Offshore wind power cable temperature trend early warning system

Abstract

The invention relates to the technical field of intelligent early warning, and particularly discloses an offshore wind power cable temperature trend early warning system, which comprises an initial module for acquiring a topological structure diagram of offshore wind power cables in a preset target area, and determining a target number based on the topological structure diagram; the acquisition module is used for determining a first sequence and setting acquisition points at intervals according to the first sequence and the optimal distance; all collection points are determined, target temperatures are obtained on the collection points, and a target curve is drawn; and the analysis module is used for grouping the acquisition points, determining representative curves according to the target curves in the groups, and determining whether the acquisition points are abnormal or not based on the representative curves. Potential safety hazards possibly existing in the offshore wind power cable can be found in advance, and the reliability and safety of an offshore wind power system are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent early warning technology, and in particular to an offshore wind power cable temperature trend early warning system. Background Art

[0002] With the growing demand for renewable energy, offshore wind power, as an important component of clean energy, is developing at an increasingly rapid pace. This rapid development has not only promoted technological innovation and industrial upgrading, but also put forward higher requirements for related infrastructure. Among them, offshore wind power cables, as the key link between wind turbines and land power grids, are responsible for safely and efficiently transmitting the electricity generated by wind turbines far away from the shore to the land power grid.

[0003] Offshore wind power cables generate a lot of heat during operation, which will not only affect the efficiency of power transmission, but also damage the insulation layer of offshore wind power cables, thereby shortening the service life of offshore wind power cables. In the prior art, most of them monitor the temperature of offshore wind power cables in real time, and when the temperature of offshore wind power cables exceeds the preset safety threshold, send warning information for reporting, prompting relevant personnel to handle it. However, when the warning information is sent for reporting, the temperature of the offshore wind power cables has reached a relatively dangerous level. At this time, there is a certain lag in reporting and carrying out corresponding processing. Summary of the invention

[0004] The purpose of the present invention is to provide an offshore wind power cable temperature trend warning system to solve the following technical problems:

[0005] When the temperature of offshore wind power cables is monitored in real time and early warning is issued, when the early warning information is sent for reporting, the temperature of the offshore wind power cables has reached a relatively dangerous level. At this time, there is a certain lag in reporting and taking corresponding measures.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An offshore wind power cable temperature trend early warning system includes an initial module, a collection module and an analysis module, specifically:

[0008] Initial module: obtain a topological structure diagram of offshore wind power cables in a preset target area, wherein the nodes of the topological structure diagram represent the intersections and endpoints of the offshore wind power cables, and the edges of the topological structure diagram represent the actual lengths between two corresponding nodes, and obtain the total number of edges passing through node Z, which is used as the target number of node Z;

[0009] Collection module: sorting the target quantity in descending order to obtain a first sorting, determining the node A corresponding to the first target quantity in the first sorting, taking the edge corresponding to the node A as the A sub-edge, determining the actual length L of the A sub-edge, calculating the theoretical quantity C=L / dys, dys represents a preset optimal distance interval, calculating the theoretical interval D=L / ⌈C⌉, ⌈C⌉ represents rounding up the theoretical quantity, starting from the node A, setting collection points on the A sub-edge at the theoretical interval D;

[0010] Remove the node A from the first sorting to obtain a new first sorting, repeat the above steps until all edges in the topological structure diagram have been set with collection points, obtain the temperature of the offshore wind power cable in real time at the collection points, use it as the target temperature, draw a curve of the target temperature changing with time, and use it as the target curve;

[0011] Analysis module: Group the acquisition points. If the similarity between any two target curves in the group is greater than the preset similarity threshold, the target curves in the same group are taken as the pending curves. Several reference points are selected on the pending curves at preset time intervals. The mean of the target temperature at the reference points corresponding to the same time is calculated to generate the coordinate point (i, T i ), T i represents the mean value of the target temperature at the i-th reference point, and the coordinate points are fitted to obtain a representative curve F(t), where t represents time, and whether there is an abnormality at the collection point is determined based on the representative curve F(t).

[0012] As a further solution of the present invention: in the analysis module, the process of determining whether there is an abnormality at the collection point specifically includes:

[0013] Calculate the average target temperature , [t1, t2] represents the domain of the representative curve;

[0014] Determine the tangent slope of any point on the representative curve, calculate the average of the tangent slopes, and use it as the target temperature average rising speed Y;

[0015] The representative value K=ηX*Y is calculated, where η represents a preset correction coefficient. When the representative value is greater than or equal to a preset representative value threshold, the corresponding collection point is regarded as an abnormal collection point, and an early warning message is sent to prompt that the abnormal collection point is abnormal.

[0016] As a further solution of the present invention: in the acquisition module, when two or more target numbers are the same, the longer the average time for the offshore wind power cable to be put into use is, the higher the corresponding target number is ranked in the first sorting.

[0017] As a further solution of the present invention: in the acquisition module, when the actual length corresponding to the edge a of the topological structure diagram is less than the optimal distance interval, the edge a is removed from the topological structure diagram.

[0018] As a further solution of the present invention: in the analysis module, the similarity of the target curve is determined based on a dynamic time warping algorithm.

[0019] As a further solution of the present invention: in the initial module, when the offshore wind power cable is put into use for a time period less than a preset time threshold, it is treated as a normal cable, and the normal cable does not participate in drawing the topology diagram.

[0020] As a further solution of the present invention: in the acquisition module, during the process of acquiring the target temperature, when the target temperature is greater than or equal to a preset temperature threshold, subsequent steps are not executed and an early warning message is sent to prompt that the corresponding acquisition point is an abnormal acquisition point.

[0021] Beneficial effects of the present invention: In this solution, the information of each node and connecting edge is obtained through the topological structure diagram, and the number of edges is used as the target number of the node for statistics and sorting, so as to preferentially lock the key nodes with more connecting edges, and provide a reasonable basis for the subsequent layout of collection points. By giving priority to the nodes with the highest connectivity, the thermal conditions of more branch lines can be monitored in one place, thereby improving efficiency in terms of cost and time, which helps to ultimately efficiently deploy points at the overall level, reduce the number of sensors and obtain better temperature coverage, and by evenly distributing the collection points, it helps to obtain relatively continuous temperature data in space, reduce temperature monitoring blind spots, and ensure the quality of subsequent fitting and analysis of time series, which not only improves the overall efficiency of the deployment of collection points, but also reduces duplication and redundancy, and ultimately provides complete and representative temperature information input for subsequent data analysis; It is worth noting The point is that the temperature of the node, as the intersection of the heat path, can not only represent the local characteristics of the node itself, but also "absorb" the changes in the heat signals from each connected edge. In this way, setting the collection points at these key nodes can maximize the use of the redundancy of thermal information: the temperature change of a point already includes the comprehensive influence of multiple edges. Taking node A as an example, if node A is connected to ten edges (i.e., ten A sub-edges), if a collection point is set on node A, it is not necessary to set the collection point near the node A (the distance between the node A and the node A is less than the theoretical interval) on these ten edges, thereby reducing the need for separate proximal monitoring of the A sub-edge; by grouping and averaging similar target curves, a representative and smooth time variation curve F(t) is generated, and judging whether the collection point has an abnormality through the representative curve, the time required for analyzing all target curves individually can be reduced, and the efficiency of judging whether an abnormality exists can be improved. The present invention can discover the potential safety hazards of offshore wind power cables in advance and improve the reliability and safety of offshore wind power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] Figure 1 It is a structural schematic diagram of an offshore wind power cable temperature trend early warning system of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] See also Figure 1 As shown, the present invention is an offshore wind power cable temperature trend early warning system, including an initial module, a collection module and an analysis module, specifically:

[0026] Initial module: obtain a topological structure diagram of offshore wind power cables in a preset target area, wherein the nodes of the topological structure diagram represent the intersections and endpoints of the offshore wind power cables, and the edges of the topological structure diagram represent the actual lengths between two corresponding nodes, and obtain the total number of edges passing through node Z, which is used as the target number of node Z;

[0027] Collection module: sorting the target quantity in descending order to obtain a first sorting, determining the node A corresponding to the first target quantity in the first sorting, taking the edge corresponding to the node A as the A sub-edge, determining the actual length L of the A sub-edge, calculating the theoretical quantity C=L / dys, dys represents a preset optimal distance interval, calculating the theoretical interval D=L / ⌈C⌉, ⌈C⌉ represents rounding up the theoretical quantity, starting from the node A, setting collection points on the A sub-edge at the theoretical interval D;

[0028] Remove the node A from the first sorting to obtain a new first sorting, repeat the above steps until all edges in the topological structure diagram have been set with collection points, obtain the temperature of the offshore wind power cable in real time at the collection points, use it as the target temperature, draw a curve of the target temperature changing with time, and use it as the target curve;

[0029] Analysis module: Group the acquisition points. If the similarity between any two target curves in the group is greater than the preset similarity threshold, the target curves in the same group are taken as the pending curves. Several reference points are selected on the pending curves at preset time intervals. The mean of the target temperature at the reference points corresponding to the same time is calculated to generate the coordinate point (i, T i), T i represents the mean value of the target temperature at the i-th reference point, and the coordinate points are fitted to obtain a representative curve F(t), where t represents time, and whether there is an abnormality at the collection point is determined based on the representative curve F(t).

[0030] It should be noted that the information of each node and connecting edge is obtained through the topological structure diagram, and the number of edges is used as the target number of the node for statistics and sorting, so as to prioritize the key nodes with more connecting edges, and provide a reasonable basis for the subsequent layout of collection points. By giving priority to the nodes with the highest connectivity, the thermal conditions of more branch lines can be monitored in one place, thereby improving efficiency in terms of cost and time. This helps to ultimately efficiently deploy points at the overall level, reduce the number of sensors and obtain better temperature coverage. By evenly distributing the collection points, it is helpful to obtain relatively continuous temperature data in space, reduce temperature monitoring blind spots, and ensure the quality of subsequent fitting and analysis of time series, which not only improves the overall efficiency of the deployment of collection points, but also reduces duplication and redundancy, and ultimately provides complete and representative temperature information input for subsequent data analysis. It is worth noting that As the intersection of the heat path, the temperature of the point can not only represent the local characteristics of the node itself, but also "absorb" the changes in thermal signals from each connected edge. In this way, setting collection points at these key nodes can maximize the use of the redundancy of thermal information: the temperature change of a point already includes the combined influence of multiple edges. Taking node A as an example, if node A is connected to ten edges (i.e., ten A sub-edges), when setting a collection point on node A, it is not necessary to set a collection point on these ten edges close to node A (the distance between node A and node A is less than the theoretical interval), thereby reducing the need for separate proximal monitoring of the A sub-edge. By grouping and averaging similar target curves, a representative and smooth time variation curve F(t) is generated, and the representative curve is used to determine whether there is an abnormality at the collection point, which can reduce the time required for separate analysis of all target curves and improve the efficiency of determining whether there is an abnormality.

[0031] In another preferred embodiment of the present invention, in the analysis module, the process of determining whether there is an abnormality at the collection point specifically includes:

[0032] Calculate the average target temperature , [t1, t2] represents the domain of the representative curve;

[0033] Determine the tangent slope of any point on the representative curve, calculate the average of the tangent slopes, and use it as the target temperature average rising speed Y;

[0034] The representative value K=ηX*Y is calculated, where η represents a preset correction coefficient. When the representative value is greater than or equal to a preset representative value threshold, the corresponding collection point is regarded as an abnormal collection point, and an early warning message is sent to prompt that the abnormal collection point is abnormal.

[0035] It is worth noting that a comprehensive index K is calculated based on the average temperature value of the representative curve F (t) and the temperature rise rate to quantify whether there is a potential overheating risk. The size of K is determined by selecting a preset threshold. If it exceeds the threshold, it means that the corresponding collection point may be abnormal and an early warning message is issued in time; the complex time series data is simplified through specific physical and mathematical indicators, taking into account both the absolute temperature level and the temperature rise rate, making the judgment more physically meaningful and engineering reference, ensuring that the system can issue an alarm in time before the early and high-risk state occurs, thereby reducing the possibility of failure and damage and improving the safety and stability of the offshore wind power cable system.

[0036] In another preferred embodiment of the present invention, in the acquisition module, when two or more target quantities are the same, the longer the average time for the offshore wind power cable to be put into use is, the higher the corresponding target quantity is ranked in the first sorting.

[0037] In another preferred embodiment of the present invention, in the acquisition module, when the actual length corresponding to the edge a of the topological structure diagram is less than the optimal distance interval, the edge a is removed from the topological structure diagram.

[0038] It should be noted that if the actual length of a cable edge segment is less than the preset optimal distance interval (dys), then it makes little sense to set a collection point on this edge, because this distance is too short and is likely to have been covered by the adjacent collection points. Removing this short edge directly from the topology diagram will help simplify the point deployment process, reduce unnecessary sensor installations, and reduce the complexity and cost of the overall system, while still maintaining effective monitoring of the overall thermal condition of the cable.

[0039] In another preferred embodiment of the present invention, in the analysis module, the similarity of the target curves is determined based on a dynamic time warping algorithm.

[0040] It should be noted that the Dynamic Time Warping (DTW) algorithm is a dynamic programming algorithm used to measure the similarity between two time series. Unlike the simple "point-to-point" comparison method, DTW allows nonlinear stretching and compression of the time axis to find the optimal matching path between the two sequences. When the optimal matching path is found, the total cost corresponding to the path is the DTW distance of the two time series. The smaller the DTW distance, the higher the degree of matching between the two sequences after time warping, that is, the more similar the overall trends are; the DTW algorithm is relatively mature in application, so I will not describe it in detail here.

[0041] In another preferred embodiment of the present invention, in the initial module, when the offshore wind power cable is put into use for a time period less than a preset time threshold, it is treated as a normal cable, and the normal cable does not participate in drawing the topology diagram.

[0042] In another preferred embodiment of the present invention, in the acquisition module, during the process of acquiring the target temperature, when the target temperature is greater than or equal to a preset temperature threshold, subsequent steps are not executed and an early warning message is sent to prompt that the corresponding acquisition point is an abnormal acquisition point.

[0043] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An offshore wind power cable temperature trend warning system, characterized in that: It includes initial module, acquisition module and analysis module, specifically: Initial module: obtain a topological structure diagram of offshore wind power cables in a preset target area, wherein the nodes of the topological structure diagram represent the intersections and endpoints of the offshore wind power cables, and the edges of the topological structure diagram represent the actual lengths between two corresponding nodes, and obtain the total number of edges passing through node Z, which is used as the target number of node Z; Collection module: sorting the target quantity in descending order to obtain a first sorting, determining the node A corresponding to the first target quantity in the first sorting, taking the edge corresponding to the node A as the A sub-edge, determining the actual length L of the A sub-edge, calculating the theoretical quantity C=L / dys, dys represents a preset optimal distance interval, calculating the theoretical interval D=L / ⌈C⌉, ⌈C⌉ represents rounding up the theoretical quantity, starting from the node A, setting collection points on the A sub-edge at the theoretical interval D; Remove the node A from the first sorting to obtain a new first sorting, repeat the above steps until all edges in the topological structure diagram have been set with collection points, obtain the temperature of the offshore wind power cable in real time at the collection points, use it as the target temperature, draw a curve of the target temperature changing with time, and use it as the target curve; Analysis module: Group the acquisition points. If the similarity between any two target curves in the group is greater than the preset similarity threshold, the target curves in the same group are taken as the pending curves. Several reference points are selected on the pending curves at preset time intervals. The mean of the target temperature at the reference points corresponding to the same time is calculated to generate the coordinate point (i, T i ), T i represents the mean value of the target temperature at the i-th reference point, and the coordinate points are fitted to obtain a representative curve F(t), where t represents time, and whether there is an abnormality at the collection point is determined based on the representative curve F(t).

2. According to claim 1, an offshore wind power cable temperature trend warning system is characterized in that: In the analysis module, the process of determining whether there is an abnormality at the collection point specifically includes: Calculate the average target temperature , [t1, t2] represents the domain of the representative curve; Determine the tangent slope of any point on the representative curve, calculate the average of the tangent slopes, and use it as the target temperature average rising speed Y; The representative value K=ηX*Y is calculated, where η represents a preset correction coefficient. When the representative value is greater than or equal to a preset representative value threshold, the corresponding collection point is regarded as an abnormal collection point, and an early warning message is sent to prompt that the abnormal collection point is abnormal.

3. According to claim 1, an offshore wind power cable temperature trend warning system is characterized in that: In the acquisition module, when two or more target quantities are the same, the longer the average time for the offshore wind power cable to be put into use is, the higher the corresponding target quantity ranks in the first sorting.

4. According to claim 1, an offshore wind power cable temperature trend warning system is characterized in that: In the acquisition module, when the actual length corresponding to the edge a of the topological structure graph is less than the optimal distance interval, the edge a is removed from the topological structure graph.

5. According to claim 1, an offshore wind power cable temperature trend warning system is characterized in that: In the analysis module, the similarity of the target curve is determined based on a dynamic time warping algorithm.

6. According to claim 1, an offshore wind power cable temperature trend warning system is characterized in that: In the initial module, when the offshore wind power cable is put into use for a time period less than a preset time threshold, it is treated as a normal cable, and the normal cable does not participate in drawing the topology diagram.

7. The offshore wind power cable temperature trend warning system according to claim 1, characterized in that: In the acquisition module, during the process of acquiring the target temperature, when the target temperature is greater than or equal to a preset temperature threshold, subsequent steps are not executed and an early warning message is sent to prompt that the corresponding acquisition point is an abnormal acquisition point.

Images