Intelligent fuel gas operation management system

Abstract

The invention discloses an intelligent fuel gas operation management system, belongs to the technical field of fuel gas operation management, and is used for solving the problem that a fuel gas supply station is difficult to predict actual fuel gas requirements of each region in different time periods, so that fuel gas supply is often unbalanced. Comprising an acquisition module, a database, an analysis prediction module and a supply detection module. The acquisition module is used for finely dividing gas use dates and time periods, and sensors are mounted in storage cabin pipelines of supply areas to acquire data, classify the data and send the data to a database; the analysis and prediction module carries out deep analysis according to historical data and integrates multiple factors to obtain an accurate prediction value; the supply detection module judges the gas supply capacity according to the predicted value, compares the actual value with the predicted value after gas supply to obtain a supply deviation value, and dynamically adjusts the predicted weight coefficient; the problem of traditional management is effectively solved, precise supply, efficient resource utilization and management intelligence are achieved, and the overall efficiency and reliability of gas operation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas operation management, and specifically relates to an intelligent gas operation management system. Background Art

[0002] In the field of gas operation and management, traditional management methods usually arrange gas supply based on relatively extensive experience and simple data records. With the acceleration of urbanization, gas supply areas have become diversified, covering different types such as residential areas, industrial areas, commercial and catering areas, and the gas demand in these areas varies significantly at different times; on the one hand, the overall gas consumption rhythm is different on weekdays and holidays; on the other hand, the gas consumption at different times of the day is also complex and changeable, making it difficult to accurately estimate; However, this traditional model has many problems. Due to the lack of data analysis and scientific forecasting methods, gas supply stations cannot know in advance the actual gas demand in various regions at different times, resulting in frequent imbalances in gas supply. Either there is insufficient supply, affecting the normal life and production activities of users; or there is oversupply, causing energy waste and potential safety hazards. At the same time, after discovering supply deviations, there is also a lack of effective adjustment mechanisms to promptly correct subsequent supply strategies, making it difficult to ensure the efficiency and rationality of gas supply. For this reason, we propose a smart gas operation management system. Summary of the invention

[0003] The purpose of the present invention is to provide a smart gas operation management system to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a gas operation intelligent management system, comprising: a collection module, a database, an analysis and prediction module, and a supply detection module; Collection module: responsible for monitoring the gas usage of each gas supply area by the gas supply station, dividing the gas usage date attributes and monitoring period, collecting the monitored gas volume and average monitored gas usage of each gas supply area in each monitoring period, and sending them to the database; Database: There are several storage areas inside, each of which stores the gas usage data in a gas supply area, and uses the name of the gas supply area as the search index. The gas usage data includes: the monitored gas volume and the average monitored gas volume in each monitoring period of the gas supply area; Analysis and prediction module: Analyze the historical monitoring and average consumption data of the gas supply area to obtain the monitoring and evaluation values ​​and the pre-parameter values, conduct a comprehensive analysis of the monitoring and evaluation values ​​and the pre-parameter values ​​to obtain the predicted values, and send them to the supply monitoring module; Supply monitoring module: Analyze the predicted value of each gas supply area to obtain the gas demand, analyze the gas demand and the gas storage capacity of the gas supply station to determine whether the gas supply station can supply gas, and after the gas supply of each gas supply area is completed, analyze the actual gas usage and the predicted value to obtain the supply deviation value, and adjust the weight coefficient in the process of calculating the predicted value based on the supply deviation value.

[0005] Preferably, the specific implementation process of the acquisition module is: Obtain each gas supply area where the gas supply station supplies gas. Each gas supply area has a gas storage area. The gas supply areas include: residential areas, industrial areas, and commercial and catering areas; the gas storage compartments include: gas storage tanks and underground gas storages; Install gas flow sensors in the main gas pipelines of the gas storage compartments corresponding to each gas supply area to monitor the gas usage in each gas supply area; The gas usage date is divided into date attributes, which include: working day attributes and holiday attributes; working day attributes include: Monday to Friday; holiday attributes include: Saturday, Sunday and various national statutory holiday periods; For each gas supply area, the duration of each day is divided into several monitoring periods; for each monitoring period, the total amount of gas used in the gas supply area during the monitoring period is counted and recorded as the monitoring gas volume, and the monitoring gas volume collected during each monitoring period is sent to the database; For any monitoring period within the working day attribute or holiday attribute, trace back and filter out the three most recent monitoring periods that are the same working day or holiday from the database, summarize the monitored gas volumes corresponding to these three periods, and then calculate the average value to obtain the average monitored gas usage of the detection period, and send the average monitored gas usage corresponding to the detection period to the database.

[0006] Preferably, the specific process of analyzing the monitoring and evaluation value by the analysis and prediction module is: Get the current date, match the date attribute according to the current date, get the current date attribute, and record it as the date attribute; According to the determined date attribute, the historical monitoring average fuel consumption data of each gas supply area in each monitoring period with the same date attribute is extracted from the database to form a data extraction package; For each gas supply area, the data of the most recent ten consecutive days are screened out from the data extraction package. From the data of these ten days, the historical data of the average gas consumption of the monitoring period that is the same as the current monitoring period and the next monitoring period immediately following the current monitoring period are further extracted; Calculate the difference in average fuel consumption between the next monitoring period and the current monitoring period in each day, recorded as the fuel consumption difference ZCi, where i is the number of the date, i=1, 2, ..., n; n is the total number of dates, using the formula: , get the monitoring difference value ZJ, calculate the average value of the average monitoring fuel consumption in the current monitoring period in the previous ten days, record it as the monitoring average value, and add the monitoring average value and the monitoring difference value as the monitoring evaluation value ZP.

[0007] Preferably, the specific process of analyzing and predicting the value by the analysis and prediction module is: Calculate the standard deviation of the monitoring difference ZCi in ten days to obtain the monitoring standard value, preset the monitoring standard threshold, if the monitoring standard value is greater than or equal to the inspection monitoring standard threshold, retrieve the monitoring average usage data of the same monitoring period and the next monitoring period every day in the past month from the database, and recalculate the monitoring average value; For each gas supply area, the next monitoring period for which the gas demand needs to be predicted is marked as the prediction period, and the average gas consumption data of all monitoring periods in the past ten days are retrieved from the data extraction package; The Spearman correlation coefficient method was used to analyze and calculate the absolute value of the correlation between the average fuel consumption corresponding to the forecast period in each of the previous ten days and the average fuel consumption corresponding to other monitoring periods, which was recorded as the correlation value. For each set of forecast period and other monitoring periods, the average value of the correlation between the two within ten days is calculated and recorded as the correlation mean; Sort the correlation means of the forecast period and other monitoring periods in descending order, select the monitoring period with the largest correlation mean with the forecast period, record it as the reference period, calculate the mean of the average monitoring fuel consumption within ten days of the reference period, record it as the pre-parameter value YC; The monitoring value ZP and the pre-parameter value YC are normalized and substituted into the preset formula: YCZ=ZP×a1+YC×a2 to obtain the predicted value YCZ, where a1 and a2 are preset weight coefficients; when transitioning from one monitoring period to the next monitoring period, the calculation operation of the predicted value of the predicted period corresponding to the next monitoring period will be immediately started, and the predicted value will be sent to the supply monitoring module.

[0008] Preferably, the specific process of the supply monitoring module determining whether the gas supply station can supply gas is as follows: When the predicted value YCZ corresponding to the predicted period of each gas supply area is received, the gas storage amount of the current gas supply station is obtained and recorded as the gas storage amount. At the same time, the sum of the predicted values ​​corresponding to each gas supply area in the predicted period is calculated to obtain the gas demand. The gas deviation is obtained by subtracting the gas storage amount from the gas demand. A gas deviation reference value is preset and the gas deviation is compared with the preset gas deviation reference value. If the gas deviation is less than the preset gas deviation reference value, the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value, and the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value; If the gas deviation is greater than or equal to a preset gas deviation reference value, gas is supplied to the gas storage areas corresponding to each gas supply area according to the predicted value corresponding to the predicted time period of each gas supply area.

[0009] Preferably, the specific process of the supply monitoring module analyzing and obtaining the supply deviation value is: For each gas supply area, after the gas supply is completed, during the forecast period, the gas flow sensors on the main gas pipelines of each gas supply area are used to collect gas usage data in real time; the actual gas usage of each gas supply area during the forecast period is compared with the gas volume supplied according to the forecast value before the start of the period; the deviation between the gas usage and supply of each gas supply area is calculated by subtracting the two, and recorded as the supply deviation value; If the supply deviation value is greater than zero, it means that the predicted value is too small and the gas supply is too little. A gas supply instruction with the supply deviation value is immediately generated and sent to the gas supply station. After receiving the instruction, the gas supply station immediately allocates the amount of gas corresponding to the supply deviation value for supply to the gas supply area.

[0010] Preferably, the specific process of the supply monitoring module adjusting the weight coefficient in the process of calculating the prediction value according to the supply deviation value is as follows: The absolute value of the bias value is obtained and recorded as the weight adjustment value. The weight adjustment threshold is preset. If the weight adjustment value is greater than the preset weight adjustment threshold, the weight coefficient adjustment operation of a1 and a2 in the process of calculating the predicted value is performed. The specific process of the adjustment operation is: The weight adjustment deviation value is obtained by subtracting the weight adjustment value from the preset weight adjustment threshold value, and multiple weight adjustment deviation value intervals are preset, and each interval corresponds to a weight increase coefficient value. The weight adjustment deviation value is matched with all weight adjustment deviation value intervals, and the corresponding weight increase coefficient value is output to obtain the weight value value; Extract all monitoring and evaluation values, pre-parameter values ​​and monitored gas volumes in the period within the last ten days from the database, and for each day within these ten days, calculate the correlation value between the monitoring and evaluation value and the monitored gas volume to obtain the monitoring value, and at the same time calculate the correlation value between the pre-parameter value and the monitored gas volume to obtain the pre-parameter value; Calculate the average value of the monitored property values ​​within ten days to obtain the monitored average value, and calculate the average value of the predicted property values ​​within ten days to obtain the predicted average value, and compare the monitored average value with the predicted average value; If the monitoring average value is large, the weight coefficient of a1 is increased, that is, a weight value is added on the basis of a1, and the weight coefficient of a2 is reduced accordingly; If the pre-uniformity value is large, the weight coefficient of a2 is increased, that is, a weight value is added on the basis of a2 and the weight coefficient of a1 is correspondingly reduced; If the monitored uniformity value is the same as the predicted uniformity value, adjust the weight coefficients of a1 and a2 to be the same. Compared with the prior art, the present invention has the following beneficial effects: (1) This intelligent gas operation management system divides the gas usage date into working days and holidays through the collection module, and subdivides the daily time into multiple monitoring periods, and collects the gas usage data in each monitoring period, realizing multi-dimensional classification and collection of data and sending it to the database, which is convenient for analyzing the gas usage patterns in different time scenarios. The analysis and prediction module is based on the historical monitoring and average gas usage in different areas and different periods, and considers the date attribute differences and the usage change trend of adjacent periods to calculate the predicted value. For residential areas, it can accurately grasp the gas usage fluctuations during the morning and evening cooking and winter heating periods; industrial areas can estimate the peak and trough of gas usage based on production scheduling and equipment operation cycle; commercial catering areas can accurately predict gas demand based on business hours and changes in passenger flow. This effectively avoids the problem of gas supply imbalance caused by the lack of data analysis in traditional management methods, greatly guarantees the stability of gas supply in various regions, and ensures that users' normal life and production activities are not affected.

[0011] (2) This intelligent management system for gas operation, through the supply monitoring module, on the one hand, compares the gas storage volume with the predicted demand volume in each area before gas supply, accurately determines the gas supply capacity of the gas supply station, reasonably arranges the filling or supply operation, ensures that the gas reserve is always in a reasonable range, avoids excessive reserve causing energy backlog waste or insufficient reserve causing supply crisis, and on the other hand, after the gas supply is completed, uses the gas flow sensor to quickly collect the actual usage and compare and analyze it with the predicted value to obtain the supply deviation value. When the supply deviation value exceeds the preset threshold, an adjustment instruction is immediately generated to achieve rapid replenishment or reasonable allocation of gas. At the same time, the weight coefficient of the predicted value calculation is dynamically adjusted according to the supply deviation value, so that the subsequent prediction is more in line with reality. This real-time feedback and adjustment mechanism greatly improves the utilization efficiency of gas resources and reduces energy waste and safety hazards.

[0012] (3) This intelligent gas operation management system realizes the full process automation and intelligent management of gas operation, from data collection, analysis and prediction to supply decision and subsequent adjustment, without the need for a large amount of manual intervention, greatly reducing labor costs and time costs. The cumbersome processes of manual meter reading, experience judgment and post-problem handling in traditional management are replaced by efficient system operation; accurate prediction and timely adjustment effectively avoid economic losses caused by gas supply accidents and energy waste, reduce equipment maintenance costs and potential safety risk costs, comprehensively improve the economic benefits and management efficiency of gas operating companies, and enhance the competitiveness of companies in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0015] See also Figure 1 ,The present invention provides a smart gas operation management system, including: a collection module, a database, an analysis and prediction module, and a supply detection module; The collection module is responsible for monitoring the gas usage of each gas supply area by the gas supply station, dividing the gas usage date attributes and monitoring period, collecting and sending the monitored gas volume and average monitored gas usage of each gas supply area in each monitoring period to the database; Obtain various gas supply areas for gas supply by gas supply stations. Each gas supply area has a gas storage area. The gas supply areas include: residential areas, industrial areas, commercial and catering areas, etc. The gas storage compartments include: gas storage tanks and underground gas storages; Install gas flow sensors in the main gas pipelines of the gas storage compartments corresponding to each gas supply area to monitor the gas usage in each gas supply area; The gas usage date is divided into date attributes, which include: working day attributes and holiday attributes; working day attributes include: Monday to Friday; holiday attributes include: Saturday, Sunday and various national statutory holiday periods; For each gas supply area, the duration of each day is divided into several monitoring periods; for each monitoring period, the total amount of gas used in the gas supply area during the monitoring period is counted and recorded as the monitoring gas volume, and the monitoring gas volume collected during each monitoring period is sent to the database; For any monitoring period within the working day attribute or holiday attribute, trace back and select the latest three same monitoring periods belonging to the same working day or the same holiday from the database, summarize the corresponding monitoring gas volumes of these three periods, and then calculate the average value to obtain the average monitoring fuel consumption of the detection period, and send the average monitoring fuel consumption corresponding to the detection period to the database; for example: taking the typical monitoring period of 12:00 to 14:00 on working days in a commercial restaurant area, which is closed after lunch, as an example, retrieve the monitoring gas volume data of the same period from 12:00 to 14:00 in the three most recent working days from the database; then, add and summarize the monitoring gas volumes of the same period on these three working days and divide by 3 to calculate the average value, and the final average value is the average monitoring fuel consumption exclusive to the monitoring period from 12:00 to 14:00; The database is provided with several storage areas, each of which stores the gas usage data in a gas supply area, and uses the name of the gas supply area as a search index. The gas usage data includes: the monitored gas volume and the average monitored gas volume in each monitoring period of the gas supply area; The analysis and prediction module analyzes the historical monitoring and average consumption data of the gas supply area to obtain the monitoring and evaluation values ​​and the pre-parameter values, conducts a comprehensive analysis of the monitoring and evaluation values ​​and the pre-parameter values, obtains the predicted values, and sends them to the supply monitoring module. The specific process is as follows: Get the current date, match the date attribute according to the current date, get the current date attribute, and record it as the date attribute; According to the determined date attribute, the historical monitoring average fuel consumption data of each gas supply area in each monitoring period with the same date attribute is extracted from the database to form a data extraction package; For each gas supply area, the data of the most recent ten consecutive days are screened out from the data extraction package. From the data of these ten days, the historical data of the average gas consumption of the monitoring period that is the same as the current monitoring period and the next monitoring period immediately following the current monitoring period are further extracted; Calculate the difference in average fuel consumption between the next monitoring period and the current monitoring period in each day, recorded as the fuel consumption difference ZCi, where i is the number of the date, i=1, 2, ..., n; n is the total number of dates, using the formula: , get the monitoring difference value ZJ, calculate the average value of the average monitoring fuel consumption in the current monitoring period in the previous ten days, record it as the monitoring average value, and add the monitoring average value and the monitoring difference value as the monitoring evaluation value ZP; Calculate the standard deviation of the monitoring difference ZCi in ten days to obtain the monitoring standard value, preset the monitoring standard threshold, if the monitoring standard value is greater than or equal to the inspection monitoring standard threshold, retrieve the monitoring average usage data of the same monitoring period and the next monitoring period every day in the past month from the database, and recalculate the monitoring average value; For each gas supply area, the next monitoring period for which the gas demand needs to be predicted is marked as the prediction period, and the average gas consumption data of all monitoring periods in the past ten days are retrieved from the data extraction package; The Spearman correlation coefficient method was used to analyze and calculate the absolute value of the correlation between the average fuel consumption corresponding to the forecast period in each of the previous ten days and the average fuel consumption corresponding to other monitoring periods, which was recorded as the correlation value. For each set of forecast period and other monitoring periods, the average value of the correlation between the two within ten days is calculated and recorded as the correlation mean; Sort the correlation means of the forecast period and other monitoring periods in descending order, select the monitoring period with the largest correlation mean with the forecast period, record it as the reference period, calculate the mean of the average monitoring fuel consumption within ten days of the reference period, record it as the pre-parameter value YC; After normalizing the monitoring and evaluation value ZP and the pre-parameter value YC, they are inserted into the preset formula: YCZ=ZP×a1+YC×a2 to obtain the predicted value YCZ, where a1 and a2 are preset weight coefficients; when transitioning from one monitoring period to the next monitoring period, the calculation operation of the predicted value of the predicted period corresponding to the next monitoring period will be immediately started, and the predicted value will be sent to the supply monitoring module; The supply monitoring module analyzes the predicted value to obtain the gas demand, analyzes the gas demand and the gas storage capacity of the gas supply station, determines whether the gas supply station can supply gas, and after the gas supply of each gas supply area is completed, analyzes the actual gas usage and the predicted value to obtain the supply deviation value, and adjusts the weight coefficient in the process of calculating the predicted value according to the supply deviation value; When the predicted value YCZ corresponding to the predicted period of each gas supply area is received, the gas storage amount of the current gas supply station is obtained and recorded as the gas storage amount. At the same time, the sum of the predicted values ​​corresponding to each gas supply area in the predicted period is calculated to obtain the gas demand. The gas deviation is obtained by subtracting the gas storage amount from the gas demand. A gas deviation reference value is preset and the gas deviation is compared with the preset gas deviation reference value. If the gas deviation is less than the preset gas deviation reference value, the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value, and the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value; If the gas deviation is greater than or equal to the preset gas deviation reference value, gas is supplied to the gas storage area corresponding to each gas supply area according to the prediction value corresponding to the prediction period of each gas supply area; For each gas supply area, after the gas supply is completed, during the forecast period, the gas flow sensors on the main gas pipelines of each gas supply area are used to collect gas usage data in real time; the actual gas usage of each gas supply area during the forecast period is compared with the gas volume supplied according to the forecast value before the start of the period; the deviation between the gas usage and supply of each gas supply area is calculated by subtracting the two, and recorded as the supply deviation value; If the supply deviation value is greater than zero, it means that the predicted value is too small and the gas supply is too little. A gas supply instruction with the supply deviation value is immediately generated and sent to the gas supply station. After receiving the instruction, the gas supply station immediately allocates the gas corresponding to the supply deviation value to supply the gas supply area. The absolute value of the bias value is obtained and recorded as the weight adjustment value. A weight adjustment threshold is preset. If the weight adjustment value is greater than the preset weight adjustment threshold, the weight coefficient adjustment operation of a1 and a2 in the process of calculating the predicted value is performed; The specific process of adjusting the weight coefficients of a1 and a2 in the process of calculating the predicted value is as follows: The weight adjustment deviation value is obtained by subtracting the weight adjustment value from the preset weight adjustment threshold value, and multiple weight adjustment deviation value intervals are preset, and each interval corresponds to a weight increase coefficient value. The weight adjustment deviation value is matched with all weight adjustment deviation value intervals, and the corresponding weight increase coefficient value is output to obtain the weight value value; Among them: the weight adjustment deviation value reflects the degree of deviation between the actual gas usage and the predicted gas usage. By dividing it into different intervals and corresponding to different weight increase coefficient values, the weight coefficient can be flexibly adjusted according to the size of the deviation. The larger the deviation, the greater the weight adjustment may be required to better adapt to the actual situation; Extract all monitoring and evaluation values, pre-parameter values ​​and monitored gas volumes in the period within the last ten days from the database, and for each day within these ten days, calculate the correlation value between the monitoring and evaluation value and the monitored gas volume to obtain the monitoring value, and at the same time calculate the correlation value between the pre-parameter value and the monitored gas volume to obtain the pre-parameter value; Calculate the average value of the monitored property values ​​within ten days to obtain the monitored average value, and calculate the average value of the predicted property values ​​within ten days to obtain the predicted average value, and compare the monitored average value with the predicted average value; If the monitoring average value is large, the weight coefficient of a1 is increased, that is, a weight value is added on the basis of a1, and the weight coefficient of a2 is reduced accordingly; If the pre-uniformity value is large, the weight coefficient of a2 is increased, that is, a weight value is added on the basis of a2 and the weight coefficient of a1 is correspondingly reduced; If the monitored uniformity value is the same as the predicted uniformity value, the weight coefficients of a1 and a2 are adjusted to be the same.

[0016] By dynamically adjusting the weight coefficients of a1 and a2, the calculated predicted value can be more closely aligned with the actual gas usage value, thereby improving the accuracy of the gas supply forecast. This can avoid excessive deviations between the predicted value and the actual usage, ensure that the gas supply is more intelligent and reliable, better meet the needs of different gas supply areas, and reduce the shortage or surplus of gas supply caused by inaccurate forecasts.

[0017] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A gas operation intelligent management system, comprising: The acquisition module, database, analysis and prediction module, and supply detection module are characterized by: Collection module: responsible for monitoring the gas usage of each gas supply area by the gas supply station, dividing the gas usage date attributes and monitoring period, collecting the monitored gas volume and average monitored gas usage of each gas supply area in each monitoring period, and sending them to the database; Database: There are several storage areas inside, each of which stores the gas usage data in a gas supply area, and uses the name of the gas supply area as the search index. The gas usage data includes: the monitored gas volume and the average monitored gas volume in each monitoring period of the gas supply area; Analysis and prediction module: Analyze the historical monitoring and average consumption data of the gas supply area to obtain the monitoring and evaluation values ​​and the pre-parameter values, conduct a comprehensive analysis of the monitoring and evaluation values ​​and the pre-parameter values ​​to obtain the predicted values, and send them to the supply monitoring module; Supply monitoring module: Analyze the predicted value of each gas supply area to obtain the gas demand, analyze the gas demand and the gas storage capacity of the gas supply station to determine whether the gas supply station can supply gas, and after the gas supply of each gas supply area is completed, analyze the actual gas usage and the predicted value to obtain the supply deviation value, and adjust the weight coefficient in the process of calculating the predicted value based on the supply deviation value.

2. According to claim 1, a smart gas operation management system is characterized by: The specific implementation process of the acquisition module is as follows: Obtain each gas supply area where the gas supply station supplies gas. Each gas supply area has a gas storage area. The gas supply areas include: residential areas, industrial areas, and commercial and catering areas; the gas storage compartments include: gas storage tanks and underground gas storages; Install gas flow sensors in the main gas pipelines of the gas storage compartments corresponding to each gas supply area to monitor the gas usage in each gas supply area; The gas usage date is divided into date attributes, which include: working day attributes and holiday attributes; working day attributes include: Monday to Friday; holiday attributes include: Saturday, Sunday and various national statutory holiday periods; For each gas supply area, the duration of each day is divided into several monitoring periods; for each monitoring period, the total amount of gas used in the gas supply area during the monitoring period is counted and recorded as the monitoring gas volume, and the monitoring gas volume collected during each monitoring period is sent to the database; For any monitoring period within the working day attribute or holiday attribute, trace back and filter out the three most recent monitoring periods that are the same working day or holiday from the database, summarize the monitored gas volumes corresponding to these three periods, and then calculate the average value to obtain the average monitored gas usage of the detection period, and send the average monitored gas usage corresponding to the detection period to the database.

3. According to claim 2, a smart gas operation management system is characterized by: The specific process of analyzing and monitoring the evaluation value of the analysis and prediction module is as follows: Get the current date, match the date attribute according to the current date, get the current date attribute, and record it as the date attribute; According to the determined date attribute, the historical monitoring average fuel consumption data of each gas supply area in each monitoring period with the same date attribute is extracted from the database to form a data extraction package; For each gas supply area, the data of the most recent ten consecutive days are screened out from the data extraction package. From the data of these ten days, the historical data of the average gas consumption of the monitoring period that is the same as the current monitoring period and the next monitoring period immediately following the current monitoring period are further extracted; Calculate the difference in average fuel consumption between the next monitoring period and the current monitoring period in each day, recorded as the fuel consumption difference ZCi, where i is the number of the date, i=1, 2, ..., n; n is the total number of dates, using the formula: , get the monitoring difference value ZJ, calculate the average value of the average monitoring fuel consumption in the current monitoring period in the previous ten days, record it as the monitoring average value, and add the monitoring average value and the monitoring difference value as the monitoring evaluation value ZP.

4. According to claim 3, a smart gas operation management system is characterized by: The specific process of analyzing and predicting the value of the analysis and prediction module is as follows: Calculate the standard deviation of the monitoring difference ZCi in ten days to obtain the monitoring standard value, preset the monitoring standard threshold, if the monitoring standard value is greater than or equal to the inspection monitoring standard threshold, retrieve the monitoring average usage data of the same monitoring period and the next monitoring period every day in the past month from the database, and recalculate the monitoring average value; For each gas supply area, the next monitoring period for which gas demand needs to be predicted is marked as the prediction period, and the average gas consumption data for all monitoring periods in the past ten days are retrieved from the data extraction package; The Spearman correlation coefficient method was used to analyze and calculate the absolute value of the correlation between the average fuel consumption corresponding to the forecast period in each of the previous ten days and the average fuel consumption corresponding to other monitoring periods, which was recorded as the correlation value. For each set of forecast period and other monitoring periods, the average value of the correlation between the two within ten days is calculated and recorded as the correlation mean; Sort the correlation means of the forecast period and other monitoring periods in descending order, select the monitoring period with the largest correlation mean with the forecast period, record it as the reference period, calculate the mean of the average monitoring fuel consumption within ten days of the reference period, record it as the pre-parameter value YC; The monitoring value ZP and the pre-parameter value YC are normalized and substituted into the preset formula: YCZ=ZP×a1+YC×a2 to obtain the predicted value YCZ, where a1 and a2 are preset weight coefficients; when transitioning from one monitoring period to the next monitoring period, the calculation operation of the predicted value of the predicted period corresponding to the next monitoring period will be immediately started, and the predicted value will be sent to the supply monitoring module.

5. According to claim 4, a smart gas operation management system is characterized by: The specific process of the supply monitoring module to determine whether the gas supply station can supply gas is as follows: When the predicted value YCZ corresponding to the predicted period of each gas supply area is received, the gas storage amount of the current gas supply station is obtained and recorded as the gas storage amount. At the same time, the sum of the predicted values ​​corresponding to each gas supply area in the predicted period is calculated to obtain the gas demand. The gas deviation is obtained by subtracting the gas storage amount from the gas demand. A gas deviation reference value is preset and the gas deviation is compared with the preset gas deviation reference value. If the gas deviation is less than the preset gas deviation reference value, the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value, and the gas supply station is charged until the gas deviation is greater than or equal to the preset gas deviation reference value; If the gas deviation is greater than or equal to a preset gas deviation reference value, gas is supplied to the gas storage areas corresponding to each gas supply area according to the predicted value corresponding to the predicted time period of each gas supply area.

6. According to claim 5, a smart gas operation management system is characterized by: The specific process of analyzing the supply deviation value by the supply monitoring module is as follows: For each gas supply area, after the gas supply is completed, during the forecast period, the gas flow sensors on the main gas pipelines of each gas supply area are used to collect gas usage data in real time; Compare the actual gas usage of each gas supply area during the forecast period with the gas volume supplied based on the forecast value before the start of the period; By subtracting the two, the deviation between the gas usage and supply in each gas supply area is calculated and recorded as the supply deviation value; If the supply deviation value is greater than zero, it means that the predicted value is too small and the gas supply is too little. A gas supply instruction with the supply deviation value is immediately generated and sent to the gas supply station. After receiving the instruction, the gas supply station immediately allocates the amount of gas corresponding to the supply deviation value to supply the gas supply area.

7. A gas operation intelligent management system according to claim 6, characterized in that: The specific process of the supply monitoring module adjusting the weight coefficient in the process of calculating the forecast value according to the supply deviation value is as follows: The absolute value of the bias value is obtained and recorded as the weight adjustment value. The weight adjustment threshold is preset. If the weight adjustment value is greater than the preset weight adjustment threshold, the weight coefficient adjustment operation of a1 and a2 in the process of calculating the predicted value is performed. The specific process of the adjustment operation is: The weight adjustment deviation value is obtained by subtracting the weight adjustment value from the preset weight adjustment threshold value, and multiple weight adjustment deviation value intervals are preset, and each interval corresponds to a weight increase coefficient value. The weight adjustment deviation value is matched with all weight adjustment deviation value intervals, and the corresponding weight increase coefficient value is output to obtain the weight value value; Extract all monitoring and evaluation values, pre-parameter values ​​and monitored gas volumes in the period within the last ten days from the database, and for each day within these ten days, calculate the correlation value between the monitoring and evaluation value and the monitored gas volume to obtain the monitoring value, and at the same time calculate the correlation value between the pre-parameter value and the monitored gas volume to obtain the pre-parameter value; Calculate the average value of the monitored property values ​​within ten days to obtain the monitored average value, and calculate the average value of the predicted property values ​​within ten days to obtain the predicted average value, and compare the monitored average value with the predicted average value; If the monitoring average value is large, the weight coefficient of a1 is increased, that is, a weight value is added on the basis of a1, and the weight coefficient of a2 is reduced accordingly; If the pre-uniformity value is large, the weight coefficient of a2 is increased, that is, a weight value is added on the basis of a2 and the weight coefficient of a1 is correspondingly reduced; If the monitored uniformity value is the same as the predicted uniformity value, the weight coefficients of a1 and a2 are adjusted to be the same.

Images