughout their life cycle. By dividing the difference between each variable in formula (8) and the initial performance by the difference between each variable in formula (6) and the initial performance, a comprehensive analysis of multiple influencing factors can be performed. In this way, it is possible to identify which factors have the greatest impact on the aging performance of optical cables, thereby providing targeted suggestions for design and maintenance. By calculating the aging output attribute parameter set θ, complex performance data can be simplified into a set of parameters that are easy to understand and explain. These parameters can help technicians quickly grasp the key performance indicators of optical cables and make more reasonable decisions.

[0055] Furthermore, the method of adding and averaging the corresponding indicators of the aging output attribute parameter set to obtain a final attribute parameter combination, and then adding and averaging to obtain the final attribute parameter, further includes:

[0056] The retained indicators are added together to obtain the average value to obtain the final attribute parameter combination, and then the final attribute parameter δ is obtained by adding and averaging.

[0057]

[0058] In formula (11), all indicators are set to be sensitive to the durability aging output, and t represents the offline test time.

[0059] By adopting the above technical solution, a comprehensive performance parameter can be obtained by adding up the corresponding indicators and averaging them. This helps to comprehensively evaluate the overall performance of the optical cable under different test conditions, rather than just focusing on a single indicator. It simplifies multiple complex performance indicators into one or several comprehensive parameters, making data processing and analysis simpler and more intuitive. This is very helpful for quickly understanding and applying test results. The comprehensive performance parameters provide more concise and easier to understand information, which helps technicians and managers make decisions faster. This simplified representation method can speed up project progress and improve work efficiency.

[0060] The present invention has the following beneficial effects:

[0061] 1. The present invention collects data related to the aerial, pipeline, and well laying scenarios of power optical cables, considers multiple types of ADSS optical cables, and calculates and obtains the aging output attribute parameter set of the offline durability test and the online pipeline durability cycle test according to the aging output range, the first output average performance, the second output average performance, and the initial performance of the power optical cable to be optimized;

[0062] 2. The present invention obtains the final attribute parameter combination by adding and averaging the corresponding indicators of the aging output attribute parameter set, and then obtains the final attribute parameter by adding and averaging. By inputting the optical cable model, size, length, and laying environment, the optimal output range of the optical cable laying machine can be automatically output to prevent damage to the optical cable and improve the laying quality;

[0063] 3. The present invention accurately calculates the aging output range and comprehensive performance parameters. The method can formulate a reasonable maintenance and replacement plan, reduce service interruptions and other problems caused by optical cable failures, thereby improving the reliability and stability of the power system. The optimized optical cable selection and use strategy reduces unnecessary maintenance and replacement costs and improves the economic benefits of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is the work flow chart of the present invention. DETAILED DESCRIPTION

[0065] 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0066] Reference Figure 1 It can be seen that a method for optimizing the laying output of power optical cables based on BP neural network includes:

[0067] Acquiring the power optical cable to be optimized and the initial performance of the power optical cable to be optimized;

[0068] Loading the power optical cable to be optimized into multiple test output scenarios with equal power and size;

[0069] According to the set actual laying working conditions, a durable aging output pipeline cycle test is performed on each test output scenario, and the cycle test time of each test output scenario is recorded;

[0070] After the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out for performance testing to obtain the first output average performance of the power optical cables to be optimized at this time;

[0071] Perform an offline durability test on the power optical cable to be optimized, and record the offline durability test time; after the test, collect the second output average performance of the power optical cable to be optimized after the offline durability test;

[0072] According to the second output average performance and initial performance of the power optical cable to be optimized, calculating and obtaining the aging output range of the power optical cable to be optimized after the pipeline durability cycle of each test output scenario;

[0073] According to the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized, an aging output attribute parameter set of an offline durability test and an online pipeline durability cycle test is calculated;

[0074] The final attribute parameter combination is obtained by adding and averaging the corresponding indices of the aging output attribute parameter set, and then the final attribute parameter is obtained by adding and averaging.

[0075] In this embodiment, a self-developed or selected OPGW (optical fiber composite overhead ground wire) sample is selected for offline performance testing. Due to the different active areas of the stack design, the size of the installed OPGW is also different. The size of the OPGW of this model is marked as S, such as S = 110 cm 2 . Since the reaction uniformity of the inlet and outlet of OPGW is different after it is installed in the fuel cell stack, the aging output range in the later stage is also different. The aging output of a local area cannot represent the overall aging output. The OPGW of size S should be divided into several grid areas of the same size, divided into 25 grids of the same size. After selecting 3 pieces for testing, the numerical average is recorded as the initial performance of OPGW. In order to avoid the test error caused by the edge effect, some areas close to the edge are discarded. For example, after discarding the edge, the middle size is 100cm 2 .

[0076] Furthermore, the obtaining of the power optical cable to be optimized and the initial performance of the power optical cable to be optimized further includes:

[0077] The test indicators of the power optical cable to be optimized include the optical cable model score H, size T, length R, contact angle C, air density E in the well, and pipeline laying depth P;

[0078] The initial performance of the power optical cable to be optimized is recorded as X;

[0079] X = [H, T, R, C, E, P] (1);

[0080] The performance of the power optical cable to be optimized after aging output is set to X′;

[0081] X′=[H′,T′,R′,C′,E′,P′] (2);

[0082] At this time, the OPGW aging output range λ is:

[0083] λ=[λ1,λ2,λ3······];

[0084]

[0085] Furthermore, the power optical cable to be optimized is loaded into a plurality of test output scenarios of equal power and size, and further includes:

[0086] The number of the battery stack is recorded as N;

[0087] N=[N 1 ,N 2 ,N 3 ……] (4);

[0088] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0089] Furthermore, the method of performing a durable aging output pipeline cycle test on each test output scenario according to the set actual laying working conditions, and recording the cycle test time of each test output scenario, further includes:

[0090] The time of each stack cycle test is recorded as T;

[0091] T=[T1, T2, T3……] (5).

[0092] In this embodiment, T1=1000h, T2=1500h, T3=2000h, etc. are set;

[0093] The actual laying working conditions are set according to the cyclic working conditions in accordance with the national standard GB / Z 44116-2024.

[0094] Further, after the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out and performance tested to obtain the first output average performance of the power optical cables to be optimized at this time, further comprising:

[0095] The first output average performance XN of the power optical cable to be optimized after the pipeline durability cycle of the multiple test output scenarios are respectively:

[0096]

[0097] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0098] Further, the method of calculating and obtaining the aging output range of the power optical cable to be optimized after each test output scenario warning pipeline durability cycle based on the average performance and initial performance of the power optical cable to be optimized also includes:

[0099] The aging output range of OPGW after multiple stack pipeline durability cycles is:

[0100]

[0101] Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

[0102] Furthermore, the method further comprises:

[0103] The second output average performance X of the power optical cable to be optimized after the offline durability test L for

[0104] X L =[H′ L ,T L ′,R′ L ,C′ L ,E′ L ,P L ′] (8)

[0105] At the same time, the aging output range of the power optical cable to be optimized obtained by offline durability test is:

[0106]

[0107] In this embodiment, offline aging acceleration methods such as electrochemical oxidation, freeze-thaw cycle, hot and cold shock, cyclic compression and other methods are used for offline durability testing. For example, the high-temperature acidic oxidation mixed accelerated aging method is: the sample is placed in a solution at a constant temperature of 80°C, and the concentration of ultrapure water is 1 mol / LH 2 SO4 and 15% H 2 O 2 After sealing, perform an aging test for a certain time t hours, then take it out, such as t = 500h, and then soak and clean it with deionized water, dry it, and then perform the test analysis again.

[0108] Further, the aging output attribute parameter set of the offline durability test and the online pipeline durability cycle test is calculated and obtained according to the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized, and further includes:

[0109] By dividing the difference between each variable and the initial performance in formula (8) by the difference between each variable and the initial performance in formula (6), the aging output attribute parameter set θ for the offline durability test and the online pipeline durability cycle test is obtained:

[0110]

[0111] It can be seen from formula (10) that each attribute parameter contains multiple indicators: cable model score H, size T, length R, contact angle C, air density E in the well, change rate of laying pipeline depth P and test time ratio, which is a combination of composite indicators to reduce the optimization error of a single indicator. Compare the results of the same indicator numbered N1, N2, and N3 in formula (10), because N 1 、N 2 、N 3 The duration of endurance operation varies greatly. If the indicator remains basically unchanged, it means that the indicator is not sensitive to the durability aging output, and the indicator will not be used for subsequent calculations.

[0112] Furthermore, the method of adding and averaging the corresponding indicators of the aging output attribute parameter set to obtain a final attribute parameter combination, and then adding and averaging to obtain the final attribute parameter, further includes:

[0113] The retained indicators are added together to obtain the average value to obtain the final attribute parameter combination, and then the final attribute parameter δ is obtained by adding and averaging.

[0114]

[0115] In formula (11), all indicators are set to be sensitive to the durability aging output, and t represents the offline test time.

[0116] Among them, in this embodiment, after random sampling, OPGW samples are subjected to offline acid corrosion or other methods of durability testing (time is t) and pipeline durability cycle testing after loading (time is T). The former is to perform performance tests on samples after offline testing in turn to obtain offline performance data set 1, and the latter is to disassemble the stack and remove the OPGW samples for offline testing to obtain offline performance data set 2. The relationship between data sets 1 and 2 is established to optimize the aging output of the power optical cable.

[0117] In this embodiment, the middle 100mm×100mm of the sample with a size of about 110mm×110mm is taken as the data test area to avoid the test error caused by the edge effect. Then each 100mm×100mm interval is evenly divided into 25 grids for testing. The size of the entire test domain is 100mm×100mm, and the horizontal and vertical axes display the scale area as (20mm, 40mm, 60mm, 80mm). A multi-zone discrete method is used to represent different position areas installed in the battery stack, that is, it is composed of discrete values ​​of 25 grids, and then the measured values ​​of the 25 grids are averaged. Then multiple samples are measured in the same way to find the average value of multiple samples, such as 3 samples. Similarly, for multiple samples of size, length, contact angle, air density in the well, pipeline laying depth, etc., the average value is calculated after online pipeline circulation and offline durability test.

[0118] Formula (1) The average initial performance of OPGW is denoted by X:

[0119] X=[242.1,18.8,6.5,148,17.1,2246.5]

[0120] Among them, the performance XN of OPGW after aging treatment after three battery stack pipeline endurance cycles (1000h, 1500h, 2000h) are:

[0121] XN 1 =[238.6,16.8,6.6,146,16.2,2278.9]

[0122] XN 2 =[236.2,15.9,6.6,145,15.4,2297.8]

[0123] XN 3 =[234.8,14.2,6.6,143,14.2,2312.5]

[0124] Equation (10) is the aging output attribute parameter set θ of the offline durability test and the online pipeline durability cycle test.

[0125] Performance prediction: BP neural network can be used to predict the aging output range of power optical cables under different laying environments. The mapping relationship between input parameters (such as optical cable model, size, length, contact angle, etc.) and output parameters (such as aging output range) is learned by training BP neural network;

[0126] Optimized calculation: BP neural network is used to optimize the calculation process, that is, to quickly calculate the optimal output range through the learned model, instead of performing time-consuming actual tests or complex mathematical operations every time;

[0127] Attribute parameter set analysis: BP neural network helps analyze and process the aging output attribute parameter set to obtain the final attribute parameter combination. By using the collected data as training samples, the neural network learns how to estimate the appropriate attribute parameters based on the given input data.

[0128] Decision support: After iterative training, the BP neural network can be used as a decision support tool to automatically provide the optimal laying machine output recommendation based on the input optical cable characteristics and laying conditions to prevent optical cable damage and improve laying quality.

[0129] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0130] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for optimizing the laying output of power optical cables based on BP neural network, characterized in that: include: Acquiring the power optical cable to be optimized and the initial performance of the power optical cable to be optimized; Loading the power optical cable to be optimized into multiple test output scenarios with equal power and size; According to the set actual laying working conditions, a durable aging output pipeline cycle test is performed on each test output scenario, and the cycle test time of each test output scenario is recorded; After the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out for performance testing to obtain the first output average performance of the power optical cables to be optimized at this time; Conducting an offline durability test on the power optical cable to be optimized, and recording the offline durability test time; After completion, collecting the second output average performance of the power optical cable to be optimized after the offline durability test; According to the second output average performance and initial performance of the power optical cable to be optimized, calculating and obtaining the aging output range of the power optical cable to be optimized after the pipeline durability cycle of each test output scenario; According to the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized, an aging output attribute parameter set of an offline durability test and an online pipeline durability cycle test is calculated; The final attribute parameter combination is obtained by adding and averaging the corresponding indices of the aging output attribute parameter set, and then the final attribute parameter is obtained by adding and averaging.

2. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 1 is characterized in that: The step of obtaining the power optical cable to be optimized and the initial performance of the power optical cable to be optimized further includes: The test indicators of the power optical cable to be optimized include the optical cable model score H, size T, length R, contact angle C, air density E in the well, and pipeline laying depth P; The initial performance of the power optical cable to be optimized is recorded as X; X = [H, T, R, C, E, P] (1); The performance of the power optical cable to be optimized after aging output is set to X′; X′=[H′,T′,R′,C′,E′,P′] (2); At this time, the OPGW aging output range λ is: λ=[λ1,λ2,λ3······]; 3. The power optical cable laying output optimization method based on BP neural network according to claim 1 is characterized in that: Loading the power optical cable to be optimized into multiple test output scenarios with equal power and size, further comprising: The number of the battery stack is recorded as N; N=[N1,N2,N3……] (4); Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

4. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 1 is characterized in that: The method further includes performing a durable aging output pipeline cycle test on each test output scenario according to the set actual laying working conditions, and recording the cycle test time of each test output scenario. The time of each stack cycle test is recorded as T; T=[T1, T2, T3……] (5).

5. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 1 is characterized in that: After the cycle test is completed, the test output scenes after multiple aging outputs at different cycle test times are disassembled piece by piece, and the respective power optical cables to be optimized are taken out for performance testing to obtain the first output average performance of the power optical cables to be optimized at this time, further comprising: The first output average performance X of the power optical cable to be optimized after the pipeline durability cycle of multiple test output scenarios N They are: Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

6. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 1 is characterized in that: The step of calculating and obtaining the aging output range of the power optical cable to be optimized after the pipeline durability cycle of each test output scenario according to the first output average performance and the initial performance of the power optical cable to be optimized also includes: The aging output range of OPGW after multiple stack pipeline durability cycles is: Among them, 1, 2, and 3 represent the numbers of the 1st, 2nd, and 3rd battery stacks.

7. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 5 is characterized in that: The method further includes: The second output average performance X of the power optical cable to be optimized after the offline durability test L for X L =[H′ L ,T L ′,R′ L ,C′ L ,E′ L ,P L ′] (8); At the same time, the aging output range of the power optical cable to be optimized obtained by offline durability test is:

8. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 7 is characterized in that: The method of calculating and obtaining an aging output attribute parameter set of an offline durability test and an online pipeline durability cycle test based on the aging output range, the first output average performance, the second output average performance and the initial performance of the power optical cable to be optimized also includes: By dividing the difference between each variable and the initial performance in formula (8) by the difference between each variable and the initial performance in formula (6), the aging output attribute parameter set θ for the offline durability test and the online pipeline durability cycle test is obtained:

9. The method for optimizing the laying output of power optical cables based on BP neural network according to claim 8, characterized in that: The method of adding and averaging the corresponding indicators of the aging output attribute parameter set to obtain a final attribute parameter combination, and then adding and averaging to obtain the final attribute parameter, further includes: The retained indicators are added together to obtain the average value to obtain the final attribute parameter combination, and then the final attribute parameter δ is obtained by adding and averaging. In formula (11), all indicators are set to be sensitive to the durability aging output, and t represents the offline test time.

Images