6kv high-power stepless power regulating molten salt energy storage electric heating system

Abstract

The present application relates to molten salt energy storage heating technical field, specifically to 6kV large power stepless power regulating molten salt energy storage electric heating system, including the following steps, data collection is carried out to different levels of molten salt energy storage architecture, respectively using space-time feature extraction function extracts the short-time feature, long-term trend feature and spatial correlation feature of molten salt energy storage architecture data, and according to the distribution difference of the data characteristics of different levels of molten salt energy storage architecture, the adaptive fusion of data is carried out by using hierarchical adaptive clustering algorithm;Based on the adaptive fusion result, the hierarchical network structure is used for intelligent analysis of molten salt energy storage architecture hierarchical partitioning, including, level judgment and partition determination of molten salt energy storage architecture data, according to the intelligent analysis result, the state transition matrix is constructed to identify the potential abnormality of molten salt energy storage architecture;According to the data of different levels of molten salt energy storage architecture, the running state of each level is analyzed, and intelligent optimization decision and control execution are carried out based on abnormal characteristics and global influence.

Description

Technical Field

[0001] This invention relates to the field of molten salt energy storage heating technology, and more particularly to a 6kV high-power stepless adjustable molten salt energy storage electric heating system. Background Technology

[0002] In modern industry and the energy sector, with the ever-increasing demands for energy efficiency and flexibility, traditional energy storage and heating systems are struggling to meet the growing needs. Existing energy storage technologies have many limitations in terms of power regulation and energy conversion efficiency, while molten salt energy storage, as a highly efficient thermal energy storage method, has advantages such as high energy density and long service life.

[0003] Regarding the above and existing related technologies, the inventors believe that the following defects often exist: Most existing molten salt energy storage electric heating systems adopt fixed power or limited-stage power adjustment methods, which not only limits the flexibility of the system, but also reduces the energy conversion efficiency. In addition, existing systems are rarely used at high voltages (such as 6kV), which poses safety and reliability problems. Summary of the Invention

[0004] The technical problem to be solved by this invention is that existing molten salt energy storage systems have limited applications under high voltage and lack effective safety monitoring and early warning mechanisms, which pose certain safety hazards. To address this, we propose a 6kV high-power stepless adjustable molten salt energy storage electric heating system.

[0005] To achieve the above objectives, this application adopts the following technical solution: a 6kV high-power stepless adjustable molten salt energy storage electric heating system, including: a heating unit: adopting a modular high-voltage radiation design, the heating tube is fixed to the stainless steel shell by ceramic insulators, the interior is filled with magnesium oxide insulation material, and the exterior is wrapped with aluminum silicate fiber insulation layer;

[0006] Flow channel system: Molten salt is distributed from the main inlet pipe to the serpentine inlet branch pipes, and enters the outlet branch pipe through the exchange chamber to form long-path convection, which enhances the uniformity of heat transfer;

[0007] Intelligent control module: integrates PLC controller, fuzzy PID algorithm and leakage detection unit, monitors temperature changes in real time through gas expansion chamber and adjusts output power in conjunction with power control cabinet;

[0008] Storage media for performing the following steps

[0009] The hierarchical and partitioned data fusion and feature construction of molten salt energy storage architecture are as follows:

[0010] Data was collected for molten salt energy storage architectures at different levels. Short-term features, long-term trend features, and spatial correlation features of the molten salt energy storage architecture data were extracted using spatiotemporal feature extraction functions. Based on the distribution differences of the data features of molten salt energy storage architectures at different levels, a hierarchical adaptive clustering algorithm was used to adaptively fuse the data.

[0011] The molten salt energy storage architecture features layered and zoned intelligent analysis and anomaly detection, specifically:

[0012] Based on the adaptive fusion results, a hierarchical network structure is used for intelligent analysis of the hierarchical partitioning of molten salt energy storage architecture. This includes determining the hierarchy and partitioning of molten salt energy storage architecture data. Based on the intelligent analysis results, a state transition matrix is ​​constructed to identify potential anomalies in the molten salt energy storage architecture.

[0013] By continuously monitoring the abnormal areas in the partitioning results, the characteristic mean and standard deviation of different levels of molten salt energy storage architecture can be dynamically adjusted, thereby enabling dynamic adjustment of the interval variation threshold.

[0014] The molten salt energy storage architecture features layered and zoned intelligent optimization decision-making and control execution, specifically as follows:

[0015] Based on data from different levels of molten salt energy storage architecture, the operational status of each level is analyzed, and intelligent optimization decisions and control execution are carried out based on abnormal characteristics and global impact.

[0016] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the data acquisition is specifically as follows:

[0017] By collecting real-time operating parameters at different levels of the molten salt energy storage architecture, we can obtain the following:

[0018] ;

[0019] in, This indicates the molten salt energy storage architecture hierarchy, including: Indicates an extremely hot zone. Indicates the main hot zone and This indicates a molten salt energy storage architecture. Indicates the first Data collection at different levels Indicates the first The first in the hierarchy Each detection point data vector is a multi-dimensional data vector, including voltage data, temperature data, frequency data, and power data. This indicates the number of detection points in each layer, and the number of detection points is the same in each layer;

[0020] Simultaneously, based on the historical database, the same historical data set as the real-time molten salt energy storage architecture data is extracted. .

[0021] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the adaptive fusion of data using a hierarchical adaptive clustering algorithm is specifically as follows:

[0022] To address the distribution differences in data characteristics across different levels of molten salt energy storage architectures, a hierarchical adaptive clustering algorithm is used to achieve adaptive fusion of data from different levels. This results in...

[0023] Data feature matrix of the constructed molten salt energy storage architecture Calculate the characteristic mean values ​​of ultra-high heat zone, regional main heat zone, and molten salt energy storage architecture. and standard deviation Based on the calculated standard deviation, the data clustering radius for each level is determined. This generates the initial set of cluster centers. ;

[0024] For the generated initial set of cluster centers, calculate the set of data points covered by each cluster center, and update the cluster centers to generate a new set of cluster centers. ;

[0025] For the generated set of second-generation cluster centers, adaptive adjustments are made to all cluster centers in the set, specifically as follows:

[0026] Select all cluster centers in the second-generation cluster center set, calculate their density adaptive adjustment factor, and update the position of the cluster centers based on the adjustment factor to generate a new cluster center set;

[0027] Based on the iteration of the selected initial cluster center set, second-generation cluster center set, and third-generation cluster center set, hierarchical adaptive clustering is achieved, then we have:

[0028] The iteration for the second-generation cluster centers is as follows:

[0029] For the initial set of cluster centers, the positions of the cluster centers are adjusted by calculating the distribution density of data points, requiring that all cluster centers in the adjusted set can cover a more reasonable data distribution than the initial set of cluster centers;

[0030] The iteration for the three generations of cluster centers is as follows:

[0031] For all cluster centers in the second-generation cluster center set, adjust the position of the cluster centers and ensure that at least one cluster center in the third-generation cluster center set can improve the cluster consistency score;

[0032] Based on the iteration of second-generation and third-generation cluster centers, the process continues until all second-generation cluster centers can find third-generation cluster centers with higher cluster consistency scores. At this point, the set of all third-generation cluster centers is the final hierarchical adaptive clustering result. .

[0033] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the clustering consistency score is as follows:

[0034] ;

[0035] ;

[0036] in, This represents the total number of cluster centers. The category index representing the cluster center, Indicates the first Cluster centers, In the second-generation cluster center set, the first... Cluster centers, In the set of three-generation cluster centers, the first... Cluster centers, Indicates the first A set of data points with cluster centers. A data point representing the cluster center. This represents the set of second-generation cluster centers. This represents the set of third-generation cluster centers. This represents the cluster consistency score, used to iterate through cluster centers. This represents the consistency score of the second-generation cluster centers. This represents the consistency score of the third-generation cluster centers.

[0037] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the hierarchical determination of the molten salt energy storage architecture data is as follows:

[0038] Input molten salt energy storage architecture data The stratification is determined based on the characteristic mean and standard deviation of different molten salt energy storage architectures, including the characteristic mean of ultra-high voltage strata. Mean of regional main heat zone hierarchical characteristics Mean characteristics of molten salt energy storage architecture hierarchy And, the standard deviation of ultra-high pressure levels Standard deviation of the main heat zone level Standard deviation of molten salt energy storage architecture at different levels Then there is,

[0039] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the ultra-high voltage level;

[0040] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the regional main thermal zone level;

[0041] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the molten salt energy storage architecture level.

[0042] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, wherein: if the input data simultaneously meets the judgment conditions of multiple levels, then the level is determined by calculating the adaptability scores of different levels, and the level is judged based on the calculated adaptability scores, specifically as follows:

[0043] Adaptability scores at different levels Then there is,

[0044] ;

[0045] in, This represents the input molten salt energy storage architecture data. , These represent the characteristic mean and standard deviation of different molten salt energy storage architectures, respectively, by controlling... The value of controls the selection of different levels of molten salt energy storage architecture. This represents the adaptability score at different levels. The adaptability score at each level is calculated based on the input molten salt energy storage architecture data, including... , as well as According to the function Hierarchical assessment is performed, including an adaptability score for ultra-high heat zones. Regional main thermal zone layer adaptability score and the adaptability score of the molten salt energy storage architecture layer According to the function Perform a hierarchy determination.

[0046] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the zoning determination is specifically as follows:

[0047] Define stable regions, dynamically adjusted regions, and abnormal regions, and set the range of interval variation thresholds. , This represents the minimum threshold for interval variation. Indicates the maximum threshold for interval variation;

[0048] Calculate the coefficient of variation corresponding to the input molten salt energy storage architecture data. It is used for partition determination, specifically:

[0049] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are stable region data;

[0050] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are dynamically adjusted region data;

[0051] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are in an abnormal region.

[0052] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the dynamic adjustment of the characteristic mean and standard deviation of the different levels of molten salt energy storage architecture is as follows:

[0053] Statistics on a time window Total amount of data detected internally And collect the number of data points in the abnormal areas within the time window. And calculate the anomaly rate within the time window. Based on the calculated anomaly rate, the characteristic mean and standard deviation of the molten salt energy storage architecture are dynamically adjusted, resulting in the following:

[0054] If the abnormality rate within the calculated time window satisfies the formula This indicates that the data anomaly rate in the current region exceeds the standard. By adjusting the characteristic mean and standard deviation of the molten salt energy storage architecture, the coefficient of variation can be adjusted, thereby enabling a re-evaluation of the region.

[0055] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the state transition matrix is ​​specifically constructed as follows:

[0056] Statistics on a time window Inside, the molten salt energy storage architecture is in operation as follows: Duration And the molten salt energy storage architecture is in operation. Duration Then, by constructing the state transition matrix, we have:

[0057] ;

[0058] in, This indicates that the molten salt energy storage architecture is in operation. Duration, This indicates that the molten salt energy storage architecture is in operation. Duration, Indicates the operating status of the molten salt energy storage architecture from Transition to running state The probability, , This indicates the operational state categories of the molten salt energy storage architecture, including stable state, dynamically adjusting state, and abnormal state, each corresponding to a data judgment region. During the construction of the state transition matrix, for... , The value of must satisfy the formula ;

[0059] Based on the calculated state transition probabilities and the state transition matrix of the molten salt energy storage architecture, we have:

[0060] State transition probability Among them, the operational status categories of molten salt energy storage architecture , Each value has three operating states, obtained through... , With different values, a dimension is constructed based on the state transition probability. State transition matrix .

[0061] As a preferred embodiment of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention, the specific steps of identifying potential anomalies in the molten salt energy storage architecture by constructing a state transition matrix are as follows:

[0062] Set a state transition probability threshold ,and Based on the set transition probability threshold, potential anomalies in the molten salt energy storage architecture are identified, and thus,

[0063] For any transition probability in the state transition matrix If the formula is satisfied This indicates that the transition of the molten salt energy storage architecture has exceeded the upper limit of the threshold, immediately triggering the early warning function. At the same time, the data collection frequency of the current area is increased, and a time series prediction model is used for secondary identification of anomalies. If the secondary identification result is still an abnormal state transition, it indicates that the current state of the molten salt energy storage architecture is abnormal, and relevant personnel are notified to carry out maintenance.

[0064] The technical effects and advantages of this invention are as follows: This invention integrates molten salt energy storage architecture data through cloud computing and combines it with intelligent algorithms for dynamic hierarchical and zonal analysis, realizing automatic perception and intelligent decision-making of the molten salt energy storage architecture's operating status, thus improving the automation and intelligence level of molten salt energy storage architecture regulation; Utilizing distributed computing methods, it achieves efficient storage, calculation, and analysis of data at different levels, such as ultra-high heat zones, regional main heat zones, and molten salt energy storage architectures, breaking through the limitations of traditional regulation modes in terms of computing power; By dynamically adjusting the zonal anomaly detection threshold and combining it with global impact analysis, it intelligently optimizes the anomaly level, achieving rapid and accurate identification of molten salt energy storage architecture faults or abnormal states, thus improving the real-time performance of molten salt energy storage architecture anomaly response; Through dynamic threshold adjustment and state transition matrix analysis based on historical data, it achieves trend prediction and accurate optimization of the molten salt energy storage architecture's operating status, reducing misjudgments and unnecessary regulation operations, and improving regulation reliability; Through intelligent hierarchical and zonal analysis and regulation, it achieves reasonable allocation of molten salt energy storage architecture resources, reducing manual intervention and energy loss, improving the economic efficiency of molten salt energy storage architecture operation, and reducing overall operation and maintenance costs. Attached Figure Description

[0065] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts:

[0066] Figure 1 This is a schematic diagram of the implementation steps of the 6kV high-power stepless adjustable molten salt energy storage electric heating system of the present invention. Detailed Implementation

[0067] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0068] Reference Figure 1 The first embodiment of the present invention provides a 6kV high-power stepless adjustable molten salt energy storage electric heating system, including a heating unit: adopting a modular high-voltage radiation design, the heating tube is fixed to a stainless steel shell by ceramic insulators, the interior is filled with magnesium oxide insulation material, and the exterior is wrapped with an aluminum silicate fiber insulation layer; the flow channel system: molten salt is diverted from the main inlet pipe to the serpentine inlet branch pipes, and enters the outlet branch pipe through the exchange chamber to form a long-path convection, which enhances the uniformity of heat transfer;

[0069] The intelligent control module integrates a PLC controller, fuzzy PID algorithm, and leakage detection unit. It monitors temperature changes in real time through the gas expansion chamber and adjusts the output power in conjunction with the power control cabinet. The molten salt electric heater, through the combination of specially designed heating elements and a pressure vessel, forms a complete heating system. This system mainly consists of an electric heating core, a heating container, and a control unit. Its basic working principle is to convert electrical energy into heat energy through resistance heating elements, and then use fluid thermodynamics principles to evenly transfer the heat generated by the heating elements to the molten salt medium, bringing its temperature to the required level, thereby achieving efficient and stable heat energy storage and release. During the operation of the molten salt electric heater, the heating elements generate heat through current, and the molten salt absorbs and stores the heat as a medium. The heat generated during the heating process is rapidly and evenly distributed within the container through the convection and conduction effects of fluid thermodynamics, ensuring efficient energy transfer and storage of the heating system. Through this technical principle, the equipment can operate stably and effectively improve energy conversion efficiency.

[0070] This molten salt electric heater features fully adjustable operation, employing variable-cycle zero-crossing control to regulate power output during the heating process. This control strategy allows the system to adjust power in real-time under different operating conditions, ensuring a more stable and precise heating process for the molten salt. In local mode, start-up and shutdown can be performed from the control cabinet and on-site operating columns. In this mode, instruments in the control cabinet monitor the deviation between the molten salt outlet temperature and the set temperature in real time and adjust the temperature using a PID algorithm. The system outputs a 4-20mA control signal based on the PID calculation results, which is then transmitted to the power regulator to precisely adjust the heater's power, ensuring accurate temperature control and heating process stability. In remote mode, the control system is centrally controlled via a distributed control system (DCS). The DCS not only monitors the difference between the outlet temperature and the set temperature but also performs real-time calculations based on the PID algorithm, outputting a 4-20mA signal to the control cabinet. Upon receiving the signal, the power regulator in the control cabinet continues to adjust the power output, ensuring precise temperature control during system operation. This intelligent and collaborative control method enables the molten salt electric heater to operate stably in large-scale energy storage systems and complex operating conditions, while optimizing energy utilization efficiency and reducing system operational complexity. To ensure safe and stable system operation, the molten salt electric heater is equipped with multiple safety protection measures. The system incorporates multiple temperature sensors to monitor the temperature changes of the molten salt in real time, ensuring that the temperature fluctuates within a safe range. If the system detects that the temperature exceeds the set range, the control system will automatically take measures to reduce the heating power or stop the heating operation, thereby avoiding equipment damage caused by overheating. In addition, the system is equipped with overcurrent, overvoltage, and overtemperature protection functions to ensure that the equipment can automatically shut down in abnormal conditions, preventing accidents.

[0071] The main performance indicators are as follows: 1. Outlet temperature: molten salt temperature > 560℃; 2. Electrothermal conversion efficiency: > 98%; 3. Rated power: > 1.2MW; 4. Surface load of electric heating element: ≦ 8w / cm2; 5. Rated voltage: 6kV.

[0072] Test performance indicators: 1. Outlet temperature: molten salt temperature >565℃, temperature control accuracy up to ±1℃; 2. Electrothermal conversion efficiency: >98.5%; 3. Rated power: >1.2MW; 4. Surface load of electric heating element: ≦8w / cm2; 5. Dielectric strength test: able to withstand AC voltage test of 13kV;

[0073] It also includes the storage medium for performing the following steps,

[0074] S1: Layered and partitioned data fusion and feature construction of molten salt energy storage architecture.

[0075] Specifically, the hierarchical and partitioned data fusion and feature construction of the molten salt energy storage architecture involves collecting data from different levels of the molten salt energy storage architecture, fusing the collected data, and constructing features based on the fused molten salt energy storage architecture data. This provides an accurate data foundation for subsequent intelligent analysis of the hierarchical and partitioned molten salt energy storage architecture. The specific implementation is as follows:

[0076] By collecting real-time operating parameters at different levels of the molten salt energy storage architecture, we can obtain the following:

[0077] ;

[0078] in, This indicates the molten salt energy storage architecture hierarchy, including: Indicates an extremely hot zone. Indicates the main hot zone and This indicates a molten salt energy storage architecture. Indicates the first Data collection at different levels Indicates the first The first in the hierarchy Each detection point data vector is a multi-dimensional data vector, including voltage data, temperature data, frequency data, and power data. This indicates the number of detection points in each layer, and the number of detection points is the same in each layer;

[0079] Simultaneously, based on the historical database, the same historical data set as the real-time molten salt energy storage architecture data is extracted. Historical data sets differ from real-time data sets only in the time dimension; their other components are completely identical.

[0080] Based on real-time acquired molten salt energy storage architecture data and extracted historical data, the feature matrix of the molten salt energy storage architecture data is extracted using a spatiotemporal feature extraction function. Then, we have...

[0081] Short-term features, long-term trend features, and spatial correlation features of molten salt energy storage architecture data are extracted using spatiotemporal feature extraction functions, specifically:

[0082] Short-term feature extraction,

[0083] ;

[0084] Long-term trend characteristics

[0085] ;

[0086] Spatial correlation characteristics

[0087] ;

[0088] Based on the extracted features, a feature matrix is ​​constructed from the molten salt energy storage architecture data, then we have:

[0089] ;

[0090] in, Indicates the first The first in the hierarchy Data vector of each detection point, This indicates the number of detection points in each layer; the number of detection points is the same in each layer. Represents a historical data set. This represents the extracted short-term features. This indicates the extracted spatial correlation features. This represents the extracted long-term trend characteristics. Represents the short-time feature extraction function. This represents the long-term trend feature extraction function. This represents the spatial correlation feature extraction function. This represents the data feature matrix of the molten salt energy storage architecture;

[0091] Adaptive fusion of data from different levels based on the molten salt energy storage architecture data matrix is ​​performed as follows:

[0092] To address the distribution differences in data characteristics across different levels of molten salt energy storage architectures, a hierarchical adaptive clustering algorithm is used to achieve adaptive fusion of data from different levels. This results in...

[0093] Data feature matrix of the constructed molten salt energy storage architecture Calculate the characteristic mean values ​​of ultra-high heat zone, regional main heat zone, and molten salt energy storage architecture. and standard deviation Based on the calculated standard deviation, the data clustering radius for each level is determined. This generates the initial set of cluster centers. ;

[0094] For the generated initial set of cluster centers, calculate the set of data points covered by each cluster center, and update the cluster centers to generate a new set of cluster centers. (Second-generation cluster centers), then we have,

[0095] For the initial set of cluster centers ,in,

[0096] ;

[0097] in, Represents the first cluster in the initial set of cluster centers. Cluster centers, Representing cluster centers The set of data points covered Representing cluster centers The data points covered;

[0098] For the generated set of second-generation cluster centers, adaptive adjustments are made to all cluster centers in the set, specifically as follows:

[0099] Select all cluster centers in the second-generation cluster center set, calculate their density adaptive adjustment factor, and update the position of the cluster centers based on the adjustment factor to generate a new cluster center set (third-generation cluster centers).

[0100] Based on the iteration of the selected initial cluster center set, second-generation cluster center set, and third-generation cluster center set, hierarchical adaptive clustering is achieved, then we have:

[0101] The iteration for the second-generation cluster centers is as follows:

[0102] For the initial set of cluster centers, the positions of the cluster centers are adjusted by calculating the distribution density of data points, requiring that all cluster centers in the adjusted set can cover a more reasonable data distribution than the initial set of cluster centers;

[0103] The iteration for the three generations of cluster centers is as follows:

[0104] For all cluster centers in the second-generation cluster center set, adjust the position of the cluster centers and ensure that at least one cluster center in the third-generation cluster center set can improve the cluster consistency score;

[0105] Based on the iteration of second-generation and third-generation cluster centers, the process continues until all second-generation cluster centers can find third-generation cluster centers with higher cluster consistency scores. At this point, the set of all third-generation cluster centers is the final hierarchical adaptive clustering result. Specifically:

[0106] Consistency score,

[0107] ;

[0108] ;

[0109] in, This represents the total number of cluster centers. The category index representing the cluster center, Indicates the first Cluster centers, Indicates the first A set of data points with cluster centers. A data point representing the cluster center. This represents the set of second-generation cluster centers. This represents the set of third-generation cluster centers. This represents the cluster consistency score, used to iterate through cluster centers. This represents the consistency score of the second-generation cluster centers. This represents the consistency score of the third-generation cluster centers.

[0110] S2: Layered and partitioned intelligent analysis and anomaly detection of molten salt energy storage architecture.

[0111] Specifically, the intelligent analysis and anomaly detection of the molten salt energy storage architecture's hierarchical partitioning utilizes a hierarchical network structure and aggregates data from the molten salt energy storage architecture to perform intelligent analysis of its hierarchical partitioning. Based on the intelligent analysis results, anomaly detection is performed on the hierarchical partitioning of the molten salt energy storage architecture through a dynamic hierarchical architecture. The specific implementation is as follows:

[0112] Aggregation results of molten salt energy storage architecture data Then there is, And by calculating the characteristic mean and standard deviation of different levels of molten salt energy storage architecture, we have the characteristic mean of the ultra-high thermal zone. Mean of characteristics of the main heat zone in the region and the average characteristics of molten salt energy storage architecture Standard deviation of ultra-high heat zone Standard deviation of the main heat zone and the standard deviation of molten salt energy storage architecture ;

[0113] Based on the aggregated data of molten salt energy storage architecture, the hierarchical determination of the molten salt energy storage architecture's layered partitioning is performed, specifically as follows:

[0114] Input molten salt energy storage architecture data Based on the characteristic mean and standard deviation of different molten salt energy storage architectures, the hierarchy is determined, and thus,

[0115] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the ultra-high voltage level;

[0116] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the regional main thermal zone level;

[0117] If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the molten salt energy storage architecture level.

[0118] It should be noted that if the input data simultaneously meets the judgment conditions of multiple levels, then the level judgment is made based on the calculated adaptability scores of different levels, specifically as follows:

[0119] Adaptability scores at different levels Then there is,

[0120] ;

[0121] in, This represents the input molten salt energy storage architecture data. , These represent the characteristic mean and standard deviation of different molten salt energy storage architectures, respectively, by controlling... The value of controls the selection of different levels of molten salt energy storage architecture. This represents the adaptability score at different levels. The adaptability score at each level is calculated based on the input molten salt energy storage architecture data, including... , as well as According to the function Perform a hierarchy determination.

[0122] After the initial hierarchical determination, partitioning is performed based on the coefficient of variation of the input data, as follows:

[0123] Define stable regions, dynamically adjusted regions, and abnormal regions, and set the range of interval variation thresholds. ;

[0124] Calculate the coefficient of variation corresponding to the input molten salt energy storage architecture data, and then we have:

[0125] ;

[0126] in, This represents the input molten salt energy storage architecture data. , These represent the characteristic mean and standard deviation of different molten salt energy storage architectures, respectively, by controlling... The value of controls the selection of different levels of molten salt energy storage architecture. The coefficients of variation for different levels are used for partitioning, specifically:

[0127] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are stable region data;

[0128] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are dynamically adjusted region data;

[0129] If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are in an abnormal region.

[0130] It should be noted that, in order to improve the accuracy of data partitioning, continuous monitoring of abnormal areas enables dynamic adjustment of the characteristic mean and standard deviation of different levels of molten salt energy storage architecture, thereby achieving dynamic adjustment of the interval variation threshold. Specifically:

[0131] Statistics on a time window Total amount of data detected internally And collect the number of data points in the abnormal areas within the time window. And by calculating the anomaly rate within the time window, we have:

[0132] ;

[0133] in, Indicates time window The total amount of data detected internally. This indicates the number of data points in the outlier region within the time window. This represents the anomaly rate within the time window, used to control the dynamic adjustment of the characteristic mean and standard deviation of the molten salt energy storage architecture, specifically:

[0134] If the abnormality rate within the calculated time window satisfies the formula This indicates that the data anomaly rate in the current region exceeds the standard. By adjusting the characteristic mean and standard deviation of the molten salt energy storage architecture, the coefficient of variation is adjusted, thereby enabling a re-evaluation of the region. Therefore, we have...

[0135] ;

[0136] ;

[0137] in, , This indicates the adjustment factor, which is set by the implementers based on the actual application scenario. , These represent the characteristic mean and standard deviation of different molten salt energy storage architectures, respectively. , These represent the mean and standard deviation of historical outlier data for the outlier region, respectively. , These represent the mean and standard deviation of the adjusted molten salt energy storage architectures at different levels, respectively.

[0138] The mean and standard deviation of different molten salt energy storage architectures were adjusted. To improve the accuracy of data region determination, the interval variation threshold was adjusted synchronously, specifically as follows:

[0139] ;

[0140] ;

[0141] in, This indicates the adjustment factor, which is set by the implementers based on the actual application scenario. , These represent the mean and standard deviation of the adjusted molten salt energy storage architecture for different tiers, respectively. This represents the minimum threshold for interval variation. Indicates the maximum threshold of interval variation. This represents the minimum threshold for the adjusted interval variation. This represents the maximum threshold for the adjusted interval variation.

[0142] After performing hierarchical and partitioned determinations on the input molten salt energy storage architecture data, potential anomalies in the molten salt energy storage architecture are identified by constructing a state transition matrix. The specific implementation is as follows:

[0143] Constructing state transition probabilities This indicates the change in the operating status of the molten salt energy storage architecture from... Transition to running state The probability of [the probability] is constructed as follows:

[0144] Statistics on a time window Inside, the molten salt energy storage architecture is in operation as follows: Duration And the molten salt energy storage architecture is in operation. Duration Then, by constructing the state transition matrix, we have:

[0145] ;

[0146] in, This indicates that the molten salt energy storage architecture is in operation. Duration, This indicates that the molten salt energy storage architecture is in operation. Duration, Indicates the operating status of the molten salt energy storage architecture from Transition to running state The probability, , This indicates the operational state categories of the molten salt energy storage architecture, including stable state, dynamically adjusting state, and abnormal state, each corresponding to a data judgment region. During the construction of the state transition matrix, for... , The value of must satisfy the formula ;

[0147] Based on the calculated state transition probabilities and the state transition matrix of the molten salt energy storage architecture, we have:

[0148] State transition probability Among them, the operational status categories of molten salt energy storage architecture , Each value has three operating states; therefore, through... , With different values, a dimension is constructed based on the state transition probability. State transition matrix Then there is,

[0149] ;

[0150] in, This represents the constructed state transition matrix. Indicates the operating status of the molten salt energy storage architecture from Transition to running state The probability, , Indicates the operational status category of the molten salt energy storage architecture;

[0151] Potential anomalies in the molten salt energy storage architecture are identified based on the constructed state transition matrix, specifically:

[0152] Set a state transition probability threshold ,and Based on the set transition probability threshold, potential anomalies in the molten salt energy storage architecture are identified, and thus,

[0153] For any transition probability in the state transition matrix If the formula is satisfied This indicates that the transition of the molten salt energy storage architecture has exceeded the upper limit of the threshold, immediately triggering the early warning function. At the same time, the data collection frequency of the current area is increased, and a time series prediction model is used for secondary identification of anomalies. If the secondary identification result is still an abnormal state transition, it indicates that the current state of the molten salt energy storage architecture is abnormal, and relevant personnel are notified to carry out maintenance.

[0154] S3: Layered and zoned intelligent optimization decision-making and control execution of molten salt energy storage architecture.

[0155] Specifically, the hierarchical and zonal intelligent optimization decision-making and control execution of the molten salt energy storage architecture analyzes the operating status of each level based on data from different levels of the molten salt energy storage architecture, and performs intelligent optimization decision-making and control execution based on abnormal characteristics and global impact, as detailed below:

[0156] For different levels of molten salt energy storage architecture, layered and zoned intelligent optimization is performed, specifically as follows:

[0157] For the input molten salt energy storage architecture data, calculate the mean and standard deviation of the operating parameters of the ultra-high heat zone, the main heat zone, and the molten salt energy storage architecture, and set the anomaly judgment threshold based on the standard deviation to initially screen out abnormal areas;

[0158] For the selected abnormal areas, analyze the status of adjacent areas, determine whether the abnormality has a global impact, and adjust the abnormality level accordingly to generate an optimization decision basis.

[0159] Based on the optimization decision-making criteria, intelligent control is implemented, specifically: selecting areas with continuous anomalies, calculating their load adjustment factor and voltage optimization factor, and adjusting operating parameters based on these factors to optimize the state of the area;

[0160] Based on the initially identified abnormal areas, the basis for optimization decisions, and the iterative execution of intelligent control, hierarchical and zoned intelligent optimization is achieved, resulting in:

[0161] The iteration for optimizing the decision-making basis is as follows:

[0162] For the initially screened abnormal areas, the abnormality level is adjusted through global impact analysis, and the adjusted abnormality level is required to more accurately reflect the operating status of the molten salt energy storage architecture.

[0163] The iteration for intelligent control execution is as follows:

[0164] For the abnormal areas in all optimization decision-making criteria, adjust their operating parameters and ensure that at least one area can be restored to a stable state, thereby improving the overall stability of the molten salt energy storage architecture.

[0165] Based on the optimization decision criteria and the iterative execution of intelligent control, until a reasonable optimization and adjustment plan can be found for all areas with continuous anomalies, the set of all optimized areas at this point is the final result of hierarchical and partitioned intelligent optimization decision and control execution.

[0166] Furthermore, if the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0167] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0168] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0169] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

A 1.6kV high-power stepless adjustable molten salt energy storage electric heating system, characterized in that: include, Heating unit; adopts a modular high-voltage radiant design; Flow channel system: Molten salt is diverted from the main inlet pipe to the serpentine inlet branches, and then enters the outlet branches through the exchange chamber to form long-path convection, which enhances the uniformity of heat transfer; Intelligent control module; integrates PLC controller, fuzzy PID algorithm and leakage detection unit; It also includes the storage medium for performing the following steps, The hierarchical and partitioned data fusion and feature construction of molten salt energy storage architecture are as follows: Data was collected for molten salt energy storage architectures at different levels. Short-term features, long-term trend features, and spatial correlation features of the molten salt energy storage architecture data were extracted using spatiotemporal feature extraction functions. Based on the distribution differences of the data features of molten salt energy storage architectures at different levels, a hierarchical adaptive clustering algorithm was used to adaptively fuse the data. The molten salt energy storage architecture features layered and zoned intelligent analysis and anomaly detection, specifically: Based on the adaptive fusion results, a hierarchical network structure is used for intelligent analysis of the hierarchical partitioning of molten salt energy storage architecture. This includes determining the hierarchy and partitioning of molten salt energy storage architecture data. Based on the intelligent analysis results, a state transition matrix is ​​constructed to identify potential anomalies in the molten salt energy storage architecture. By continuously monitoring the abnormal areas in the partitioning results, the characteristic mean and standard deviation of different levels of molten salt energy storage architecture can be dynamically adjusted, thereby enabling dynamic adjustment of the interval variation threshold. The molten salt energy storage architecture features layered and zoned intelligent optimization decision-making and control execution, specifically as follows: Based on the data of molten salt energy storage architecture at different levels, the operating status of each level is analyzed, and intelligent optimization decisions and control execution are carried out based on abnormal characteristics and global impact. The data collection process is as follows: By collecting real-time operating parameters at different levels of the molten salt energy storage architecture, we can obtain the following: ； in, This indicates the molten salt energy storage architecture hierarchy, including: Indicates an extremely hot zone. Indicates the main hot zone and This indicates a molten salt energy storage architecture. Indicates the first Data collection at different levels Indicates the first The first in the hierarchy Each detection point data vector is a multi-dimensional data vector, including voltage data, temperature data, frequency data, and power data. This indicates the number of detection points in each layer, and the number of detection points is the same in each layer; Simultaneously, based on the historical database, the same historical data set as the real-time molten salt energy storage architecture data is extracted. ; The adaptive fusion of data using a hierarchical adaptive clustering algorithm is described in detail below: To address the distribution differences in data characteristics across different levels of molten salt energy storage architectures, a hierarchical adaptive clustering algorithm is used to achieve adaptive fusion of data from different levels. This results in... Data feature matrix of the constructed molten salt energy storage architecture Calculate the characteristic mean values ​​of ultra-high heat zone, regional main heat zone, and molten salt energy storage architecture. and standard deviation Based on the calculated standard deviation, the data clustering radius for each level is determined. This generates the initial set of cluster centers. ; For the generated initial set of cluster centers, calculate the set of data points covered by each cluster center, and update the cluster centers to generate a new set of cluster centers. ; For the generated set of second-generation cluster centers, adaptive adjustments are made to all cluster centers in the set, specifically as follows: Select all cluster centers in the second-generation cluster center set, calculate their density adaptive adjustment factor, and update the position of the cluster centers based on the adjustment factor to generate a new cluster center set; Based on the iteration of the selected initial cluster center set, second-generation cluster center set, and third-generation cluster center set, hierarchical adaptive clustering is achieved, then we have: The iteration for the second-generation cluster centers is as follows: For the initial set of cluster centers, the positions of the cluster centers are adjusted by calculating the distribution density of data points, requiring that all cluster centers in the adjusted set can cover a more reasonable data distribution than the initial set of cluster centers; The iteration for the three generations of cluster centers is as follows: For all cluster centers in the second-generation cluster center set, adjust the position of the cluster centers and ensure that at least one cluster center in the third-generation cluster center set can improve the cluster consistency score; Based on the iteration of second-generation and third-generation cluster centers, the process continues until all second-generation cluster centers can find third-generation cluster centers with higher cluster consistency scores. At this point, the set of all third-generation cluster centers is the final hierarchical adaptive clustering result. ; The state transition matrix is ​​constructed as follows: Statistics on a time window Inside, the molten salt energy storage architecture is in operation as follows: Duration And the molten salt energy storage architecture is in operation. Duration Then, by constructing the state transition matrix, we have: ； in, This indicates that the molten salt energy storage architecture is in operation. Duration, This indicates that the molten salt energy storage architecture is in operation. Duration, Indicates the operating status of the molten salt energy storage architecture from Transition to running state The probability, , This indicates the operational state categories of the molten salt energy storage architecture, including stable state, dynamically adjusting state, and abnormal state, each corresponding to a data judgment region. During the construction of the state transition matrix, for... , The value of must satisfy the formula ; Based on the calculated state transition probabilities and the state transition matrix of the molten salt energy storage architecture, we have: State transition probability Among them, the operational status categories of molten salt energy storage architecture , Each value has three operating states, obtained through... , With different values, a dimension is constructed based on the state transition probability. State transition matrix ; The specific steps for identifying potential anomalies in molten salt energy storage architectures by constructing a state transition matrix are as follows: Set a state transition probability threshold ,and Based on the set transition probability threshold, potential anomalies in the molten salt energy storage architecture are identified, and thus, For any transition probability in the state transition matrix If the formula is satisfied This indicates that the transition of the molten salt energy storage architecture has exceeded the upper limit of the threshold, immediately triggering the early warning function. At the same time, the data collection frequency of the current area is increased, and a time series prediction model is used for secondary identification of anomalies. If the secondary identification result is still an abnormal state transition, it indicates that the current state of the molten salt energy storage architecture is abnormal, and relevant personnel are notified to carry out maintenance.

2. The 6kV high-power stepless adjustable molten salt energy storage electric heating system according to claim 1, characterized in that, The specific cluster consistency score is as follows: ； ； in, This represents the total number of cluster centers. The category index representing the cluster center, Indicates the first Cluster centers, In the second-generation cluster center set, the first... Cluster centers, In the set of three-generation cluster centers, the first... Cluster centers, Indicates the first A set of data points with cluster centers. A data point representing the cluster center. This represents the set of second-generation cluster centers. This represents the set of third-generation cluster centers. This represents the cluster consistency score, used to iterate through cluster centers. This represents the consistency score of the second-generation cluster centers. This represents the consistency score of the third-generation cluster centers.

3. The 6kV high-power stepless adjustable molten salt energy storage electric heating system according to claim 2, characterized in that, The hierarchical determination of the molten salt energy storage architecture data is as follows: Input molten salt energy storage architecture data The stratification is determined based on the characteristic mean and standard deviation of different molten salt energy storage architectures, including the characteristic mean of ultra-high voltage strata. Mean of regional main heat zone hierarchical characteristics Mean characteristics of molten salt energy storage architecture hierarchy And, the standard deviation of ultra-high pressure levels Standard deviation of the main heat zone level Standard deviation of molten salt energy storage architecture at different levels Then there is, If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the ultra-high voltage level; If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the regional main thermal zone level; If the input molten salt energy storage architecture data and the characteristic mean and standard deviation of different levels of molten salt energy storage architecture satisfy the formula This indicates that the currently input molten salt energy storage architecture data is at the molten salt energy storage architecture level.

4. The 6kV high-power stepless adjustable molten salt energy storage electric heating system according to claim 3, characterized in that, If the input data simultaneously meets the judgment conditions of multiple levels, then the level is determined by calculating the adaptability scores of different levels, and the level is judged based on the calculated adaptability scores. Specifically: Adaptability scores at different levels Then there is, ； in, This represents the input molten salt energy storage architecture data. , These represent the characteristic mean and standard deviation of different molten salt energy storage architectures, respectively, by controlling... The value of controls the selection of different levels of molten salt energy storage architecture. This represents the adaptability score at different levels. It is calculated using the input molten salt energy storage architecture data, and includes the adaptability score for the ultra-high thermal zone layer. Regional main thermal zone layer adaptability score and the adaptability score of the molten salt energy storage architecture layer According to the function Perform a hierarchy determination.

5. The 6kV high-power stepless adjustable molten salt energy storage electric heating system according to claim 4, characterized in that, The partition determination is as follows: Define stable regions, dynamically adjusted regions, and abnormal regions, and set the range of interval variation thresholds. , This represents the minimum threshold for interval variation. Indicates the maximum threshold for interval variation; Calculate the coefficient of variation corresponding to the input molten salt energy storage architecture data. It is used for partition determination, specifically: If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are stable region data; If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are dynamically adjusted region data; If the calculated coefficient of variation satisfies the formula This indicates that the data points in the current level are in an abnormal region.

6. The 6kV high-power stepless adjustable molten salt energy storage electric heating system according to claim 5, characterized in that, The dynamic adjustment of the characteristic mean and standard deviation of the different molten salt energy storage architectures is as follows: Statistics on a time window Total amount of data detected internally And collect the number of data points in the abnormal areas within the time window. And calculate the anomaly rate within the time window. Based on the calculated anomaly rate, the characteristic mean and standard deviation of the molten salt energy storage architecture are dynamically adjusted, resulting in the following: If the abnormality rate within the calculated time window satisfies the formula This indicates that the data anomaly rate in the current region exceeds the standard. By adjusting the characteristic mean and standard deviation of the molten salt energy storage architecture, the coefficient of variation can be adjusted, thereby enabling a re-evaluation of the region.

Images