An electric appliance and a control system thereof

Abstract

The application relates to the technical field of electric appliance control, in particular to an electric appliance and a control system thereof, which comprises a feature extraction module, a distribution alignment module, a parameter trend modeling module, a sensitivity analysis module and an operation strategy optimization module.In the application, through accurate screening of environmental parameters and feature parameter sparse basis vector calculation, data redundancy is significantly reduced, the analysis efficiency and pertinence are improved, the statistical adjustment of differentiated time period distribution optimizes data consistency in combination with equipment performance parameters, accurate adaptability to complex working conditions is provided, dynamic feature modeling based on time series trends realizes future change prediction of environmental parameters, effectively enhances the prediction ability and regulation efficiency of the system, the sensitivity weight distribution clearly shows the influence of each feature parameter, optimizes the collaborative control among equipment, balances performance and energy consumption, and realizes dynamic optimization of multifunction linkage.

Description

Technical Field

[0001] This invention relates to the field of electrical control technology, and in particular to an electrical device and its control system. Background Technology

[0002] The field of electrical control technology encompasses methods for controlling and managing electrical equipment, as well as related system design. The core of this technology lies in achieving intelligent, efficient, and precise control of electrical equipment, involving multiple stages such as the detection of operating parameters, the generation and transmission of control signals, and the operation of actuators. The overall technology systematically covers the design and optimization of hardware controllers, the development and implementation of control logic, system communication and coordination, and the inter-device linkage control of various electrical devices.

[0003] Among them, the electrical control system refers to the technical means of combining hardware and software to achieve centralized or decentralized management of electrical equipment. This patent focuses on the automated control and intelligent operation of electrical equipment, covering the design and collaboration of signal acquisition and processing modules, circuit control modules, and logic execution units. By establishing efficient data transmission paths and precise logical judgment mechanisms, it realizes the switching control, working status adjustment, and multi-functional linkage task allocation of electrical equipment.

[0004] Existing technologies rely on static analysis for parameter selection, failing to effectively eliminate non-critical parameters and resulting in redundant data that affects control accuracy. Parameter distribution alignment lacks dynamic adaptability, making it difficult to handle nonlinear data deviations under complex operating conditions and impacting system consistency. Time series analysis is limited to simple modeling of historical data, lacking the ability to accurately predict dynamic environmental changes. Sensitivity analysis between characteristic parameters lacks a systematic strategy, hindering precise parameter control and optimized resource allocation, and failing to meet the demands of intelligent control and multi-functional linkage. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and to propose an electrical device and its control system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an electrical control system comprising:

[0007] The feature extraction module calculates the sparse basis vectors of environmental parameters in the feature space based on the set of environmental parameters, removes parameters based on correlation, compares the impact of temperature control with the operating data of compressor and refrigerant flow, filters features directly related to temperature control performance fluctuations, and generates a set of key feature parameters.

[0008] Based on the set of key feature parameters, the distribution alignment module calculates the statistical distribution pattern of parameters in different time periods, adjusts the parameters by comparing the deviation values ​​in the distribution, establishes mapping rules by combining the performance data of expansion valve and condenser, adjusts the feature distribution values ​​to a unified reference distribution, calculates the consistency of the adjusted data, and generates aligned feature distribution values.

[0009] Based on the aligned feature distribution values, the parameter trend modeling module analyzes the trend of time-series feature changes, establishes a feature evolution model by combining evaporator and compressor operating data, fits the future distribution pattern through time-series feature changes, infers the dynamic changes of environmental parameters, and generates feature time-series prediction values.

[0010] Based on the predicted time series values ​​of the features, the sensitivity analysis module calculates the sensitivity changes of multiple features to temperature control performance, analyzes the effect trend of sensitivity values ​​on performance indicators in conjunction with refrigerant flow rate changes, extracts the gradient relationship between sensitivity and performance, adjusts the weight allocation of the feature set, and generates sensitivity adjustment weight values.

[0011] The operation strategy optimization module adjusts the equipment operating parameters based on the sensitivity adjustment weight value, updates the control strategy in conjunction with the operating status of the compressor and expansion valve, and gradually optimizes the operating parameters of multiple key components. The optimization is completed through multiple calculations of equipment operating parameters, generating a dynamic control optimization parameter set.

[0012] As a further aspect of the present invention, the feature extraction module includes:

[0013] The sparse basis vector extraction submodule calculates the sparse basis vectors of the environmental parameters in the feature space based on the set of environmental parameters, normalizes the range of multiple parameter values ​​in the set of environmental parameters, decomposes the feature space using matrix operations, and extracts the sparse basis vectors of the parameters in the spatial dimension based on the decomposition results, generating a sparse basis vector set.

[0014] The correlation elimination submodule analyzes the correlation between environmental parameters based on the sparse basis vector set, eliminates parameters with correlation below a specified threshold based on the calculation results, and verifies the filtered parameter set using the correlation calculation model to obtain the correlation-filtered parameter set.

[0015] The key feature screening submodule, based on the aforementioned correlation screening parameter set and combined with the operating data of the compressor and refrigerant flow, uses a correlation calculation model to compare the correlation between temperature control performance fluctuations and parameters, and screens the feature parameters that contribute the most to temperature control performance fluctuations, thereby generating a key feature parameter set.

[0016] As a further aspect of the present invention, the feature space is decomposed using matrix operations, employing the following formula:

[0017] ;

[0018] Calculate matrix decomposition weights Based on the decomposition results, sparse basis vectors of the parameters in the spatial dimension are extracted to generate a sparse basis vector set;

[0019] in, Indicates environmental parameters and The weighted coefficient matrix generated during the feature space decomposition process. and These represent the first element in the set of environmental parameters. Item and the Standardized value of the item and These represent the first element in the set of environmental parameters. Item and the The parameters of the term in the feature space are... Projection values ​​in the dimension, The dimension of the feature space. and These represent the first element in the set of environmental parameters. Item and the The term after decomposition in the feature space is the first The absolute weight of each subspace, This indicates the number of subspaces after the feature space is decomposed.

[0020] As a further aspect of the present invention, the distribution alignment module includes:

[0021] The distribution pattern calculation submodule extracts parameter values ​​within the differentiated time periods based on the key feature parameter set, performs statistical classification on the parameter set, calculates the central value, distribution range and skewness of multiple parameters in the differentiated time periods, performs data pattern feature analysis on the statistical results, and obtains the time period distribution feature set.

[0022] The parameter deviation adjustment submodule calculates the difference between distributions based on the time period distribution feature set using a difference degree calculation model based on pairwise comparisons. It determines the deviation direction by comparing data, adjusts the parameter value range based on the difference degree, and corrects the adjustment result by combining the performance data of the expansion valve and condenser, thereby generating a deviation adjustment parameter set.

[0023] The unified distribution mapping submodule establishes a mapping rule between parameters and a unified reference distribution based on the deviation adjustment parameter set. It adjusts the range of distribution data by calculating the mapping position of multiple parameter values ​​in the unified distribution, recalculates the data consistency between the adjusted parameters, and generates aligned feature distribution values.

[0024] As a further aspect of the present invention, the parameter trend modeling module includes:

[0025] The time-series feature analysis submodule extracts the parameter change sequence in the time dimension based on the alignment feature distribution value, analyzes the change rate of the parameter in multiple time periods on the time axis, and summarizes the periodicity and abrupt change points of the time distribution feature by calculating the growth rate, decrease magnitude and fluctuation frequency of the parameter in multiple time periods, and generates a time-series distribution feature set.

[0026] The feature evolution modeling submodule, based on the time-series distribution feature set and combined with the operating data of the evaporator and compressor, establishes a correlation matrix for the change pattern of feature parameters on the time axis, calculates and derives the dynamic change trend of parameters based on the correlation between time periods, and establishes a parameter evolution model.

[0027] The dynamic change prediction submodule, based on the parameter evolution model, uses a time series fitting method to infer the distribution of feature values ​​in the future. By calculating the feature change trend parameter values ​​and generating the distribution results at future time points, it obtains the feature time series prediction value.

[0028] As a further aspect of the present invention, the step of calculating the characteristic change trend parameter value and generating the distribution result at future time points adopts the following formula:

[0029] ;

[0030] Calculate the characteristic change trend parameter value Obtain the time-series predicted values ​​of the features;

[0031] in, Indicates time Parameter values ​​representing the changing trend of time-series characteristics. Indicates parameters The weighting factors are determined based on the contribution ratio of historical time series data. Represents parameters in historical time series The observed values, The weighted average of all parameters in the time series is calculated using the following formula: , Indicates the first The absolute change of each distribution parameter This indicates the number of historical time series parameters involved in the calculation. This represents the total number of distribution parameters within the current time period.

[0032] As a further aspect of the present invention, the sensitivity analysis module includes:

[0033] The sensitivity change calculation submodule extracts the effect data of the feature value on the temperature control performance during the differentiated time period based on the feature time-series prediction value. By analyzing the correspondence between the change amplitude of the feature value and the performance fluctuation, it calculates the fluctuation range and offset direction of the feature sensitivity value, summarizes the sensitivity feature change trend during the differentiated time period, and generates a feature sensitivity dataset.

[0034] The gradient relationship extraction submodule, based on the feature sensitivity dataset and combined with the refrigerant flow rate change data, analyzes the dynamic relationship between the sensitivity value and the performance index. By calculating the gradient ratio between the sensitivity value and the performance parameter increment, it summarizes the nonlinear gradient pattern of the sensitivity value changing with performance and generates a sensitivity gradient relationship set.

[0035] The weight allocation adjustment submodule calculates the weight adjustment ratio of multiple features based on the sensitivity gradient relationship set, redistributes the weight ratio of the feature set according to the distribution of sensitivity value changes, adjusts the matching relationship between feature weights and performance sensitivity, and generates sensitivity adjustment weight values.

[0036] As a further aspect of the present invention, the weight ratio of the feature set is redistributed based on the distribution of changes in sensitivity values, using the following formula:

[0037] ;

[0038] Calculate the feature weight adjustment value Generate sensitivity adjustment weight values;

[0039] in, Representation of features The final weighting ratio after weight adjustment Representation of features The sensitivity value was obtained through monitoring the sensitivity gradient relationship set. The mean of all characteristic sensitivity values ​​is represented by the following formula: , Representation of features The original weight ratios are obtained through initial feature assignment. This represents the total number of features in the feature set.

[0040] As a further aspect of the present invention, the operation strategy optimization module includes:

[0041] The operating parameter adjustment submodule extracts key influencing items from the equipment operating parameters based on the sensitivity adjustment weight value, analyzes the distribution pattern of the weight value in multiple operating parameters, adjusts the initial configuration and matching range of the equipment operating parameters by calculating the offset of the weight's effect on the parameters, gradually corrects the degree of influence of characteristic parameters on the operating state, and generates an adjusted set of operating parameters.

[0042] The control strategy update submodule, based on the adjusted set of operating parameters and combined with the real-time operating status data of the compressor and expansion valve, analyzes the deviation relationship between the equipment operating parameters and the control logic by comparing the current operating status with the matched values ​​after parameter adjustment, updates the dynamic control strategy of the equipment, calculates the difference after adjustment, and generates the updated equipment control strategy.

[0043] Based on the updated equipment control strategy, the dynamic optimization calculation submodule iteratively calculates the operating parameters of key equipment, extracts the dynamic change patterns of equipment parameters from multiple calculation results, optimizes the adaptation relationship between the control strategy and parameters, reallocates the operating adjustment rules between equipment, and generates a dynamic control optimization parameter set.

[0044] An electrical device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the aforementioned electrical control system.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In this invention, precise screening of environmental parameters and sparse basis vector calculation of feature parameters significantly reduce data redundancy, improving the efficiency and relevance of the analysis. Statistical adjustment of differentiated time-period distributions, combined with optimization of equipment performance parameters, enhances data consistency and provides accurate adaptability to complex operating conditions. Dynamic feature modeling based on time-series trends enables prediction of future changes in environmental parameters, effectively enhancing the system's predictive capabilities and control efficiency. Sensitivity weight allocation clarifies the impact of each feature parameter, optimizes collaborative control between equipment, achieves a balance between performance and energy consumption, and realizes dynamic optimization of multi-functional linkage. Attached Figure Description

[0047] Figure 1 This is a system flowchart of the present invention;

[0048] Figure 2 This is a system block diagram of the present invention;

[0049] Figure 3 This is a flowchart of the feature extraction module of the present invention;

[0050] Figure 4 This is a flowchart of the distribution alignment module of the present invention;

[0051] Figure 5 This is a flowchart of the parameter trend modeling module of the present invention;

[0052] Figure 6 This is a flowchart of the sensitivity analysis module of the present invention;

[0053] Figure 7 This is a flowchart of the operation strategy optimization module of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0055] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0056] Example 1

[0057] Please see Figure 1 The present invention provides a technical solution: an electrical control system comprising:

[0058] The feature extraction module calculates the sparse basis vectors of environmental parameters in the feature space based on the set of environmental parameters, removes parameters based on correlation, compares the impact of temperature control with the operating data of compressor and refrigerant flow, filters features directly related to temperature control performance fluctuations, and generates a set of key feature parameters.

[0059] The distribution alignment module calculates the statistical distribution pattern of parameters in different time periods based on the key feature parameter set, adjusts the parameters by comparing the deviation values ​​in the distribution, establishes mapping rules by combining the performance data of expansion valve and condenser, adjusts the feature distribution values ​​to a unified reference distribution, calculates the consistency of the adjusted data, and generates aligned feature distribution values.

[0060] The parameter trend modeling module analyzes the trend of time-series feature changes based on the aligned feature distribution values, establishes a feature evolution model by combining evaporator and compressor operating data, fits the future distribution pattern through time-series feature changes, infers the dynamic changes of environmental parameters, and generates feature time-series predicted values.

[0061] The sensitivity analysis module calculates the sensitivity changes of multiple features to temperature control performance based on the feature time series prediction values. It combines the refrigerant flow rate changes to analyze the trend of the effect of sensitivity values ​​on performance indicators, extracts the gradient relationship between sensitivity and performance, adjusts the feature set weight allocation, and generates sensitivity adjustment weight values.

[0062] The operation strategy optimization module adjusts the equipment operating parameters based on the sensitivity adjustment weight value, updates the control strategy in combination with the operating status of the compressor and expansion valve, and gradually optimizes the operating parameters of multiple key components. The optimization is completed through multiple calculations of equipment operating parameters, generating a dynamic control optimization parameter set.

[0063] The key feature parameter set includes sparse basis vectors, removed unrelated parameters, and features directly related to temperature control performance fluctuations. Aligned feature distribution values ​​include adjusted parameter distribution values, unified reference distribution, and data consistency. The feature evolution model specifically includes feature change trends, evaporator and compressor operating characteristics, and future distribution patterns. Feature time-series prediction values ​​include time-series feature changes, dynamic environmental parameters, and future feature distribution patterns. Sensitivity adjustment weight values ​​include multi-feature sensitivity gradient relationships, performance index influence trends, and feature set weight allocation. The dynamic control optimization parameter set includes equipment operating parameters, control strategy update values, and optimization parameters for multiple key components.

[0064] Please see Figures 2 to 7 The feature extraction module includes a sparse basis vector extraction submodule, an association removal submodule, and a key feature selection submodule. The distribution alignment module includes a distribution shape calculation submodule, a parameter deviation adjustment submodule, and a unified distribution mapping submodule. The parameter trend modeling module includes a time series feature analysis submodule, a feature evolution modeling submodule, and a dynamic change prediction submodule. The sensitivity analysis module includes a sensitivity change calculation submodule, a gradient relationship extraction submodule, and a weight allocation adjustment submodule. The operation strategy optimization module includes an operation parameter adjustment submodule, a control strategy update submodule, and a dynamic optimization calculation submodule.

[0065] Please see Figure 3 The feature extraction module includes:

[0066] The sparse basis vector extraction submodule calculates the sparse basis vectors of the environmental parameters in the feature space based on the set of environmental parameters, normalizes the range of multiple parameter values ​​in the set of environmental parameters, decomposes the feature space using matrix operations, and extracts the sparse basis vectors of the parameters in the spatial dimension based on the decomposition results, generating a sparse basis vector set.

[0067] The sparse basis vector extraction submodule, based on an environmental parameter set, adjusts the range of multi-parameter values ​​in the set through normalization. First, the environmental parameter set needs to be analyzed, decomposed, and its multi-parameter data values ​​extracted. This step can be performed using matrix operations. For a specific feature space, the environmental parameters are standardized according to a specific formula. Standardization is completed, where x is the original parameter value. The mean, The standard deviation is used as the input parameter. After standardization, these parameters are input into the sparse basis vector extraction algorithm. The feature space is decomposed by a sparse matrix factorization algorithm (such as K-SVD). The result of the decomposition is a set of sparse basis vectors. A specific sparse vector screening model is then used to calculate the effectiveness of the basis vectors. The effective vector set is extracted by comparing the contribution threshold of the basis vectors in the feature space. A stable set of sparse basis vectors is obtained through multiple decomposition iterations.

[0068] The correlation elimination submodule analyzes the correlation between environmental parameters based on sparse basis vector sets, eliminates parameters with correlation below a specified threshold based on the calculation results, and verifies the filtered parameter set using a correlation calculation model to obtain the correlation-filtered parameter set.

[0069] The correlation elimination submodule, based on a sparse basis vector set, analyzes the degree of correlation between environmental parameters through a correlation calculation model. First, a correlation model needs to be constructed, calculating the correlation index between each basis vector in the sparse basis vector set; the Pearson correlation coefficient can be used as an example. ,in These represent the data points in the vector. The correlation coefficient, calculated using the mean, can be used to analyze the correlation between basis vectors. Parameters with correlation coefficients below a threshold (e.g., 0.3) are removed based on the calculation results. The remaining parameters form a new parameter set. The parameters after removal are further verified using an association verification model. The verification method can be association network analysis, which constructs a parameter association graph using graph theory and analyzes the connectivity indicators of parameter nodes (such as degree centrality and betweenness centrality). After obtaining the final association screening parameter set, the list of parameters removed and screened during the process is recorded.

[0070] The key feature screening submodule, based on the correlation screening parameter set and combined with the operating data of the compressor and refrigerant flow, uses a correlation calculation model to compare the correlation between temperature control performance fluctuations and parameters, and screens the feature parameters that contribute the most to temperature control performance fluctuations, thus generating a key feature parameter set.

[0071] The key feature screening submodule, based on a correlation-based parameter set and combined with compressor and refrigerant flow operation data, compares the correlation between temperature control performance fluctuations and parameters by constructing a correlation calculation model. First, the operation data needs to be collected and cleaned. Compressor operation data includes real-time power, speed, and temperature, while refrigerant flow operation data includes pressure and flow rate. After data cleaning, the data is normalized. Then, an objective function for temperature control performance fluctuations is constructed, and a correlation calculation formula is used. ,in For covariance, Let X and Y be the standard deviations, respectively. Through regression analysis of multidimensional parameters and temperature control performance, feature parameters with larger contribution values ​​are selected. The specific calculation method can be the stepwise regression method, which sorts the parameters from largest to smallest contribution. Based on the set contribution threshold, key parameters are selected to generate the final set of key feature parameters.

[0072] The feature space is decomposed using matrix operations, using the following formula:

[0073] ;

[0074] Calculate matrix decomposition weights Based on the decomposition results, sparse basis vectors of the parameters in the spatial dimension are extracted to generate a sparse basis vector set;

[0075] in, Indicates environmental parameters and The weighted coefficient matrix generated during the feature space decomposition process. and These represent the first and second elements in the set of environmental parameters, respectively. Item and the Standardized value of the item and These represent the first element in the set of environmental parameters. Item and the The parameters of the term in the feature space are... Projection values ​​in the dimension, The dimension of the feature space. and These represent the first and second elements in the set of environmental parameters, respectively. Item and the The term after decomposition in the feature space is the first The absolute weight of each subspace, This indicates the number of subspaces after the feature space is decomposed.

[0076] formula:

[0077]

[0078] Detailed explanation of the formula and its calculation derivation:

[0079] In this formula, Indicates environmental parameters and The weighted coefficient matrix generated during the feature space decomposition process.

[0080] first, and These represent the first element in the set of environmental parameters. Item and the The standardized value of the item.

[0081] The standardization process is typically achieved through the following steps:

[0082] Data acquisition: Obtaining raw data of environmental parameters through sensors or other measuring devices. For example, the data collected on the first... The environmental parameter value is , No. The environmental parameter value is .

[0083] Calculate the mean and standard deviation: Based on the collected data, calculate the mean of this environmental parameter. and standard deviation Assuming the mean Standard deviation .

[0084] Standardization: Using formulas Standardize the data.

[0085] For the item: ;

[0086] For the item: ;

[0087] Next, and These represent the first element in the set of environmental parameters. Item and the The parameters of the term in the feature space are... Projection value in a dimension.

[0088] These projection values ​​are obtained in the following way:

[0089] Feature extraction: Dimensionality reduction techniques such as principal component analysis (PCA) are applied to project high-dimensional environmental parameter data into a low-dimensional feature space.

[0090] Calculate the projection values: Based on the feature vector, calculate the projection value of each parameter in each dimension of the feature space. Assume that in the... In terms of dimensions, the first The projected value of the item is , No. The projected value of the item is .

[0091] Then, and These represent the first element in the set of environmental parameters. Item and the The term after decomposition in the feature space is the first The absolute weight of each subspace.

[0092] These weights are determined in the following way:

[0093] Matrix decomposition: Decomposing the matrix in the feature space (such as singular value decomposition) to obtain the basis vectors and corresponding singular values ​​of each subspace.

[0094] Calculate weights: Based on the singular values, determine the weight of each parameter in each subspace. Assume that in the... In the subspace, the first The weight of the item is , No. The weight of the item is .

[0095] Finally, substitute the above values ​​into the formula to perform the calculation:

[0096] Calculate the numerator: ;

[0097] Calculate the sum of squared differences: ;

[0098] Calculate the square root of the sum of the differences of squares: ;

[0099] Calculate the sum of the square roots of the absolute values ​​of the weighted product: ;

[0100] Calculate the denominator: ;

[0101] Calculate the elements of the weighted coefficient matrix: ;

[0102] This result indicates that environmental parameters and The weighted coefficient matrix generated during the feature space decomposition process has an element count of 10.2. This value reflects the parameters. and The similarity in the feature space is represented by a higher numerical value, indicating a greater difference. In subsequent sections, this can be further explained using the matrix... For each element, further extract the sparse basis vectors of the parameters in the spatial dimension to generate a sparse basis vector set.

[0103] Please see Figure 4 The distribution alignment module includes:

[0104] The distribution pattern calculation submodule extracts parameter values ​​within differentiated time periods based on the key feature parameter set, performs statistical classification on the parameter set, calculates the central value, distribution range and skewness of multiple parameters in differentiated time periods, performs data pattern feature analysis on the statistical results, and obtains the time period distribution feature set;

[0105] The distribution pattern calculation submodule, based on a set of key feature parameters, analyzes parameter values ​​extracted from differentiated time periods. First, these differentiated time periods are categorized, with the parameter values ​​for each period treated as an independent dataset. Statistical analysis is then performed on each dataset to obtain the central value, distribution range, and skewness. The central value can be calculated using the mean formula. The distribution range can be calculated using statistical extreme value differences. The skewness calculation uses the skewness coefficient formula. ,in The mean, The standard deviation is used to obtain the statistical indicators for each time period using the above formula. These indicators are then integrated to form a time period distribution feature set. Combined with statistical chart tools, their morphological characteristics are used for data visualization analysis, generating an analysis report and storing it as a specific data file for subsequent calculations and corrections.

[0106] The parameter deviation adjustment submodule calculates the difference between distributions based on the time period distribution feature set using a difference degree calculation model based on pairwise comparison. It determines the deviation direction by comparing data, adjusts the parameter value range based on the difference degree, and corrects the adjustment result by combining the performance data of the expansion valve and condenser, thus generating a deviation adjustment parameter set.

[0107] The parameter deviation adjustment submodule calculates the difference between distributions based on the time-period distribution feature set using a pairwise comparison difference calculation model. First, it needs to organize the data on the central value, distribution range, and skewness of the parameters in each time period. Then, it calculates the difference using a pairwise comparison method. The difference calculation can be performed using the following formula: ,in and These represent the statistical characteristic values ​​of the parameters in the two time periods, respectively. The calculated difference matrix can be displayed through a heatmap and used to identify distribution pairs with high differences. The direction of deviation is determined by comparing the parameter data. Correction is then performed by introducing performance data from the expansion valve and condenser. During the correction process, curve fitting analysis of the collected performance data is required, and a quadratic polynomial regression formula can be used for the fitting. ,in , , The corrected parameter values ​​are used to adjust the parameter set by updating the bias for subsequent use, representing the fitting coefficients.

[0108] The unified distribution mapping submodule establishes mapping rules between parameters and a unified reference distribution based on the deviation adjustment parameter set. It adjusts the range of distribution data by calculating the mapping position of multiple parameter values ​​in the unified distribution, recalculates the data consistency between the adjusted parameters, and generates aligned feature distribution values.

[0109] The unified distribution mapping submodule establishes mapping rules between parameters and a unified reference distribution based on the deviation adjustment parameter set. By comparing the positional relationship between the deviation-adjusted parameter values ​​and the unified reference distribution, the unified reference distribution must first be defined, which can be a standard normal distribution or a uniform distribution. This is done by constructing a mapping function. By mapping the bias-adjusted parameter values ​​to a uniform distribution, the consistency index among the mapped data is calculated. Consistency analysis can be performed using the standard deviation formula. Perform calculations, where The mean, This indicates the degree of data consistency. The adjusted parameter distribution data range is obtained through calculation. The statistical indicators of each parameter are compared and updated, and finally, aligned feature distribution values ​​are generated for subsequent feature analysis or model optimization.

[0110] Please see Figure 5 The parameter trend modeling module includes:

[0111] The time series feature analysis submodule extracts the parameter change sequence in the time dimension based on the aligned feature distribution value, analyzes the change rate of the parameter in multiple time periods on the time axis, and summarizes the periodicity and abrupt change points of the time distribution feature by calculating the growth rate, decrease magnitude and fluctuation frequency of the parameter in multiple time periods, and generates a time series distribution feature set.

[0112] The time-series feature analysis submodule, based on aligned feature distribution values, analyzes parameters by extracting their temporal variation sequences. First, it categorizes and sorts the temporal variation values ​​of each feature parameter. For the rate of change across multiple time periods on the time axis, a formula is used. ,in This represents the increase or decrease of a parameter within a certain time period. Representing time intervals, by comparing the rate of change over multiple time periods, we can initially analyze the parameter growth rate and the magnitude of decline. Then, we introduce fluctuation frequency analysis, employing a periodic analysis method based on the Fourier transform formula. Extract the main fluctuation frequency components of each parameter, and label the periodicity and abrupt change points of the parameters. When labeling abrupt change points, the cumulative change formula can be used as a reference. Cumulative analysis was performed, and the precise location of the mutation point was obtained by comparing the time series data. The above results were then compiled into a time series distribution feature set.

[0113] The feature evolution modeling submodule, based on the time-series distributed feature set and combined with the operating data of the evaporator and compressor, establishes a correlation matrix for the change pattern of feature parameters on the time axis, calculates and derives the dynamic change trend of parameters based on the correlation between time periods, and establishes a parameter evolution model.

[0114] The feature evolution modeling submodule, based on a time-series distributed feature set, establishes a correlation matrix for the variation patterns of feature parameters along the time axis by combining the operating data of the evaporator and compressor. First, it extracts key performance data of the evaporator and compressor, including the evaporator's refrigeration efficiency and energy consumption coefficient, and the compressor's power curve and load variation curve. This data is then normalized, and the correlation between various parameters is calculated using the time dimension, through formulas... ,in For covariance, The standard deviations of the two parameters are used to calculate the correlation matrix between time periods. Principal component analysis of the matrix is ​​used to extract the main dynamic change characteristics. Furthermore, a time evolution model is established based on the correlation law. The dynamic change law is modeled in the form of difference equations. The dynamic change trend of the parameters is determined by the model fitting results.

[0115] The dynamic change prediction submodule is based on a parametric evolution model and uses a time series fitting method to infer the distribution of feature values ​​in the future. By calculating the feature change trend parameter values ​​and generating the distribution results at future time points, the feature time series prediction values ​​are obtained.

[0116] The dynamic change prediction submodule, based on a parametric evolution model, uses time series fitting methods to predict the distribution of feature values ​​in the future. First, it extracts a fitting function from the time-varying trends in the parametric evolution model. Commonly used fitting methods include the ARIMA model, whose basic form is... ,in For constant terms, These are the autoregressive coefficients. To account for random errors, model parameters are fitted using training data. When predicting future time points, known data is input into the model for iterative calculation to obtain the feature value distribution. Subsequently, the distribution results at multiple time points are used to generate feature time series prediction values. The prediction results are cross-validated with historical distribution data to verify their accuracy and reliability.

[0117] The distribution results for future time points are generated by calculating the characteristic change trend parameter values, using the following formula:

[0118] ;

[0119] Calculate the characteristic change trend parameter value Obtain the time-series predicted values ​​of the features;

[0120] in, Indicates time Parameter values ​​representing the changing trend of time-series characteristics. Indicates parameters The weighting factors are determined based on the contribution ratio of historical time series data. Represents parameters in historical time series The observed values, The weighted average of all parameters in the time series is calculated using the following formula: , Indicates the first The absolute change of each distribution parameter This indicates the number of historical time series parameters involved in the calculation. This represents the total number of distribution parameters within the current time period.

[0121] formula:

[0122] ;

[0123] Detailed explanation of the formula and its calculation derivation:

[0124] When calculating the characteristic change trend parameter values, the required parameters are obtained sequentially in the following ways:

[0125] parameter Indicates parameters The weighting factors are determined based on the contribution proportions of historical time series data. Assuming that the weighting factors are set to [values] through time series analysis of historical data... , , , .

[0126] parameter Represents parameters in historical time series The observed values ​​are obtained through sensor monitoring or real-time data acquisition, and the observed values ​​are set as follows: , , , .

[0127] parameter The weighted average of all parameters in the time series is calculated using the following formula: ;

[0128] Substitute the parameters into the calculation:

[0129] ;

[0130] ;

[0131] parameter Indicates the first The absolute change of each distribution parameter is calculated by monitoring the distribution differences at each time point in the time series. The absolute change of the distribution parameter is set as... , , The total change is calculated as follows: ;

[0132] Substitute the above results into the formula to calculate. :

[0133] Calculate the molecule part ;

[0134] Calculate item by item:

[0135] ;

[0136] ;

[0137] ;

[0138] ;

[0139] The sum of the numerators is:

[0140] ;

[0141] Calculate the denominator

[0142] ;

[0143] calculate

[0144] ;

[0145] The results show that the characteristic trend parameter value is 0.382, which reflects the intensity of parameter change in the time series at the current moment; a larger value indicates a more significant change. Furthermore, this trend parameter can be used to generate the feature value distribution for future time points and predict time series values.

[0146] Please see Figure 6 The sensitivity analysis module includes:

[0147] The sensitivity change calculation submodule extracts the effect data of feature values ​​on temperature control performance during different time periods based on feature time-series predicted values. By analyzing the correspondence between the change amplitude of feature values ​​and the performance fluctuation, it calculates the fluctuation range and offset direction of feature sensitivity values, summarizes the sensitivity feature change trend during different time periods, and generates a feature sensitivity dataset.

[0148] The sensitivity change calculation submodule, based on feature time-series predicted values, extracts data on the impact of feature values ​​on temperature control performance during differentiated time periods. First, it collects feature value change data within these differentiated time periods, extracts the time-dimensional distribution values, and compares them item by item with the temperature control performance fluctuations. The calculation of the feature value change amplitude can be performed using the formula... ,in The characteristic value for the current time period. Given the characteristic values ​​from the previous period, further analysis of the relationship between the magnitude of change and the performance fluctuation can be conducted. A linear regression model can be used to construct a fitting relationship between the characteristic change and the temperature control performance fluctuation. For example, the fitting equation could be: ,in For constant terms, The coefficient representing the influence of the characteristic variation amplitude on the temperature control performance fluctuation. To account for random errors, the sensitivity value range of the variation interval is determined by fitting calculation, and the direction of sensitivity value offset is statistically analyzed. Based on the sensitivity change trend of each time period, a feature sensitivity dataset is generated, which will be used for subsequent sub-module processing.

[0149] The gradient relationship extraction submodule, based on the feature sensitivity dataset and combined with the refrigerant flow rate change data, analyzes the dynamic relationship between the sensitivity value and the performance index. By calculating the gradient ratio between the sensitivity value and the performance parameter increment, it summarizes the nonlinear gradient pattern of the sensitivity value changing with performance and generates a sensitivity gradient relationship set.

[0150] The gradient relationship extraction submodule, based on the feature sensitivity dataset, analyzes the dynamic relationship between sensitivity values ​​and performance indicators by combining data on refrigerant flow rate changes. First, it needs to perform difference calculations on each feature value in the sensitivity dataset. The difference formula is as follows: ,in This represents the sensitivity value for the current time period. To determine the sensitivity value for the next time period, it is also necessary to extract the real-time change value of the refrigerant flow rate. Combining this with the flow rate change data, the gradient ratio between the sensitivity value and the performance parameter increment is calculated. The formula for calculating the gradient ratio is: ,in This represents the incremental value of the performance parameter. By calculating the nonlinear relationship between sensitivity and performance parameter piecewise, the gradient pattern of sensitivity value changing with performance is summarized. Pattern extraction can be combined with nonlinear fitting methods, such as using polynomial fitting equations. The fitting was validated, and the sensitivity gradient relationship set was finally generated.

[0151] The weight allocation adjustment submodule calculates the weight adjustment ratio of multiple features based on the sensitivity gradient relationship set, redistributes the weight ratio of the feature set according to the distribution of sensitivity value changes, adjusts the matching relationship between feature weights and performance sensitivity, and generates sensitivity adjustment weight values.

[0152] The weight allocation adjustment submodule optimizes the sensitivity distribution based on the sensitivity gradient relationship set by calculating the weight adjustment ratios of multiple features. First, each feature in the sensitivity gradient relationship set needs to be normalized using the following formula: ,in The original gradient value. These are the minimum and maximum values, respectively. After normalization, the weight distribution within the feature set needs to be updated. By calculating the weight ratio adjustment proportion of each feature, the distribution matching update of the feature weights is completed, and the final sensitivity adjustment weight value is generated. The weight value update result is output in matrix form for system model optimization.

[0153] The weights of the feature set are redistributed based on the distribution of sensitivity values, using the following formula:

[0154] ;

[0155] Calculate the feature weight adjustment value Generate sensitivity adjustment weight values;

[0156] in, Representation of features The final weighting ratio after weight adjustment Representation of features The sensitivity value was obtained through monitoring the sensitivity gradient relationship set. The mean of all characteristic sensitivity values ​​is represented by the following formula: , Representation of features The original weight ratios are obtained through initial feature assignment. This represents the total number of features in the feature set.

[0157] formula:

[0158] ;

[0159] Detailed explanation of the formula and its calculation derivation:

[0160] The sensitivity adjustment weighting formula is used to redistribute the weight ratios of the feature set. The relevant parameters are obtained and calculated in the following ways:

[0161] Sensitivity value Representation of features The sensitivity value was calculated by collecting the sensitivity gradient relationship in the dataset and using the gradient change relationship between the feature performance and the target performance. The sensitivity monitoring results are as follows:

[0162] , , , .

[0163] Mean sensitivity The mean of all characteristic sensitivity values ​​is represented by the following formula:

[0164] ;

[0165] Substitute the sensitivity value:

[0166] ;

[0167] Original weight ratio Representation of features The initial weight ratios are determined by scoring the importance of the feature set, and the initial weight allocation is as follows:

[0168] , , , .

[0169] The normalized weight coefficient in the denominator of the weight adjustment formula is:

[0170] ;

[0171] Calculate item by item:

[0172] ;

[0173] ;

[0174] ;

[0175] ;

[0176] The sum is:

[0177] ;

[0178] The molecular part is:

[0179] ;

[0180] Calculate item by item :

[0181] for :

[0182] ;

[0183] for :

[0184] ;

[0185] for :

[0186] ;

[0187] for :

[0188] ;

[0189] Weight adjustment value , , , .

[0190] The results indicate that the adjusted weight values ​​reflect the degree of influence of each feature sensitivity value. After the feature weight ratios were redistributed, a matching relationship between sensitivity and weight was achieved. The generated sensitivity adjustment weight values ​​were used for further analysis and processing.

[0191] Please see Figure 7 The operation strategy optimization module includes:

[0192] The operating parameter adjustment submodule is based on sensitivity adjustment weight values, extracts key influencing items in equipment operating parameters, analyzes the distribution pattern of weight values ​​in multiple operating parameters, and adjusts the initial configuration and matching range of equipment operating parameters by calculating the offset of the weight effect on the parameters. It gradually corrects the degree of influence of characteristic parameters on the operating status and generates an adjusted set of operating parameters.

[0193] The operating parameter adjustment submodule, based on sensitivity adjustment weight values, analyzes key influencing factors from equipment operating parameters. First, it requires data collection of equipment operating parameters, including real-time power, temperature, and flow rate. Then, it extracts the distribution pattern of sensitivity adjustment weight values, which can be calculated using the weight distribution formula. ,in The sensitivity weight value for a single feature. The sum of weighted values ​​is determined by analyzing the distribution of each characteristic parameter to identify key influencing factors, and then the adjustment offset calculation formula is used. ,in For parameter offset, The initial configuration range of parameters is adjusted according to the weight ratio of the feature values, and finally the adjusted running parameter set is formed by gradually correcting the influence of the feature parameters.

[0194] The control strategy update submodule is based on the adjusted set of operating parameters and combines the real-time operating status data of the compressor and expansion valve. By comparing the current operating status with the matched values ​​after parameter adjustment, it analyzes the deviation relationship between the equipment operating parameters and the control logic, updates the dynamic control strategy of the equipment, calculates the difference after adjustment, and generates the updated equipment control strategy.

[0195] The control strategy update submodule, based on the adjusted operating parameter set, analyzes the data by combining real-time operating status data of the compressor and expansion valve. First, it needs to collect the compressor's power curve and the expansion valve's flow curve data. The adjusted operating parameter set is then compared one by one with this real-time data. During the comparison, the parameter matching difference value needs to be calculated. The formula for calculating the matching difference is as follows: ,in The adjusted matching value, As the real-time operating value, the deviation relationship between the parameters and the control logic is determined by point-by-point difference value analysis, and dynamic correction is made based on the difference. The updated control strategy is verified through a real-time feedback mechanism to generate the final equipment control strategy.

[0196] The dynamic optimization calculation submodule, based on the updated equipment control strategy, iteratively calculates the operating parameters of key equipment, extracts the dynamic change patterns of equipment parameters from multiple calculation results, optimizes the adaptation relationship between the control strategy and parameters, reallocates the operating adjustment rules among equipment, and generates a dynamic control optimization parameter set.

[0197] The dynamic optimization calculation submodule, based on the updated equipment control strategy, extracts dynamic change patterns by iteratively calculating key equipment operating parameters. This first requires multiple rounds of iterative calculations of the key operating parameters, employing dynamic optimization algorithms such as gradient descent. The gradient update formula is as follows: ,in Let be the parameter value for the t-th iteration. For learning rate, The gradient of the parameters with respect to the objective function is used to extract patterns from the results of multiple calculations in dynamic optimization through fitting analysis. The fitting equation is as follows: ,in The fitting coefficients are used to optimize the relationship between the control strategy and parameters, reallocate the operating rules between devices, generate a set of dynamic control optimization parameters, and then verify them.

[0198] An electrical device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned electrical control system.

[0199] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. An electrical control system, characterized in that, The system includes: The feature extraction module calculates the sparse basis vectors of environmental parameters in the feature space based on the set of environmental parameters, removes parameters based on correlation, compares the impact of temperature control with the operating data of compressor and refrigerant flow, filters features directly related to temperature control performance fluctuations, and generates a set of key feature parameters. Based on the set of key feature parameters, the distribution alignment module calculates the statistical distribution pattern of parameters in different time periods, adjusts the parameters by comparing the deviation values ​​in the distribution, establishes mapping rules by combining the performance data of expansion valve and condenser, adjusts the feature distribution values ​​to a unified reference distribution, calculates the consistency of the adjusted data, and generates aligned feature distribution values. Based on the aligned feature distribution values, the parameter trend modeling module analyzes the trend of time-series feature changes, establishes a feature evolution model by combining evaporator and compressor operating data, fits the future distribution pattern through time-series feature changes, infers the dynamic changes of environmental parameters, and generates feature time-series prediction values. Based on the predicted time series values ​​of the features, the sensitivity analysis module calculates the sensitivity changes of multiple features to temperature control performance, analyzes the trend of the effect of sensitivity values ​​on performance indicators in conjunction with the refrigerant flow rate changes, extracts the gradient relationship between sensitivity and performance, adjusts the weight allocation of the feature set, and generates sensitivity adjustment weight values. The operation strategy optimization module adjusts the equipment operating parameters based on the sensitivity adjustment weight value, updates the control strategy in conjunction with the operating status of the compressor and expansion valve, and gradually optimizes the operating parameters of multiple key components. The optimization is completed through multiple calculations of equipment operating parameters, generating a dynamic control optimization parameter set.

2. The electrical control system according to claim 1, characterized in that, The feature extraction module includes: The sparse basis vector extraction submodule calculates the sparse basis vectors of the environmental parameters in the feature space based on the set of environmental parameters, normalizes the range of multiple parameter values ​​in the set of environmental parameters, decomposes the feature space using matrix operations, and extracts the sparse basis vectors of the parameters in the spatial dimension based on the decomposition results, generating a sparse basis vector set. The correlation elimination submodule analyzes the correlation between environmental parameters based on the sparse basis vector set, eliminates parameters with correlation below a specified threshold based on the calculation results, and verifies the filtered parameter set using the correlation calculation model to obtain the correlation-filtered parameter set. The key feature screening submodule, based on the aforementioned correlation screening parameter set and combined with the operating data of the compressor and refrigerant flow, uses a correlation calculation model to compare the correlation between temperature control performance fluctuations and parameters, and screens the feature parameters that contribute the most to temperature control performance fluctuations, thereby generating a key feature parameter set.

3. The electrical control system according to claim 2, characterized in that, The feature space is decomposed using matrix operations, using the following formula: ； Calculate matrix decomposition weights Based on the decomposition results, sparse basis vectors of the parameters in the spatial dimension are extracted to generate a sparse basis vector set; in, Indicates environmental parameters and The weighted coefficient matrix generated during the feature space decomposition process. and These represent the first element in the set of environmental parameters. Item and the Standardized value of the item and These represent the first element in the set of environmental parameters. Item and the The parameters of the term in the feature space are... Projection values ​​in the dimension, The dimension of the feature space. and These represent the first element in the set of environmental parameters. Item and the The term after decomposition in the feature space is the first The absolute weight of each subspace, This indicates the number of subspaces after the feature space is decomposed.

4. The electrical control system according to claim 1, characterized in that, The distribution alignment module includes: The distribution pattern calculation submodule extracts parameter values ​​within the differentiated time periods based on the key feature parameter set, performs statistical classification on the parameter set, calculates the central value, distribution range and skewness of multiple parameters in the differentiated time periods, performs data pattern feature analysis on the statistical results, and obtains the time period distribution feature set. The parameter deviation adjustment submodule calculates the difference between distributions based on the time period distribution feature set using a difference degree calculation model based on pairwise comparisons. It determines the deviation direction by comparing data, adjusts the parameter value range based on the difference degree, and corrects the adjustment result by combining the performance data of the expansion valve and condenser, thereby generating a deviation adjustment parameter set. The unified distribution mapping submodule establishes a mapping rule between parameters and a unified reference distribution based on the deviation adjustment parameter set. It adjusts the range of distribution data by calculating the mapping position of multiple parameter values ​​in the unified distribution, recalculates the data consistency between the adjusted parameters, and generates aligned feature distribution values.

5. The electrical control system according to claim 1, characterized in that, The parameter trend modeling module includes: The time-series feature analysis submodule extracts the parameter change sequence in the time dimension based on the alignment feature distribution value, analyzes the change rate of the parameter in multiple time periods on the time axis, and summarizes the periodicity and abrupt change points of the time distribution feature by calculating the growth rate, decrease magnitude and fluctuation frequency of the parameter in multiple time periods, and generates a time-series distribution feature set. The feature evolution modeling submodule, based on the time-series distribution feature set and combined with the operating data of the evaporator and compressor, establishes a correlation matrix for the change pattern of feature parameters on the time axis, calculates and derives the dynamic change trend of parameters based on the correlation between time periods, and establishes a parameter evolution model. The dynamic change prediction submodule, based on the parameter evolution model, uses a time series fitting method to infer the distribution of feature values ​​in the future. By calculating the feature change trend parameter values ​​and generating the distribution results at future time points, it obtains the feature time series prediction value.

6. The electrical control system according to claim 5, characterized in that, The method of calculating characteristic change trend parameter values ​​and generating distribution results for future time points uses the following formula: ； Calculate the characteristic change trend parameter value Obtain the time-series predicted values ​​of the features; in, Indicates time Parameter values ​​representing the changing trend of time-series characteristics. Indicates parameters The weighting factors are determined based on the contribution ratio of historical time series data. Represents parameters in historical time series The observed values, The weighted average of all parameters in the time series is calculated using the following formula: , Indicates the first The absolute change of each distribution parameter This indicates the number of historical time series parameters involved in the calculation. This represents the total number of distribution parameters within the current time period.

7. The electrical control system according to claim 1, characterized in that, The sensitivity analysis module includes: The sensitivity change calculation submodule extracts the effect data of the feature value on the temperature control performance during the differentiated time period based on the feature time-series prediction value. By analyzing the correspondence between the change amplitude of the feature value and the performance fluctuation, it calculates the fluctuation range and offset direction of the feature sensitivity value, summarizes the sensitivity feature change trend during the differentiated time period, and generates a feature sensitivity dataset. The gradient relationship extraction submodule, based on the feature sensitivity dataset and combined with the refrigerant flow rate change data, analyzes the dynamic relationship between the sensitivity value and the performance index. By calculating the gradient ratio between the sensitivity value and the performance parameter increment, it summarizes the nonlinear gradient pattern of the sensitivity value changing with performance and generates a sensitivity gradient relationship set. The weight allocation adjustment submodule calculates the weight adjustment ratio of multiple features based on the sensitivity gradient relationship set, redistributes the weight ratio of the feature set according to the distribution of sensitivity value changes, adjusts the matching relationship between feature weights and performance sensitivity, and generates sensitivity adjustment weight values.

8. The electrical control system according to claim 7, characterized in that, The weight ratio of the feature set is redistributed based on the distribution of changes in sensitivity values, using the following formula: ； Calculate the feature weight adjustment value Generate sensitivity adjustment weight values; in, Representation of features The final weighting ratio after weight adjustment Representation of features The sensitivity value was obtained through monitoring the sensitivity gradient relationship set. The mean of all characteristic sensitivity values ​​is represented by the following formula: , Representation of features The original weight ratios are obtained through initial feature assignment. This represents the total number of features in the feature set. Represents the first in the feature set Sensitivity values ​​for each feature Represents the first in the feature set The original weight ratio of each feature.

9. The electrical control system according to claim 1, characterized in that, The operation strategy optimization module includes: The operating parameter adjustment submodule extracts key influencing items from the equipment operating parameters based on the sensitivity adjustment weight value, analyzes the distribution pattern of the weight value in the equipment operating parameters, adjusts the initial configuration and matching range of the equipment operating parameters by calculating the offset of the weight's effect on the equipment operating parameters, gradually corrects the degree of influence of the characteristic parameters on the operating state, and generates an adjusted set of operating parameters. The control strategy update submodule, based on the adjusted set of operating parameters and combined with the real-time operating status data of the compressor and expansion valve, analyzes the deviation relationship between the equipment operating parameters and the control logic by comparing the current operating status with the adjusted matching value of the characteristic parameters, updates the dynamic control strategy of the equipment, calculates the adjusted difference, and generates the updated equipment control strategy. Based on the updated equipment control strategy, the dynamic optimization calculation submodule iteratively calculates the key equipment operating parameters, extracts the dynamic change patterns of the equipment operating parameters from multiple calculation results, optimizes the adaptation relationship between the control strategy and the equipment operating parameters, reallocates the operating adjustment rules between equipment, and generates a dynamic control optimization parameter set.

10. An electrical device comprising a memory and a processor, characterized in that, The memory stores a computer program, and when the processor executes the computer program, it implements the electrical control system according to any one of claims 1 to 9.

Images