Railway station novel refrigerant filling method and system based on feedback regulation

Abstract

The invention discloses a novel railway station refrigerant filling method and system based on feedback regulation, and the method comprises the steps: obtaining and analyzing historical monitoring data related to the load demand of a refrigeration system, determining key operation parameters affecting the load demand of the refrigeration system, extracting the characteristics of the key operation parameters, and calculating the load demand of the refrigeration system; constructing a prediction model based on the features and a preset neural network model to obtain load demand prediction data; obtaining current load data, analyzing the current load data and the load demand prediction data, and determining load difference characteristics; and evaluating the load difference of the refrigerating system based on the load difference characteristics to obtain a load difference evaluation value, and determining a feedback adjustment coefficient based on the load difference evaluation value to adjust the current refrigerant filling working condition. According to the refrigerant filling technology based on intelligent feedback adjustment, the load difference is determined through data prediction, the current refrigerant filling process is adjusted through evaluation and analysis, the refrigerant filling process can be adjusted timely and accurately, and the future load requirement of a refrigeration system is met.

Description

Technical Field

[0001] The present invention relates to the technical field of refrigerant filling, and in particular to a novel refrigerant filling method and system for railway stations based on feedback regulation. Background Art

[0002] Refrigerant injection is a common process, often used in refrigeration and air conditioning systems. It involves injecting a refrigerant (also known as a refrigerant) into the refrigeration system. The refrigerant circulates through the system, absorbing and releasing heat to achieve cooling. In transportation hubs like railway stations, the stable operation of the refrigeration system is crucial to ensuring passenger comfort and proper equipment function.

[0003] However, traditional refrigerant filling methods mainly rely on static experience values ​​or fixed filling procedures, which have significant limitations and cannot accurately control the refrigerant filling process. Overfilling will cause the compressor power consumption to increase, and insufficient filling will cause the cooling capacity to decrease, which cannot meet the load requirements of the refrigeration system. In addition, the inability to accurately control the refrigerant filling process will also lead to uneven refrigerant distribution, which may cause liquid hammer, evaporator frosting or high-pressure alarms, shortening the equipment life. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a new refrigerant filling method and system for railway stations based on feedback regulation, comprising: Obtain historical monitoring data related to the load demand of the refrigeration system, analyze the historical monitoring data, and determine the key operating parameters that affect the load demand of the refrigeration system; Extract the characteristics of key operating parameters, and build a load demand forecasting model for the refrigeration system based on the characteristics and the preset neural network model to perform load forecasting and obtain load demand forecast data; Obtain the current refrigeration system load data, and perform difference analysis between the load data and load demand forecast data to determine the load difference characteristics; Evaluating the load difference of the refrigeration system based on the load difference characteristics to obtain a load difference evaluation value, and determining a feedback adjustment coefficient based on the load difference evaluation value; The current refrigerant filling working condition is adjusted according to the feedback adjustment coefficient, and the refrigerant filling is performed according to the adjusted refrigerant filling working condition.

[0005] Furthermore, the acquisition of historical monitoring data related to the load demand of the refrigeration system and analysis of the historical monitoring data to determine key operating parameters affecting the load demand of the refrigeration system include: Obtain historical monitoring data related to the load demand of the refrigeration system and preprocess the historical monitoring data. The preprocessing includes removing outliers and noise in the data, filling missing values ​​in the data, and standardizing the data. Dividing the pre-processed historical monitoring data into multiple monitoring parameter data groups according to parameter types, and determining historical load data of the refrigeration system; The correlation between each monitoring parameter data group and the historical load data is calculated, and the parameters corresponding to the monitoring parameter data groups with correlations greater than a preset threshold are determined as key operating parameters affecting the load demand of the refrigeration system.

[0006] Furthermore, the features of the key operating parameters are extracted, and a load demand prediction model of the refrigeration system is constructed based on the features and a preset neural network model to perform load prediction, thereby obtaining load demand prediction data, including: Extracting features of the monitoring parameter data group corresponding to the key operating parameters, and constructing a data set based on the monitoring parameter data group and the corresponding features; Input the data set into the corresponding preset neural network model to build an initial load demand forecast model; The data set is divided into a training set and a test set according to a preset ratio, and the training set and the test set are input into the initial load demand forecasting model; The load demand prediction initial model is trained and tested until the load demand prediction initial model meets the preset convergence conditions, thereby obtaining a load demand prediction model for the refrigeration system; The real-time monitoring data related to the load demand of the refrigeration system is obtained, and the real-time monitoring data is input into the load demand prediction model of the refrigeration system for prediction output to obtain the load demand prediction data of the refrigeration system.

[0007] Furthermore, the method of obtaining the load data of the current refrigeration system and performing a difference analysis between the load data and the load demand forecast data to determine the load difference characteristics includes: Obtain the current refrigeration system load data and determine the load demand forecast data of the refrigeration system; Calculate the difference between the load demand forecast data and the load data to obtain load difference data, and construct a time-progress load difference data change curve based on the load difference data; Determining a change period in a load difference data change curve, and dividing the load difference data change curve into a plurality of curve segments according to the change period; The slope value and the variation amplitude value of each curve segment are determined, and the slope value and the variation amplitude value of each curve segment are determined as the load difference feature.

[0008] Furthermore, the load difference of the refrigeration system is evaluated based on the load difference characteristics to obtain a load difference evaluation value, including: Determine the slope value and variation range value of each curve segment, and determine the preset standard slope value and standard variation range value of the curve segment; Calculate the difference between the slope value and the standard slope value, and the difference between the variation amplitude value and the standard variation amplitude value of each curve segment to obtain a first difference value and a second difference value, and evaluate the first difference value and the second difference value to obtain a first evaluation value and a second evaluation value of each curve segment; The first evaluation value and the second evaluation value are added together to obtain a sub-load difference evaluation value of each curve segment, and a weight of each curve segment is determined; The load difference evaluation value is obtained by calculating the sub-load difference evaluation value and the weight of each curve segment.

[0009] Furthermore, determining the weight of each curve segment includes: Determine the data average value of each curve segment and determine the overall data average value of the load difference data change curve; The ratio of the data average of each curve segment to the overall data average of the load difference data change curve is calculated respectively, and all the calculated ratios are normalized to obtain the weight of each curve segment.

[0010] Furthermore, the calculation formula of the load difference evaluation value is: , Where K is the load difference evaluation value, ai is the weight of the i-th curve segment, Xi is the sub-load difference evaluation value of the i-th curve segment, and n is the number of curve segments.

[0011] Furthermore, determining the feedback adjustment coefficient based on the load difference evaluation value includes: A corresponding relationship between the feedback adjustment coefficient and the load difference evaluation value interval is preset, and the corresponding relationship between the feedback adjustment coefficient and the load difference evaluation value interval is associated with a corresponding feedback adjustment coefficient for each load difference evaluation value interval; Obtain a load difference evaluation value, and based on the mapping relationship between the load difference evaluation value interval to which the load difference evaluation value belongs and the feedback adjustment coefficient corresponding to the load difference evaluation value interval is selected and determined as the corresponding feedback adjustment coefficient.

[0012] Furthermore, the adjusting the current refrigerant filling working condition according to the feedback adjustment coefficient and performing refrigerant filling according to the adjusted refrigerant filling working condition includes: Get the current refrigerant filling working conditions, including filling rate and filling volume; The perfusion rate and the perfusion volume are adjusted respectively according to the feedback regulation coefficient, and the refrigerant perfusion is performed according to the adjusted perfusion rate and perfusion volume.

[0013] The present invention also provides a new type of refrigerant filling system for railway stations based on feedback regulation, comprising: An acquisition module is used to acquire historical monitoring data related to the load demand of the refrigeration system, analyze the historical monitoring data, and determine the key operating parameters that affect the load demand of the refrigeration system; The prediction module is used to extract the characteristics of key operating parameters and build a load demand prediction model for the refrigeration system based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data; The analysis module is used to obtain the load data of the current refrigeration system, and perform difference analysis on the load data and the load demand forecast data to determine the load difference characteristics; An evaluation module is used to evaluate the load difference of the refrigeration system based on the load difference characteristics, obtain a load difference evaluation value, and determine a feedback adjustment coefficient based on the load difference evaluation value; The adjustment module is used to adjust the current refrigerant filling working conditions according to the feedback adjustment coefficient, and perform refrigerant filling according to the adjusted refrigerant filling working conditions.

[0014] Compared with the prior art, the novel refrigerant filling method and system for railway stations based on feedback regulation according to the embodiment of the present invention has the following beneficial effects: The present invention is based on the refrigerant perfusion technology of intelligent feedback regulation. It determines the load difference through data prediction and adjusts the current refrigerant perfusion process through evaluation and analysis. It can timely and accurately adjust the refrigerant perfusion process to meet the future load requirements of the refrigeration system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 1 is a schematic diagram of the process structure of a new refrigerant filling method for railway stations based on feedback regulation in an embodiment of the present invention; Figure 2 Schematic diagram of the composition of a new type of refrigerant filling system for railway stations based on feedback regulation in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0017] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on this application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Persons of ordinary skill in the art will understand the specific meanings of the above terms in this application based on specific circumstances.

[0020] like Figure 1 As shown, in an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, including: S100: obtaining historical monitoring data related to the load demand of the refrigeration system, and analyzing the historical monitoring data to determine the key operating parameters that affect the load demand of the refrigeration system; S200: extracting the characteristics of the key operating parameters, and constructing a load demand prediction model of the refrigeration system based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data; S300: obtaining the load data of the current refrigeration system, and performing a difference analysis on the load data and the load demand prediction data to determine the load difference characteristics; S400: evaluating the load difference of the refrigeration system based on the load difference characteristics to obtain a load difference evaluation value, and determining a feedback regulation coefficient based on the load difference evaluation value; S500: adjusting the current refrigerant filling working conditions according to the feedback regulation coefficient, and performing refrigerant filling according to the adjusted refrigerant filling working conditions.

[0021] Furthermore, the present invention is based on the refrigerant perfusion technology of intelligent feedback regulation. It determines the load difference through data prediction and adjusts the current refrigerant perfusion process through evaluation and analysis. It can timely and accurately adjust the refrigerant perfusion process to meet the future load requirements of the refrigeration system.

[0022] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, wherein historical monitoring data related to the load demand of the refrigeration system is obtained, and the historical monitoring data is analyzed to determine the key operating parameters affecting the load demand of the refrigeration system, including: obtaining historical monitoring data related to the load demand of the refrigeration system, and preprocessing the historical monitoring data, the preprocessing including removing outliers and noise in the data and filling missing values ​​in the data and standardizing the data; dividing the preprocessed historical monitoring data into multiple monitoring parameter data groups according to parameter type, and determining the historical load data of the refrigeration system; calculating the correlation between each monitoring parameter data group and the historical load data, and determining the parameters corresponding to the monitoring parameter data group whose correlation is greater than a preset threshold as the key operating parameters affecting the load demand of the refrigeration system.

[0023] Specifically, historical monitoring data related to the load demand of the refrigeration system over a period of time is collected and preprocessed, including removing outliers and noise, filling missing values, and standardizing the data. This can improve data quality and analysis accuracy. Grouping the preprocessed data by parameter type and determining the historical load data of the refrigeration system can better understand the relationship between each parameter and the system load. By calculating the correlation between each parameter data group and the historical load data, it is possible to determine which parameters have a significant impact on the load. Parameters with correlations greater than a preset threshold are selected as key operating parameters, which will receive special attention in subsequent system optimization and control. This step can improve the operating efficiency and performance of the refrigeration system by determining key operating parameters and optimizing the control of these parameters. By optimizing the control of key parameters, energy waste can be reduced and energy utilization efficiency can be improved. Improving system performance and energy efficiency can reduce the operating costs of the refrigeration system. Providing information on key operating parameters can support decision-making for system operation.

[0024] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, wherein the characteristics of key operating parameters are extracted, and a load demand prediction model of a refrigeration system is constructed based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data, including: extracting the characteristics of a monitoring parameter data group corresponding to the key operating parameters, and constructing a data set based on the monitoring parameter data group and the corresponding characteristics; inputting the data set into the corresponding preset neural network model to construct an initial model for load demand prediction; dividing the data set into a training set and a test set according to a preset ratio, and inputting the training set and the test set into the initial model for load demand prediction; training and testing the initial model for load demand prediction until the initial model for load demand prediction meets the preset convergence condition to obtain a load demand prediction model for the refrigeration system; obtaining real-time monitoring data related to the load demand of the refrigeration system, and inputting the real-time monitoring data into the load demand prediction model of the refrigeration system for prediction output to obtain load demand prediction data for the refrigeration system.

[0025] Specifically, the features of the monitoring parameter data group corresponding to the key operating parameters are extracted, and a data set containing the features and key operating parameters is constructed to ensure that the correspondence between the features in the data set and the key operating parameters is accurate; a suitable neural network model architecture is selected, and a suitable regression neural network model is selected for the load demand forecasting task; the data set is divided into a training set and a test set according to a certain ratio, usually 80% of the data is used for training and 20% of the data is used for testing; the training set is input into the neural network model for training, and the model is tested and evaluated using the test set. Through iterative training and testing until the model meets the preset convergence conditions, a load demand forecasting model is obtained; the obtained load demand forecasting model is used to predict the load demand data for a period of time in the future. Through this process, future load demand data can be accurately predicted, the full-operating condition prediction error and transient response delay can be reduced, feature dimensionality reduction reduces training time, and the embedded inference speed increases, providing core decision-making support for precise refrigerant regulation.

[0026] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, wherein the load data of the current refrigeration system is obtained, and the difference analysis between the load data and the load demand forecast data is performed to determine the load difference characteristics, including: obtaining the load data of the current refrigeration system, and determining the load demand forecast data of the refrigeration system; calculating the difference between the load demand forecast data and the load data to obtain load difference data, and constructing a time-progressive load difference data change curve based on the load difference data; determining the change period in the load difference data change curve, and dividing the load difference data change curve into multiple curve segments according to the change period; determining the slope value and change amplitude value of each curve segment, and determining the slope value and change amplitude value of each curve segment as the load difference characteristics.

[0027] Specifically, load differential data is generated by acquiring current refrigeration system load data in real time and calculating the difference between it and the predicted load demand data. A load differential change curve is constructed based on the time series, identifying periodic variations within the curve and segmenting it into multiple segments based on the period. The slope (rate of change) and amplitude (intensity of fluctuation) of each segment are extracted as core load differential features. This step accurately extracts dynamic features to identify transient changes in load differentials. By segmenting the load differentials into periods, trends are captured, preventing regulation oscillations. This reduces temperature fluctuations, preventing sudden increases in amplitude from triggering leak warnings, and reduces false alarm rates, providing a highly accurate differential quantification basis for dynamic refrigerant injection.

[0028] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, wherein the load difference of the refrigeration system is evaluated based on the load difference characteristics to obtain a load difference evaluation value, including: determining the slope value and the change amplitude value of each curve segment, and determining the preset standard slope value and standard change amplitude value of the curve segment; calculating the difference between the slope value of each curve segment and the standard slope value, and the difference between the change amplitude value and the standard change amplitude value, to obtain a first difference value and a second difference value, and evaluating the first difference and the second difference respectively to obtain a first evaluation value and a second evaluation value of each curve segment; adding the first evaluation value and the second evaluation value to obtain a sub-load difference evaluation value of each curve segment, and determining the weight of each curve segment; calculating based on the sub-load difference evaluation value and weight of each curve segment to obtain a load difference evaluation value.

[0029] Specifically, the deviation between the actual slope and amplitude of each curve segment and the standard value (the first and second differences) is calculated and converted into a risk assessment value. The slope and amplitude assessment values ​​are summed to obtain a sub-load difference assessment value, which is then combined with the weight of each curve segment to calculate a comprehensive load difference assessment value. This step reduces the false trigger rate by eliminating the impact of periodic background fluctuations. The assessment value gradient is used to predict refrigerant demand trends, improve dynamic infusion matching, and provide a core decision-making basis for system energy efficiency and stability.

[0030] In an embodiment of the present application, a new refrigerant perfusion method for a railway station based on feedback regulation is provided, and the determination of the weight of each curve segment includes: determining the data average value of each curve segment, and determining the overall data average value of the load difference data change curve; respectively calculating the ratio of the data average value of each curve segment to the overall data average value of the load difference data change curve, and normalizing all the calculated ratios to obtain the weight of each curve segment.

[0031] Specifically, the ratio of the average data value of each curve segment to the average value of the overall load difference curve is calculated, and then weighted through normalization. This step automatically strengthens the evaluation contribution of critical time periods, weakens interference during stable periods, and shortens the perception of sudden load changes to milliseconds. By capturing the degree of local and global deviations through the mean ratio, the error in differential feature extraction is significantly reduced. The normalization mechanism suppresses the impact of background fluctuations, significantly reducing the load regulation malfunction rate, and providing an adaptive evaluation foundation for precise refrigerant feedback control.

[0032] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, and the calculation formula of the load difference evaluation value is: , Where K is the load difference evaluation value, ai is the weight of the i-th curve segment, Xi is the sub-load difference evaluation value of the i-th curve segment, and n is the number of curve segments.

[0033] In an embodiment of the present application, a new refrigerant filling method for a railway station based on feedback regulation is provided, and the feedback regulation coefficient is determined based on the load difference evaluation value, including: pre-setting a feedback regulation coefficient-load difference evaluation value interval correspondence relationship, and the feedback regulation coefficient-load difference evaluation value interval correspondence relationship is associated with a corresponding feedback regulation coefficient for each load difference evaluation value interval; obtaining the load difference evaluation value, and based on the mapping relationship between the load difference evaluation value interval to which the load difference evaluation value belongs within the feedback regulation coefficient-load difference evaluation value interval correspondence relationship, selecting the feedback regulation coefficient corresponding to the load difference evaluation value interval as the corresponding feedback regulation coefficient.

[0034] Specifically, by mapping preset load difference assessment intervals to feedback adjustment coefficients, the system automatically matches the intervals based on the real-time calculated load difference assessment value, accurately locking the corresponding feedback adjustment coefficient. This step quickly completes the mapping of assessment values ​​to adjustment coefficients, reducing decision latency. The interval-based design avoids continuous calculation overhead, reduces refrigerant flow adjustment errors, and extends equipment life. By grading the coefficients to match different imbalance levels (e.g., gentle adjustment for small deviations, aggressive compensation for severe imbalances), energy efficiency is improved, providing a highly robust control core for dynamic refrigerant injection.

[0035] In an embodiment of the present application, a new refrigerant perfusion method for a railway station based on feedback regulation is provided, wherein the current refrigerant perfusion working conditions are adjusted according to the feedback regulation coefficient, and refrigerant perfusion is performed according to the adjusted refrigerant perfusion working conditions, including: obtaining the current refrigerant perfusion working conditions, the refrigerant perfusion working conditions include the perfusion rate and the perfusion volume; adjusting the perfusion rate and the perfusion volume respectively according to the feedback regulation coefficient, and performing refrigerant perfusion according to the adjusted perfusion rate and perfusion volume.

[0036] Specifically, by acquiring current refrigerant injection parameters in real time and dynamically adjusting them based on a feedback adjustment coefficient, the system implements precise injection according to the adjusted parameters: rate adjustment: new rate = original rate × adjustment coefficient; quantity adjustment: new injection volume = original planned volume × adjustment coefficient. This process delays adjustment during sudden load changes, speeding up refrigerant supply and demand matching, reducing refrigerant injection errors, improving superheat control accuracy, eliminating the risk of liquid hammer, and preventing compressor power loss caused by overcharging, thereby ensuring stable system operation and extending equipment life.

[0037] like Figure 2 As shown, in an embodiment of the present application, a new refrigerant filling system for a railway station based on feedback regulation is provided, including: an acquisition module for acquiring historical monitoring data related to the load demand of the refrigeration system, and analyzing the historical monitoring data to determine the key operating parameters that affect the load demand of the refrigeration system; a prediction module for extracting the characteristics of the key operating parameters, and constructing a load demand prediction model of the refrigeration system based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data; an analysis module for acquiring the load data of the current refrigeration system, and performing difference analysis on the load data and the load demand prediction data to determine the load difference characteristics; an evaluation module for evaluating the load difference of the refrigeration system based on the load difference characteristics to obtain a load difference evaluation value, and determining a feedback regulation coefficient based on the load difference evaluation value; an adjustment module for adjusting the current refrigerant filling working conditions according to the feedback regulation coefficient, and performing refrigerant filling according to the adjusted refrigerant filling working conditions.

[0038] In summary, an embodiment of the present invention provides a new refrigerant filling method and system for railway stations based on feedback regulation, which includes: obtaining and analyzing historical monitoring data related to the load demand of the refrigeration system, determining the key operating parameters that affect the load demand of the refrigeration system, extracting their characteristics, and constructing a prediction model based on the characteristics and a preset neural network model to obtain load demand prediction data; obtaining current load data, and analyzing it and the load demand prediction data to determine the load difference characteristics; evaluating the load difference of the refrigeration system based on the load difference characteristics to obtain a load difference evaluation value, and adjusting the current refrigerant filling working conditions based on the feedback adjustment coefficient. The present invention is based on a refrigerant filling technology based on intelligent feedback regulation. It determines the load difference through data prediction, and adjusts the current refrigerant filling process through evaluation and analysis. It can timely and accurately adjust the refrigerant filling process to meet the future load demand of the refrigeration system.

[0039] Finally, it should be noted that it is apparent that various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations as long as they fall within the scope of the present invention and its equivalents.

[0040] The above description is only an example of an embodiment of the present invention, but it does not limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be considered to fall within the scope of protection of the present invention and be subject to restrictions. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0041] The term "comprise," "comprising," or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0042] Thus far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to closely related technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0043] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A new refrigerant filling method for railway stations based on feedback regulation, characterized in that: include: Obtain historical monitoring data related to the load demand of the refrigeration system, analyze the historical monitoring data, and determine the key operating parameters that affect the load demand of the refrigeration system; Extract the characteristics of key operating parameters, and build a load demand forecasting model for the refrigeration system based on the characteristics and the preset neural network model to perform load forecasting and obtain load demand forecast data; Obtain the current refrigeration system load data, and perform difference analysis between the load data and load demand forecast data to determine the load difference characteristics; Evaluating the load difference of the refrigeration system based on the load difference characteristics to obtain a load difference evaluation value, and determining a feedback adjustment coefficient based on the load difference evaluation value; The current refrigerant filling working condition is adjusted according to the feedback adjustment coefficient, and the refrigerant filling is performed according to the adjusted refrigerant filling working condition.

2. A new refrigerant filling method for railway stations based on feedback regulation according to claim 1, characterized in that: The acquisition of historical monitoring data related to the refrigeration system load demand and analysis of the historical monitoring data to determine key operating parameters that affect the refrigeration system load demand include: Obtain historical monitoring data related to the load demand of the refrigeration system and preprocess the historical monitoring data. The preprocessing includes removing outliers and noise in the data, filling missing values ​​in the data, and standardizing the data. Dividing the pre-processed historical monitoring data into multiple monitoring parameter data groups according to parameter types, and determining historical load data of the refrigeration system; The correlation between each monitoring parameter data group and the historical load data is calculated, and the parameters corresponding to the monitoring parameter data groups with correlations greater than a preset threshold are determined as key operating parameters affecting the load demand of the refrigeration system.

3. A new refrigerant filling method for railway stations based on feedback regulation according to claim 2, characterized in that: The extraction of the characteristics of the key operating parameters and the construction of a load demand prediction model for the refrigeration system based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data include: Extracting features of the monitoring parameter data group corresponding to the key operating parameters, and constructing a data set based on the monitoring parameter data group and the corresponding features; Input the data set into the corresponding preset neural network model to build an initial load demand forecast model; The data set is divided into a training set and a test set according to a preset ratio, and the training set and the test set are input into the initial load demand forecasting model; The load demand prediction initial model is trained and tested until the load demand prediction initial model meets the preset convergence conditions, thereby obtaining a load demand prediction model for the refrigeration system; The real-time monitoring data related to the load demand of the refrigeration system is obtained, and the real-time monitoring data is input into the load demand prediction model of the refrigeration system for prediction output to obtain the load demand prediction data of the refrigeration system.

4. A new refrigerant filling method for railway stations based on feedback regulation according to claim 3, characterized in that: The process of obtaining the current load data of the refrigeration system and performing a difference analysis between the load data and the load demand forecast data to determine the load difference characteristics includes: Obtain the current refrigeration system load data and determine the load demand forecast data of the refrigeration system; Calculate the difference between the load demand forecast data and the load data to obtain load difference data, and construct a time-progress load difference data change curve based on the load difference data; Determining a change period in a load difference data change curve, and dividing the load difference data change curve into a plurality of curve segments according to the change period; The slope value and the variation amplitude value of each curve segment are determined, and the slope value and the variation amplitude value of each curve segment are determined as the load difference feature.

5. A new refrigerant filling method for railway stations based on feedback regulation according to claim 4, characterized in that: The step of evaluating the load difference of the refrigeration system based on the load difference characteristic to obtain a load difference evaluation value includes: Determine the slope value and variation range value of each curve segment, and determine the preset standard slope value and standard variation range value of the curve segment; Calculate the difference between the slope value and the standard slope value, and the difference between the variation amplitude value and the standard variation amplitude value of each curve segment to obtain a first difference value and a second difference value, and evaluate the first difference value and the second difference value to obtain a first evaluation value and a second evaluation value of each curve segment; The first evaluation value and the second evaluation value are added together to obtain a sub-load difference evaluation value of each curve segment, and a weight of each curve segment is determined; The load difference evaluation value is obtained by calculating the sub-load difference evaluation value and the weight of each curve segment.

6. A new refrigerant filling method for railway stations based on feedback regulation according to claim 5, characterized in that: Determining the weight of each curve segment includes: Determine the data average value of each curve segment and determine the overall data average value of the load difference data change curve; The ratio of the data average of each curve segment to the overall data average of the load difference data change curve is calculated respectively, and all the calculated ratios are normalized to obtain the weight of each curve segment.

7. A new refrigerant filling method for railway stations based on feedback regulation according to claim 6, characterized in that: The calculation formula of the load difference evaluation value is: ， Where K is the load difference evaluation value, ai is the weight of the i-th curve segment, Xi is the sub-load difference evaluation value of the i-th curve segment, and n is the number of curve segments.

8. A new refrigerant filling method for railway stations based on feedback regulation according to claim 5, characterized in that: The step of determining the feedback adjustment coefficient based on the load difference evaluation value includes: A corresponding relationship between the feedback adjustment coefficient and the load difference evaluation value interval is preset, and the corresponding relationship between the feedback adjustment coefficient and the load difference evaluation value interval is associated with a corresponding feedback adjustment coefficient for each load difference evaluation value interval; Obtain a load difference evaluation value, and based on the mapping relationship between the load difference evaluation value interval to which the load difference evaluation value belongs and the feedback adjustment coefficient corresponding to the load difference evaluation value interval is selected and determined as the corresponding feedback adjustment coefficient.

9. A new refrigerant filling method for railway stations based on feedback regulation according to claim 8, characterized in that: The adjusting the current refrigerant filling working condition according to the feedback adjustment coefficient and performing refrigerant filling according to the adjusted refrigerant filling working condition includes: Get the current refrigerant filling working conditions, including filling rate and filling volume; The perfusion rate and the perfusion volume are adjusted respectively according to the feedback regulation coefficient, and the refrigerant perfusion is performed according to the adjusted perfusion rate and perfusion volume.

10. A new type of refrigerant filling system for railway stations based on feedback regulation, characterized in that: include: An acquisition module is used to acquire historical monitoring data related to the load demand of the refrigeration system, analyze the historical monitoring data, and determine the key operating parameters that affect the load demand of the refrigeration system; The prediction module is used to extract the characteristics of key operating parameters and build a load demand prediction model for the refrigeration system based on the characteristics and a preset neural network model to perform load prediction and obtain load demand prediction data; The analysis module is used to obtain the load data of the current refrigeration system, and perform difference analysis on the load data and the load demand forecast data to determine the load difference characteristics; An evaluation module is used to evaluate the load difference of the refrigeration system based on the load difference characteristics, obtain a load difference evaluation value, and determine a feedback adjustment coefficient based on the load difference evaluation value; The adjustment module is used to adjust the current refrigerant filling working conditions according to the feedback adjustment coefficient, and perform refrigerant filling according to the adjusted refrigerant filling working conditions.

Images