Cable hidden danger prediction and assessment platform based on big data analysis

Abstract

The present invention provides a cable hidden danger prediction and evaluation platform based on big data analysis, including: a data retrieval and analysis module, which retrieves and analyzes historical cable safety monitoring data sets, divides the historical cable safety monitoring data sets according to a number of safety monitoring dimensions, and obtains a number of sub-historical cable safety monitoring data sets; a network construction module, which identifies each sub-historical cable safety monitoring data set respectively, and constructs a cable hidden danger evaluation prediction path of the corresponding dimension; a model construction module, which constructs a target model; a cable hidden danger prediction and evaluation module, which collects the safety monitoring data of the cable in real time, and transmits the safety monitoring data of the cable to the target model for prediction and evaluation, and outputs a prediction and evaluation report, which is transmitted to the monitoring terminal, and automatically matches the maintenance auxiliary information in the preset maintenance library based on the prediction and evaluation report; thereby helping to improve the efficiency of maintenance, avoid the occurrence of major accidents, and ensure the safe operation of the cable.

Description

Technical Field

[0001] The present invention relates to the technical field of cable hidden danger prediction and assessment, and in particular to a cable hidden danger prediction and assessment platform based on big data analysis. Background Art

[0002] At present, cable is an electrical device used to transmit power or signals. It consists of one or more insulated wires. Cable has become an indispensable part of life. It covers almost all fields that require power or signal transmission, such as: power supply and lighting in building electrical, power cables for motors and transformers in the industrial field, and railway signal and power supply cables in transportation. Therefore, in order to reduce the possibility of accidents, ensure the safety of personnel and equipment, and reduce maintenance costs during the operation of cables, cable hidden danger prediction and assessment have become inevitable safeguards for the healthy operation of cables.

[0003] However, in the process of cable hidden danger prediction and assessment, it is difficult to obtain data, which is not conducive to the staff to predict and evaluate the cable hidden dangers according to the current data situation. At the same time, the prediction and evaluation of cable hidden dangers based on the staff's experience not only wastes manpower and cannot guarantee the timeliness of the prediction, but also greatly reduces the accuracy of the evaluation. The cable hidden danger model in the existing technology is not combined with big data analysis and learning, which makes the existing cable hidden danger model prediction limited and not intelligent, thereby reducing the efficiency of cable hidden danger prediction and evaluation;

[0004] Therefore, in order to overcome the above technical problems, the present invention provides a cable hidden danger prediction and assessment platform based on big data analysis. Summary of the invention

[0005] The present invention provides a cable hidden danger prediction and evaluation platform based on big data analysis, which is used to retrieve and analyze historical cable safety detection data and determine several safety detection dimensions, thereby effectively realizing the division of historical cable safety detection data, thereby ensuring detailed analysis of several sub-historical cable safety detection data sets, and thus improving the comprehensiveness of cable hidden danger prediction and evaluation. By constructing and learning the cable hidden danger evaluation prediction path corresponding to each safety detection dimension, a target model is effectively constructed, and effective analysis of real-time collected cable safety monitoring data is realized, which is conducive to identifying, prejudging and locating cable hidden dangers, timely discovering early defects and predicting defect development trends, thereby improving the timeliness and intelligence of cable hidden danger identification. By transmitting the generated prediction and evaluation report to the monitoring terminal, users can monitor the cable in real time. By automatically matching the maintenance auxiliary information of the preset maintenance library, it is beneficial to improve the efficiency of maintenance, avoid the occurrence of major accidents, and ensure the safe operation of the cable.

[0006] A cable hidden danger prediction and assessment platform based on big data analysis, including:

[0007] A data retrieval and analysis module is used to retrieve and analyze historical cable safety monitoring data sets, determine a number of safety monitoring dimensions, and divide the historical cable safety monitoring data sets according to the several safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets;

[0008] The network construction module is used to identify each sub-historical cable safety monitoring data set and construct a cable hidden danger assessment prediction path of the corresponding dimension;

[0009] The model building module is used to learn several cable hidden danger assessment prediction paths and build a target model;

[0010] The cable hidden danger prediction and evaluation module is used to collect the cable safety monitoring data in real time, and transmit the cable safety monitoring data to the target model for prediction and evaluation, and output the prediction and evaluation report, and transmit it to the monitoring terminal. At the same time, when there are safety hazards, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report.

[0011] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a data retrieval and analysis module, comprises:

[0012] A data retrieval unit, used to retrieve historical cable safety monitoring data sets;

[0013] A data analysis unit, used to analyze the retrieved historical cable safety monitoring data and determine several safety monitoring dimensions;

[0014] The data division unit is used to divide the historical cable safety monitoring data set according to a number of safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets.

[0015] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, the data analysis unit comprises:

[0016] A keyword determination subunit is used to analyze the retrieved historical safety monitoring data and determine the monitoring keywords of the historical safety monitoring data and the data type keywords of the monitoring data;

[0017] The matching subunit is used to match the monitoring keywords of the historical safety monitoring data with the type keywords of the monitoring data, and output several safety monitoring dimensions corresponding to the historical cable safety monitoring data set according to the matching results.

[0018] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, the data division unit includes:

[0019] The dimension reading subunit is used to read a number of security monitoring dimensions, determine the dimension identifier of each security monitoring dimension, and at the same time, read the data identifier of each historical security monitoring data in the historical security monitoring data set;

[0020] A similarity calculation subunit is used to perform similarity calculation on the data identifier of each historical safety monitoring data and the dimension identifier of each safety monitoring dimension, and determine the identifier similarity of each dimension corresponding to each historical safety monitoring data;

[0021] A comparison subunit, used to obtain a preset threshold value, and use the historical security monitoring data with identification similarity greater than the preset threshold value as the historical security monitoring data under the corresponding dimension;

[0022] The data division subunit is used to complete the division of the historical cable safety monitoring data set according to the comparison result, and obtain several sub-historical cable safety monitoring data sets.

[0023] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a network construction module, includes:

[0024] A data identification unit is used to identify the sub-historical cable safety monitoring data set corresponding to each safety monitoring dimension, and determine a first sub-historical cable safety monitoring data set representing the safe operation of the cable and a second sub-historical safety monitoring data set representing the existence of a cable fault in the sub-historical cable safety monitoring data set;

[0025] The path construction unit is used to analyze the first sub-historical cable safety monitoring data to construct the first sub-cable hidden danger assessment prediction path. At the same time, the second sub-historical cable safety monitoring data is analyzed to construct the second sub-cable hidden danger assessment prediction path. According to the first sub-cable hidden danger assessment prediction path and the second sub-cable hidden danger assessment prediction path, a cable hidden danger assessment prediction path of corresponding dimensions is constructed.

[0026] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a data identification unit, comprises:

[0027] The cable safety assessment rule determination subunit is used to read the cable safety assessment rule corresponding to the safety monitoring dimension, and identify the sub-historical cable safety monitoring data set of the corresponding safety monitoring dimension according to the cable safety assessment rule;

[0028] Identify assessment subunits for:

[0029] Based on the identification results, the sub-historical cable safety data set that meets the cable safety assessment rules and the sub-historical cable safety data set that does not meet the cable safety assessment rules are output under the current safety monitoring dimension;

[0030] The sub-historical cable safety dataset that complies with the cable safety assessment rules is used as the first sub-historical cable safety monitoring dataset when the cable is in safe operation, and the sub-historical cable safety dataset that does not comply with the cable safety assessment rules is used as the second sub-historical safety monitoring dataset when a cable fault exists.

[0031] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a path construction unit, comprises:

[0032] The first analysis subunit is used for:

[0033] Obtaining the collection time of the first sub-historical cable safety monitoring data set;

[0034] Mapping the first sub-historical cable safety monitoring data in the first sub-historical cable safety monitoring data set on a first preset coordinate system according to the acquisition time, and obtaining a first dynamic change curve corresponding to the first sub-historical cable safety monitoring data set;

[0035] Reading the first dynamic change curve and extracting key information points in the first dynamic change curve;

[0036] Marking key information points in the first dynamic change curve to obtain a curve trend corresponding to each key information point in the first dynamic change curve;

[0037] A first path node is constructed according to key information points in the first dynamic change curve. At the same time, path information corresponding to the first path node is determined according to the curve trend corresponding to each key information point in the first dynamic change curve. Multiple first path nodes and the path information corresponding to each first path node are integrated to obtain a first sub-cable hidden danger assessment path.

[0038] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a path construction unit, comprises:

[0039] The second analysis subunit is used for:

[0040] The second sub-historical cable safety monitoring data set is read, and the second sub-historical cable safety monitoring data set is mapped on a second preset coordinate system according to the acquisition time of the second sub-historical cable safety monitoring data set to obtain a second dynamic change curve corresponding to the second sub-historical cable safety monitoring data set;

[0041] Reading the second dynamic change curve and extracting key information points in the second dynamic change curve;

[0042] Marking key information points in the second dynamic change curve, and obtaining a curve trend corresponding to each key information point in the second dynamic change curve;

[0043] Constructing a second path node according to key information points in the second dynamic change curve, and determining path information corresponding to the second path node according to the curve trend corresponding to each key point information in the second dynamic change curve;

[0044] Merging the plurality of second path nodes and the path information corresponding to each second path node to obtain a second sub-cable hidden danger assessment path;

[0045] The cable hidden danger prediction path determination subunit is used to:

[0046] Overlapping the first dynamic change curve and the second dynamic change curve according to corresponding acquisition times, and determining an intersection point between the first dynamic change curve and the second dynamic change curve;

[0047] Obtaining the change characteristics of the first dynamic change curve at the intersection point, and constructing a cable hidden danger prediction path according to the change characteristics;

[0048] The path construction subunit is used to integrate the first sub-cable hidden danger assessment path, the second sub-cable hidden danger assessment path and the cable hidden danger prediction path to obtain the cable hidden danger assessment prediction path of the corresponding dimension.

[0049] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a model building module, comprises:

[0050] A learning unit is used to read a number of safety monitoring dimensions, learn the corresponding cable hidden danger assessment paths for the several safety monitoring dimensions, and construct a sub-goal model under each safety monitoring dimension;

[0051] The association unit is used to associate the sub-target models under each sub-safety monitoring dimension according to the connection result to obtain the target model.

[0052] Preferably, a cable hidden danger prediction and assessment platform based on big data analysis, a cable hidden danger assessment module, comprises:

[0053] A data acquisition unit, used for real-time acquisition of safety monitoring data of the corresponding cables under each safety monitoring dimension;

[0054] A model analysis unit is used to transmit the safety monitoring data to the target model, identify the safety monitoring data according to the target model, and output a prediction evaluation report according to the corresponding safety monitoring dimension;

[0055] The transmission unit is used to transmit the prediction and evaluation report to the monitoring terminal. At the same time, when there is a safety hazard, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows: by retrieving and analyzing historical cable safety detection data and determining several safety detection dimensions, the division of historical cable safety detection data can be effectively realized, thereby ensuring detailed analysis of several sub-historical cable safety detection data sets, thereby improving the comprehensiveness of cable hidden danger prediction and evaluation, by constructing and learning the cable hidden danger evaluation prediction path corresponding to each safety detection dimension, thereby effectively constructing a target model, and realizing effective analysis of real-time collected cable safety monitoring data, which is conducive to identifying, predicting and locating cable hidden dangers, timely discovering early defects and predicting defect development trends, thereby improving the timeliness and intelligence of cable hidden danger identification, by transmitting the generated prediction and evaluation report to the monitoring terminal, users can monitor the cable in real time, and by automatically matching the maintenance auxiliary information of the preset maintenance library, it is beneficial to improve the efficiency of maintenance, avoid major accidents, and ensure the safe operation of the cable.

[0057] 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 specifically pointed out in this application document.

[0058] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0060] Figure 1 This is a structural diagram of a cable hidden danger prediction and assessment platform based on big data analysis in an embodiment of the present invention;

[0061] Figure 2 This is a structural diagram of a data retrieval and analysis module in a cable hidden danger prediction and assessment platform based on big data analysis in an embodiment of the present invention;

[0062] Figure 3 This is a structural diagram of a network construction module in a cable hidden danger prediction and assessment platform based on big data analysis in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0064] Embodiment 1:

[0065] This embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis. Figure 1 As shown, including:

[0066] A data retrieval and analysis module is used to retrieve and analyze historical cable safety monitoring data sets, determine a number of safety monitoring dimensions, and divide the historical cable safety monitoring data sets according to the several safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets;

[0067] A network construction module is used to identify each sub-historical cable safety monitoring data set and construct a cable hidden danger assessment prediction path corresponding to the safety monitoring dimension;

[0068] The model building module is used to learn several cable hidden danger assessment prediction paths and build a target model;

[0069] The cable hidden danger prediction and evaluation module is used to collect the cable safety monitoring data in real time, and transmit the cable safety monitoring data to the target model for prediction and evaluation, and output the prediction and evaluation report, and transmit it to the monitoring terminal. At the same time, when there are safety hazards, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report.

[0070] In this embodiment, the historical cable safety monitoring data set may be cable safety monitoring data retrieved from a network and a database stored in advance.

[0071] In this embodiment, several safety monitoring dimensions may include: cable aging and damage detection, temperature detection (used to detect cable overload status), humidity detection (used to detect cable moisture), etc.

[0072] In this embodiment, the sub-historical cable safety monitoring data set is the result of dividing the historical cable safety monitoring data set according to a number of safety monitoring dimensions, and the sub-historical cable safety monitoring data set corresponds one-to-one to the safety monitoring dimensions.

[0073] In this embodiment, the cable hidden danger assessment prediction path can be based on analyzing the sub-historical safety detection data to determine the data change state of the cable when it is in a safe operation state under the safety detection dimension and the data change state of the cable when the cable is processing a non-safe operation state under the safety detection dimension, thereby determining the path trend (i.e., data change trend) according to different change states, thereby forming a cable hidden danger assessment prediction path, wherein the cable hidden danger assessment prediction path corresponds one-to-one to the safety detection dimension.

[0074] In this embodiment, the target model can be used to evaluate and predict cable hidden dangers, thereby timely discovering early defects and predicting defect development trends.

[0075] In this embodiment, the preset maintenance library may be pre-set, including maintenance records of different faulty cables, so that the maintenance auxiliary information can be obtained through matching.

[0076] The working principle and beneficial effects of the above technical solution are: by retrieving and analyzing historical cable safety detection data and determining several safety detection dimensions, the historical cable safety detection data can be effectively divided, thereby ensuring detailed analysis of several sub-historical cable safety detection data sets, thereby improving the comprehensiveness of cable hidden danger prediction and evaluation, and by constructing and learning the cable hidden danger assessment prediction path corresponding to each safety detection dimension, so as to effectively construct the target model, and realize effective analysis of the real-time collected cable safety monitoring data, which is conducive to the identification, prediction and positioning of cable hidden dangers, timely discovery of early defects and prediction of defect development trends, thereby improving the timeliness and intelligence of cable hidden danger identification, and by transmitting the generated prediction and evaluation report to the monitoring terminal, the user can monitor the cable in real time, and by automatically matching the maintenance auxiliary information of the preset maintenance library, it is beneficial to improve the efficiency of maintenance, avoid major accidents, and ensure the safe operation of the cable.

[0077] Embodiment 2:

[0078] Based on Example 1, this example provides a cable hidden danger prediction and assessment platform based on big data analysis, such as Figure 2 As shown, the data retrieval and analysis module includes:

[0079] A data retrieval unit, used to retrieve historical cable safety monitoring data sets;

[0080] A data analysis unit, used to analyze the retrieved historical cable safety monitoring data and determine several safety monitoring dimensions;

[0081] The data division unit is used to divide the historical cable safety monitoring data set according to a number of safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets.

[0082] In this embodiment, the safety monitoring dimension is used to characterize the project category for monitoring historical cable safety monitoring data, including cable aging and damage detection, temperature detection, humidity detection, etc.

[0083] The working principle and beneficial effects of the above technical solution are: by analyzing the retrieved historical cable safety monitoring data, accurate and effective determination of the safety monitoring dimensions is achieved; secondly, the historical cable safety monitoring data set is divided according to the determined safety monitoring dimensions, and accurate and effective determination of the sub-historical cable safety monitoring data set is achieved, thereby effectively improving the accuracy of the processing of the historical cable safety monitoring data set and providing data support for cable hidden danger prediction.

[0084] Embodiment 3:

[0085] Based on Example 2, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and the data analysis unit includes:

[0086] A keyword determination subunit is used to analyze the retrieved historical safety monitoring data and determine the monitoring keywords of the historical safety monitoring data and the data type keywords of the monitoring data;

[0087] The matching subunit is used to match the monitoring keywords of the historical safety monitoring data with the type keywords of the monitoring data, and output several safety monitoring dimensions corresponding to the historical cable safety monitoring data set according to the matching results.

[0088] In this embodiment, the monitoring keyword may be a key data segment in the historical security monitoring data that can characterize the main content of the data.

[0089] In this embodiment, the data type keyword may be a data parameter that can characterize the type of monitored data.

[0090] The working principle and beneficial effects of the above technical solution are: by analyzing the retrieved historical security monitoring data, the monitoring keywords of the historical security monitoring data and the data type keywords of the monitoring data are realized, which provides a reference basis for determining the security monitoring dimensions; secondly, the monitoring keywords are matched with the type keywords of the monitoring data to realize accurate and effective determination of the security monitoring dimensions according to the matching results, thereby ensuring the comprehensiveness and effectiveness of obtaining several security monitoring dimensions.

[0091] Embodiment 4:

[0092] Based on Example 2, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and the data division unit includes:

[0093] The dimension reading subunit is used to read a number of security monitoring dimensions, determine the dimension identifier of each security monitoring dimension, and at the same time, read the data identifier of each historical security monitoring data in the historical security monitoring data set;

[0094] A similarity calculation subunit is used to perform similarity calculation on the data identifier of each historical safety monitoring data and the dimension identifier of each safety monitoring dimension, and determine the identifier similarity of each dimension corresponding to each historical safety monitoring data;

[0095] A comparison subunit, used to obtain a preset threshold value, and use the historical security monitoring data with identification similarity greater than the preset threshold value as the historical security monitoring data under the corresponding dimension;

[0096] The data division subunit is used to complete the division of the historical cable safety monitoring data set according to the comparison result, and obtain several sub-historical cable safety monitoring data sets.

[0097] In this embodiment, the dimension identifier is a marking symbol used to mark different security monitoring dimensions. Different security monitoring dimensions can be distinguished quickly and effectively through the dimension identifier.

[0098] In this embodiment, the data identifier is a marking symbol used to mark different historical safety monitoring data.

[0099] In this embodiment, the preset threshold is set in advance and is a measurement indicator used to measure whether there is a similar relationship between the dimension identifier and the data identifier, and can be adjusted.

[0100] The working principle and beneficial effects of the above technical scheme are: by reading several safety monitoring dimensions, the dimension identifier of each safety monitoring dimension is determined; secondly, the data identifier of each historical safety monitoring data in the historical safety monitoring data set is obtained, and the similarity between the data identifier of each safety monitoring data and the dimension identifier of each safety monitoring dimension is determined, so as to complete the division of the historical cable safety monitoring data set according to the similarity, thereby ensuring the accuracy and reliability of several sub-historical cable safety monitoring data sets, and effectively ensuring the effectiveness of the division of several sub-historical cable safety monitoring data sets, thereby improving the comprehensiveness of cable hidden danger prediction and assessment.

[0101] Embodiment 5:

[0102] Based on Example 1, this example provides a cable hidden danger prediction and assessment platform based on big data analysis, such as Figure 3 As shown, the network building blocks include:

[0103] A data identification unit is used to identify the sub-historical cable safety monitoring data set corresponding to each safety monitoring dimension, and determine a first sub-historical cable safety monitoring data set representing the safe operation of the cable and a second sub-historical safety monitoring data set representing the existence of a cable fault in the sub-historical cable safety monitoring data set;

[0104] The path construction unit is used to analyze the first sub-historical cable safety monitoring data to construct the first sub-cable hidden danger assessment prediction path. At the same time, the second sub-historical cable safety monitoring data is analyzed to construct the second sub-cable hidden danger assessment prediction path. According to the first sub-cable hidden danger assessment prediction path and the second sub-cable hidden danger assessment prediction path, a cable hidden danger assessment prediction path of corresponding dimensions is constructed.

[0105] In this embodiment, the first sub-historical cable safety monitoring data set may be all data in the sub-historical cable safety monitoring data set that can characterize the safe operation of the cable.

[0106] In this embodiment, the second sub-historical safety monitoring data set may be all data in the sub-historical cable safety monitoring data set that can characterize the presence of a cable fault.

[0107] In this embodiment, the first sub-cable hidden danger assessment prediction path may be to perform an assessment on the first sub-historical cable safety monitoring data to determine a data change state of the first sub-historical cable safety monitoring data.

[0108] In this embodiment, the second sub-cable hidden danger assessment prediction path may be a data change state of the second sub-historical cable safety monitoring data obtained after analyzing the second sub-historical cable safety monitoring data.

[0109] The working principle and beneficial effects of the above technical scheme are: by identifying the sub-historical cable safety monitoring data set corresponding to each safety monitoring dimension, the first sub-historical cable safety monitoring data set that characterizes the safe operation of the cable and the second sub-historical safety monitoring data set that characterizes the existence of a cable fault in the sub-historical cable safety monitoring data set can be accurately and effectively determined; secondly, the first sub-historical cable safety monitoring data and the second sub-historical cable safety monitoring data are analyzed respectively to accurately and effectively determine the first sub-cable hidden danger assessment prediction path and the second sub-cable hidden danger assessment prediction path; finally, a cable hidden danger assessment prediction path of corresponding dimensions is constructed according to the first sub-cable hidden danger assessment prediction path and the second sub-cable hidden danger assessment prediction path, thereby facilitating accurate and effective prediction of cable hidden dangers and ensuring the safe operation of the cable.

[0110] Embodiment 6:

[0111] Based on Example 5, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and the data identification unit includes:

[0112] The cable safety assessment rule determination subunit is used to read the cable safety assessment rule corresponding to the safety monitoring dimension, and identify the sub-historical cable safety monitoring data set of the corresponding safety monitoring dimension according to the cable safety assessment rule;

[0113] Identify assessment subunits for:

[0114] Based on the identification results, the sub-historical cable safety data set that meets the cable safety assessment rules and the sub-historical cable safety data set that does not meet the cable safety assessment rules are output under the current safety monitoring dimension;

[0115] The sub-historical cable safety dataset that complies with the cable safety assessment rules is used as the first sub-historical cable safety monitoring dataset when the cable is in safe operation, and the sub-historical cable safety dataset that does not comply with the cable safety assessment rules is used as the second sub-historical safety monitoring dataset when a cable fault exists.

[0116] In this embodiment, the cable safety assessment rule may be a criterion for assessing the safety of the cable.

[0117] The working principle and beneficial effects of the above technical scheme are: by determining the cable safety assessment rules corresponding to the safety monitoring dimensions, the sub-historical cable safety monitoring data sets of each safety monitoring dimension are identified according to the cable safety assessment rules, and the first sub-historical cable safety monitoring data set representing the safe operation of the cable and the second sub-historical safety monitoring data set representing the existence of cable faults are accurately and effectively determined, and the first sub-historical cable safety monitoring data set and the second sub-historical safety monitoring data set are accurately and effectively distinguished, thereby facilitating accurate and effective prediction and assessment of cable hidden dangers.

[0118] Embodiment 7:

[0119] Based on Example 5, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and a path construction unit, including:

[0120] The first analysis subunit is used for:

[0121] Obtaining the collection time of the first sub-historical cable safety monitoring data set;

[0122] Mapping the first sub-historical cable safety monitoring data in the first sub-historical cable safety monitoring data set on a first preset coordinate system according to the acquisition time, and obtaining a first dynamic change curve corresponding to the first sub-historical cable safety monitoring data set;

[0123] Reading the first dynamic change curve and extracting key information points in the first dynamic change curve;

[0124] Marking key information points in the first dynamic change curve to obtain a curve trend corresponding to each key information point in the first dynamic change curve;

[0125] A first path node is constructed according to key information points in the first dynamic change curve. At the same time, path information corresponding to the first path node is determined according to the curve trend corresponding to each key information point in the first dynamic change curve. Multiple first path nodes and the path information corresponding to each first path node are integrated to obtain a first sub-cable hidden danger assessment path.

[0126] In this embodiment, the first preset coordinate system is constructed in advance and is used to visualize the first sub-historical cable safety monitoring data, that is, the obtained first dynamic change curve represents the value change of the first sub-historical cable safety monitoring data.

[0127] In this embodiment, the key information point may be a key information representation point in the first dynamic change curve determined after reading the first dynamic change curve, for example, a value turning point.

[0128] In this embodiment, the first path node may be formed according to key information points in the first dynamic change curve.

[0129] In this embodiment, the path information may be a data change trend of a key information point in the first path node.

[0130] The working principle and beneficial effects of the above technical scheme are: by mapping the first sub-historical cable safety monitoring data in the first sub-historical cable safety monitoring data set on the first preset coordinate system, the corresponding first dynamic change curve is accurately and effectively generated according to the mapping result; secondly, the key information points are locked according to the first dynamic change curve, and the curve trend of the key information points is determined; at the same time, the first path node is constructed according to the key information point, and the path information corresponding to the first path node is accurately and effectively determined according to the curve trend of the key information point, so as to accurately and effectively determine the first sub-cable hidden danger assessment path, thereby facilitating accurate and effective prediction and evaluation of cable hidden dangers, and ensuring the accuracy of cable hidden danger prediction.

[0131] Embodiment 8:

[0132] Based on Example 5, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and a path construction unit, including:

[0133] The second analysis subunit is used for:

[0134] The second sub-historical cable safety monitoring data set is read, and the second sub-historical cable safety monitoring data set is mapped on a second preset coordinate system according to the acquisition time of the second sub-historical cable safety monitoring data set to obtain a second dynamic change curve corresponding to the second sub-historical cable safety monitoring data set;

[0135] Reading the second dynamic change curve and extracting key information points in the second dynamic change curve;

[0136] Marking key information points in the second dynamic change curve, and obtaining a curve trend corresponding to each key information point in the second dynamic change curve;

[0137] Constructing a second path node according to key information points in the second dynamic change curve, and determining path information corresponding to the second path node according to the curve trend corresponding to each key point information in the second dynamic change curve;

[0138] Merging the plurality of second path nodes and the path information corresponding to each second path node to obtain a second sub-cable hidden danger assessment path;

[0139] The cable hidden danger prediction path determination subunit is used to:

[0140] Overlapping the first dynamic change curve and the second dynamic change curve according to corresponding acquisition times, and determining an intersection point between the first dynamic change curve and the second dynamic change curve;

[0141] Obtaining the change characteristics of the first dynamic change curve at the intersection point, and constructing a cable hidden danger prediction path according to the change characteristics;

[0142] The path construction subunit is used to integrate the first sub-cable hidden danger assessment path, the second sub-cable hidden danger assessment path and the cable hidden danger prediction path to obtain the cable hidden danger assessment prediction path of the corresponding dimension.

[0143] In this embodiment, the second preset coordinate system is set in advance and is used to visualize the second sub-historical cable safety monitoring data, that is, to obtain the second dynamic change curve.

[0144] In this embodiment, the key information point in the second dynamic change curve may be a key point that can characterize the change of data values ​​in the second dynamic change curve.

[0145] In this embodiment, the second path node may be formed according to key information points in the second dynamic change curve, and is used to characterize the change of the key information points in the second dynamic change curve.

[0146] In this embodiment, the intersection point refers to an overlapping point where the first dynamic change curve and the second dynamic change curve exist for a long time during the acquisition.

[0147] In this embodiment, the change feature refers to the change in the value of the first dynamic change curve at the intersection point.

[0148] The working principle and beneficial effects of the above technical solution are: by reading the second sub-historical cable safety monitoring data set, the second dynamic change curve is accurately and effectively formulated, and the key information points and the curve trends corresponding to the key information points are accurately and effectively determined based on the obtained second dynamic change curve. Secondly, the second path node is constructed according to the key information point, and the path information corresponding to the second path node is locked according to the curve trend, so as to accurately and effectively determine the second sub-cable hidden danger assessment path according to the locking result. Finally, the first dynamic change curve and the second dynamic change curve are overlapped according to the corresponding acquisition time to lock the intersection point of the two, and determine the change characteristics of the first dynamic change curve at the intersection point, so as to accurately and effectively determine the cable hidden danger prediction path according to the change characteristics, and finally, the cable hidden danger assessment prediction path is accurately and effectively constructed according to the first sub-cable hidden danger assessment path, the second sub-cable hidden danger assessment path and the cable hidden danger prediction path, which provides convenience and guarantee for cable hidden danger prediction and assessment.

[0149] Embodiment 9:

[0150] Based on Example 1, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and the model building module includes:

[0151] A learning unit is used to read a number of safety monitoring dimensions, learn the corresponding cable hidden danger assessment paths for the several safety monitoring dimensions, and construct a sub-goal model under each safety monitoring dimension;

[0152] The association unit is used to associate the sub-target models under each sub-safety monitoring dimension according to the connection result to obtain the target model.

[0153] In this embodiment, the sub-goal model may be a result obtained after learning the cable hidden danger assessment path under each safety monitoring dimension, and is used to analyze the cable status under each safety monitoring dimension.

[0154] The working principle and beneficial effects of the above technical solution are: by learning the corresponding cable hidden danger assessment path for each safety monitoring dimension, the sub-goal model under each safety monitoring dimension can be accurately and effectively constructed. Finally, the obtained sub-goal models are associated to achieve accurate and effective construction of the target model, thereby facilitating accurate and effective prediction and assessment of cable hidden dangers through the target model.

[0155] Embodiment 10:

[0156] Based on Example 1, this embodiment provides a cable hidden danger prediction and assessment platform based on big data analysis, and a cable hidden danger assessment module, including:

[0157] A data acquisition unit, used for real-time acquisition of safety monitoring data of the corresponding cables under each safety monitoring dimension;

[0158] A model analysis unit is used to transmit the safety monitoring data to the target model, identify the safety monitoring data according to the target model, and output a prediction evaluation report according to the corresponding safety monitoring dimension;

[0159] The transmission unit is used to transmit the prediction and evaluation report to the monitoring terminal. At the same time, when there is a safety hazard, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report.

[0160] In this embodiment: the prediction and evaluation report may include the safety monitoring status of the cable corresponding to each safety monitoring dimension and the corresponding potential safety hazard type when the cable has a potential safety hazard.

[0161] The beneficial effects of the above technical solution are: it realizes effective analysis of the real-time collected cable safety monitoring data, which is conducive to the identification, prediction and positioning of cable hidden dangers, timely detection of early defects and prediction of defect development trends, thereby improving the timeliness and intelligence of cable hidden danger identification, and by transmitting the generated predictive evaluation report to the monitoring terminal, the user can monitor the cable in real time, and by automatically matching the maintenance auxiliary information of the preset maintenance library, it is beneficial to improve the efficiency of maintenance, avoid major accidents, and ensure the safe operation of the cable.

[0162] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A cable hidden danger prediction and assessment platform based on big data analysis, characterized in that: include: A data retrieval and analysis module is used to retrieve and analyze historical cable safety monitoring data sets, determine a number of safety monitoring dimensions, and divide the historical cable safety monitoring data sets according to the several safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets; The network construction module is used to identify each sub-historical cable safety monitoring data set and construct a cable hidden danger assessment prediction path of the corresponding dimension; The model building module is used to learn several cable hidden danger assessment prediction paths and build a target model; The cable hidden danger prediction and evaluation module is used to collect the safety monitoring data of the cable in real time, and transmit the safety monitoring data of the cable to the target model for prediction and evaluation, and output the prediction and evaluation report, and transmit it to the monitoring terminal. At the same time, when there is a safety hazard, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report; Network building blocks, including: A data identification unit is used to identify the sub-historical cable safety monitoring data set corresponding to each safety monitoring dimension, and determine a first sub-historical cable safety monitoring data set representing the safe operation of the cable and a second sub-historical safety monitoring data set representing the existence of a cable fault in the sub-historical cable safety monitoring data set; A path construction unit is used to analyze the first sub-historical cable safety monitoring data to construct a first sub-cable hidden danger assessment prediction path, and at the same time, analyze the second sub-historical cable safety monitoring data to construct a second sub-cable hidden danger assessment prediction path, and construct a cable hidden danger assessment prediction path of corresponding dimensions according to the first sub-cable hidden danger assessment prediction path and the second sub-cable hidden danger assessment prediction path; Path building unit, including: The first analysis subunit is used for: Obtaining the collection time of the first sub-historical cable safety monitoring data set; Mapping the first sub-historical cable safety monitoring data in the first sub-historical cable safety monitoring data set on a first preset coordinate system according to the acquisition time, and obtaining a first dynamic change curve corresponding to the first sub-historical cable safety monitoring data set; Reading the first dynamic change curve and extracting key information points in the first dynamic change curve; Marking key information points in the first dynamic change curve to obtain a curve trend corresponding to each key information point in the first dynamic change curve; Construct a first path node according to key information points in the first dynamic change curve, and at the same time, determine the path information corresponding to the first path node according to the curve trend corresponding to each key information point in the first dynamic change curve, merge multiple first path nodes and the path information corresponding to each first path node, and obtain a first sub-cable hidden danger assessment path; Path building unit, including: The second analysis subunit is used for: The second sub-historical cable safety monitoring data set is read, and the second sub-historical cable safety monitoring data is mapped on a second preset coordinate system according to the acquisition time of the second sub-historical cable safety monitoring data set to obtain a second dynamic change curve corresponding to the second sub-historical cable safety monitoring data set; Reading the second dynamic change curve and extracting key information points in the second dynamic change curve; Marking key information points in the second dynamic change curve, and obtaining a curve trend corresponding to each key information point in the second dynamic change curve; Constructing a second path node according to key information points in the second dynamic change curve, and determining path information corresponding to the second path node according to the curve trend corresponding to each key point information in the second dynamic change curve; Merging the plurality of second path nodes and the path information corresponding to each second path node to obtain a second sub-cable hidden danger assessment path; The cable hidden danger prediction path determination subunit is used to: Overlapping the first dynamic change curve and the second dynamic change curve according to corresponding acquisition times, and determining an intersection point between the first dynamic change curve and the second dynamic change curve; Obtaining the change characteristics of the first dynamic change curve at the intersection point, and constructing a cable hidden danger prediction path according to the change characteristics; The path construction subunit is used to integrate the first sub-cable hidden danger assessment path, the second sub-cable hidden danger assessment path and the cable hidden danger prediction path to obtain the cable hidden danger assessment prediction path of the corresponding dimension.

2. A cable hidden danger prediction and assessment platform based on big data analysis according to claim 1, characterized in that: Data retrieval and analysis module, including: A data retrieval unit, used to retrieve historical cable safety monitoring data sets; A data analysis unit, used to analyze the retrieved historical cable safety monitoring data and determine several safety monitoring dimensions; The data division unit is used to divide the historical cable safety monitoring data set according to a number of safety monitoring dimensions to obtain a number of sub-historical cable safety monitoring data sets.

3. A cable hidden danger prediction and assessment platform based on big data analysis according to claim 2, characterized in that: Data Analysis Unit, including: A keyword determination subunit is used to analyze the retrieved historical safety monitoring data and determine the monitoring keywords of the historical safety monitoring data and the data type keywords of the monitoring data; The matching subunit is used to match the monitoring keywords of the historical safety monitoring data with the type keywords of the monitoring data, and output several safety monitoring dimensions corresponding to the historical cable safety monitoring data set according to the matching results.

4. A cable hidden danger prediction and assessment platform based on big data analysis according to claim 2, characterized in that: The data partitioning unit includes: The dimension reading subunit is used to read a number of security monitoring dimensions, determine the dimension identifier of each security monitoring dimension, and at the same time, read the data identifier of each historical security monitoring data in the historical security monitoring data set; A similarity calculation subunit is used to perform similarity calculation on the data identifier of each historical safety monitoring data and the dimension identifier of each safety monitoring dimension, and determine the identifier similarity of each dimension corresponding to each historical safety monitoring data; A comparison subunit, used to obtain a preset threshold value, and use the historical security monitoring data with identification similarity greater than the preset threshold value as the historical security monitoring data under the corresponding dimension; The data division subunit is used to complete the division of the historical cable safety monitoring data set according to the comparison result, and obtain several sub-historical cable safety monitoring data sets.

5. The cable hidden danger prediction and assessment platform based on big data analysis according to claim 1 is characterized in that: Data identification unit, including: The cable safety assessment rule determination subunit is used to read the cable safety assessment rule corresponding to the safety monitoring dimension, and identify the sub-historical cable safety monitoring data set of the corresponding safety monitoring dimension according to the cable safety assessment rule; Identify assessment subunits for: Based on the identification results, the sub-historical cable safety data set that meets the cable safety assessment rules and the sub-historical cable safety data set that does not meet the cable safety assessment rules are output under the current safety monitoring dimension; The sub-historical cable safety dataset that complies with the cable safety assessment rules is used as the first sub-historical cable safety monitoring dataset when the cable is in safe operation, and the sub-historical cable safety dataset that does not comply with the cable safety assessment rules is used as the second sub-historical safety monitoring dataset when a cable fault exists.

6. The cable hidden danger prediction and assessment platform based on big data analysis according to claim 1 is characterized in that: Model building modules, including: A learning unit is used to read a number of safety monitoring dimensions, learn the corresponding cable hidden danger assessment paths for the several safety monitoring dimensions, and construct a sub-goal model under each safety monitoring dimension; The association unit is used to associate the sub-target models under each sub-safety monitoring dimension according to the connection result to obtain the target model.

7. The cable hidden danger prediction and assessment platform based on big data analysis according to claim 1 is characterized in that: Cable hazard assessment module, including: A data acquisition unit, used for real-time acquisition of safety monitoring data of the corresponding cables under each safety monitoring dimension; A model analysis unit is used to transmit the safety monitoring data to the target model, identify the safety monitoring data according to the target model, and output a prediction evaluation report according to the corresponding safety monitoring dimension; The transmission unit is used to transmit the prediction and evaluation report to the monitoring terminal. At the same time, when there is a safety hazard, the maintenance auxiliary information is automatically matched in the preset maintenance library based on the prediction and evaluation report.

Images