Submarine cable life prediction method based on cloud model algorithm and GM (1, 1)

Abstract

The invention discloses a submarine cable life prediction method based on a cloud model algorithm and GM (1, 1), and relates to the technical field of submarine cable management, and the method comprises the steps: constructing a submarine cable operation state evaluation index system with the fusion of dynamic and static index quantities; based on a cloud model algorithm and in combination with the evaluation index system, constructing a submarine cable operation state evaluation model, and obtaining a submarine cable operation state evaluation result; calculating a comprehensive health index of the submarine cable by using the equipment health index and combining the actual operation condition of the submarine cable based on the operation state evaluation result; and a GM (1, 1) algorithm is introduced, a submarine cable residual life prediction model is constructed, the residual service life of the submarine cable is predicted, and the precision of a prediction result is verified. According to the method, the service life of the submarine cable can be predicted, more scientific decision support can be provided for safety management and maintenance of the submarine cable, the operation efficiency is improved, and normal operation of ocean engineering is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of submarine cable management, and more particularly to a submarine cable life prediction method based on a cloud model algorithm and GM (1,1). Background Art

[0002] At present, due to the increasing depletion of land resources and the continuous improvement of marine resource development technology, many energy sources such as offshore fossil energy, offshore wind energy, tidal energy, etc. have been widely used, and related marine projects such as offshore oil and gas platforms, offshore wind power plants, and offshore observation stations have also been greatly developed. Compared with traditional onshore projects, marine projects are extremely inconvenient in terms of energy and communication with land due to the influence of complex environmental factors at sea, which greatly hinders the further development and utilization of marine energy. Therefore, as the energy and communication channel of the offshore platform, the normal operation of submarine cables is not only related to the normal operation of marine projects, but also an important guarantee for promoting the in-depth development of marine projects.

[0003] In recent years, with the progress of science and technology, the dynamic and static monitoring indicators of submarine cables are fully utilized to evaluate the operating status of submarine cables, and preventive maintenance is carried out for possible operating defects, so as to determine the remaining life of submarine cables, so as to ensure the normal operation of marine engineering. At present, many scholars at home and abroad have carried out research from the perspectives of submarine cable status monitoring and evaluation, and the use of artificial intelligence algorithms to predict the remaining life of power equipment. Zhang Changsheng et al. used the BOTDA and ROTDR principles of distributed optical fibers to monitor the strain and temperature of DC submarine cables in real time. Huang Xiaowei et al. designed an all-fiber monitoring system, which obtained the surface temperature of the submarine cable based on distributed optical fiber sensing based on Brillouin optical time domain analysis, and measured the conductor current through the optical fiber current sensor installed at the terminal, which can calculate and monitor the conductor temperature of the submarine cable in real time. He Wei et al. used phase-sensitive optical time domain reflection technology to monitor the submarine cable in real time, and obtained the energy distribution data of the submarine cable vibration signal in time and space in a variety of different situations. After analysis, it can be seen that monitoring the vibration of the submarine cable can effectively detect the anchor failure of the submarine cable. Li Qian et al. proposed a comprehensive submarine cable status assessment method that integrates online monitoring data, filling the gap in the submarine cable health status assessment indicator system. In the study of the remaining life of electrical equipment, Li Dong proposed a transformer remaining service life prediction method based on particle filters to accurately identify the remaining service life of transformers under various working conditions. Zhang Huijuan et al. proposed a traction transformer oil-paper insulation remaining life prediction method based on hidden Markov models, providing a theoretical reference for the subsequent formulation of traction transformer maintenance strategies. Liu Minghao et al. proposed a BiLSTM lithium battery remaining service life prediction method based on transfer learning training, which greatly improved the accuracy of lithium battery life prediction.

[0004] In summary, as a special electrical equipment, there are few studies on the status assessment and remaining service life prediction of submarine cables. At present, most of the literature on the status assessment and prediction of electrical equipment mainly focuses on transformers, batteries and other equipment, and there is no discussion on the operating status prediction and life prediction of submarine cables. Summary of the invention

[0005] In view of this, the present invention provides a submarine cable life prediction method based on cloud model algorithm and GM (1,1) in response to the situation that the existing submarine cable monitoring data is increasing and the factors affecting the service life of submarine cables are becoming more and more abundant. The method can solve the problem that the existing technology is insufficient in research on submarine cable life prediction, improve the management efficiency of submarine cables and reduce risks.

[0006] To achieve the above object, the technical solution adopted by the present invention is:

[0007] In a first aspect, the present invention provides a method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1), the method comprising the following steps:

[0008] S1. Construct an evaluation index system for submarine cable operation status that integrates dynamic and static indicators;

[0009] S2. Based on the cloud model algorithm and in combination with the submarine cable operation status evaluation index system, a submarine cable operation status evaluation model is constructed to obtain a submarine cable operation status evaluation result;

[0010] S3. Based on the evaluation result of the submarine cable operation status, using the equipment health index and the actual operation status of the submarine cable, calculate the comprehensive health index of the submarine cable;

[0011] S4. Based on the comprehensive health index of the submarine cable, the GM (1,1) algorithm is introduced to construct a submarine cable remaining life prediction model, predict the remaining service life of the submarine cable, and verify the accuracy of the prediction result.

[0012] Furthermore, in step S1, the submarine cable operation status evaluation index system includes: evaluation indicators of online monitoring data, test data and operation inspection data categories.

[0013] Furthermore, in step S2, the submarine cable status assessment result is divided into four status levels: good, caution, abnormal, and severe.

[0014] Furthermore, in step S2, the weights and degradation degrees corresponding to the various evaluation indicators are calculated, and the operation status of the submarine cable is determined using the cloud model. The specific evaluation method includes:

[0015] The subjective weight, objective weight and optimal weight of the evaluation indicators are calculated based on the improved analytic hierarchy process, CRITIC method and relative entropy method respectively;

[0016] Calculate the degradation score of each indicator and combine it with the corresponding weight to get the overall degradation score of the submarine cable. The calculation formula is:

[0017]

[0018] In the formula: n means there are n indicators, w i is the weight of the ith indicator, x i is the degradation score of the ith indicator, and s is the overall degradation score of the submarine cable;

[0019] Using the cloud model membership discrimination algorithm, the membership vector B corresponding to the four states of the submarine cable as a whole is obtained. According to the maximum membership principle, the state level corresponding to the maximum value in the membership vector B is taken as the real-time evaluation result of the submarine cable.

[0020] Combined with the membership vector B, the overall score of the submarine cable is calculated using the following formula:

[0021]

[0022] Where S is the overall score of the submarine cable, f(p) i is the submarine cable operation status membership, a i Indicates the corresponding scores under different operating conditions, a i The corresponding value matrix is: [35,55,75,95];

[0023] The current status level of the submarine cable is determined by the overall score of the submarine cable.

[0024] Furthermore, in step S3, based on the submarine cable status assessment result, the equipment health index is used, combined with the number of maintenance times, operation time, and design life of the submarine cable, to determine the comprehensive health index of the submarine cable. The specific process includes:

[0025] a. Calculate the traditional health index HI of submarine cables n , the calculation formula is:

[0026]

[0027] Where ΔT represents the operating life of the submarine cable; T des It represents the design life of the submarine cable; S1 represents the correction factor for the number of overhauls of the submarine cable;

[0028] b. Determine the health index correction factor h1 based on the submarine cable operation status assessment results;

[0029] c. Calculate the comprehensive health index of the submarine cable using the following formula:

[0030] HI z =HI n ×h1

[0031] Among them, HI z Represents the comprehensive health index of submarine cables.

[0032] Furthermore, in step S4, the remaining service life of the submarine cable is predicted, and the specific process includes:

[0033] The original data sequence of the GM(1,1) model is constructed based on the historical submarine cable comprehensive health index;

[0034] Predict the comprehensive health index of the submarine cable at the next time based on the GM (1,1) model;

[0035] When the comprehensive health index is greater than the preset value, the prediction ends and the corresponding time node is saved; if it does not exceed the preset value, the first value of the original data sequence is discarded, and the predicted value is saved to the end of the original sequence to continue to predict the comprehensive health index of the submarine cable at the next time through the GM (1,1) model until the comprehensive health index is greater than the preset value, and the prediction ends.

[0036] Furthermore, in step S4, the accuracy of the prediction result is verified using the indicators of average relative error, a posteriori error and correlation error.

[0037] In a second aspect, the present invention further provides a submarine cable life prediction system based on a cloud model algorithm and GM (1,1), which is applied to the above-mentioned submarine cable life prediction method based on a cloud model algorithm and GM (1,1) to predict the life of a submarine cable, and the system comprises:

[0038] Evaluation index system construction module, used to construct an evaluation index system for submarine cable operation status integrating dynamic and static index quantities;

[0039] The status assessment result acquisition module is used to construct a submarine cable operation status assessment model based on the cloud model algorithm and in combination with the submarine cable operation status assessment indicator system, and obtain the submarine cable operation status assessment results;

[0040] A comprehensive health index calculation module is used to calculate the comprehensive health index of the submarine cable based on the evaluation results of the submarine cable operation status, using the equipment health index and the actual operation status of the submarine cable;

[0041] The submarine cable life prediction module is used to introduce the GM (1,1) algorithm based on the comprehensive health index of the submarine cable, build a submarine cable remaining life prediction model, predict the remaining service life of the submarine cable, and verify the accuracy of the prediction results.

[0042] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned submarine cable life prediction method based on the cloud model algorithm and GM (1,1).

[0043] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0044] 1. The present invention provides a submarine cable life prediction method based on cloud model algorithm and GM (1,1), which can predict the life of submarine cables, provide more scientific decision support for the safe management and maintenance of submarine cables, improve operation efficiency, and help ensure the normal operation of marine engineering.

[0045] 2. The present invention provides a method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1), wherein a cloud model algorithm is used to integrate a plurality of monitoring quantities so as to determine the operating status of the submarine cable; and the health index of the submarine cable is determined by combining the health index theory and the operating status evaluation results; and a grey fuzzy algorithm is used to predict the remaining service life of the submarine cable, which can improve the management efficiency of the submarine cable and reduce risks.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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.

[0049] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0050] Figure 1 A schematic flow chart of a method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1) is provided in an embodiment of the present invention.

[0051] Figure 2 A schematic diagram of a time-of-input level cloud model provided in an embodiment of the present invention.

[0052] Figure 3 A schematic diagram of a submarine cable life prediction process based on GM (1,1) provided in an embodiment of the present invention.

[0053] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0055] In the description of the present invention, it should be noted that: in some processes described in the specification and drawings of this application, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be performed in the order in which they appear in this document or may be performed in parallel. In addition, various serial numbers are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] In the embodiment of the present invention, in view of the increasing amount of existing submarine cable monitoring data and the increasingly rich factors affecting the service life of submarine cables, the cloud model algorithm is considered to be used to integrate many monitoring quantities to determine the operating status of the submarine cable; and the health index of the submarine cable is determined by combining the health index theory and the operating status evaluation results; and the gray fuzzy algorithm is used to predict the remaining service life of the submarine cable, thereby obtaining a submarine cable remaining service life prediction method based on the cloud model algorithm and GM (1,1). See the method flow for details. Figure 1 As shown, it mainly includes the following steps:

[0058] Step 1: Based on relevant literature research and actual on-site work conditions, a multi-level indicator system for submarine cable evaluation that integrates dynamic and static indicators (i.e., submarine cable operation status evaluation indicator system) is constructed to make the factors considered in the evaluation more comprehensive and scientific.

[0059] Step 2: Based on the cloud model algorithm and combined with the submarine cable operation status evaluation index system, a submarine cable operation status evaluation model is constructed to calculate the operation status results and scores of the submarine cable;

[0060] Step 3: Based on the submarine cable status assessment results, the health index theory is introduced to determine the comprehensive health index of the submarine cable by combining factors such as the number of maintenance, operation time, and design life of the submarine cable;

[0061] Step 4: Based on the comprehensive health index of the submarine cable, the GM (1,1) algorithm is introduced to construct a submarine cable remaining life prediction model, so as to calculate the remaining service life of the submarine cable and verify the accuracy of the prediction results.

[0062] The relevant principles and specific implementation methods of the method of the present invention are described in detail below:

[0063] 1. Establish a multi-level indicator system for submarine cable evaluation based on a combination of dynamic and static factors:

[0064] The submarine cable is a multivariate and complex system. There are many factors that affect its operation status, and the influence of each factor on the submarine cable itself is also different. Some of these factors are difficult to describe quantitatively, resulting in a certain ambiguity and uncertainty in the final status assessment results of the submarine cable. Although the research on the submarine cable status assessment index system is still almost blank, there is a certain research foundation for the onshore cable status indicators and submarine cable operation procedures. There are some studies and analyses on the aging status of submarine cable insulation, but the evaluation of submarine cable status is still in the process of exploration and accumulation. There is a lack of unified connection between the status of submarine cables and their characteristic parameters. It is necessary to construct a status assessment index system suitable for submarine cables to achieve an accurate assessment of the health status of submarine cables.

[0065] Based on the literature review and relevant research work, the present invention combines the relevant research results and systems such as "Guidelines for Cable Line Status Evaluation", "Submarine Power Cable Operation Regulations", "110KV and Below Submarine Power Cable Line Acceptance Specifications", and considers the influence of the complex structure of the submarine cable and the particularly harsh operating environment. A comprehensive and reasonable submarine cable status evaluation index system is established to obtain a more accurate and effective submarine cable health status. The operating status evaluation index set is shown in Table 1 below.

[0066] Table 1 Submarine cable evaluation index set

[0067]

[0068] 2. Establish a submarine cable operation status assessment model based on cloud model algorithm:

[0069] 1. Basic theory of cloud model:

[0070] The cloud model was proposed by Professor Li Deyi in 1995. It can realize the mutual conversion from qualitative concepts to quantitative data through three digital features: expectation Ex, entropy En, and super entropy He. The model is designed to deal with uncertainty, fuzziness and randomness. It is suitable for problems facing complex, fuzzy and uncertain information. It is widely used in prediction, comprehensive evaluation and knowledge expression. Among them, expectation refers to the expected value in the domain U, which is also the value that best represents this qualitative concept; entropy represents the uncertainty measure of qualitative concepts, which is jointly determined by the randomness and fuzziness of the concept; super entropy He represents the uncertainty measure of entropy, that is, the entropy of entropy. Super entropy is used to measure the randomness of the membership of cloud droplets, which is jointly determined by the randomness and fuzziness of entropy.

[0071] 2. Method for processing index degradation degree:

[0072] (1) Quantitative index degradation degree processing method

[0073] When evaluating the operating status of submarine cables, due to the different dimensions of the indicators, there are also obvious differences between their values. In the embodiment of the present invention, in order to avoid the loss of a large amount of data information caused by direct evaluation, the indicator state quantity is first processed and converted into the relative degree of degradation of the indicator. In addition, the types of evaluation indicators mainly include the larger the value, the more stable type and the smaller the value, the more stable type. The relative degree of degradation also needs to be calculated according to the characteristics of each indicator. The specific calculation formula is as follows:

[0074] a. For indicators with smaller values ​​and more stability, the formula for normalizing the state indicators is as follows:

[0075]

[0076] b. For indicators with larger values ​​and more stability, the formula for normalizing the state indicators is as follows:

[0077]

[0078] Where: p i is the relative degradation degree of the index, with a value between [0,1]; Q max and Q min are the limit value and rated value of the mth state indicator under the normal range, Q i is the measured data value.

[0079] (2) Qualitative index degradation degree processing method

[0080] For descriptive status indicators in static indicators, such as the sealing condition of the submarine cable casing, the condition of the submarine cable in the landing section, etc., there is a lack of clear division standards between the various status levels of the indicators, and they may belong to two adjacent status levels. In the embodiment of the present invention, the fuzzy statistical test method is used to obtain the membership of such indicators, and the expert scoring method is used to distribute the formulated questionnaire to experts and on-site operators, as shown in Table 2 below:

[0081] Table 2 Expert Deterioration Survey

[0082] Degree of control (scale) good Notice abnormal serious Very confident (1) √ Confident (0.84) √ More confident (0.68) √ Normal (0.5) √ Less sure (0.32) √ Very unsure (0.16) √ Unsure (0) √

[0083] Meaning in the table: The expert believes the degree of grasp of the indicator status level.

[0084] After sorting out the survey results, we can get the membership degree of the static index, and the calculation expression is:

[0085]

[0086] In the formula, l ij.k Expert k (k = 1, 2, ..., D) believes that the state level of the static indicator is v i (i=1,2,3,4) degree of certainty scale; l i ' j All experts believe that the status level of this static indicator is v i The average scale of the degree of confidence; ij.k for l i ' j The normalized value of the expert survey table is obtained. Finally, the expert survey table result L = [l ij (1),l ij (2),l ij (3),l ij (4)].

[0087] For the qualitative status indicators in the static indicators, such as some preventive tests, there are clear division standards between the various status levels of the indicators, and they can only belong to a certain status level. For example, the AC withstand voltage test has only two states: pass and fail, corresponding to good and severe states respectively. Different qualitative status indicators divide their states according to the degree of degradation of the submarine cable system. For example, if the optical fiber attenuation test fails, it will not directly lead to the operation of the submarine cable system, but it will affect the monitoring equipment, so it corresponds to good and abnormal states respectively.

[0088] 3. Calculation method of indicator weights:

[0089] (1) Determine subjective weights based on improved analytic hierarchy process

[0090] At present, the most commonly used method for obtaining subjective weights for indicators is the hierarchical analysis method. Since the traditional hierarchical analysis method cannot pass the consistency test when calculating weights, it is impossible to obtain subjective weights. Therefore, the present invention adopts an improved hierarchical analysis method to avoid the above problem. The specific steps are as follows:

[0091] a. First, arrange the n indicators (x1, x2, ..., xn) to be evaluated in descending order of importance, and establish the scale v of adjacent indicators according to the following table: i ;

[0092] Table 3 Scale and meaning

[0093] Scale value meaning 1.0 Indicator xi is as important as indicator xi+1 1.2 The index xi and the index xi+1 are slightly important 1.4 Indicators xi and xi+1 are very important 1.6 Indicators xi and xi+1 are obviously important 1.8 Indicators xi and xi+1 are absolutely important

[0094] b. Obtain an n-order judgment matrix R by comparing the scale values ​​of each indicator;

[0095]

[0096] In the formula, R is the judgment matrix.

[0097] c. The above judgment matrix R can be directly used to calculate the subjective weight of each indicator without consistency test. The weight calculation formula is as follows:

[0098]

[0099] In the formula, r ij is the value of the element in the i-th row and j-th column of the matrix R, w i is the subjective weight value of indicator i.

[0100] (2) CRITIC method to determine objective weights

[0101] Objective weighting is to allocate weights to various indicators by mining data and making full use of the information in the data. Commonly used objective weighting methods include: entropy weight method, coefficient of variation method and CRITIC method. This article uses the CRITIC method to assign objective weights. The importance of indicators is mainly reflected by volatility and conflict. The larger the standard deviation of the data, the more important the indicator and the greater the weight, and vice versa. The conflict is represented by the correlation coefficient. The larger the correlation coefficient value, the smaller the conflict and the lower the weight; vice versa. For weight processing, the volatility value and the conflict value are multiplied and then normalized to obtain the final indicator weight. The specific steps are as follows:

[0102] a. Assume that there are n objects to be evaluated, each object has m evaluation indicators, and the sample matrix is ​​as follows:

[0103]

[0104] b. In order to eliminate the errors caused by different dimensions of sample data, the sample data is processed to obtain a new sample matrix.

[0105] If the indicator is a positive indicator:

[0106]

[0107] If the indicator is a reverse indicator:

[0108]

[0109] c. Calculate the information carrying capacity:

[0110] Volatility:

[0111]

[0112] In the formula is the mean value of the j-th indicator data.

[0113] Conflict: When calculating conflict, the correlation matrix M of the indicator should be calculated first.

[0114]

[0115] The conflict calculation is as follows:

[0116]

[0117] Where r ij Represents the correlation coefficient between the i-th indicator and the j-th indicator

[0118] Information volume calculation:

[0119] C j =S j ×A j

[0120] d. Calculate objective weights

[0121]

[0122] Where w j represents the objective weight of the jth indicator; C j is the amount of information carried by the jth indicator.

[0123] (3) Determine the optimal weight using relative entropy method

[0124] The relative entropy method is a common method for fusion of subjective and objective weights. It is based on the information entropy theory and determines the subjective and objective fusion weights by calculating the relative entropy between the subjective and objective weights. The basic idea is to regard the subjective weight and the objective weight as two probability distributions, and use the information entropy of the objective weight to measure the distance between the two distributions. The smaller the distance, the closer the two distributions are, and the more reliable the fusion weights are. Based on the above idea, the following model is established:

[0125] Let the fusion weight vector be W i ={w i1 ,w i1 ,…,w in}, then:

[0126]

[0127] In the formula, is the kth probability distribution corresponding to W i The relative entropy of ; l is the total number.

[0128] The above single-objective optimal planning model is established, and the Lagrange constant method is used to obtain the optimal weight vector after integrating the subjective and objective weights. The calculation formula is:

[0129] W=(w1,w2,w3,…,w n );

[0130] Where W is the optimal weight vector (i.e., comprehensive weight) after integrating subjective and objective weights.

[0131] 3. Cloud model membership determination:

[0132] The formation of clouds depends on cloud generators. According to their operating mechanisms, cloud models can be divided into forward cloud generators, reverse cloud generators, and conditional cloud generators. Among them, the forward cloud generator reflects the mapping from qualitative concepts to their quantitative representations. In the evaluation of submarine cable status, the forward cloud generator is used to calculate the degree to which a certain indicator value belongs to a certain qualitative concept, that is, the indicator membership degree.

[0133] In the embodiment of the present invention, the steps for implementing the evaluation index membership discrimination algorithm of the positive normal cloud generator are as follows:

[0134] a. Generate an expected value of E x , the standard deviation is H e Normal random numbers;

[0135]

[0136] Among them, E N Represents a normal random number, NORM represents generating a normal random number, and represents generating an expected value of E N, the standard deviation is Normal random numbers.

[0137] b. Calculate the membership degree based on the expected value Ex and the input value p;

[0138]

[0139] c. Repeat steps a and b n times to calculate the arithmetic average and get the final membership degree:

[0140]

[0141] In a specific embodiment, since only using the normal cloud model to judge the degree of membership will cause large errors in the submarine cable when the degradation degree is large or small, the present invention introduces a trapezoidal cloud based on the normal cloud, and disassembles the trapezoidal cloud into a left-half and a right-half trapezoidal cloud, and accurately judges the degree of membership by combining the left-half or right-half trapezoidal cloud with the normal cloud.

[0142] ① The right half trapezoidal cloud + normal cloud membership discrimination algorithm is as follows:

[0143] a. According to the input degradation degree p, judge whether p is consistent with the expected E x If p≤E x , then the final membership

[0144] b. If p>E x , then according to the normal cloud model membership algorithm, the final membership is obtained

[0145] ② The left semi-trapezoidal cloud + normal cloud membership discrimination algorithm is as follows:

[0146] a. According to the input degradation degree p, judge whether p is consistent with the expected E x If p ≥ E x , then the final membership

[0147] b. If p <E x , then according to the normal cloud model membership algorithm, the final membership is obtained

[0148] In the embodiment of the present invention, combined with the maintenance guidelines for power cables and submarine cables, the submarine cable status level is divided into four states: good, caution, abnormal, and severe. The normal state is a left-half trapezoidal cloud, the severe state is a right-half trapezoidal cloud, and the caution and abnormal states are both normal clouds. Each state level is a double-constrained space [x min ,x max ], as shown in Table 4 below:

[0149] Table 4 Status level interval

[0150] Status Level good Notice abnormal serious cloud Left half trapezoidal cloud Normal Cloud Normal Cloud Right half trapezoid cloud Interval [0,0.2] (0.2,0.5] (0.5,08] (0.8,1]

[0151] According to cloud theory and the above-mentioned level intervals, cloud models of different status levels can be converted into digital features (Ex, En, He), as shown in Table 5 below:

[0152] Table 5 Digital characteristics of hierarchical cloud model

[0153]

[0154] The specific steps are as follows:

[0155] a.Expect E x It is the center of the sample interval and best reflects the sample mean, so the middle value of each level interval is taken as the expectation.

[0156]

[0157] b. Entropy En is a measure of sample randomness and fuzziness, indicating the randomness and fuzziness of sample values. To achieve both fuzziness and randomness, entropy is determined according to the 50% principle.

[0158]

[0159] c.He is the super entropy of entropy, which is a measure of entropy uncertainty. It is reflected in the degree of uncertainty of sample data within the interval and in the thickness of the cloud model. In this paper, it is taken as 0.01.

[0160] The digital features of cloud models at different levels obtained through the above steps are shown in Table 5 above. Figure 2 shown.

[0161] 4. Evaluation of submarine cable operation status based on cloud model:

[0162] With the continuous improvement of monitoring methods, the monitoring system has higher and higher accuracy in collecting various parameters of submarine cables, and the collection and evaluation rate has become faster and faster. It is becoming more and more important to evaluate the operating status of submarine cables based on the collected data. In the evaluation process, this article uses the evaluation system constructed above to calculate the corresponding weights and degradation degrees of various evaluation indicators, and substitutes them into the cloud model to determine the operating status of the submarine cable. The specific evaluation method is as follows:

[0163] a. Establish an evaluation system based on submarine cable operation data and original data;

[0164] b. Obtain the subjective and objective weights of online monitoring data, inspection data and test data based on expert experience and indicator data, and finally obtain the comprehensive weight W of each indicator;

[0165] c. According to the latest evaluation data, the degradation degree score of each data indicator is obtained by the formula and multiplied by the corresponding weight. The overall degradation score of the submarine cable is finally obtained by summing them up; the calculation formula is:

[0166]

[0167] In the formula: n means there are n indicators, w i is the weight of the ith indicator, x i is the degradation score of the ith indicator, and s is the overall degradation score of the submarine cable.

[0168] d. Based on historical data, a hierarchical cloud model is constructed, and s is brought into the cloud model membership discrimination algorithm to obtain the membership vector B corresponding to the four states of the submarine cable as a whole. According to the maximum membership principle, the state level corresponding to the maximum value in the membership vector B is taken as the real-time evaluation result of the submarine cable, that is, the state level of the submarine cable.

[0169] e. After obtaining the membership vector B, the overall score of the submarine cable is calculated using the following formula.

[0170]

[0171] Where S is the overall score of the submarine cable, f(p) i is the submarine cable operation status membership, a i It represents the corresponding scores under different operating conditions, a=[35,55,75,95]. The submarine cable score is used to judge the degree of the current status of the submarine cable.

[0172] 3. Calculation model of submarine cable health index based on health index theory;

[0173] 1. Equipment Health Index Theory:

[0174] As an advanced tool for evaluating and quantifying the health status of equipment, the Equipment Health Index (EHI) can be traced back to the scientific and technological frontier exploration in the 1960s. At that time, a country's Air Force Research Laboratory took the lead in applying this concept to the aviation field. By integrating real-time monitoring and intelligent analysis technology, it accurately evaluated the health status of each aircraft system and effectively warned of potential failure risks, greatly improving flight safety and mission success rate. This innovation not only marks a milestone in the development of preventive maintenance strategies, but also lays a solid foundation for the subsequent transformation of equipment management models in multiple industries.

[0175] With the continuous advancement of technology, the application scope of the Equipment Health Index (EHI) has rapidly expanded to many key areas such as industrial manufacturing, energy, transportation, etc. Its core lies in the deep integration of big data analysis, machine learning algorithms and Internet of Things technology to comprehensively collect and analyze the operating parameters, maintenance logs and historical fault records of the equipment. This process not only realizes real-time and dynamic monitoring of the health status of the equipment, but also accurately predicts potential failure points through complex data processing and modeling, and provides customized maintenance strategies and operation and maintenance solutions for the equipment. The implementation of EHI, on the one hand, significantly extends the service life of the equipment and reduces production stagnation and economic losses caused by sudden failures. On the other hand, it also achieves precise control of operating costs and continuous improvement of production efficiency by optimizing maintenance processes and resource allocation.

[0176] 2. Calculation of comprehensive health index of submarine cables:

[0177] The health index of a submarine cable is an important physical quantity that characterizes its health. When the initial state remains unchanged during commissioning, the health index of a submarine cable is only related to its service life and design life. However, based on actual operating conditions, the calculation of the health index is too idealistic. Therefore, the actual operating conditions should be considered when calculating the health index, and the results of the submarine cable operating status assessment should be included in the calculation process of its health index. The specific calculation process is as follows:

[0178] a. Calculate the traditional health index HI of submarine cables n , the calculation formula is as follows:

[0179]

[0180] Where ΔT refers to the operating life of the submarine cable; T des It represents the design life of the submarine cable; s1 refers to the correction factor for the number of overhauls of the submarine cable.

[0181] It is assumed that the initial health index of the submarine cable is 0.5, and when the design life is reached, the health index of the submarine cable is 6.5. The determination of the overhaul correction factor s1 is shown in Table 6.

[0182] Table 6 Overhaul frequency correction factor values

[0183] Overhaul times <2 2-4 4-6 >6 <![CDATA[s1]]> 1.0 0.98 0.96 0.94

[0184] b. The health index correction factor h1 is determined based on the submarine cable status assessment results. The specific correction factor values ​​are shown in Table 7 below.

[0185] Table 7 Correction coefficient values

[0186] <![CDATA[h1]]> Operation status assessment score S 1 >85 1.15 70＜C≤85 1.35 55＜C≤70 1.55 40＜C≤55 1.65 ≤40

[0187] c. Calculate the comprehensive health index of the submarine cable. The specific formula is as follows:

[0188] HI z =HI n ×h1

[0189] Among them, HI z It represents the comprehensive health index of the submarine cable. The larger the score, the worse the health of the submarine cable.

[0190] 4. Establishment of submarine cable life prediction model based on GM (1,1):

[0191] 1.GM(1,1) model principle:

[0192] The grey system theory was first proposed by scholar Deng Julong in the 1980s. It is mainly used to describe and analyze uncertainty and complexity, and is suitable for dealing with uncertainty problems such as small amounts of information and lack of data. In layman's terms, in daily life, most information is not comprehensive enough to be fully utilized, and we also need to make predictions in advance based on this information. The grey system is very good at dealing with such problems. Based on limited information and data, it can mine information as much as possible through combing statistics to achieve prediction functions.

[0193] The GM(1,1) model is a one-dimensional linear grey model in the grey system theory. In this theory, the first "1" represents the order of the equation, and the second "1" represents the number of predicted objects. This model mainly uses the first-order differential equation to fit the data of one-dimensional variables to achieve prediction. The advantage of the GM(1,1) model is that it does not require high data and is suitable for smaller-scale time series data. However, it also has some limitations, such as strong sensitivity to the smoothness and trend of the data. This model is usually used for medium- and short-term predictions, but may have limited effect in long-term predictions. The modeling process of this model is as follows:

[0194] a. Accumulate the original one-dimensional data:

[0195] Based on the given original non-negative sequence:

[0196] X (0) {X (0) (1),X (0) (2),X (0) (3),…,X (0) (n)}

[0197] The original data of the above formula is accumulated and summed:

[0198] X (1) {X (1) (1),X (1) (2),X (1) (3),…,X(1) (n)}

[0199] The purpose of continuing to accumulate and sum the original data is to weaken the volatility and randomness of the original data. The first accumulation is marked as 1, the second accumulation is marked as 2, and so on.

[0200]

[0201] b. Construct discrete differential equations:

[0202]

[0203] Its differential form is:

[0204] X (0) (k)+aZ (1) (k) = b

[0205] Among them, a is the development coefficient, which reflects the development trend between the cumulative series and the original series; b is the coordination coefficient, which reflects the changing relationship between the data.

[0206] c. Calculate parameters a and b:

[0207] The least squares method is generally used to solve the parameters a and b:

[0208] [a,b] T =(B T B) -1 B T Y

[0209] in:

[0210]

[0211] z (1) is the background value sequence, which can be expressed as:

[0212] Z (1) (k+1)=(1-ρ)X (1) (k)+ρX (1) (k+1), k=1,2,…,n-1;

[0213] Among them, ρ∈[0,1] is the weight coefficient, which is generally taken as 0.5, then:

[0214]

[0215] Finally, it can be discretized as:

[0216] X (1) (k)-X (1) (k-1)+aZ (1)(k) = b, k = 2, 3, ..., n;

[0217] Finally, the values ​​of a and b are calculated by the least squares method.

[0218] d. Solve the prediction sequence:

[0219] After obtaining the values ​​of a and b, we can further obtain:

[0220]

[0221] Let X (1) (1) = X (0) (1) is the initial value, so:

[0222]

[0223] c represents the residual ratio, which is used to evaluate the fitting effect of the model at the initial moment.

[0224] So we get:

[0225]

[0226] By performing cumulative reduction, the grey prediction model based on the initial value is obtained as follows:

[0227] X (0) (k) = X (1) (k)-X (1) (k-1), k=2,3,…,n.

[0228] 2.GM(1,1) model accuracy verification:

[0229] Precision test is an important test method to measure the prediction effect of the model, which mainly judges whether the relative error of the model is within the allowable range. The main indicators of precision error are average relative error, posterior error and correlation error.

[0230] (1) Average relative error It is the degree of closeness between the simulated value and the original value. The larger the average relative error, the larger the fitting error and the worse the effect. Table 8 gives the average relative error accuracy level:

[0231] Table 8 Average relative error accuracy level

[0232]

[0233] The calculation is as follows:

[0234] Let the fitted value series be X (0) (k), k=1,2,3,…,n, then the residual is:

[0235] ε(k)=X (0) (k)-X(k),k=1,2,…,n

[0236] The relative error is:

[0237]

[0238] So the mean relative error

[0239]

[0240] (2) The posterior difference ratio test is calculated as follows:

[0241] First, find the original data X (0) (k) and the mean and variance of the residual sequence ε(k):

[0242]

[0243] Define the posterior difference ratio C = S2 / S1. The smaller C is, the closer the fitting value is to the actual value, and the better the effect is. Table 9 gives the accuracy level of the posterior difference ratio.

[0244] Table 9 Delay ratio accuracy level

[0245] C Accuracy level C≤0.35 Level 1 (Excellent) 0.35＜C≤0.5 Level 2 (good) 0.5＜C≤0.65 Level 3 (Pass) C＞0.65 Level 4 (poor)

[0246] (3) Correlation test is mainly used to describe the similarity between the fitted value curve and the original data curve. The larger the value, the better the model fitting effect. The calculation is as follows:

[0247] Assume that the fitted value sequence is: X (0) (k), k = 1, 2, 3, ..., n, then the correlation γ is:

[0248]

[0249] Usually when the correlation degree γ>0.6, it indicates that the prediction model is qualified. Table 10 gives the correlation degree accuracy level.

[0250] Table 10 Correlation accuracy level

[0251] γ Accuracy level γ ≥ 0.9 Level 1 (Excellent) 0.8≤γ<0.9 Level 2 (good) 0.6≤γ<0.8 Level 3 (Pass) γ<0.6 Level 4 (poor)

[0252] 3. Life prediction model based on submarine cable health index:

[0253] The comprehensive health index of submarine cables is not only composed of the aging index, but also needs to consider the impact of the equipment operating status. Therefore, the calculation of the submarine cable health index in the present invention needs to be based on the operating years, combined with the equipment operating environment and equipment defects, faults and other status information, so that it is more in line with the actual operating conditions. At the same time, due to the long cycle of the comprehensive health index of submarine cables, lack of information, small amount of data and other problems, the gray system theory is better at dealing with such problems. Therefore, this paper proposes a submarine cable life prediction method based on GM (1,1) and the comprehensive health index. For specific steps, see Figure 3 As shown, the specific process is as follows:

[0254] a. First, based on historical data and the aging health index calculation formula, the aging health index HI of the submarine cable running to the current time is obtained. Secondly, the equipment health index HI is calculated based on the annual evaluation results. n ;

[0255] b. Calculate the comprehensive health index HI of submarine cables z , and construct the original data sequence of GM(1,1) model based on the historical comprehensive health index;

[0256] c. Predict the HI of the submarine cable at the next time based on the GM(1,1) model z ;

[0257] d. The present invention stipulates that when the comprehensive health index is greater than 6.5, the equipment will be forced to retire, so according to the prediction results, it is determined whether the comprehensive health index meets the retirement requirements at the next time;

[0258] e. If the comprehensive health index is greater than 6.5, the prediction ends and the corresponding time node is saved; if it does not exceed 6.5, the first value of the original sequence is discarded, and the predicted value is saved to the end of the original sequence to continue predicting the comprehensive health index at the next time through the GM (1,1) model until the comprehensive health index is greater than 6.5 and the prediction ends.

[0259] 5. Feasibility and accuracy verification:

[0260] In order to verify the feasibility and accuracy of the submarine cable remaining life prediction method based on the cloud model algorithm and GM (1,1) established in the present invention, the HYJQF41 three-core submarine cable of an actual offshore platform of an oil field of CNOOC is taken as the research object, and its management level and technical level indicators are selected to construct an evaluation index system as shown in Table 1 above. The idea of ​​combined weighting is adopted to determine the weight of each indicator as shown in Table 11 below:

[0261] Table 11 Evaluation index weights

[0262] index Subjective weight Objective weight Comprehensive weight <![CDATA[q1]]> 0.285 0.287 0.386 <![CDATA[q2]]> 0.285 0.140 0.188 <![CDATA[q3]]> ,0.198 0.323 0.302 <![CDATA[q4]]> 0.137 0.064 0.041 <![CDATA[q5]]> 0.095 0.186 0.083 <![CDATA[f1]]> 0.273 0 0.273 <![CDATA[f2]]> 0.190 0 0.190 <![CDATA[f3]]> 0.132 0 0.132 <![CDATA[f4]]> 0.132 0 0.132 <![CDATA[f5]]> 0.273 0 0.273 <![CDATA[l1]]> 0.144 0 0.144 <![CDATA[l2]]> 0.144 0 0.144 <![CDATA[l3]]> 0.298 0 0.298 <![CDATA[l4]]> 0.207 0 0.207 <![CDATA[l5]]> 0.207 0 0.207

[0263] In this embodiment, based on the submarine cable cloud model, the degradation degree score of each indicator is calculated, and the model membership discrimination method is used to obtain the submarine cable operation status membership matrix [0.252, 0.543, 0.121, 0.084]. Based on the maximum membership principle, it can be obtained that the operation status of the submarine cable is the attention state. Combined with the relevant calculation formula, the submarine cable score can be calculated to be 74.26. The comprehensive health index calculation formula is used to determine that the health indexes of the first five years are: 0.5684, 0.6461, 7346, 0.8351, respectively. The submarine cable life prediction effect of the GM (1, 1) model is verified, and the actual value and predicted value of the comprehensive health index of the submarine cable in the first five years and the accuracy test effect of the GM (1, 1) model are shown in Tables 12 and 13 respectively:

[0264] Table 12 Actual and fitted values ​​of comprehensive health index in the first five years of evaluation index weight

[0265] years Actual value Fitted values Relative error 2019 0.5684 0.568 0.000％ 2020 0.6461 0.6296 2.681％ 2021 0.7346 0.7651 4.129％ 2022 0.9604 0.9310 3.106％ 2023 1.1321 1.1320 0.003％

[0266] Table 13GM(1,1) model accuracy test table

[0267]

[0268] According to the prediction results and accuracy test results, C<0.35 and γ>0.95, indicating that the model effect is excellent; from the data, the relative error between the actual value and the fitted value is far less than 10%, the difference between the actual value and the fitted value is small, and the fitting effect is good.

[0269] In this embodiment, the life prediction is performed according to the actual value of the comprehensive health index in the previous five years combined with the submarine cable life prediction model proposed in this article. The health index prediction results and service life of the submarine cable are shown in Table 14 below:

[0270] Table 14 Submarine cable life prediction results

[0271]

[0272]

[0273] According to the prediction results, the comprehensive health index of the submarine cable will exceed 6.5 in 2036, that is, its technical life should be in service until the end of 2035. The submarine cable has been put into use since 2018 and will be out of service at the end of 2035, with a service life of 18 years. According to the actual situation of the operating platform, the submarine cable was officially put into use in 2018, with an estimated service life of 20 years and is expected to be out of service at the end of 2037. The model prediction value proposed in this paper is that the transformer will be out of service at the end of 2035, which is 2 years earlier than the manufacturer's estimated service life. This is because the historical maintenance records of the equipment and the annual comprehensive evaluation results of the equipment are taken into account in the prediction model. The submarine cable has undergone a major overhaul in the five years of actual operation, and the equipment is located on the offshore platform. The influence of environmental factors and the lack of stability of the microgrid of the offshore operating platform make the prediction results earlier than the ideal service life. However, according to the actual situation, the prediction results of the model are more consistent with the actual operation, indicating the practical applicability of the model prediction results.

[0274] From the description of the above embodiments, those skilled in the art can know that: the present invention provides a method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1), and the beneficial effects achieved by the present invention include:

[0275] 1) A comprehensive and reasonable evaluation index system for the operation status of submarine cables has been established to facilitate more accurate and effective submarine cable operation status. 2) The evaluation method for the operation status of submarine cables based on cloud model and combined weight theory has the advantages of handling uncertainty, integrating multi-dimensional information and improving evaluation accuracy. Through this method, more scientific decision-making support can be provided for the safe management and maintenance of submarine cables, thereby reducing risks and improving operating efficiency. 3) The remaining life of submarine cables is predicted based on the health index theory and GM (1,1) algorithm, which can solve the problem of insufficient research on submarine cable life prediction in existing technologies, improve the management efficiency of submarine cables and reduce risks.

[0276] Furthermore, the present invention also provides a submarine cable life prediction system based on a cloud model algorithm and GM (1,1), which is applied to a submarine cable life prediction method based on a cloud model algorithm and GM (1,1) described in the above embodiment to predict the life of a submarine cable, and the system includes:

[0277] Evaluation index system construction module, used to construct an evaluation index system for submarine cable operation status integrating dynamic and static index quantities;

[0278] The status assessment result acquisition module is used to construct a submarine cable operation status assessment model based on the cloud model algorithm and in combination with the submarine cable operation status assessment indicator system, and obtain the submarine cable operation status assessment results;

[0279] A comprehensive health index calculation module is used to calculate the comprehensive health index of the submarine cable based on the evaluation results of the submarine cable operation status, using the equipment health index and the actual operation status of the submarine cable;

[0280] The submarine cable life prediction module is used to introduce the GM (1,1) algorithm based on the comprehensive health index of the submarine cable, build a submarine cable remaining life prediction model, predict the remaining service life of the submarine cable, and verify the accuracy of the prediction results.

[0281] The embodiment of the present invention provides a submarine cable life prediction system based on a cloud model algorithm and GM (1,1). Its implementation principle and the technical effects produced are the same as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in this embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment, which will not be repeated here.

[0282] In addition, refer to Figure 4 As shown, an embodiment of the present invention further provides an electronic device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, the processor executes the computer program to implement a method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1) in the above method embodiment.

[0283] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory 11, and calling data stored in the memory 11.

[0284] The memory 11 here is a computer-readable storage medium, including: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, DVD-ROM, Blu-ray or optical disk memory, hard disk drive (HDD), solid state drive (SSD), card memory (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage system, optical data storage system, hard disk, solid state disk and any other system, any of the above-mentioned any other system is configured to store computer programs and any associated data, data files and data structures in a non-temporary manner and provide the computer programs and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the above-mentioned computer-readable storage medium can be executed in an environment deployed in a computer device such as a client, a host, an agent system, a server, etc. In addition, in one example, the computer program and any associated data, data files, and data structures are distributed on a networked computer system, so that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner by one or more processors or computers.

[0285] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, electronic devices or computer program products, etc. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0286] It should be noted that the word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several distinct components, and by means of a suitably programmed computer.

[0287] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0288] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting submarine cable life based on cloud model algorithm and GM (1,1), characterized in that: The method comprises the following steps: S1. Construct an evaluation index system for submarine cable operation status that integrates dynamic and static indicators; S2. Based on the cloud model algorithm and in combination with the submarine cable operation status evaluation index system, a submarine cable operation status evaluation model is constructed to obtain a submarine cable operation status evaluation result; S3. Based on the evaluation result of the submarine cable operation status, using the equipment health index and the actual operation status of the submarine cable, calculate the comprehensive health index of the submarine cable; S4. Based on the comprehensive health index of the submarine cable, the GM (1,1) algorithm is introduced to construct a submarine cable remaining life prediction model, predict the remaining service life of the submarine cable, and verify the accuracy of the prediction result.

2. The method for predicting submarine cable life based on cloud model algorithm and GM (1,1) according to claim 1, characterized in that: In the step S1, the submarine cable operation status evaluation index system includes: evaluation indicators of online monitoring data, test data and operation inspection data categories.

3. The method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1) according to claim 1, characterized in that: In step S2, the submarine cable status assessment result is divided into four status levels: good, caution, abnormal, and severe.

4. The method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1) according to claim 3, characterized in that: In step S2, the weights and degradation degrees corresponding to the various evaluation indicators are calculated, and the operation status of the submarine cable is determined using the cloud model. The specific evaluation method includes: The subjective weight, objective weight and optimal weight of the evaluation indicators are calculated based on the improved analytic hierarchy process, CRITIC method and relative entropy method respectively; Calculate the degradation score of each indicator and combine it with the corresponding weight to get the overall degradation score of the submarine cable. The calculation formula is: In the formula: n means there are n indicators, w i is the weight of the ith indicator, x i is the degradation score of the ith indicator, and s is the overall degradation score of the submarine cable; Using the cloud model membership discrimination algorithm, the membership vector B corresponding to the four states of the submarine cable as a whole is obtained. According to the maximum membership principle, the state level corresponding to the maximum value in the membership vector B is taken as the real-time evaluation result of the submarine cable. Combined with the membership vector B, the overall score of the submarine cable is calculated using the following formula: Where S is the overall score of the submarine cable, f(b) i is the submarine cable operation status membership, a i Indicates the corresponding scores under different operating conditions; The current status level of the submarine cable is determined by the overall score of the submarine cable.

5. The method for predicting the life of a submarine cable based on a cloud model algorithm and GM (1,1) according to claim 4, characterized in that: In step S3, based on the submarine cable status assessment result, the equipment health index is used, combined with the number of maintenance times, operation time, and design life of the submarine cable, to determine the comprehensive health index of the submarine cable. The specific process includes: a. Calculate the traditional health index HI of submarine cables n , the calculation formula is: Where ΔT represents the operating life of the submarine cable; T des It represents the design life of the submarine cable; S1 represents the correction factor for the number of overhauls of the submarine cable; b. Determine the health index correction factor h1 based on the submarine cable operation status assessment results; c. Calculate the comprehensive health index of the submarine cable using the following formula: HI z HI n ×h1 Among them, HI z Represents the comprehensive health index of submarine cables.

6. A method for predicting submarine cable life based on cloud model algorithm and GM (1,1) according to claim 5, characterized in that: In step S4, the remaining service life of the submarine cable is predicted, and the specific process includes: The original data sequence of the GM(1,1) model is constructed based on the historical submarine cable comprehensive health index; Predict the comprehensive health index of the submarine cable at the next time based on the GM(1,1) model; When the comprehensive health index is greater than the preset value, the prediction ends and the corresponding time node is saved; if it does not exceed the preset value, the first value of the original data sequence is discarded, and the predicted value is saved to the end of the original sequence to continue to predict the comprehensive health index of the submarine cable at the next time through the GM (1,1) model until the comprehensive health index is greater than the preset value, and the prediction ends.

7. The method for predicting submarine cable life based on cloud model algorithm and GM (1,1) according to claim 1, characterized in that: In step S4, the accuracy of the prediction result is verified using the indicators of average relative error, a posteriori error and correlation error.

8. A submarine cable life prediction system based on cloud model algorithm and GM (1,1), characterized in that: When applied, a submarine cable life prediction method based on a cloud model algorithm and GM (1,1) as described in any one of claims 1 to 7 is executed to predict the life of a submarine cable, and the system comprises: Evaluation index system construction module, used to construct an evaluation index system for submarine cable operation status integrating dynamic and static index quantities; The status assessment result acquisition module is used to construct a submarine cable operation status assessment model based on the cloud model algorithm and in combination with the submarine cable operation status assessment indicator system, and obtain the submarine cable operation status assessment results; A comprehensive health index calculation module is used to calculate the comprehensive health index of the submarine cable based on the evaluation results of the submarine cable operation status, using the equipment health index and the actual operation status of the submarine cable; The submarine cable life prediction module is used to introduce the GM (1,1) algorithm based on the comprehensive health index of the submarine cable, build a submarine cable remaining life prediction model, predict the remaining service life of the submarine cable, and verify the accuracy of the prediction results.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement a submarine cable life prediction method based on a cloud model algorithm and GM (1,1) as described in any one of claims 1 to 7.

Images