An intelligent sensing method for monitoring key operating parameters of cables

Abstract

The present invention relates to the field of cable monitoring and data analysis technology, and in particular to an intelligent perception method for monitoring key operating parameters of a cable, comprising the following steps: obtaining a first key operating parameter of a cable and first external environment data, and preprocessing the first key operating parameter of the cable and the first external environment data respectively; inputting the preprocessed first key operating parameter of the cable and the first external environment data into an environmental impact model respectively to generate environmental impact dynamic data. The present invention realizes dynamic monitoring of the cable status through a self-learning perception model and an environmental impact model. The method is based on a multi-level abnormality judgment and hierarchical early warning mechanism, and can dynamically adjust the threshold according to the real-time change trend of the key operating parameters of the cable and the external environment data, which can not only improve the accuracy of cable operation status monitoring, but also conduct risk assessment of potential faults and take preventive measures in time.

Description

Technical Field

[0001] The present invention relates to the technical field of cable monitoring and data analysis, and in particular to an intelligent sensing method for monitoring key operating parameters of a cable. Background Art

[0002] During the daily operation and maintenance of cables, the key operating parameters of cables may fluctuate under various environmental conditions and be affected by external environmental factors such as temperature, humidity and vibration. The interaction between these external environmental factors may cause abnormal cable operation or even failure, thus affecting the safety and stability of the power supply system. Therefore, how to monitor the operating parameters of cables in real time and accurately, and timely identify and warn potential abnormal conditions, is of great significance to ensure the reliable operation of cables.

[0003] Most existing cable detection methods are based on fixed rule-based early warnings that are difficult to cope with complex environmental fluctuations, especially under dynamic operating conditions, and it is difficult to effectively identify abnormal trends in cable status.

[0004] In addition, the lack of trend prediction methods for real-time data limits the early judgment and handling of failure risks, which is not conducive to proactive maintenance and accident prevention. Summary of the invention

[0005] The present invention provides an intelligent sensing method for monitoring key operating parameters of cables, aiming to solve the problem in related technologies that it is difficult to effectively identify abnormal trends in cable status under dynamic operating conditions, thereby avoiding safety issues such as limited early judgment and processing of fault risks, and further avoiding subsequent problems that are not conducive to proactive maintenance and accident prevention.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent sensing method for monitoring key operating parameters of a cable, characterized in that it comprises the following steps:

[0008] Acquire the first key operating parameters of the cable and the first external environment data, and preprocess the first key operating parameters of the cable and the first external environment data respectively; the first key operating parameters of the cable refer to the cable operation status data acquired and saved in the first historical operation stage, including the cable temperature, current, voltage and stress in the first historical operation stage; the first external environment data refer to the historical environment data corresponding to the first key operating parameters of the cable, including the ambient temperature, ambient humidity, air pressure and vibration in the first historical operation stage.

[0009] The preprocessed first cable key operating parameters and the first external environment data are respectively input into the environmental impact model to generate environmental impact dynamic data.

[0010] The preprocessed first key operating parameter of the cable and the first external environment data are respectively input into the self-learning perception model for correlation analysis, and the normal value range of the key operating parameter of the cable is output.

[0011] Based on the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the upper and lower limit thresholds of the key operating parameters of the cable are dynamically adjusted.

[0012] Obtain the second cable's key operating parameters and the second external environment data; the second cable's key operating parameters refer to the key operating data obtained when the cable is in real-time operation, including cable temperature, current, voltage and stress; the second external environment data refers to the external environment data obtained when the cable is in real-time operation, including ambient temperature, ambient humidity, air pressure and vibration.

[0013] The second cable key operating parameters are compared with the upper and lower limit thresholds of the dynamically adjusted cable key operating parameters to make an abnormality classification judgment.

[0014] The second cable key operating parameters and the second external environment data are input into the LSTM model to predict and output the development trend of the cable key operating parameters, and the potential failure risk is evaluated based on the predicted development trend.

[0015] The risk level is determined based on the abnormal classification results and potential failure risks, and the alarm mechanism is triggered based on the risk level.

[0016] As a preferred solution of the present invention, the pre-processed first cable key operating parameters and the first external environment data are respectively input into the environmental impact model to generate environmental impact dynamic data, specifically including:

[0017] The preprocessed key operating parameters of the first cable and the first external environment data are respectively input into the environmental impact model, and the dynamic impact of the first external environment data on the key operating parameters of the first cable is evaluated to obtain a dynamic impact evaluation result.

[0018] According to the dynamic impact assessment results, combined with the historical average and associated weights of environmental factors, the dynamic environmental impact data is generated. The generation formula is:

[0019]

[0020] In the formula, represents the dynamic data of environmental impact at the i-th time point, represents the jth external environment parameter value at the i-th time point, represents the historical mean of the jth external environment parameter, represents the association weight of the jth external environment parameter, represents the dynamic impact assessment result of the jth external environmental parameter, represents the model intercept term; represents the error term.

[0021] The environmental impact dynamic data includes the impact degree and trend change of the first external environmental data on the key operating parameters of the first cable.

[0022] As a preferred solution of the present invention, before the step of obtaining the first cable key operating parameter and the first external environment data, it also includes:

[0023] Construct the environmental impact model of cable status. The specific steps are as follows:

[0024] The key operating parameters of the third cable and the third external environment data are preprocessed respectively to obtain the preprocessed key operating parameters of the third cable and the third external environment data; the preprocessing includes data cleaning, denoising, outlier identification and elimination, and standardization; the key operating parameters of the third cable refer to the cable operation status data obtained and saved in the second historical operation stage, including the cable temperature, current, voltage and stress in the second historical operation stage; the third external environment data refers to the historical environment data corresponding to the key operating parameters of the third cable, including the ambient temperature, ambient humidity, air pressure and vibration in the second historical operation stage.

[0025] The preprocessed third cable key operating parameters are correlated with the third external environment data to determine the correlation calculation results between the parameters.

[0026] Based on the correlation calculation results, feature extraction is performed on the third external environment data and the third cable key operating parameters with significant correlation to obtain the impact feature; the impact feature is the feature of the impact of the third external environment data on the third cable key operating parameters.

[0027] An environmental impact model of the cable status is established based on the impact characteristics, the pre-processed third cable key operating parameters and the third external environment data.

[0028] As a preferred solution of the present invention, the preprocessed first cable key operating parameter and the first external environment data are respectively input into the self-learning perception model for correlation analysis, and the normal value range of the cable key operating parameter is output, specifically including:

[0029] An unsupervised learning algorithm is used to input the preprocessed first cable key operating parameters and the first external environment data into the self-learning perception model. Through cluster analysis and distribution learning, the normal value range of the cable key operating parameters is generated. The generation formula is:

[0030]

[0031]

[0032] In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable. Indicates the lower limit of the normal value range of the key operating parameters of the cable. represents the historical mean of the key operating parameters of the i-th cable, represents the correlation strength of the external environment parameters to the i-th cable parameters; represents the jth external environment parameter value at the i-th time point, represents the historical mean of the jth external environment parameter, represents the range expansion factor, and n represents the total number of external environment parameters.

[0033] As a preferred solution of the present invention, based on the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the upper and lower limit thresholds of the key operating parameters of the cable are dynamically adjusted, specifically including:

[0034] According to the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the fluctuation range of the key operating parameters of the cable is dynamically adjusted, and the initial threshold range of the key operating parameters of the cable is set according to the fluctuation range.

[0035] Combined with the operating data of the key operating parameters of the cable, the initial threshold range is adaptively adjusted to generate the upper and lower thresholds of the key operating parameters of the cable.

[0036] According to the changing trend of the second external environment data and the changing trend of the second cable key operating parameters, the upper and lower limit thresholds of the cable key operating parameters are dynamically adjusted, and the adjustment formula is:

[0037]

[0038]

[0039] In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable, which is used to define the maximum acceptable value of the cable operating status; It indicates the lower limit of the normal value range of the key operating parameters of the cable, and is used to define the minimum acceptable value of the cable operating status; Indicates dynamic data of environmental impact, reflecting the immediate impact of external environmental factors on the operating status of the cable; It represents the dynamic impact coefficient, reflecting the weight of environmental impact on threshold adjustment; Represents the environmental data trend adjustment coefficient, which is used to adjust the impact of the predicted trend of cable parameters on the upper and lower thresholds; Indicates the changing trend of the dynamic data of environmental impact, and is used to reflect the long-term changing trend of the second external environmental data; Indicates the change trend of the key operating parameters of the second cable, which is used to reflect the short-term fluctuation trend of the cable operating status; It represents the parameter trend adjustment coefficient, reflecting the weight of the change trend of the key operating parameters of the cable on the threshold adjustment; Indicates the upper threshold of the key operating parameters of the cable. Indicates the lower threshold of the key operating parameters of the cable.

[0040] As a preferred solution of the present invention, the second cable key operating parameter is compared with the upper and lower limit thresholds of the dynamically adjusted cable key operating parameter to perform abnormal classification judgment, specifically including:

[0041] The upper and lower limit thresholds of the dynamically adjusted key operating parameters of the cable are compared with the second key operating parameters of the cable to determine whether the second key operating parameters of the cable exceed the upper and lower limit thresholds.

[0042] If it is within the threshold range, it is determined that the second cable key operating parameter is in a normal state.

[0043] If it exceeds the threshold range, the second cable key operating parameter is determined to be in an abnormal state, and an abnormal classification determination is performed for the second cable key operating parameter that exceeds the threshold, specifically:

[0044] The abnormality classification results include low-level abnormalities, medium-level abnormalities and high-level abnormalities.

[0045] If the value exceeding the threshold is within the set low-level abnormality range, it is determined to be a low-level abnormality and a low-level abnormality notification is generated.

[0046] If the value exceeding the threshold is within the set intermediate abnormal range, it is judged as an intermediate abnormality and an intermediate abnormality notification is generated.

[0047] If the value exceeding the threshold is within the set high-level exception range, it is determined to be a high-level exception and a high-level exception notification is generated.

[0048] As a preferred solution of the present invention, the second key operating parameters of the cable and the second external environment data are input into the LSTM model, the development trend of the key operating parameters of the cable is predicted and output, and the potential failure risk is evaluated according to the predicted development trend, specifically including:

[0049] The second key operating parameters of the cable and the second external environment data are input into the LSTM model to predict the changing trend of the key operating parameters of the cable in the future and obtain the predicted development trend of the key operating parameters of the cable.

[0050] According to the data fluctuation trend in the predicted development trend, combined with the upper and lower limit thresholds of the key operating parameters of the cable, the abnormal situation of the second cable key operating parameters in the future is judged to generate a fault risk assessment result; the fault risk assessment result includes slight risk, moderate risk and high risk.

[0051] As a preferred solution of the present invention, the risk level is determined according to the abnormal classification determination result and the potential failure risk, and the alarm mechanism is triggered based on the risk level, specifically including:

[0052] Based on the abnormality classification results and fault risk assessment results, the risk level of the abnormal situation is determined, and the risk level includes three levels: low risk, medium risk and high risk.

[0053] If the abnormality classification result is a low-level abnormality and the fault risk assessment result is a slight risk, the risk level is determined to be low risk.

[0054] If the abnormality classification result is a medium abnormality or the fault risk assessment result is a medium risk, the risk level is determined to be medium risk.

[0055] If the abnormality classification result is a high-level abnormality or the fault risk assessment result is a high risk, the risk level is determined to be high risk.

[0056] If there is a conflict between the abnormality classification result and the fault risk assessment result, the one with a higher risk level will be used as the risk level.

[0057] The alert mechanism is triggered according to the risk level, including:

[0058] If the risk level is low, a low-level warning signal is triggered to prompt maintenance personnel to pay attention and record the abnormal situation but do not trigger an alarm.

[0059] If the risk level is medium, an intermediate warning signal is triggered to notify maintenance personnel to conduct an inspection, and an intermediate alarm is generated, and an audio warning is issued through the monitoring system to indicate the possibility of potential failure.

[0060] If the risk level is high, a high-level warning signal will be triggered, an emergency alarm will be activated, an alarm message will be sent to the relevant person in charge, and on-site maintenance personnel will be notified to take emergency investigation and disposal measures.

[0061] The beneficial effects of the technical solution of the present invention are:

[0062] 1. The present invention realizes real-time monitoring of key operating parameters of the cable and external environmental data by combining the self-learning perception model and the environmental impact model; according to the real-time changes of the cable operation data, the normal state of the cable under different environmental conditions is automatically identified, so as to accurately determine the abnormal situation and reduce the risk of false alarm and missed alarm.

[0063] 2. Through the analysis of self-learning perception models and historical data, the present invention can adaptively adjust the upper and lower thresholds of cable operating parameters based on changes in environmental conditions; the dynamic threshold setting method ensures the monitoring accuracy in different environments, so that the cable operating parameters can be kept within a safe range even when the environment fluctuates, thereby improving the stability of cable operation.

[0064] 3. The present invention provides a multi-level hierarchical warning mechanism by determining low, medium and high risk levels; for low-risk, medium-risk and high-risk situations, different levels of alarms are generated and corresponding response measures are taken; the hierarchical warning method enables maintenance personnel to take appropriate maintenance and protection measures according to the risk level, avoiding unnecessary interference and improving the response speed to sudden abnormalities.

[0065] 4. Furthermore, through the trend prediction function of the LSTM model, the present invention can identify the changing trend of the cable operation status in advance and conduct fault risk assessment; based on the analysis of the predicted values, it can judge the possible abnormalities of the key operating parameters of the cable in the future, issue early warning signals in advance, and prevent faults from occurring.

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0068] Figure 1 A flow chart of an intelligent sensing method for monitoring key operating parameters of a cable provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0070] See also Figure 1 , Figure 1 A flow chart of an intelligent sensing method for monitoring key operating parameters of a cable is provided for an embodiment of the present invention.

[0071] In this embodiment, an intelligent sensing method for monitoring key operating parameters of a cable includes step S101, step S102, step S103, step S104, step S105, step S106, step S107 and step S108.

[0072] Before step S101, the method further includes: constructing an environmental impact model of the cable status, the specific steps of which are:

[0073] The key operating parameters of the third cable and the third external environment data are preprocessed respectively to obtain the preprocessed key operating parameters of the third cable and the third external environment data; the preprocessing includes data cleaning, denoising, outlier identification and elimination, and standardization; the key operating parameters of the third cable refer to the cable operation status data obtained and saved in the second historical operation stage, including the cable temperature, current, voltage and stress in the second historical operation stage; the third external environment data refers to the historical environment data corresponding to the key operating parameters of the third cable, including the ambient temperature, ambient humidity, air pressure and vibration in the second historical operation stage.

[0074] The preprocessed third cable key operating parameters are correlated with the third external environment data to determine the correlation calculation results between the parameters.

[0075] It should be noted that the correlation calculation uses the Pearson coefficient, and its calculation formula is:

[0076]

[0077] In the formula, and They represent the key operating parameters of the cable and the external environment parameters at the i-th moment, and They represent the means of the key operating parameters of the cable and the external environmental data respectively. By calculating r, the linear and nonlinear relationship between the cable operating status and the external environmental parameters can be evaluated. r represents the result of the correlation calculation.

[0078] Based on the correlation calculation results, feature extraction is performed on the third external environment data and the third cable key operating parameters with significant correlation to obtain the impact feature; the impact feature is the feature of the impact of the third external environment data on the third cable key operating parameters.

[0079] It should be noted that if the absolute value of the correlation coefficient is greater than 0.7, it is considered that the external environmental data has a significant correlation with the cable operating status; based on the above correlation calculation results, the external environmental data and cable parameters that are significantly correlated with the key operating parameters of the cable are extracted, and the significantly correlated environmental data are subjected to feature extraction through principal component analysis; the characteristic data that affect the cable operating status are screened out, and the screened characteristic data are the influencing features; the influencing features represent the quantitative expression of the relationship between the external environmental variables and the key operating parameters of the cable.

[0080] An environmental impact model of the cable status is established based on the impact characteristics, the pre-processed third cable key operating parameters and the third external environment data.

[0081] Step S101, obtaining the first key operating parameters of the cable and the first external environment data, and preprocessing the first key operating parameters of the cable and the first external environment data respectively; the first key operating parameters of the cable refer to the cable operating state data obtained and saved in the first historical operating stage, including the cable temperature, current, voltage and stress in the first historical operating stage; the first external environment data refers to the historical environment data corresponding to the first key operating parameters of the cable, including the ambient temperature, ambient humidity, air pressure and vibration in the first historical operating stage, specifically including:

[0082] Sensors are deployed to obtain key operating parameters of the first cable and first external environmental data. After obtaining, the key operating parameters of the first cable and the first external environmental data are preprocessed respectively, and the preprocessing includes data cleaning, denoising, outlier identification and elimination, and standardization.

[0083] It should be noted that data cleaning, denoising, outlier identification and elimination, and standardization are specifically as follows:

[0084] Data cleaning: cleaning the first cable key parameters and the first external environment data collected by the sensor. By checking the data integrity and removing the null values ​​and duplicate values ​​in the data, the integrity of the data set is ensured.

[0085] De-noising: Since the acquisition process may be affected by electromagnetic interference and environmental noise factors, the low-pass filtering signal processing method is used to denoise the data, thereby filtering out high-frequency noise signals and extracting effective fluctuation information of key cable operating parameters; in addition, for some high-frequency noise in external environmental data, the wavelet denoising method is used to further remove background noise.

[0086] Outlier identification and elimination, for outlier identification, a box plot method combined with Z-score scoring is used to identify outliers in the data; specifically, by calculating the joint distribution range of the first cable key operating parameters and the first external environment data, it is determined whether the data points deviate from the normal fluctuation range; the deviated data points are marked and eliminated.

[0087] Standardization processing, since the dimensions of key cable parameters and external environment data are different, in order to improve the comparability of the data, the Min-Max standardization method is used to scale all data to the same numerical range; in addition, for the specific requirements of different sensors, Z-score standardization is used as an alternative in the specific requirements to make the data more in line with the input requirements of the model processing.

[0088] Step S102: input the preprocessed first cable key operating parameter and the first external environment data into the environmental impact model respectively to generate environmental impact dynamic data.

[0089] Here, specifically include:

[0090] The preprocessed key operating parameters of the first cable and the first external environment data are respectively input into the environmental impact model, and the dynamic impact of the first external environment data on the key operating parameters of the first cable is evaluated to obtain a dynamic impact evaluation result.

[0091] According to the dynamic impact assessment results, combined with the historical average and associated weights of environmental factors, the dynamic environmental impact data is generated. The generation formula is:

[0092]

[0093] In the formula, represents the dynamic data of environmental impact at the i-th time point, represents the jth external environment parameter value at the i-th time point, represents the historical mean of the jth external environment parameter, represents the association weight of the jth external environment parameter, represents the dynamic impact assessment result of the jth external environmental parameter, represents the model intercept term; represents the error term.

[0094] The environmental impact dynamic data includes the impact degree and trend change of the first external environmental data on the key operating parameters of the first cable.

[0095] It should be noted that before step S103, the process also includes: constructing a self-learning perception model based on the pre-processed third cable key operating parameters and the third external environment data, and the specific steps are:

[0096] Based on the preprocessed third cable key operating parameters and the third external environment data, a self-learning perception model is constructed; after the model is constructed, the self-learning perception model is trained through an unsupervised learning algorithm; in order to improve the adaptability and perception accuracy of the model, the K-means clustering algorithm is used to perform cluster analysis on the cable operation data under different environmental conditions to identify the normal operation range of the cable in various environments; at the same time, the Gaussian mixture model is introduced to further identify the probability distribution of the cable operation data, so as to more accurately distinguish between the normal state and the potential abnormal state.

[0097] During the model training process, the K-means clustering algorithm clusters similar cable operation data into one category to construct normal operating status groups under different environmental conditions; while the Gaussian mixture model evaluates the characteristics of each group of data points through probability distribution, so as to automatically identify the normal operating status range of the cable under different environmental conditions; through unsupervised learning, data can be adaptively analyzed without the need for manual setting of rules, ensuring that the model can dynamically adapt to changing environments.

[0098] Step S103: input the preprocessed first cable key operating parameter and the first external environment data into the self-learning perception model for correlation analysis, and output the normal value range of the cable key operating parameter, specifically including:

[0099] An unsupervised learning algorithm is used to input the preprocessed first cable key operating parameters and the first external environment data into the self-learning perception model. Through cluster analysis and distribution learning, the normal value range of the cable key operating parameters is generated. The generation formula is:

[0100]

[0101]

[0102] In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable. Indicates the lower limit of the normal value range of the key operating parameters of the cable. represents the historical mean of the key operating parameters of the i-th cable, represents the correlation strength of the external environment parameters to the i-th cable parameters; represents the jth external environment parameter value at the i-th time point, represents the historical mean of the jth external environment parameter, represents the range expansion factor, and n represents the total number of external environment parameters.

[0103] Step S104: Based on the normal value range of the key operating parameters of the cable and in combination with the dynamic data of environmental impact, the upper and lower thresholds of the key operating parameters of the cable are dynamically adjusted, specifically including:

[0104] According to the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the fluctuation range of the key operating parameters of the cable is dynamically adjusted, and the initial threshold range of the key operating parameters of the cable is set according to the fluctuation range.

[0105] Combined with the operating data of the key operating parameters of the cable, the initial threshold range is adaptively adjusted to generate the upper and lower thresholds of the key operating parameters of the cable.

[0106] According to the changing trend of the second external environment data and the changing trend of the second cable key operating parameters, the upper and lower limit thresholds of the cable key operating parameters are dynamically adjusted, and the adjustment formula is:

[0107]

[0108]

[0109] In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable, which is used to define the maximum acceptable value of the cable operating status; It indicates the lower limit of the normal value range of the key operating parameters of the cable, and is used to define the minimum acceptable value of the cable operating status; Indicates dynamic data of environmental impact, reflecting the immediate impact of external environmental factors on the operating status of the cable; It represents the dynamic impact coefficient, reflecting the weight of environmental impact on threshold adjustment; Represents the environmental data trend adjustment coefficient, which is used to adjust the impact of the predicted trend of cable parameters on the upper and lower thresholds; Indicates the changing trend of the dynamic data of environmental impact, and is used to reflect the long-term changing trend of the second external environmental data; Indicates the change trend of the key operating parameters of the second cable, which is used to reflect the short-term fluctuation trend of the cable operating status; It represents the parameter trend adjustment coefficient, reflecting the weight of the change trend of the key operating parameters of the cable on the threshold adjustment; Indicates the upper threshold of the key operating parameters of the cable. Indicates the lower threshold of the key operating parameters of the cable.

[0110] It should be noted that during the operation, the pre-processed second cable key operating parameters and the second external environment data are continuously input into the environmental impact model; the environmental impact model calculates the degree of influence of environmental changes on the cable operating parameters through real-time dynamic data, and feeds back to the self-learning perception model; according to the real-time changes in the environment, the upper and lower limit threshold intervals of the key operating parameters of the cable are dynamically updated, so that it can adapt to external environmental fluctuations in a timely manner and further improve its sensitivity to abnormal conditions.

[0111] Step S105, obtain the second cable key operating parameters and the second external environment data; the second cable key operating parameters refer to the key operating data obtained by the cable in the real-time operating state, including cable temperature, current, voltage and stress; the second external environment data refers to the external environment data obtained by the cable in the real-time operating state, including ambient temperature, ambient humidity, air pressure and vibration.

[0112] It should be noted that the acquisition of the key operating parameters of the second cable and the second external environment data is achieved by real-time data transmission through a multi-point sensor network deployed; the network is deployed in the cable operation nodes and the surrounding environment, and collects the key operating parameters of the second cable and the second external environment data in real time, and transmits them through the data acquisition terminal.

[0113] Step S106, comparing the second cable key operating parameter with the upper and lower limit thresholds of the dynamically adjusted cable key operating parameter, and making an abnormal classification determination, specifically including:

[0114] The upper and lower limit thresholds of the dynamically adjusted key operating parameters of the cable are compared with the second key operating parameters of the cable to determine whether the second key operating parameters of the cable exceed the upper and lower limit thresholds.

[0115] If it is within the threshold range, it is determined that the second cable key operating parameter is in a normal state.

[0116] If it exceeds the threshold range, the second cable key operating parameter is determined to be in an abnormal state, and an abnormal classification determination is performed for the second cable key operating parameter that exceeds the threshold, specifically:

[0117] The abnormality classification results include low-level abnormalities, medium-level abnormalities and high-level abnormalities.

[0118] If the value exceeding the threshold is within the set low-level abnormality range, it is determined to be a low-level abnormality and a low-level abnormality notification is generated.

[0119] If the value exceeding the threshold is within the set intermediate abnormal range, it is judged as an intermediate abnormality and an intermediate abnormality notification is generated.

[0120] If the value exceeding the threshold is within the set high-level exception range, it is determined to be a high-level exception and a high-level exception notification is generated.

[0121] Step S107: input the second key operating parameter of the cable and the second external environment data into the LSTM model, predict and output the development trend of the key operating parameter of the cable, and evaluate the potential failure risk according to the predicted development trend, specifically including:

[0122] The second key operating parameters of the cable and the second external environment data are input into the LSTM model to predict the changing trend of the key operating parameters of the cable in the future and obtain the predicted development trend of the key operating parameters of the cable.

[0123] According to the data fluctuation trend in the predicted development trend, combined with the upper and lower limit thresholds of the key operating parameters of the cable, the abnormal situation of the second cable key operating parameters in the future is judged to generate a fault risk assessment result; the fault risk assessment result includes slight risk, moderate risk and high risk.

[0124] It should be noted that historical data related to the key operating parameters of the cable and external environmental data are collected and used to construct a training data set; the training data set contains time series information, which is used as the input of the LSTM model; the LSTM model is suitable for modeling and predicting the changing trends of the key operating parameters of the cable in different periods.

[0125] It should be further explained that after the training of the LSTM model is completed, the real-time collected key operating parameters of the second cable and the second external environment data are input into the trained LSTM model; the LSTM model captures the temporal dependency of the cable operating status based on the input data, and predicts the changing trend of the key operating parameters of the second cable in the future; the prediction results are output in the form of a predicted value sequence, indicating the expected trend of the key operating parameters of the second cable.

[0126] It should be further explained that the failure risk of the cable is further evaluated based on the prediction value sequence generated by the LSTM model; by analyzing the fluctuation trend in the prediction value sequence and combining the upper and lower limit thresholds set previously, it is determined whether the cable will have abnormal conditions in the future; if the prediction value shows that the key operating parameters of the second cable exceed the safety range for a certain period of time, it is necessary to evaluate the potential risk level.

[0127] Step S108, determining the risk level according to the abnormal classification determination result and the potential failure risk, and triggering an alarm mechanism based on the risk level, specifically including:

[0128] Based on the abnormality classification results and fault risk assessment results, the risk level of the abnormal situation is determined, and the risk level includes three levels: low risk, medium risk and high risk.

[0129] If the abnormality classification result is a low-level abnormality and the fault risk assessment result is a slight risk, the risk level is determined to be low risk.

[0130] If the abnormality classification result is a medium abnormality or the fault risk assessment result is a medium risk, the risk level is determined to be medium risk.

[0131] If the abnormality classification result is a high-level abnormality or the fault risk assessment result is a high risk, the risk level is determined to be high risk.

[0132] If there is a conflict between the abnormality classification result and the fault risk assessment result, the one with a higher risk level will be used as the risk level.

[0133] The alert mechanism is triggered according to the risk level, including:

[0134] If the risk level is low, a low-level warning signal is triggered to prompt maintenance personnel to pay attention and record the abnormal situation but do not trigger an alarm.

[0135] If the risk level is medium, an intermediate warning signal is triggered to notify maintenance personnel to conduct an inspection, and an intermediate alarm is generated, and an audio warning is issued through the monitoring system to indicate the possibility of potential failure.

[0136] If the risk level is high, a high-level warning signal will be triggered, an emergency alarm will be activated, an alarm message will be sent to the relevant person in charge, and on-site maintenance personnel will be notified to take emergency investigation and disposal measures.

[0137] It should be noted that low risk corresponds to slight environmental fluctuations or brief deviations from the key operating parameters of the second cable, and has a low correlation; this risk level corresponds to a low-level abnormality, indicating that the key operating parameters of the second cable have a slight deviation within the range beyond the upper and lower limit thresholds; the low-risk numerical range deviates from the normal value range of the key operating parameters of the second cable by no more than 10%; the low-risk fluctuation lasts for a short time and does not affect the normal operation of the cable, generating a low-level abnormality warning, which only prompts maintenance personnel to pay attention and observe; no immediate action is required.

[0138] Medium risk corresponds to moderate abnormality and moderate failure risk; this level of risk is related to the intensified fluctuations in the environment, indicating that the frequency or amplitude of the deviation of the key operating parameters of the second cable from the normal range begins to increase, and there is a potential medium-level risk; the numerical range of medium risk is between 10% and 30% of the deviation of the key operating parameters of the second cable from the normal range; medium-risk fluctuations affect the stability of the cable, last slightly longer and show a trend of repeated fluctuations or intensification; an intermediate abnormality warning is generated to remind maintenance personnel to check the cable operation status as soon as possible to prevent the risk from escalating.

[0139] High risk means that there is a significant abnormality in the cable operation status, corresponding to advanced abnormalities and high-risk fault assessments; high risk is strongly associated with severe environmental fluctuations or high-load conditions of the cable, which usually means that the key operating parameters of the second cable deviate significantly from the threshold range and show a trend of continuous deterioration; the numerical range of high risk is when the key operating parameters of the cable deviate from the normal range by more than 30%; high risk may cause major failures or damage cable equipment; when high risk is identified, an advanced abnormality alarm is immediately generated, the emergency warning mechanism is activated, and maintenance personnel are notified to take emergency inspection and disposal measures to ensure the safety of cable operation.

[0140] This method collects the key operating parameters of the cable and external environmental data, builds a self-learning perception model and an environmental impact model, and realizes dynamic monitoring of the cable status. This method is based on a multi-level abnormality judgment and graded early warning mechanism, and can dynamically adjust the threshold according to the real-time change trend of the key operating parameters of the cable and the external environmental data, and predict the development trend of the cable status through machine learning algorithms such as LSTM. This method can not only improve the accuracy of cable operation status monitoring, but also conduct risk assessment of potential faults, take preventive measures in time, and significantly improve the operation safety and reliability of the cable.

[0141] At this point, an intelligent sensing method for monitoring key operating parameters of cables has been completed.

[0142] The above is only a specific implementation of the present invention, but the protection scope of the embodiments of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the embodiments of the present invention, which should be included in the protection scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent sensing method for monitoring key operating parameters of a cable, characterized in that: The steps include: Acquire the first key operating parameters of the cable and the first external environment data, and pre-process the first key operating parameters of the cable and the first external environment data respectively; the first key operating parameters of the cable refer to the cable operating status data acquired and saved in the first historical operating stage, including the cable temperature, current, voltage and stress in the first historical operating stage; the first external environment data refer to the historical environment data corresponding to the first key operating parameters of the cable, including the ambient temperature, ambient humidity, air pressure and vibration in the first historical operating stage; The pre-processed first cable key operating parameters and the first external environment data are respectively input into the environmental impact model to generate environmental impact dynamic data, specifically including: Inputting the preprocessed key operating parameters of the first cable and the first external environment data into the environmental impact model respectively, evaluating the dynamic impact of the first external environment data on the key operating parameters of the first cable, and obtaining a dynamic impact evaluation result; According to the dynamic impact assessment results, combined with the historical average and associated weights of environmental factors, the dynamic environmental impact data is generated. The generation formula is: In the formula, represents the dynamic data of environmental impact at time point o, represents the jth external environment parameter value at the oth time point, represents the historical mean of the jth external environment parameter, represents the association weight of the jth external environment parameter, represents the dynamic impact assessment result of the jth external environmental parameter, represents the model intercept term, represents the error term; The environmental impact dynamic data include the impact degree and trend change of the first external environmental data on the key operating parameters of the first cable; Inputting the preprocessed first key operating parameter of the cable and the first external environment data into the self-learning perception model for correlation analysis, and outputting the normal value range of the key operating parameter of the cable; Based on the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the upper and lower thresholds of the key operating parameters of the cable are dynamically adjusted; Obtaining the second cable key operating parameters and the second external environment data; the second cable key operating parameters refer to the key operating data obtained when the cable is in real-time operation, including cable temperature, current, voltage and stress; the second external environment data refer to the external environment data obtained when the cable is in real-time operation, including ambient temperature, ambient humidity, air pressure and vibration; Compare the second cable key operating parameter with the upper and lower limit thresholds of the cable key operating parameter after dynamic adjustment to make abnormal classification judgment; Input the second cable key operating parameters and the second external environment data into the LSTM model, predict and output the development trend of the cable key operating parameters, and evaluate the potential failure risk according to the predicted development trend; The risk level is determined based on the abnormal classification results and potential failure risks, and the alarm mechanism is triggered based on the risk level.

2. According to claim 1, an intelligent sensing method for monitoring key operating parameters of a cable is characterized in that: Before the step of obtaining the first cable key operating parameter and the first external environment data, the method further includes: Construct the environmental impact model of cable status. The specific steps are as follows: Preprocessing the key operating parameters of the third cable and the third external environment data respectively to obtain the preprocessed key operating parameters of the third cable and the third external environment data; the preprocessing includes data cleaning, denoising, outlier identification and elimination, and standardization; the key operating parameters of the third cable refer to the cable operation status data obtained and saved in the second historical operation stage, including the cable temperature, current, voltage and stress in the second historical operation stage; the third external environment data refers to the historical environment data corresponding to the key operating parameters of the third cable, including the ambient temperature, ambient humidity, air pressure and vibration in the second historical operation stage; Performing correlation calculation on the preprocessed third cable key operating parameters and the third external environment data to determine the correlation calculation results between the parameters; Based on the correlation calculation result, feature extraction is performed on the third external environment data and the third cable key operating parameters with significant correlation to obtain the impact feature; the impact feature is the feature of the impact of the third external environment data on the third cable key operating parameters; An environmental impact model of the cable status is established based on the impact characteristics, the pre-processed third cable key operating parameters and the third external environment data.

3. According to claim 1, an intelligent sensing method for monitoring key operating parameters of a cable is characterized in that: The pre-processed first cable key operating parameter and the first external environment data are respectively input into the self-learning perception model for correlation analysis, and the normal value range of the cable key operating parameter is output, specifically including: An unsupervised learning algorithm is used to input the preprocessed first cable key operating parameters and the first external environment data into the self-learning perception model. Through cluster analysis and distribution learning, the normal value range of the cable key operating parameters is generated. The generation formula is: In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable. Indicates the lower limit of the normal value range of the key operating parameters of the cable. represents the historical mean of the key operating parameters of the i-th cable, represents the correlation strength of the external environment parameters to the i-th cable parameters; represents the jth external environment parameter value at the oth time point, represents the historical mean of the jth external environment parameter, represents the range expansion factor, and n represents the total number of external environment parameters.

4. The intelligent sensing method for monitoring key operating parameters of a cable according to claim 3 is characterized in that: Based on the normal value range of the key operating parameters of the cable and combined with the dynamic data of environmental impact, the upper and lower limit thresholds of the key operating parameters of the cable are dynamically adjusted, including: According to the normal value range of the key operating parameters of the cable, combined with the dynamic data of environmental impact, the fluctuation range of the key operating parameters of the cable is dynamically adjusted, and the initial threshold range of the key operating parameters of the cable is set according to the fluctuation range; Combined with the operation data of the key operation parameters of the cable, the initial threshold range is adaptively adjusted to generate the upper and lower thresholds of the key operation parameters of the cable; According to the changing trend of the second external environment data and the changing trend of the second cable key operating parameters, the upper and lower limit thresholds of the cable key operating parameters are dynamically adjusted, and the adjustment formula is: In the formula, Indicates the upper limit of the normal value range of the key operating parameters of the cable. Indicates the lower limit of the normal value range of the key operating parameters of the cable; represents the dynamic data of environmental impact at time point o, It represents the dynamic impact coefficient, reflecting the weight of environmental impact on threshold adjustment; Represents the environmental data trend adjustment coefficient, which is used to adjust the impact of the predicted trend of cable parameters on the upper and lower thresholds; Indicates the changing trend of dynamic data of environmental impact and reflects the long-term changing trend of the second external environment data; Indicates the change trend of the key operating parameters of the second cable, which is used to reflect the short-term fluctuation trend of the cable operating status; It represents the parameter trend adjustment coefficient, reflecting the weight of the change trend of the key operating parameters of the cable on the threshold adjustment; Indicates the upper threshold of the key operating parameters of the cable. Indicates the lower threshold of the key operating parameters of the cable.

5. The intelligent sensing method for monitoring key operating parameters of a cable according to claim 1 is characterized in that: The second cable key operating parameters are compared with the upper and lower limit thresholds of the cable key operating parameters after dynamic adjustment to make abnormal classification judgment, specifically including: Compare the upper and lower limit thresholds of the dynamically adjusted key operating parameters of the cable with the second key operating parameters of the cable to determine whether the second key operating parameters of the cable exceed the upper and lower limit thresholds; If it is within the threshold range, it is determined that the key operating parameter of the second cable is in a normal state; If it exceeds the threshold range, the second cable key operating parameter is determined to be in an abnormal state, and an abnormal classification determination is performed for the second cable key operating parameter that exceeds the threshold, specifically: The abnormality classification results include low-level abnormality, medium-level abnormality and high-level abnormality; If the value exceeding the threshold is within the set low-level abnormal range, it is determined as a low-level abnormality and a low-level abnormality notification is generated; If the value exceeding the threshold is within the set intermediate abnormal range, it is judged as an intermediate abnormality and an intermediate abnormality notification is generated; If the value exceeding the threshold is within the set high-level exception range, it is determined to be a high-level exception and a high-level exception notification is generated.

6. The intelligent sensing method for monitoring key operating parameters of a cable according to claim 1 is characterized in that: The second cable key operating parameters and the second external environment data are input into the LSTM model to predict and output the development trend of the cable key operating parameters, and the potential failure risk is evaluated according to the predicted development trend, including: Input the second key operating parameters of the cable and the second external environment data into the LSTM model, predict the change trend of the key operating parameters of the cable in the future, and obtain the predicted development trend of the key operating parameters of the cable; According to the data fluctuation trend in the predicted development trend, combined with the upper and lower limit thresholds of the key operating parameters of the cable, the abnormal situation of the second cable key operating parameters in the future is judged to generate a fault risk assessment result; the fault risk assessment result includes slight risk, moderate risk and high risk.

7. The intelligent sensing method for monitoring key operating parameters of a cable according to claim 1 is characterized in that: The risk level is determined based on the abnormal classification results and potential failure risks, and the alarm mechanism is triggered based on the risk level, including: Based on the abnormality classification results and fault risk assessment results, determine the risk level of the abnormal situation, which includes three levels: low risk, medium risk and high risk; If the abnormality classification result is a low-level abnormality and the fault risk assessment result is a slight risk, the risk level is determined to be low risk; If the abnormality classification result is a medium abnormality or the fault risk assessment result is a medium risk, the risk level is determined to be medium risk; If the abnormality classification result is a high-level abnormality or the fault risk assessment result is a high risk, the risk level is determined to be high risk; If there is a conflict between the abnormality classification result and the fault risk assessment result, the one with a higher risk level shall be used as the risk level; The alert mechanism is triggered according to the risk level, including: If the risk level is low, a low-level warning signal is triggered to prompt maintenance personnel to pay attention and record the abnormal situation but do not trigger an alarm; If the risk level is medium, an intermediate warning signal is triggered to notify maintenance personnel to conduct an inspection, and an intermediate alarm is generated, with an audio warning issued through the monitoring system to indicate the possibility of potential failure; If the risk level is high, a high-level warning signal will be triggered, an emergency alarm will be activated, an alarm message will be sent to the relevant person in charge, and on-site maintenance personnel will be notified to take emergency investigation and disposal measures.

Images