An intelligent metering method and system for airport gas energy

Abstract

The present invention proposes an intelligent metering method and system for airport gas energy. The method includes: preprocessing gas data and extracting key characteristic parameters. Inputting these parameters into a gas consumption prediction model to obtain a predicted value. Formulating a gas supply strategy based on the predicted value and the airport operation plan. Monitoring the actual consumption in real time and comparing it with the predicted value to optimize the supply strategy. The present invention first collects and preprocesses gas data to eliminate noise and fill in missing values to ensure the accuracy and integrity of the data. Then, key characteristic parameters are extracted to reflect the gas consumption pattern. Based on these parameters, a prediction model is constructed to predict future consumption using historical data and auxiliary information. The model is trained and optimized through machine learning algorithms to improve accuracy. When formulating the supply strategy, the demand is evaluated by combining the predicted value and the airport operation plan to determine the supply priority and allocation plan. The actual consumption is monitored in real time, compared with the predicted value, and the supply strategy is adjusted in a timely manner to optimize management and improve the level of intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent metering and energy management, and particularly to an intelligent metering method and system for airport gas energy. Background Art

[0002] With the rapid development of the global aviation industry, airports, as the core nodes of air transportation, have an increasing energy consumption, and gas energy occupies an important proportion. Traditional gas metering methods mainly rely on mechanical gas meters. Although these devices can meet the basic metering requirements to a certain extent, they have obvious deficiencies in terms of accuracy, real-time performance, intelligence, and data analysis.

[0003] First of all, the metering accuracy of traditional gas meters is limited by their mechanical structure and working principle, and it is often difficult to meet the requirements of high-precision metering. In large energy-consuming places such as airports, even a small difference in gas usage can bring significant changes in energy costs. Therefore, improving metering accuracy is of great significance for energy conservation and emission reduction and cost control. Secondly, traditional gas meters lack real-time monitoring and remote communication capabilities, resulting in difficulty in obtaining and analyzing gas usage data in a timely manner. This not only limits the real-time performance and accuracy of the energy management system but also increases the workload of manual meter reading and data analysis. In addition, traditional gas metering methods lack intelligence and data analysis capabilities. In airport gas energy management, simply knowing the gas usage is not enough; in-depth analysis of the usage data is also required to discover potential energy-saving opportunities and optimization strategies. However, traditional gas meters cannot provide sufficient data support, making energy management decisions lack a scientific basis. Summary of the Invention

[0004] The present invention aims to at least solve the technical problem in the prior art that traditional gas metering methods lack intelligence and data analysis capabilities, and particularly innovatively proposes an intelligent metering method and system for airport gas energy.

[0005] To achieve the above object of the present invention, the present invention provides an intelligent metering method for airport gas energy, and the method includes:

[0006] S1. Collect gas data, preprocess the gas data, and extract key characteristic parameters based on the preprocessed gas data;

[0007] S2. Input the extracted key characteristic parameters into a pre-constructed gas energy consumption prediction model to obtain a gas energy consumption prediction value;

[0008] S3. According to the gas energy consumption prediction value and in combination with the airport operation plan, formulate a gas energy supply strategy;

[0009] S4. Monitor the actual consumption of gas energy in real time, compare it with the predicted value of gas energy consumption, and optimize the gas energy supply strategy according to the comparison result.

[0010] As an alternative embodiment of the present invention, optionally, extracting the key feature parameters in step S1 includes:

[0011] S101. Set the data acquisition time interval, obtain the gas meter reading sequence based on the image collector, and complete the missing values in the gas meter reading sequence;

[0012] S102. Smooth the gas meter reading sequence;

[0013] S103. Based on the smoothed gas meter reading sequence, extract the gas consumption features using the feature extraction algorithm;

[0014] S104. Screen the gas consumption features to obtain the key feature parameters.

[0015] As an alternative embodiment of the present invention, optionally, the expression for extracting the gas consumption features in step S103 is:

[0016]

[0017] where represents the gas consumption feature, represents the length of the gas meter reading sequence, represents the difference between the gas reading at the th time point and the gas reading at the previous time point, represents the th gas reading at the time point, represents the mean value of the gas meter reading sequence, represents the standard deviation of the gas meter reading sequence, represents the exponential function, represents the standard deviation of the temperature sequence, represents the th temperature value at the time point, represents the mean value of the temperature sequence.

[0018] As an alternative embodiment of the present invention, optionally, the expression for completing the missing values in the gas meter reading sequence in step S101 is:

[0019] ,

[0020] ,

[0021] ,

[0022] ,

[0023] ;

[0024] Among them, represents the first missing value, represents the valid value before the position of the th missing value, represents the valid value after the position of the th missing value, represents the second missing value, represents the number of valid values in the set, represents the th reading in the gas meter reading sequence , represents the third missing value, represents the pre-trained time series trend prediction function, represents the position index of the th missing value in the set of missing value positions , represents the th reading after completion at the position of the missing value, , and both represent the weights used for weighted average calculation.

[0025] As an alternative embodiment of the present invention, optionally, constructing the gas energy consumption prediction model in step S2 includes:

[0026] S201. Collect historical gas data and auxiliary data, where the auxiliary data includes weather data and airport operation data;

[0027] S202. Perform preprocessing and feature extraction on the historical gas data and auxiliary data in sequence to obtain historical gas consumption features;

[0028] S203. Construct a loss function, and based on the historical gas consumption features and the loss function, construct a gas energy consumption prediction model using a machine learning algorithm, and train the gas energy consumption prediction model using the backpropagation algorithm until a preset training accuracy or number of iterations is reached.

[0029] As an alternative embodiment of the present invention, optionally, formulating the gas energy supply strategy in step S3 includes:

[0030] S301. Based on the predicted value of gas energy consumption, combined with the flight takeoff and landing plan of the airport, the predicted passenger flow, and the operating requirements of airport facilities, comprehensively evaluate the supply demand of gas energy to obtain an evaluation result;

[0031] S302. Based on the evaluation result, determine the gas supply priorities for different time periods or different facilities. Based on the priorities, formulate a gas energy allocation plan and a supply schedule;

[0032] S303. According to the gas energy supply strategy and the supply schedule, adjust the operating parameters of the gas supply equipment;

[0033] S304. Regularly evaluate the execution efficiency of the gas energy supply strategy, and optimize the gas energy supply strategy based on the results of the regular evaluation.

[0034] As an alternative embodiment of the present invention, optionally, determining the gas supply priorities for different time periods or different facilities in step S302 includes:

[0035] S3021. According to the historical gas consumption data, the flight takeoff and landing density, the passenger flow fluctuation, and the operating characteristics of airport facilities, analyze the degree of dependence of different time periods and different facilities on gas energy to obtain an analysis result;

[0036] S3022. Based on the analysis result, use the priority analysis method to quantitatively score the gas supply demands of different time periods and different facilities. The higher the score, the higher the gas supply priority;

[0037] S3023. Based on the quantitative scoring result, formulate a priority list for gas supply.

[0038] As an alternative embodiment of the present invention, optionally, the priority analysis method in step S3022 includes:

[0039] S30221. Obtain a judgment matrix , , where represents the degree of importance of alternative relative to alternative ;

[0040] S30222. Normalize the judgment matrix , , where , represents the normalized judgment matrix, represents the element in the normalized judgment matrix, which is the result after the original judgment matrix element is normalized, represents the order of the judgment matrix, that is, the number of alternatives, Representation of the solution Relative to the solution Degree of importance;

[0041] S30223. Based on the normalized judgment matrix Calculate the weight vector of each solution , , , where Represents the solution Weight;

[0042] S30224. Use the consistency index And the random consistency ratio Perform consistency test, where Represents the maximum eigenvalue of the judgment matrix, Represents the random consistency index;

[0043] If < 0.1, the judgment matrix has consistency;

[0044] If > 0.1, the judgment matrix does not have consistency, and the judgment matrix needs to be adjusted until the consistency requirement is met.

[0045] On the other hand, the present invention also provides an intelligent metering system for airport gas energy, and the system includes the above-mentioned intelligent metering method for airport gas energy;

[0046] The system further includes:

[0047] Data acquisition module, used to acquire gas data;

[0048] Communication module, connected to the data acquisition module;

[0049] Pretreatment module, connected to the communication module, used to preprocess the gas data;

[0050] Feature extraction module, connected to the pretreatment module, used to extract key feature parameters based on the preprocessed gas data;

[0051] Prediction model module, connected to the feature extraction module, used to input the extracted key feature parameters into a pre-constructed gas energy consumption prediction model to obtain a gas energy consumption prediction value;

[0052] Strategy formulation module, connected to the prediction model module, used to formulate a gas energy supply strategy according to the gas energy consumption prediction value and in combination with the airport operation plan;

[0053] The monitoring and adaptive optimization module, connected to the strategy formulation module, is used to monitor the actual consumption of gas energy in real time, compare it with the predicted value of gas energy consumption, and adaptively optimize the gas energy supply strategy based on the comparison result.

[0054] Advantages of the present invention: First, the present invention collects gas data and preprocesses these data to eliminate noise, fill in missing values, etc., so as to ensure the accuracy and integrity of the data. Then, key feature parameters are extracted from the preprocessed data, and these feature parameters can reflect the main laws and trends of gas consumption. Next, based on the extracted key feature parameters, a gas energy consumption prediction model is constructed. This model can use historical data and auxiliary information (such as weather data, airport operation data, etc.) to predict future gas consumption. During the construction of the prediction model, machine learning algorithms are used for training, and optimization means such as backpropagation are used to improve the prediction accuracy. When formulating the gas energy supply strategy, this method will comprehensively evaluate the gas energy supply demand according to the predicted gas consumption value and in combination with the airport operation plan (such as flight takeoff and landing plan, passenger flow prediction, etc.). Based on this evaluation result, the gas supply priorities for different time periods or different facilities can be determined, and accordingly, a gas energy distribution plan and supply schedule can be formulated. Finally, this method will also monitor the actual consumption of gas energy in real time and compare it with the predicted value. According to the comparison result, the deviation in the supply strategy can be detected and corrected in time, so as to continuously optimize the gas energy supply strategy, improve the intelligent level, solve the problem that the traditional gas metering method lacks intelligence and data analysis ability, and also realize the efficient management and utilization of gas energy through real-time monitoring and optimization of the supply strategy.

[0055] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. Brief Description of the Drawings

[0056] The above and / or additional aspects and advantages of the present invention will become apparent and easy to understand from the description of the embodiments in conjunction with the following drawings, wherein:

[0057] Figure 1 is a flowchart of an airport gas energy intelligent metering method in Embodiment 1 of the present invention;

[0058] Figure 2 is a structural schematic diagram of an airport gas energy intelligent metering system in Embodiment 2 of the present invention. Detailed Embodiments

[0059] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation of the present invention.

[0060] Embodiment 1

[0061] As Figure 1 shown, an intelligent metering method for airport gas energy, the method comprising:

[0062] S1. Collect gas data, preprocess the gas data, and extract key feature parameters based on the preprocessed gas data;

[0063] It should be noted that in step S1, the gas data includes the readings of gas meters, the flow data of gas pipelines, the gas pressure data, and the gas temperature data, etc. The preprocessing process includes but is not limited to operations such as data cleaning, data conversion, and data normalization, aiming to improve the data quality. Data cleaning can eliminate outliers and duplicates in the data to ensure the accuracy and consistency of the data; data conversion is to convert the data into a format suitable for model processing; data normalization helps to eliminate the dimensional differences between different features and improve the convergence speed and prediction accuracy of the model. When extracting key feature parameters, this embodiment not only considers the information of the gas meter reading sequence itself, but also incorporates time factors and external environmental factors (such as temperature, etc.). These features together constitute a comprehensive perspective reflecting the gas consumption law. By deeply mining and analyzing these features, the internal law of gas consumption can be grasped more accurately, providing strong support for subsequent prediction and strategy formulation.

[0064] S2. Input the extracted key feature parameters into a pre-constructed gas energy consumption prediction model to obtain a gas energy consumption prediction value;

[0065] It should be noted that in step S2, the constructed gas energy consumption prediction model is specifically a prediction model based on machine learning. This model can receive the key feature parameters extracted from gas data as input and output the prediction value of gas energy consumption. To construct this model, a large amount of historical gas data will be collected first as training samples, and these data include the readings of gas meters, the flow data of gas pipelines, the gas pressure data, the gas temperature data, etc. At the same time, auxiliary data related to gas consumption will also be collected, such as weather data (such as temperature, humidity, wind speed, etc.) and airport operation data (such as flight takeoff and landing plans, passenger flow, etc.). These data will jointly constitute the input feature set of the model.

[0066] During the model training phase, appropriate machine learning algorithms (such as support vector machines, random forests, neural networks, etc.) are used to build a prediction model. These algorithms can learn the patterns and trends of gas consumption from the input feature set and predict future gas consumption based on these patterns and trends. To improve the prediction accuracy of the model, some optimization techniques are also adopted, such as feature selection, parameter tuning, cross-validation, etc.

[0067] After the model is built, it can be applied to actual gas energy metering. By inputting the real-time collected gas data into the model, the predicted value of gas energy consumption can be obtained. This predicted value can provide an important reference for the gas energy management of the airport, helping the airport formulate a reasonable gas energy supply strategy, optimize the distribution and utilization of gas energy, improve energy utilization efficiency, and reduce operating costs.

[0068] S3. According to the predicted value of gas energy consumption and combined with the airport operation plan, formulate a gas energy supply strategy;

[0069] It should be noted that in step S3, when formulating a gas energy supply strategy, first, a rough estimate of the airport's future gas demand will be made based on the predicted value of gas energy consumption. Then, combined with the airport operation plan, such as flight takeoff and landing plans, passenger flow forecasts, and operating requirements of airport facilities, etc., the demand distribution of gas energy will be further refined. In this process, the degree of dependence of different time periods and different facilities on gas energy will be fully considered to ensure the pertinence and effectiveness of the supply strategy.

[0070] S4. Real-time monitor the actual consumption of gas energy and compare it with the predicted value of gas energy consumption, and optimize the gas energy supply strategy according to the comparison result.

[0071] It should be noted that in step S4, real-time monitoring is a key link to ensure the effectiveness of the gas energy supply strategy. Through real-time monitoring, the differences between the actual consumption of gas energy and the predicted value can be discovered in a timely manner. Such differences may stem from various factors, such as sudden weather changes, temporary adjustments of flight plans, or operating failures of airport facilities, etc. Once a significant deviation between the actual consumption and the predicted value is found, the system will immediately trigger an early warning mechanism to notify relevant personnel for verification and handling. In the process of comparing the actual consumption with the predicted value, the system will use data analysis techniques to conduct a detailed analysis and attribution of the deviation. This not only helps to quickly locate the problem, but also provides a scientific basis for subsequent optimization. Based on the comparison result, the system will adaptively adjust the gas energy supply strategy to ensure the dynamic balance between supply and demand. This adaptive optimization mechanism can continuously improve the management efficiency of gas energy and achieve more refined and intelligent energy management.

[0072] In summary, in this embodiment, first, gas data is collected and preprocessed to eliminate noise, fill in missing values, etc., so as to ensure the accuracy and integrity of the data. Then, key feature parameters are extracted from the preprocessed data, and these feature parameters can reflect the main laws and trends of gas consumption. Next, based on the extracted key feature parameters, a gas energy consumption prediction model is constructed. This model can use historical data and auxiliary information (such as weather data, airport operation data, etc.) to predict future gas consumption. During the construction of the prediction model, machine learning algorithms are used for training, and optimization means such as backpropagation are used to improve the accuracy of the prediction. When formulating the gas energy supply strategy, this method will comprehensively evaluate the gas energy supply demand according to the predicted gas consumption value and in combination with the airport operation plan (such as flight takeoff and landing plan, passenger flow prediction, etc.). Based on this evaluation result, the gas supply priorities for different time periods or different facilities can be determined, and accordingly, the gas energy allocation plan and supply schedule can be formulated. Finally, this method will also monitor the actual gas energy consumption in real time and compare it with the predicted value. According to the comparison result, the deviation in the supply strategy can be discovered and corrected in time, so as to continuously optimize the gas energy supply strategy, improve the intelligent level, solve the problem that the traditional gas metering method lacks intelligence and data analysis ability, and also realize the efficient management and utilization of gas energy through real-time monitoring and optimization of the supply strategy.

[0073] As an alternative embodiment of the present invention, optionally, the extraction of key feature parameters in step S1 includes:

[0074] S101. Set the data collection time interval, obtain the gas meter reading sequence based on the image collector, and complete the missing values in the gas meter reading sequence;

[0075] It should be noted that in step S101, the setting of the data collection time interval aims to balance data accuracy and system overhead, ensuring that both the detailed changes in gas consumption can be captured and the system burden will not be increased due to overly frequent data collection. The high precision and stability of the image collector are crucial for accurately obtaining the gas meter readings, and it can effectively avoid inaccurate subsequent analysis caused by reading errors. For the missing gas meter readings caused by equipment failures, data transmission interruptions, etc., this embodiment will use interpolation algorithms to complete the missing values to ensure the integrity and continuity of the data sequence.

[0076] S102. Smooth the gas meter reading sequence;

[0077] It should be noted that in step S102, the smoothing process aims to eliminate noise and fluctuations in the gas meter reading sequence, improving the accuracy and reliability of the data. By smoothing the reading sequence, abnormal fluctuations caused by reading errors or equipment failures can be reduced, making the data more stable and continuous. In this embodiment, an appropriate smoothing algorithm, such as the moving average method, exponential smoothing method, etc., will be used to process the gas meter reading sequence to obtain a smoother and more accurate data sequence.

[0078] S103. Based on the smoothed gas meter reading sequence, use a feature extraction algorithm to extract gas consumption features;

[0079] It should be noted that in step S103, the feature extraction algorithm can deeply explore the potential information and patterns in the gas meter reading sequence, thereby extracting key indicators reflecting gas consumption characteristics. These features may include the daily change trend of gas consumption, weekly change cycle, seasonal fluctuations, etc., as well as the correlation with other relevant factors (such as weather, flight schedules, etc.).

[0080] S104. Screen the gas consumption features to obtain key feature parameters.

[0081] It should be noted that in step S104, this embodiment will use a variety of screening methods, such as correlation coefficient analysis, mutual information analysis, recursive feature elimination, etc., to comprehensively evaluate the extracted gas consumption features. By comprehensively considering the importance, stability of the features and their correlation with the prediction target, the most representative key feature parameters are finally selected. These parameters will be used as the input of the prediction model for subsequent gas energy consumption prediction.

[0082] As an alternative embodiment of the present invention, optionally, the expression for extracting gas consumption features in step S103 is:

[0083]

[0084] where represents the gas consumption feature;

[0085] represents the length of the gas meter reading sequence;

[0086] represents the th difference between the gas reading at the

[0087] th time point and the gas reading at the previous time point; represents the gas reading at the

[0088] represents the mean of the gas meter reading sequence;

[0089] represents the standard deviation of the gas meter reading sequence;

[0090] represents the exponential function;

[0091] represents the standard deviation of the temperature sequence;

[0092] represents the temperature value at the

[0093] time point;

[0094] It should be noted that this part calculates the square root of the sum of squares of the gas consumption change rate, reflecting the fluctuation of gas consumption. A larger value indicates a large change in gas consumption in a short period of time. This part calculates the cube root of the average of the cubes of the absolute values of the deviation of gas consumption from the mean, which is used to measure the degree of deviation of gas consumption from the normal level. A larger value indicates a large deviation of gas consumption from the average level. This part is the reciprocal of a Gaussian function, which is used to measure the concentration degree of the temperature sequence. A smaller value indicates a large temperature fluctuation, which may have a significant impact on gas consumption. If the temperature has no significant impact on gas consumption, this item can be omitted or replaced by other relevant factors during specific implementation.

[0095] As an alternative embodiment of the present invention, optionally, the expression for filling in the missing values in the gas meter reading sequence in step S101 is:

[0096] ,

[0097] ,

[0098] ,

[0099] ,

[0100] ;

[0101] where represents the first missing value;

[0102] represents the valid value before the

[0103] Indicates the valid value after the th missing value position;

[0104] Indicates the second missing value;

[0105] Indicates the number of valid values in the set;

[0106] Indicates the th reading in the gas meter reading sequence;

[0107] Indicates the third missing value;

[0108] Indicates the pre-trained time series trend prediction function;

[0109] Indicates the set of missing value positions in the th position index of the missing value;

[0110] Indicates the th completed reading at the missing value position;

[0111] , and all indicate the weights used for weighted average calculation.

[0112] As an alternative embodiment of the present invention, optionally, constructing the gas energy consumption prediction model in step S2 includes:

[0113] S201. Collect historical gas data and auxiliary data, where the auxiliary data includes weather data and airport operation data;

[0114] S202. Preprocess and extract features from the historical gas data and auxiliary data in sequence to obtain historical gas consumption features;

[0115] S203. Construct a loss function, and based on the historical gas consumption features and the loss function, use a machine learning algorithm to construct a gas energy consumption prediction model, and use the backpropagation algorithm to train the gas energy consumption prediction model until a preset training accuracy or number of iterations is reached.

[0116] It should be noted that in step S201, the collection of historical gas data and auxiliary data is the basis for constructing the prediction model. The historical gas data records the past gas consumption situation of the airport, while the auxiliary data such as weather data and airport operation data provides information on external factors related to gas consumption. These data together constitute the input set for model training, providing a rich source of information for the model to learn the patterns and trends of gas consumption.

[0117] In step S202, preprocessing and feature extraction of the historical gas data and auxiliary data are key steps to ensure the quality of the model. The preprocessing stage aims to eliminate noise and outliers in the data, fill in missing values, and perform necessary data transformations to ensure the accuracy and consistency of the data. The feature extraction stage extracts key indicators that can reflect the characteristics of gas consumption by deeply mining the potential information and patterns in the data, and these indicators will be used as input features for model training.

[0118] In step S203, the loss function defines the degree of difference between the predicted value and the actual value of the model. By minimizing the loss function, the parameters of the model can be continuously adjusted to improve the prediction accuracy of the model. In this embodiment, a machine learning algorithm is used to construct a gas energy consumption prediction model, and the model is trained through the backpropagation algorithm. The backpropagation algorithm calculates the gradient of the loss function with respect to the model parameters and updates the model parameters along the opposite direction of the gradient, thereby continuously optimizing the prediction performance of the model. The training process will continue until the preset training accuracy or the number of iterations is reached to ensure the stability and reliability of the model.

[0119] As an alternative embodiment of the present invention, optionally, formulating the gas energy supply strategy in step S3 includes:

[0120] S301. According to the predicted value of the gas energy consumption, combined with the flight takeoff and landing plan of the airport, the passenger flow prediction, and the operation requirements of the airport facilities, comprehensively evaluate the supply demand of the gas energy to obtain an evaluation result;

[0121] It should be noted that in step S301, the evaluation result not only considers the predicted value of gas consumption, but also fully incorporates the actual operation situation of the airport, such as the flight takeoff and landing plan, the passenger flow prediction, and the operation requirements of the airport facilities, etc., to ensure the comprehensiveness and accuracy of the evaluation result. The specific evaluation process will adopt a variety of evaluation methods and models, such as time series analysis, regression analysis, machine learning algorithms, etc., to comprehensively consider the impact of various factors on the gas energy supply demand. By comprehensively analyzing these factors, a more accurate and reliable evaluation result can be obtained. Based on this evaluation result, the airport can more accurately grasp the supply demand of the gas energy.

[0122] S302. Based on the evaluation results, determine the gas supply priorities for different time periods or different facilities. Based on the priorities, formulate a gas energy allocation plan and a supply schedule;

[0123] It should be noted that in step S302, the determination of gas supply priorities will consider various factors, such as the accuracy of gas consumption prediction values, the importance of airport operation plans, and the reliability and stability of gas supply. For time periods or facilities with higher prediction values and more critical airport operation plans, higher supply priorities will be given to ensure the satisfaction of their gas demands. At the same time, when formulating the gas energy allocation plan and supply schedule, the reliability and stability of gas supply will also be fully considered to avoid adverse impacts on airport operations due to insufficient supply or interruptions. By comprehensively considering these factors, a more reasonable and effective gas energy supply strategy can be formulated to achieve efficient management and utilization of gas energy.

[0124] S303. According to the gas energy supply strategy and supply schedule, adjust the operating parameters of gas supply equipment;

[0125] It should be noted that in step S303, the parameters include gas supply pressure, flow rate, temperature, etc. By precisely regulating these parameters, it can be ensured that the gas supply matches the actual demands of the airport, meeting the operation requirements while avoiding energy waste. The adjustment process will be dynamically adjusted according to the supply strategy and supply schedule to adapt to the gas demand changes in different time periods and different facilities. At the same time, regular maintenance and inspection of gas supply equipment will also be carried out to ensure its good operating condition and avoid adverse impacts on gas supply due to equipment failures.

[0126] S304. Regularly evaluate the execution efficiency of the gas energy supply strategy and optimize the gas energy supply strategy based on the regular evaluation results.

[0127] It should be noted that in step S304, in this embodiment, various indicators and methods will be used in the evaluation process, such as the comparison of gas consumption, the analysis of supply stability, the evaluation of equipment operation efficiency, etc., to comprehensively measure the execution efficiency of the strategy. Based on the evaluation results, the gas energy supply strategy can be adjusted and optimized, such as adjusting supply priorities, optimizing the allocation plan, improving the equipment operation status, etc., to achieve more efficient and reliable gas energy management and utilization.

[0128] As an alternative embodiment of the present invention, optionally, determining the gas supply priorities for different time periods or different facilities in step S302 includes:

[0129] S3021. Analyze the degree of dependence on gas energy for different time periods and different facilities based on the historical gas consumption data, flight takeoff and landing density, passenger flow fluctuations, and operating characteristics of airport facilities, and obtain the analysis results;

[0130] It should be noted that in step S3021, the analysis results can reveal the gas consumption patterns of the airport at different time periods and different facilities, so as to determine which time periods or facilities have a higher degree of dependence on gas energy. For example, during the time periods with intensive flight takeoffs and landings, the gas consumption may increase significantly, so these time periods should be given higher supply priorities. Similarly, for facilities whose operating characteristics determine a large gas consumption, higher supply priorities should also be given to ensure the timely satisfaction of their gas demands. By deeply analyzing these factors, it can provide strong support for formulating more accurate and effective gas energy supply strategies.

[0131] S3022. Based on the analysis results, use the priority analysis method to quantitatively score the gas supply demands of different time periods and different facilities. The higher the score, the higher the gas supply priority;

[0132] It should be noted that in step S3022, the priority analysis method will comprehensively consider various factors, such as the accuracy of gas consumption prediction values, flight takeoff and landing density, passenger flow fluctuations, operating characteristics of airport facilities, and the reliability and stability of gas supply. By assigning different weights to these factors and combining historical data and actual situations for quantitative scoring, the gas supply priorities of different time periods and different facilities can be obtained. A higher score means that this time period or facility has a higher priority in gas supply and requires more attention and resource investment.

[0133] S3023. Based on the quantitative scoring results, formulate a priority list for gas supply.

[0134] It should be noted that in step S3023, the priority list not only helps airport managers intuitively understand the gas supply priorities of each time period and facility, but also can be used as an important basis for formulating gas energy distribution plans and supply schedules. When formulating the priority list, the comprehensive impacts of various factors will be fully considered to ensure the accuracy and rationality of the list. By following this list, the airport can more efficiently manage and utilize gas energy, meet the actual needs of airport operations, and at the same time reduce energy consumption and costs.

[0135] As an optional embodiment of the present invention, optionally, in step S3022, the priority analysis method includes:

[0136] S30221. Obtain the judgment matrix , , where Representation scheme Relative to the scheme Degree of importance;

[0137] It should be noted that in step S30221, to obtain the judgment matrix, specifically, the objects to be compared need to be determined first. These objects can be different criteria (such as historical gas consumption data, flight takeoff and landing density, etc.), or different schemes (such as different time periods or facilities). To quantify the relative importance between the comparison objects, a 1-9 scale is usually adopted. This scale reflects the comparison levels and order-of-magnitude characteristics of people's judgment psychology, where 1 means that two objects are equally important, 9 means that one object is extremely more important than the other object, and the intermediate values represent different degrees of relative importance. Next, pairwise comparisons are made for the comparison objects. For each criterion in the criterion layer, a judgment matrix is constructed to compare the relative importance of each scheme under this criterion. For the schemes in the scheme layer, pairwise comparisons also need to be made according to the criteria in the upper layer. According to the results of the pairwise comparisons, the judgment matrix is filled. The elements of the judgment matrix Represent the object Relative to the object Degree of importance. Since the judgment matrix is a positive reciprocal matrix, that is = 1 / , so only the upper triangular or lower triangular part of the matrix needs to be filled, and the rest can be obtained through reciprocity. In practical applications, the data of the judgment matrix is usually obtained through the expert scoring method. Experts make subjective judgments on the comparison objects based on their knowledge and experience and give the corresponding scale values. Then, these scale values are synthesized to obtain each element of the judgment matrix.

[0138] S30222. Normalize the judgment matrix , , where , Represents the normalized judgment matrix, Represents the element in the normalized judgment matrix, which is the result after the original judgment matrix element is normalized, Represents the order of the judgment matrix, that is, the number of schemes, Represents the scheme Relative to the scheme Degree of importance;

[0139] S30223. Calculate the weight vector of each scheme based on the normalized judgment matrix , , , , where Represents the scheme Weight;

[0140] S30224. Use the consistency index and the random consistency ratio to perform consistency test, where represents the maximum eigenvalue of the judgment matrix, represents the random consistency index;

[0141] If < 0.1, the judgment matrix has consistency;

[0142] If > 0.1, the judgment matrix does not have consistency, and the judgment matrix needs to be adjusted until the consistency requirement is met.

[0143] Embodiment 2

[0144] As Figure 2 shown, an intelligent metering system for airport gas energy, the system includes the above-mentioned intelligent metering method for airport gas energy;

[0145] The system further includes:

[0146] A data acquisition module, used to acquire gas data; specifically, the data acquisition module includes a sensor network and a data processing unit. The sensor network is deployed at key gas supply points and consumption points in the airport, and can monitor key parameters such as gas flow and pressure in real time. The data processing unit is responsible for receiving the data transmitted by the sensor network and performing preliminary processing and storage.

[0147] A communication module, connected to the data acquisition module; specifically, the communication module is connected to the data acquisition module and is responsible for transmitting the processed gas data and related information to the preprocessing module in real time. This communication module uses an efficient and stable data transmission protocol to ensure the timeliness and accuracy of the data.

[0148] A preprocessing module, connected to the communication module, used to preprocess the gas data; specifically, the preprocessing module will perform operations such as cleaning, integrating, and formatting on the received gas data. In the cleaning stage, outliers and duplicate data will be removed, and missing values will be filled to ensure the accuracy and integrity of the data. In the integration stage, data from different sources will be merged to form a unified data format. The formatting stage will perform necessary conversions and encodings on the data to meet the requirements of subsequent analysis and processing. Through the processing of the preprocessing module, the gas data will be converted into a high-quality and standardized data set.

[0149] A feature extraction module, connected to the preprocessing module, used to extract key feature parameters based on the preprocessed gas data;

[0150] A prediction model module, connected to the feature extraction module, is configured to input the extracted key feature parameters into a pre-constructed gas energy consumption prediction model to obtain a gas energy consumption prediction value;

[0151] A strategy formulation module, connected to the prediction model module, is configured to formulate a gas energy supply strategy according to the gas energy consumption prediction value in combination with the airport operation plan; specifically, when formulating the gas energy supply strategy, the strategy formulation module will comprehensively consider various factors, such as the predicted value of gas consumption, flight takeoff and landing plans, passenger flow forecasts, and the operating requirements of airport facilities. These factors together constitute the input set for strategy formulation, providing strong support for formulating a gas energy supply strategy that meets actual needs and is energy-efficient. The strategy formulation module will adopt advanced algorithms and models, such as time series analysis, regression analysis, machine learning algorithms, etc., to comprehensively analyze the input set to obtain the optimal gas energy supply strategy. At the same time, the strategy formulation module will also dynamically adjust and optimize the strategy according to the actual situation and operating requirements of the airport to ensure that it always remains in the best state.

[0152] A monitoring and adaptive optimization module, connected to the strategy formulation module, is configured to monitor the actual consumption of gas energy in real time, compare it with the gas energy consumption prediction value, and adaptively optimize the gas energy supply strategy based on the comparison result.

[0153] It should be noted that in this embodiment, the gas data of the airport is first collected in real time by the data collection module. These data include, but are not limited to, key parameters such as gas flow, pressure, and temperature, providing a basis for subsequent preprocessing and feature extraction. The communication module is responsible for transmitting the collected data to the preprocessing module, ensuring the timeliness and accuracy of the data.

[0154] The preprocessing module cleans and organizes the received gas data, including operations such as removing outliers, filling in missing values, and data smoothing, to improve the quality and usability of the data. The preprocessed data will be transmitted to the feature extraction module.

[0155] Based on the preprocessed gas data, the feature extraction module uses feature extraction algorithms to extract key feature parameters that can reflect the gas consumption pattern and trend. These feature parameters not only contain information on historical gas consumption but may also incorporate external factors such as weather and flight plans, providing rich input features for the construction of the prediction model.

[0156] The prediction model module inputs the extracted key feature parameters into a pre-constructed gas energy consumption prediction model, and through complex calculations and analyses, obtains the prediction value of gas consumption. This prediction value not only considers the pattern of historical data but also incorporates changes in current and future external factors, with high accuracy and reliability.

[0157] The strategy formulation module formulates a reasonable gas energy supply strategy based on the predicted gas energy consumption value output by the prediction model, in combination with the operation plan and actual demand of the airport. This strategy not only includes the total amount and time arrangement of gas supply, but may also involve adjusting the supply priority for different facilities or time periods to ensure the stability and efficiency of airport operations.

[0158] The monitoring and adaptive optimization module monitors the actual consumption of gas energy in real time and conducts a comparative analysis with the predicted value. Once a large deviation is found between the actual consumption and the predicted value, this module will immediately activate the adaptive optimization mechanism to adjust and optimize the gas energy supply strategy to ensure the accuracy and effectiveness of the strategy. This real-time monitoring and adaptive optimization ability not only improves the management efficiency of gas energy, but also helps to reduce energy consumption and costs.

[0159] As another optional embodiment of the present invention, optionally, the system further includes:

[0160] An alarm module, connected to the monitoring and adaptive optimization module, for sending an alarm signal when the actual consumption of gas energy exceeds a preset threshold or the gas energy supply strategy cannot meet the airport operation requirements;

[0161] It should be noted that when the monitoring and adaptive optimization module finds that the actual gas consumption exceeds the preset safe range, or the current gas energy supply strategy cannot meet the airport operation requirements, the alarm module will be immediately activated to send a clear and definite alarm signal. These signals can be conveyed to relevant personnel in various ways, such as sound alarms, flashing lights or sending text message notifications, etc., to ensure that relevant personnel can quickly learn about the situation and take corresponding countermeasures. The alarm module not only improves the safety of airport gas energy management, but also helps to enhance the airport's ability to respond to emergencies. Through real-time monitoring and timely alarm, the airport can quickly discover and solve potential problems in gas supply, avoiding adverse effects on airport operations caused by gas shortages or interruptions. At the same time, the alarm module can also be an important part of the airport gas energy management system, working in coordination with other modules to jointly achieve the efficient management and utilization of gas energy.

[0162] A historical data storage sub-module for storing historical gas data, auxiliary data, gas consumption characteristics, gas energy consumption prediction model parameters, and the optimized supply strategy;

[0163] A user interaction interface sub-module that provides a user-friendly operation interface for providing gas energy consumption situations, gas energy consumption prediction values, supply strategies, and alarm information. Users can perform parameter settings and strategy adjustments through the user interaction interface sub-module;

[0164] It should be noted that the user interaction interface sub-module provides an intuitive and easy-to-use operation platform, enabling airport managers to conveniently view the consumption situation, predicted values, and current supply strategies of gas energy. Through this interface, managers can not only grasp the dynamic information of gas energy in real time but also set parameters and adjust strategies according to actual needs. This flexibility and convenience greatly improve the efficiency and accuracy of gas energy management. At the same time, the historical data storage sub-module is responsible for storing a large amount of historical data and optimized supply strategies, providing a solid foundation for subsequent data analysis and strategy optimization. By making full use of these data and strategies, the airport can continuously optimize its gas energy management process and achieve more efficient and sustainable development.

[0165] The adaptive optimization module includes:

[0166] A comparative analysis sub-module, used to compare the actual consumption of gas energy with the predicted value of gas energy consumption and generate a comparative analysis report;

[0167] A strategy adjustment sub-module, connected to the comparative analysis sub-module, automatically adjusts the parameters in the gas energy supply strategy based on the differences in the comparative analysis report using machine learning algorithms.

[0168] It should be noted that the adaptive optimization module includes a comparative analysis sub-module and a strategy adjustment sub-module. These two sub-modules work together to achieve continuous optimization of the gas energy supply strategy. The comparative analysis sub-module is responsible for carefully comparing the actual consumption of gas energy monitored in real time with the predicted value to identify the differences between the actual consumption and the predicted value. This comparison not only focuses on the total deviation but also deeply analyzes the consumption differences in different time periods and different facilities, providing detailed data support for subsequent optimization. The strategy adjustment sub-module, based on the report generated by the comparative analysis sub-module, uses advanced machine learning algorithms to automatically adjust the key parameters in the gas energy supply strategy; specifically, such as adjusting the time interval of gas supply, optimizing the allocation ratio, and improving the operating parameters of equipment, etc., to achieve the refinement and intelligence of gas energy supply. Through the continuous learning and optimization of machine learning algorithms, the gas energy supply strategy of the airport can gradually adapt to various complex situations, improve energy utilization efficiency and supply stability. This adaptive optimization mechanism not only reduces the workload of managers but also greatly improves the intelligent level of gas energy management. At the same time, the adaptive optimization module can also timely feedback the optimized supply strategy to the user interaction interface sub-module for managers to view and adjust, thus forming a complete closed-loop management system.

[0169] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. An intelligent metering method for airport gas energy, characterized in that: The method comprises: S1. Collecting gas data, preprocessing the gas data, and extracting key characteristic parameters based on the preprocessed gas data; Extracting key feature parameters in step S1 includes: S101, setting a data collection time interval, acquiring a gas meter reading sequence based on an image collector, and completing missing values ​​of the gas meter reading sequence; S102, smoothing the gas meter reading sequence; S103, extracting gas consumption features using a feature extraction algorithm based on the smoothed gas meter reading sequence; The expression for extracting the gas consumption characteristics in step S103 is: in, Indicates the gas consumption characteristics, represents the length of the gas meter reading sequence, Indicates The difference between the gas reading at a time point and the gas reading at the previous time point, Indicates Gas readings at time points, Indicates Gas readings at time points, represents the mean of the gas meter reading sequence, represents the standard deviation of the series of gas meter readings, represents the exponential function, represents the standard deviation of the temperature series, Indicates The temperature value at a time point, represents the mean of the temperature series; S104, screening the gas consumption characteristics to obtain key characteristic parameters; S2. Inputting the extracted key characteristic parameters into a pre-built gas energy consumption prediction model to obtain a gas energy consumption prediction value; S3. Formulate a gas energy supply strategy based on the predicted gas energy consumption value and in combination with the airport operation plan; S4. Monitor the actual consumption of gas energy in real time, compare it with the predicted value of gas energy consumption, and optimize the gas energy supply strategy according to the comparison result.

2. The intelligent metering method for airport gas energy according to claim 1, characterized in that: In step S101, the expression for completing missing values ​​of the gas meter reading sequence is: ， ， ， ， ； in, represents the first missing value, Indicates The valid value before the missing value position, Indicates Valid values ​​after missing value positions, represents the second missing value, express the number of valid values ​​in the set, Represents a sequence of gas meter readings The Readings, represents the third missing value, represents the pre-trained time series trend prediction function, Represents the set of missing value locations The The position index of the missing values, Indicates The completed readings at the missing value positions, , and Both represent the weights used in weighted average calculation.

3. The intelligent metering method for airport gas energy according to claim 1, characterized in that: Constructing the gas energy consumption prediction model in step S2 includes: S201, collecting historical gas data and auxiliary data, wherein the auxiliary data includes weather data and airport operation data; S202, preprocessing and feature extraction are performed on the historical gas data and auxiliary data in sequence to obtain historical gas consumption features; S203, constructing a loss function, based on the historical gas consumption characteristics and the loss function, using a machine learning algorithm to construct a gas energy consumption prediction model, and using a back propagation algorithm to train the gas energy consumption prediction model until a preset training accuracy or number of iterations is reached.

4. The intelligent metering method for airport gas energy according to claim 1, characterized in that: Formulating the gas energy supply strategy in step S3 includes: S301, comprehensively evaluating the supply demand of gas energy according to the predicted value of gas energy consumption, combined with the airport's flight take-off and landing plan, passenger flow forecast, and airport facility operation requirements, to obtain an evaluation result; S302, based on the evaluation results, determining the gas supply priorities for different time periods or different facilities, and formulating a gas energy distribution plan and supply schedule based on the priorities; S303, adjusting the operating parameters of the gas supply equipment according to the gas energy supply strategy and supply schedule; S304: Regularly evaluate the execution efficiency of the gas energy supply strategy, and optimize the gas energy supply strategy based on the regular evaluation results.

5. The intelligent metering method for airport gas energy according to claim 4, characterized in that: Determining the gas supply priorities of different time periods or different facilities in step S302 includes: S3021. Analyze the degree of dependence of different facilities on gas energy in different time periods and according to historical gas consumption data, flight take-off and landing density, passenger flow fluctuations and the operating characteristics of airport facilities, and obtain analysis results; S3022. Based on the analysis results, a priority analysis method is used to quantitatively score the gas supply demands of different time periods and different facilities, wherein a higher score indicates a higher priority for gas supply; S3023. Based on the quantitative scoring results, formulate a priority list for gas supply.

6. The intelligent metering method for airport gas energy according to claim 5, characterized in that: In step S3022, the priority analysis method includes: S30221. Obtaining the judgment matrix , ,in Representation scheme Relative to the plan degree of importance; S30222, normalizing the judgment matrix , ,in, , represents the normalized judgment matrix, Represents the elements in the normalized judgment matrix, which are the elements of the original judgment matrix After normalization, the result is represents the order of the judgment matrix, that is, the number of options, Representation scheme Relative to the plan degree of importance; S30223, based on the normalized judgment matrix Calculate the weight vector for each solution , , ,in Representation scheme The weight of S30224, using consistency indicators and random consistency ratio Perform consistency check, where represents the maximum eigenvalue of the judgment matrix, represents the random consistency index; like <0.1, the judgment matrix is ​​consistent; like >0.1, the judgment matrix is ​​not consistent and needs to be adjusted until the consistency requirement is met.

7. An airport gas energy intelligent metering system, characterized in that: The system comprises an airport gas energy intelligent metering method as claimed in any one of claims 1 to 6; The system further comprises: Data acquisition module, used to collect gas data; Communication module and the data acquisition module; A preprocessing module, connected to the communication module, for preprocessing the gas data; A feature extraction module, connected to the preprocessing module, for extracting key feature parameters based on the preprocessed gas data; A prediction model module, connected to the feature extraction module, for inputting the extracted key feature parameters into a pre-built gas energy consumption prediction model to obtain a gas energy consumption prediction value; A strategy formulation module, connected to the prediction model module, for formulating a gas energy supply strategy based on the predicted value of gas energy consumption and in combination with the airport operation plan; The monitoring adaptive optimization module is connected to the strategy formulation module, and is used to monitor the actual consumption of gas energy in real time, and compare it with the predicted value of gas energy consumption, and adaptively optimize the gas energy supply strategy based on the comparison result.

8. The airport gas energy intelligent metering system according to claim 7, characterized in that: The system further comprises: An alarm module, connected to the monitoring adaptive optimization module, is used to send out an alarm signal when the actual consumption of gas energy exceeds a preset threshold or the gas energy supply strategy cannot meet the airport operation requirements; Historical data storage submodule, used to store historical gas data, auxiliary data, gas consumption characteristics, gas energy consumption prediction model parameters and optimized supply strategies; A user interaction interface submodule provides a user-friendly operation interface for providing gas energy consumption, gas energy consumption forecast values, supply strategies and alarm information. Users can set parameters and adjust strategies through the user interaction interface submodule; The adaptive optimization module comprises: The comparison and analysis submodule is used to compare the actual consumption of gas energy with the predicted value of gas energy consumption and generate a comparison and analysis report; The strategy adjustment submodule is connected to the comparison and analysis submodule, and based on the differences in the comparison and analysis report, automatically adjusts the parameters in the gas energy supply strategy using a machine learning algorithm.

Images