A data acquisition system for a flow-converting cabin

Abstract

The invention discloses a data acquisition system for a flow converter cabin, relates to the technical field of data processing, and comprises an edge acquisition module, a control center, a node configuration module and a data analysis module; the edge acquisition module is an edge acquisition node connected to the flow converter cabin, and is used to collect equipment resource data of the flow converter cabin according to a preset period; the node configuration module is used to pre-configure a corresponding number of edge acquisition nodes for the flow converter cabin, and allocate different numbers of edge acquisition nodes to the flow converter cabin according to the acquisition configuration coefficient of the flow converter cabin, so as to reasonably allocate node resources and effectively improve data acquisition efficiency; the data reconstruction module is used to convert and fuse the data collected by the edge acquisition module; and transmit the fused data to the control center for aggregation and analysis; the data analysis module is used to parse the equipment resource data received by the control center, so as to judge the fault conditions of the flow converter cabin and the distribution network, so that the management personnel can perform inspection and maintenance, and improve the power safety.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, in particular to a variable flow cabin data acquisition system. Background Art

[0002] The energy storage converter and booster integrated cabin is an important component of the energy storage power station. It is a device that realizes the energy conversion between the energy storage battery and the power grid, thereby rationally distributing the electric energy of the energy storage system, making the power grid stable and improving the quality of the power grid.

[0003] The existing data collection methods for converter cabins focus on the collection and processing of structured data such as electrical signals, but pay less attention to the collection and fusion methods of semi-structured and unstructured data such as communication message information, equipment abnormality information, and monitor audio and video data. It is impossible to effectively perceive the operating status of all distributed power sources and new energy equipment in the energy storage system.

[0004] However, as more and more types of power equipment are deployed in the power grid and the amount of data transmission is increasing, there is a problem of being unable to reasonably allocate edge collection nodes for data collection, which affects the overall data collection efficiency. Based on the above shortcomings, the present invention proposes a converter cabin data acquisition system. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a flow control cabin data acquisition system.

[0006] To achieve the above-mentioned object, according to an embodiment of the first aspect of the present invention, a data acquisition system for a flow-converting cabin is provided, comprising an edge acquisition module, a control center, a node configuration module, a node evaluation module, a data reconstruction module and a data analysis module;

[0007] The edge acquisition module is an edge acquisition node connected to the flow conversion cabin, and is used to collect the equipment resource data of the flow conversion cabin according to a preset period; the equipment resource data is divided into three categories according to the degree of structure: structured data, semi-structured data and unstructured data;

[0008] The node configuration module is connected to the control center and is used to pre-configure a corresponding number of edge acquisition nodes for the conversion cabin, specifically including:

[0009] In a preset time period, historical equipment resource data and fault event records generated by the converter cabin are collected for comprehensive analysis, and a collection configuration coefficient CM of the converter cabin is calculated;

[0010] The corresponding number of edge collection nodes are allocated according to the collection configuration coefficient CM, specifically:

[0011] The control center pre-stores a comparison table of the acquisition configuration coefficient range and the node quantity threshold; based on the comparison table, the node quantity threshold corresponding to the acquisition configuration coefficient CM is determined and marked as Yz;

[0012] The data reconstruction module includes a data conversion unit, a data cleaning unit and a data fusion unit; the data conversion unit, the data cleaning unit and the data fusion unit are used to convert and fuse the data collected by the edge acquisition module; and transmit the fused data to the control center for aggregation, analysis and storage;

[0013] The data analysis module is connected to the control center and is used to analyze the equipment resource data received by the control center to determine the fault conditions of the converter cabin and the distribution network, and issue a string cut-off instruction to the control center according to the fault conditions;

[0014] After receiving the string disconnection instruction, the control center controls the converter cabin or other power equipment connected to the distribution network to disconnect so that the management personnel can perform inspection and maintenance.

[0015] Furthermore, when the node configuration module configures Yz edge collection nodes for the conversion cabin, the specific configuration process is:

[0016] Obtain several edge collection nodes controlled by the control center;

[0017] Automatically obtain the collection efficiency value CK of the edge collection node from the cloud platform;

[0018] The edge acquisition nodes are arranged in descending order according to the efficiency values ​​CK, and the first Yz edge acquisition nodes are selected as target nodes and configured to the converter cabin.

[0019] Furthermore, the node evaluation module is used to collect data collection volume and operation sequence parameters of edge collection nodes to evaluate the collection efficiency value CK. The specific evaluation steps are as follows:

[0020] In one collection cycle of the edge collection node, the data collection amount of the edge collection node is counted as Cz; the collection time of the edge collection node is counted as YT;

[0021] Obtaining the operating timing parameters of the edge collection node, wherein the operating timing parameters include the number of access node connections, CPU load rate, network access rate, and operating temperature at the same time;

[0022] The maximum number of access node connections is marked as Ft, the maximum CPU load rate is marked as Nt, the maximum network access rate is marked as Wt, and the maximum operating temperature is marked as Mt;

[0023] The efficiency value CK of the edge collection node is calculated using the formula CK = γ × Cz × (Wt × g4) / [YT × (Mt × g5 + Ft × g6 + Nt × g7)], wherein g4, g5, g6, and g7 are all preset coefficient factors; γ is the preset balancing coefficient; the node evaluation module is used to timestamp the efficiency value CK of the edge collection node and store it on the cloud platform.

[0024] Furthermore, the specific analysis steps of the node configuration module for the acquisition configuration coefficient CM are as follows:

[0025] The data capacity of each historical device resource data is marked as Ri, and a data capacity information group is obtained; the average value of the data capacity information group is calculated according to the average value calculation formula as Gz;

[0026] Traverse the data capacity information group to obtain the maximum data capacity Rmax and the minimum data capacity Rmin, and use the formula Rb = (Rmax-Rmin) / Rmax to calculate the capacity difference ratio Rb;

[0027] The capacity sensitivity coefficient RM of the variable flow compartment is calculated using the formula RM=f×Gz×(1+Rb), where f is a preset balancing coefficient;

[0028] Collect the fault event records of the converter cabin; evaluate the fault threat index GW of the converter cabin according to the fault event records; the fault event records include fault duration, fault affected area and property loss; use the formula CM=RM×b1+GW×b2 to calculate the collection configuration coefficient CM, where b1 and b2 are preset coefficient factors.

[0029] Furthermore, the fault threat index GW of the converter cabin is evaluated according to the fault event record; the specific steps are:

[0030] The total number of faults of the converter cabin is counted as Z1; the duration of the fault, the affected area of ​​the fault, and the property loss in each fault event record are obtained;

[0031] The maximum fault duration is marked as GTmax, the maximum fault affected area is marked as GBmax, and the maximum property loss is marked as CSmax;

[0032] The maximum value of the fault affected area refers to the maximum value of the power supply coefficient in the fault affected area; the power supply coefficient is obtained by combining the length of the power supply line, the number of households powered, and the average power consumption per household in the fault affected area;

[0033] The fault threat index GW is calculated using the formula GW=b3×Z1×(GTmax×b4+GBmax×b5+CSmax×b6), where b3, b4, b5, and b6 are all preset coefficient factors.

[0034] Furthermore, the data conversion unit is used to convert the device resource data, specifically including:

[0035] Preprocessing the structured data by using a key-value information matching method, and further processing the preprocessed structured data by using a key-value direct extraction method;

[0036] Preprocessing the semi-structured data by using a homologous data association method, and further processing the preprocessed semi-structured data by using an information tag extraction method;

[0037] The unstructured data is preprocessed by using a stream data sampling matrix, and the preprocessed unstructured data is further processed by using a convolutional feature extraction method.

[0038] Furthermore, the data cleaning unit is used to remove garbled characters and repeated parts contained in the collected data, and to control the length of the collected data to achieve data standardization.

[0039] Furthermore, the data fusion unit is used to extract features and classify the cleaned multi-source heterogeneous data using a deep learning model; specifically, the following is performed:

[0040] For the cleaned data from each data source, the corresponding sparse denoising autoencoder deep belief network model is constructed respectively; the model parameters are set, the model is trained, and the data features of multi-source heterogeneous data are extracted and fused respectively; the fusion is based on the HFCM clustering algorithm.

[0041] Furthermore, the structured data includes distributed power output, measurement node electrical quantities and distribution network status information; the semi-structured data includes device communication messages, system fault information and user complaint information; and the unstructured data includes video stream data and audio recording data.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The edge acquisition module in the present invention is an edge acquisition node connected to the converter cabin, which is used to collect the equipment resource data of the converter cabin according to a preset period; the node configuration module is used to configure a corresponding number of edge acquisition nodes for the converter cabin, firstly collect the historical equipment resource data and fault event records generated by the converter cabin for comprehensive analysis, and calculate the acquisition configuration coefficient CM of the converter cabin; then allocate the corresponding number of edge acquisition nodes according to the acquisition configuration coefficient CM; reasonably allocate node resources, and effectively improve data acquisition efficiency;

[0044] 2. The node evaluation module in the present invention is used to collect the data collection volume and operation timing parameters of the edge collection node to evaluate the collection efficiency value CK; when the node configuration module configures Yz edge collection nodes for the converter cabin, first obtain a number of edge collection nodes controlled by the control center; then automatically obtain the collection efficiency value CK of the edge collection node from the cloud platform, and arrange the edge collection nodes in descending order according to the size of the collection efficiency value CK; finally, select the first Yz edge collection nodes in the sorting as the target nodes and configure them to the converter cabin to further improve the data collection efficiency;

[0045] 3. The data reconstruction module in the present invention includes a data conversion unit, a data cleaning unit and a data fusion unit; the data conversion unit, the data cleaning unit and the data fusion unit are used to convert and fuse the data collected by the edge acquisition module; and transmit the fused data to the control center for aggregation, analysis and storage; the data analysis module is used to parse the equipment resource data received by the control center to determine the fault conditions of the converter cabin and the distribution network, and issue a string cut-off command to the control center according to the fault conditions; so that management personnel can carry out inspection and maintenance to improve power safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 The system block diagram of a variable flow cabin data acquisition system of the present invention. DETAILED DESCRIPTION

[0048] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0049] like Figure 1 As shown, a flow-converting cabin data acquisition system includes an edge acquisition module, a control center, a node configuration module, a node evaluation module, a cloud platform, a data reconstruction module, and a data analysis module;

[0050] The edge acquisition module is an edge acquisition node connected to the converter cabin, which is used to collect the equipment resource data of the converter cabin according to a preset period; the equipment resource data is divided into three categories according to the degree of structure: structured data, semi-structured data and unstructured data;

[0051] Among them, structured data includes distributed power output, electrical quantity of measurement nodes and distribution network status information; semi-structured data includes equipment communication messages, system fault information and user complaint information; unstructured data includes video stream data and audio recording data;

[0052] In this embodiment, the node configuration module is connected to the control center and is used to pre-configure a corresponding number of edge collection nodes for the variable flow cabin to improve data collection efficiency; specifically, it includes:

[0053] Acquire historical equipment resource data generated by the converter cabin within a preset time period; mark the data capacity of each historical equipment resource data as Ri to obtain a data capacity information group;

[0054] The average value of the data capacity information group is calculated according to the average value calculation formula as Gz;

[0055] Traverse the data capacity information group to obtain the maximum data capacity Rmax and the minimum data capacity Rmin, and use the formula Rb = (Rmax-Rmin) / Rmax to calculate the capacity difference ratio Rb;

[0056] The capacity sensitivity coefficient RM of the variable flow compartment is calculated using the formula RM = f × Gz × (1 + Rb), where f is the preset balancing coefficient;

[0057] Collect fault event records of the converter cabin within a preset time period; evaluate the fault threat index GW of the converter cabin based on the fault event records; the fault event records include fault duration, fault affected area, and property loss;

[0058] The capacity sensitivity coefficient and the fault threat index are normalized and their values ​​are taken, and the acquisition configuration coefficient CM is calculated using the formula CM = RM × b1 + GW × b2, where b1 and b2 are both preset coefficient factors;

[0059] According to the acquisition configuration coefficient CM, a corresponding number of edge acquisition nodes are allocated, including:

[0060] The control center pre-stores a comparison table of the acquisition configuration coefficient range and the node quantity threshold;

[0061] Based on the comparison table, the node quantity threshold corresponding to the acquisition configuration coefficient CM is determined and marked as Yz; wherein, the larger the acquisition configuration coefficient CM is, the larger the node quantity threshold is;

[0062] The present invention allocates different numbers of edge acquisition nodes to the flow conversion cabin according to the acquisition configuration coefficient CM of the flow conversion cabin, reasonably allocates node resources, and effectively improves data acquisition efficiency;

[0063] In one embodiment of the present application, when the node configuration module configures Yz edge collection nodes for the conversion cabin, the specific configuration process is:

[0064] Obtain several edge collection nodes controlled by the control center;

[0065] Automatically obtain the collection efficiency value CK of the edge collection node from the cloud platform;

[0066] Arrange the edge acquisition nodes in descending order according to the efficiency value CK, select the first Yz edge acquisition nodes as target nodes and assign them to the converter cabin to further improve the data acquisition efficiency;

[0067] The node evaluation module is used to collect the data collection volume and operation sequence parameters of the edge collection node to evaluate the collection efficiency value CK. The specific evaluation steps are as follows:

[0068] In one collection cycle of the edge collection node, the data collection amount of the edge collection node is Cz; the collection time of the edge collection node is YT;

[0069] Obtain the operating timing parameters of the edge collection node, which include the number of access node connections, CPU load rate, network access rate, and operating temperature at the same time;

[0070] The maximum number of access node connections is marked as Ft, the maximum CPU load rate is marked as Nt, the maximum network access rate is marked as Wt, and the maximum operating temperature is marked as Mt;

[0071] The efficiency value CK of the edge collection node is calculated using the formula CK = γ × Cz × (Wt × g4) / [YT × (Mt × g5 + Ft × g6 + Nt × g7)], where g4, g5, g6, and g7 are all preset coefficient factors; γ is the preset balancing coefficient; the node evaluation module is used to timestamp the efficiency value CK of the edge collection node and store it on the cloud platform;

[0072] In one embodiment of the present application, the fault threat index GW of the converter cabin is evaluated according to the fault event record; the specific evaluation steps are as follows:

[0073] The total number of faults of the converter compartment is counted as Z1; the fault duration, fault affected area and property loss in each fault event record are obtained;

[0074] The maximum fault duration is marked as GTmax, the maximum fault affected area is marked as GBmax, and the maximum property loss is marked as CSmax; the fault threat index GW is calculated using the formula GW = b3 × Z1 × (GTmax × b4 + GBmax × b5 + CSmax × b6), where b3, b4, b5, and b6 are all preset coefficient factors;

[0075] The maximum value of the fault affected area GBmax refers to the maximum value of the power supply coefficient in the fault affected area; the power supply coefficient is obtained by combining the length of the power supply line, the number of households powered and the average power consumption per household in the fault affected area; for example: RW = W1×g1+W2×g2+W3×g3; RW is the power supply coefficient, W1 is the length of the power supply line, W2 is the number of households powered, W3 is the average power consumption per household, and g1, g2, and g3 are all preset coefficient factors;

[0076] In one embodiment of the present invention, the data reconstruction module includes a data conversion unit, a data cleaning unit and a data fusion unit; the data conversion unit is connected to the edge acquisition module, the data conversion unit is connected to the data cleaning unit, and the data cleaning unit is connected to the data fusion unit;

[0077] The data conversion unit, data cleaning unit and data fusion unit are used to convert and fuse the data collected by the edge acquisition module; and transmit the fused data to the control center for aggregation, analysis and storage;

[0078] The data conversion unit is used to pre-process the structured data by using a key-value information matching method, and further process the pre-processed structured data by using a key-value direct extraction method;

[0079] The semi-structured data is preprocessed by using the homologous data association method, and the preprocessed semi-structured data is further processed by using the information tag extraction method;

[0080] The unstructured data is preprocessed using a stream data sampling matrix, and the preprocessed unstructured data is further processed using a convolutional feature extraction method;

[0081] The data cleaning unit is used to remove the garbled characters and repeated parts contained in the collected data, and to control the length of the collected data to achieve data standardization;

[0082] The data fusion unit is used to extract features and classify the cleaned multi-source heterogeneous data using a deep learning model; specifically, it is as follows:

[0083] For each cleaned data source, a corresponding sparse denoising autoencoder deep belief network model is constructed; model parameters are set, the model is trained, and the data features of multi-source heterogeneous data are extracted and fused; the fusion is based on the HFCM clustering algorithm, which is used to explore the value of multi-source heterogeneous data and realize the interconnection, exchange and sharing of multi-source heterogeneous data;

[0084] The data analysis module is connected to the control center and is used to analyze the equipment resource data received by the control center to determine the fault conditions of the converter cabin and the distribution network, and issue a string cut-off command to the control center according to the fault conditions;

[0085] After receiving the string disconnection command, the control center controls the converter cabin or other power equipment connected to the distribution network to disconnect, so that management personnel can carry out inspection and maintenance to improve power safety.

[0086] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0087] Working principle of the present invention:

[0088] A data acquisition system for a flow conversion cabin, when working, an edge acquisition module is an edge acquisition node connected to the flow conversion cabin, and is used to collect equipment resource data of the flow conversion cabin according to a preset period; a node configuration module is used to configure a corresponding number of edge acquisition nodes for the flow conversion cabin, firstly collect the historical equipment resource data and fault event records generated by the flow conversion cabin for comprehensive analysis, and calculate the acquisition configuration coefficient CM of the flow conversion cabin; then allocate a corresponding number of edge acquisition nodes according to the acquisition configuration coefficient CM; reasonably allocate node resources, and effectively improve data acquisition efficiency;

[0089] The node evaluation module is used to collect the data collection volume and operation sequence parameters of the edge collection nodes to evaluate the collection efficiency value CK; when the node configuration module configures Yz edge collection nodes for the converter cabin, it first obtains a number of edge collection nodes controlled by the control center; then automatically obtains the collection efficiency value CK of the edge collection nodes from the cloud platform, and arranges the edge collection nodes in descending order according to the size of the collection efficiency value CK; finally, the first Yz edge collection nodes in the sorting are selected as target nodes and configured to the converter cabin to further improve the data collection efficiency;

[0090] The data reconstruction module includes a data conversion unit, a data cleaning unit and a data fusion unit; the data conversion unit, the data cleaning unit and the data fusion unit are used together to convert and fuse the data collected by the edge acquisition module; and the fused data is transmitted to the control center for aggregation, analysis and storage; the data analysis module is used to parse the equipment resource data received by the control center to determine the fault conditions of the converter cabin and the distribution network, and issue a string cut-off command to the control center according to the fault conditions; so that management personnel can carry out inspection and maintenance to improve power safety.

[0091] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0092] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A flow control cabin data acquisition system, characterized in that: It includes edge acquisition module, control center, node configuration module, node evaluation module, data reconstruction module and data analysis module; The edge acquisition module is an edge acquisition node connected to the flow conversion cabin, and is used to collect equipment resource data of the flow conversion cabin according to a preset period; The device resource data is divided into three categories according to the degree of structure: structured data, semi-structured data and unstructured data; The node configuration module is connected to the control center and is used to pre-configure a corresponding number of edge acquisition nodes for the conversion cabin, specifically including: In a preset time period, historical equipment resource data and fault event records generated by the converter cabin are collected for comprehensive analysis, and a collection configuration coefficient CM of the converter cabin is calculated; The corresponding number of edge collection nodes are allocated according to the collection configuration coefficient CM, specifically: The control center pre-stores a comparison table of the acquisition configuration coefficient range and the node quantity threshold; based on the comparison table, the node quantity threshold corresponding to the acquisition configuration coefficient CM is determined and marked as Yz; The data reconstruction module includes a data conversion unit, a data cleaning unit and a data fusion unit; the data conversion unit, the data cleaning unit and the data fusion unit are used to convert and fuse the data collected by the edge acquisition module; and transmit the fused data to the control center for aggregation, analysis and storage; The data analysis module is connected to the control center and is used to analyze the equipment resource data received by the control center to determine the fault conditions of the converter cabin and the distribution network, and issue a string cut-off instruction to the control center according to the fault conditions; After receiving the string disconnection instruction, the control center controls the converter cabin or power equipment connected to the distribution network to disconnect so that the management personnel can perform inspection and maintenance.

2. A flow control cabin data acquisition system according to claim 1, characterized in that: When the node configuration module configures Yz edge collection nodes for the conversion cabin, the specific configuration process is as follows: Obtain several edge collection nodes controlled by the control center; Automatically obtain the collection efficiency value CK of the edge collection node from the cloud platform; The edge acquisition nodes are arranged in descending order according to the efficiency values ​​CK, and the first Yz edge acquisition nodes are selected as target nodes and configured to the converter cabin.

3. A flow control cabin data acquisition system according to claim 2, characterized in that: The node evaluation module is used to collect the data collection volume and operation sequence parameters of the edge collection node to evaluate the collection efficiency value CK. The specific evaluation steps are as follows: In one collection cycle of the edge collection node, the data collection amount of the edge collection node is counted as Cz; the collection time of the edge collection node is counted as YT; Obtaining the operating timing parameters of the edge collection node, wherein the operating timing parameters include the number of access node connections, CPU load rate, network access rate, and operating temperature at the same time; The maximum number of access node connections is marked as Ft, the maximum CPU load rate is marked as Nt, the maximum network access rate is marked as Wt, and the maximum operating temperature is marked as Mt; The efficiency value CK of the edge collection node is calculated using the formula CK=γ×Cz×(Wt×g4) / [YT×(Mt×g5+Ft×g6+Nt×g7)], where g4, g5, g6, and g7 are all preset coefficient factors; γ is the preset balancing coefficient; the node evaluation module is used to timestamp the efficiency value CK of the edge collection node and store it on the cloud platform.

4. A flow control cabin data acquisition system according to claim 1, characterized in that: The specific analysis steps of the node configuration module for the acquisition configuration coefficient CM are as follows: Mark the data capacity of each historical device resource data as Ri, and obtain a data capacity information group; The average value of the data capacity information group is calculated according to the average value calculation formula as Gz; Traverse the data capacity information group to obtain the maximum data capacity Rmax and the minimum data capacity Rmin, and use the formula Rb=(Rmax-Rmin) / Rmax to calculate the capacity difference ratio Rb; The capacity sensitivity coefficient RM of the variable flow cabin is calculated using the formula RM=ƒ×Gz×(1+Rb), where ƒ is a preset balancing coefficient; Collecting fault event records of the converter cabin; Evaluate the fault threat index GW of the converter cabin according to the fault event record; The fault event record includes the duration of the fault, the area affected by the fault, and the property loss; The acquisition configuration coefficient CM is calculated using the formula CM=RM×b1+GW×b2, where b1 and b2 are both preset coefficient factors.

5. A flow control cabin data acquisition system according to claim 4, characterized in that: The fault threat index GW of the converter cabin is evaluated according to the fault event records; the specific steps are: The total number of faults of the converter cabin is counted as Z1; the duration of the fault, the affected area of ​​the fault, and the property loss in each fault event record are obtained; The maximum fault duration is marked as GTmax, the maximum fault affected area is marked as GBmax, and the maximum property loss is marked as CSmax; The maximum value of the fault affected area refers to the maximum value of the power supply coefficient in the fault affected area; the power supply coefficient is obtained by combining the length of the power supply line, the number of households powered, and the average power consumption per household in the fault affected area; The fault threat index GW is calculated using the formula GW=b3×Z1×(GTmax×b4+GBmax×b5+CSmax×b6), where b3, b4, b5, and b6 are all preset coefficient factors.

6. The data acquisition system for a flow conversion cabin according to claim 1, characterized in that: The data conversion unit is used to convert the device resource data, specifically including: Preprocessing the structured data by using a key-value information matching method, and further processing the preprocessed structured data by using a key-value direct extraction method; Preprocessing the semi-structured data by using a homologous data association method, and further processing the preprocessed semi-structured data by using an information tag extraction method; The unstructured data is preprocessed by using a stream data sampling matrix, and the preprocessed unstructured data is further processed by using a convolutional feature extraction method.

7. A flow control cabin data acquisition system according to claim 6, characterized in that: The data cleaning unit is used to remove garbled characters and repeated parts contained in the collected data, and to control the length of the collected data to achieve data standardization.

8. A flow control cabin data acquisition system according to claim 7, characterized in that: The data fusion unit is used to extract features and classify the cleaned multi-source heterogeneous data using a deep learning model; specifically, it is as follows: Construct the corresponding sparse denoising autoencoder deep belief network model for each cleaned data source; set the model parameters, train the model, extract the data features of multi-source heterogeneous data and fuse them; The fusion is based on the HFCM clustering algorithm.

9. The data acquisition system for a flow conversion cabin according to claim 1, characterized in that: The structured data includes the output of distributed power sources, electrical quantities of measurement nodes and distribution network status information; the semi-structured data includes equipment communication messages, system fault information and user complaint information; the unstructured data includes video stream data and audio recording data.

Images