Oil storage and transportation intelligent management system based on Internet

Abstract

The invention discloses an oil storage and transportation intelligent management system based on the Internet, belongs to the technical field of energy storage and transportation management, and aims to solve the problem that an existing oil storage and transportation system cannot predict inventory use time. According to the invention, through integration of the business management module, the vehicle management module, the metering management module, the data analysis and prediction module and the user management and report module, intelligent management of the whole oil storage and transportation process is realized; through combination of an ARIMA model and high-order statistic calculation of the oil price fluctuation analysis unit, multiple linear regression analysis of the oil consumption increase prediction unit and grey prediction and particle swarm optimization algorithms of the remaining oil prediction unit, the remaining oil usage time and the change trend can be accurately predicted, the inventory management level is improved, and the economic benefit is improved. The problem that an existing oil product storage and transportation system cannot predict market demands and inventory use time is effectively solved, the oil product storage and transportation management and control capability of enterprises is enhanced, the operation efficiency is improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage and transportation management, and in particular to an intelligent management system for oil storage and transportation based on the Internet. Background Art

[0002] In the field of oil storage and transportation, effective management of oil tank areas is crucial to ensuring the stability and continuity of oil supply. As a storage and transit hub for oil, the oil tank area needs to ensure normal oil supply under various circumstances to meet the oil demand in industrial production, transportation and other fields. Therefore, the inventory management of oil in the oil tank area has become a key link. It is necessary not only to ensure the normal oil use in daily operations, but also to reserve a certain amount of redundancy to cope with the surge in oil demand in unexpected situations.

[0003] However, the oil replenishment method of the oil tank farm is restricted by many factors, among which pipeline layout is a key factor. Although pipeline transportation has the advantages of high efficiency and low cost in oil transportation, not all oil tank farms have a complete pipeline transportation network to fill oil shortages in a timely manner; in many areas, especially some remote areas or areas with relatively backward infrastructure construction, oil tank farms may not be able to obtain oil replenishment directly through pipelines. In this case, oil tank farms often need to rely on oil tank trains for oil transportation, or dispatch oil from other more distant oil tank farms, which has poor timeliness.

[0004] However, the existing oil storage and transportation management system only has the functions of business management, vehicle entry and exit management, and metering management. It is unable to predict market demand based on oil prices, macroeconomic indicators, and seasonal factors, and is unable to predict usage time based on inventory. This has led to an incompatibility between supply and demand and increased transportation costs. Summary of the invention

[0005] The purpose of the present invention is to provide an Internet-based intelligent management system for oil storage and transportation to solve the problem that the existing oil storage and transportation system cannot predict market demand and inventory usage time.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: An Internet-based intelligent management system for oil storage and transportation, comprising: a business management module, a vehicle management module, a metering management module, a data analysis and prediction module, and a user management and reporting module;

[0007] The business management module is used to coordinate the purchase, sales and inventory of oil products;

[0008] The vehicle management module is used to coordinate vehicles during the storage and transportation of oil products;

[0009] The metering management module is used to provide accurate metering for oil storage and transportation;

[0010] The data analysis and prediction module includes an oil price fluctuation analysis unit, an oil consumption growth prediction unit and a remaining oil prediction unit. The oil price fluctuation analysis unit is used to collect international oil price market data and use the ARIMA model in the time series analysis algorithm to model and predict the oil price data. The oil consumption growth prediction unit uses multiple linear regression to predict the oil consumption growth trend based on local oil consumption historical data and macroeconomic indicators. The remaining oil prediction unit uses gray prediction and particle swarm optimization algorithms to predict the use time of the remaining oil and the future remaining oil change trend based on the real-time metering data of the oil tank, the oil product in and out of the warehouse record, the oil consumption growth prediction and the supply and demand relationship prediction under the influence of oil price fluctuations.

[0011] The user management and reporting module is used to manage users and generate various reports.

[0012] Furthermore, the business management module specifically includes a purchase order management unit, a sales order management unit and an inventory management unit; the purchase order management unit is used to create, edit, review and query purchase orders; the sales order management unit is used to process oil sales order related business, including entering customer information, sales quantity, sales price and delivery date data, and performing full life cycle management of sales orders, including order generation, delivery arrangement and payment confirmation, and real-time query of order progress and status; the inventory management unit dynamically updates the oil inventory information in the tank area according to the real-time metering data of the oil tank and the entry and exit records.

[0013] Furthermore, the vehicle management module includes a vehicle entry management unit and a vehicle exit management unit; the vehicle entry management unit is connected to the vehicle identification system, identifies the license plate number of the entering vehicle through a high-definition camera, automatically obtains the basic information of the vehicle and matches it with the system database for registration, and records the entry time and the initial load of the vehicle; the vehicle exit management unit is used to identify the license plate again when the vehicle exits, and to check whether the vehicle load information and exit procedures are complete, calculate the actual cargo capacity of the vehicle based on the loading record and the vehicle entry information, and involve fee settlement, perform fee accounting in accordance with the standard and complete the settlement process, and record the exit time, actual cargo capacity and fee payment information.

[0014] Furthermore, the metering management module includes a self-service metering unit and a quantitative loading metering unit; the self-service metering unit automatically collects the level, temperature and pressure data of the oil product through the sensors in the oil tank area, and processes the data to calculate the volume and mass of the oil product in the oil tank according to the physical properties of the oil product; the quantitative loading metering unit sets the target value according to the loading quantity required by the order during the loading process. , control the opening and flow of the loading valve; during the loading process, the quantitative loading metering unit uses a PID control algorithm to adjust the valve opening and monitors the loading flow in real time through a flow meter With cumulative total , the formula is , To control the output signal of the valve opening, is the deviation between the set value and the actual loading quantity, are the proportional coefficient, integral coefficient and differential coefficient respectively.

[0015] Furthermore, the steps of modeling and predicting the oil price data by the oil price fluctuation analysis unit are as follows:

[0016] S11. Collect international oil price market data to form oil price time series , perform a stationarity test on the collected oil price time series data. If the data is stable, proceed to the next step; if the data is not stable, perform a differential operation to make it stable;

[0017] S12. Calculate the higher-order statistics of oil price fluctuations, including kurtosis K and skewness S. Suppose the oil price fluctuation data sequence is , the sample mean is , the sample standard deviation is The calculation formula of kurtosis K is , the calculation formula of skewness S is , through the calculated kurtosis and skewness values, the asymmetric and peak-thick tail characteristics of oil price fluctuations are analyzed. If the kurtosis value is greater than 3, it indicates that the oil price fluctuation has obvious peak-thick tail characteristics, and extreme price fluctuations are more frequent; the positive and negative skewness values ​​reflect the asymmetry of oil price fluctuations on both sides of the mean. Positive skewness indicates that oil price increases may fluctuate more frequently or with greater amplitude, and negative skewness indicates that oil price decreases are more prominent.

[0018] S13. Calculate the autocorrelation function and partial autocorrelation function graph of oil price time series data, and determine the order of ARIMA based on the autocorrelation function and partial autocorrelation function graph , where p is the autoregressive order, determined by the partial autocorrelation function graph, d is the difference order, which has been determined in the stationarity test step. If the data is differentiated to make it stationary, d is the number of differences, and q is the moving average order, which is determined by the autocorrelation function graph; at the same time, according to the results of kurtosis and skewness analysis, the value range of d is optimized and adjusted. If the kurtosis value is large, the value range of d is appropriately increased, or the introduction of nonlinear models and ARIMA models for mixed modeling is considered; if the skewness value is not 0, consider using asymmetric data transformation methods in the data preprocessing stage;

[0019] S14. Use parameter estimation methods such as the least squares method to determine the parameters in the ARIMA model based on historical oil price data and The value of , , , ; For ARIMA model , substitute the current and historical oil price data into the established ARIMA model to predict the future oil price trend. When evaluating the prediction effect of the model, the mean square error is used in combination with the kurtosis and skewness values ​​of the predicted oil price data series and the degree of closeness to the actual data to optimize the model.

[0020] Furthermore, the step of predicting the oil consumption growth trend by the oil consumption growth prediction unit is as follows:

[0021] S21. Collect historical data on oil consumption from the company's internal systems and external related institutions, covering oil consumption information for different time periods, different oil types and different application fields. At the same time, collect data on related factors that may affect oil consumption, including macroeconomic indicators, seasonal factors and industry development trend data. Macroeconomic indicators include GDP growth rate and industrial added value. Seasonal factors are divided by month. Industry development trend data include transportation industry development index and industrial oil industry capacity expansion. Clean the collected data, remove erroneous data and missing data, and arrange the data in chronological order.

[0022] S22. Based on business knowledge and data analysis, factors that are significantly correlated with oil consumption are selected as feature variables, and the data set is divided into a training set and a test set. Usually, 70-80% of the data is used as the training set, and 20-30% of the data is used as the test set.

[0023] S23. Construct a multiple linear regression model: Assume that the oil consumption is The selected feature variables are , the model is ,in is the regression coefficient, is a random error term, and the regression coefficient is estimated by the least squares method using the training set data. The value of is to minimize the residual sum of squares ,in is the actual amount of oil used. is the oil consumption predicted by the regression model. After obtaining the regression model, the accuracy of the model is evaluated using the test set data.

[0024] Furthermore, the remaining fuel amount prediction unit predicts the remaining fuel amount usage time and the future remaining fuel amount change trend in the following steps:

[0025] S31. Obtain real-time measurement data of oil tanks and oil in and out records from the oil storage and transportation system, collect forecast data on oil consumption growth and forecast data on supply and demand relationship under the influence of oil price fluctuations, organize and pre-process the collected data to ensure the accuracy and consistency of the data;

[0026] S32. Construct a grey prediction model, assuming that the original remaining oil time series is , , perform first-order accumulation to generate a new sequence ,in , establish the grey prediction model The differential equation , a and u are the model parameters to be estimated, and the parameters a and u are solved by the least squares method. The formula is ,in , ;

[0027] S33. Assume that the size of the particle group is N, and the position vector of each particle represents the combination of parameters a and u of the grey prediction model, that is, , , the particle's velocity vector is , the particle updates its velocity and position according to the following formula:

[0028]

[0029]

[0030]

[0031]

[0032] in, is the inertia weight, and They are cognitive coefficient and social coefficient, and for A random number uniformly distributed in the interval, and are the values ​​of parameters a and u in the individual optimal position of the i-th particle, and is the value of the parameters a and u in the optimal position of the group. By continuously iteratively updating the speed and position of the particles, we can find the parameter combination that minimizes the prediction error of the grey prediction model.

[0033] S34. According to the grey prediction model combined with particle swarm optimization, the usage time of the remaining oil and the future trend of the remaining oil are predicted, and the prediction results are analyzed.

[0034] Furthermore, the user management and reporting module includes a user management unit and a report generation unit. The user management unit is used to perform authority management on system users and divides user roles into administrators, operators and data analysts. Administrators can perform account management, system configuration, data backup and recovery; operators are mainly responsible for daily business operations, such as order processing, metering operations, vehicle dispatch execution, etc.; data analysts focus on the construction and optimization of data analysis and prediction models, and can access and analyze system data, but have no authority to modify business data; the report generation unit generates various reports according to user needs, including inventory reports, business reports, metering reports and data analysis reports.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The Internet-based intelligent management system for oil storage and transportation provided by the present invention realizes intelligent management of the entire process of oil storage and transportation by integrating business management, vehicle management, metering management, data analysis and prediction, and user management and reporting modules. Combined with the ARIMA model and high-order statistical calculation of the oil price fluctuation analysis unit, the multivariate linear regression analysis of the oil consumption growth prediction unit, and the grey prediction and particle swarm optimization algorithm of the remaining oil prediction unit, it can accurately predict the remaining oil usage time and change trend, improve the inventory management level, and effectively solve the problem that the existing oil storage and transportation system cannot predict market demand and inventory usage time, enhance the company's control ability over oil storage and transportation, improve operational efficiency, and reduce costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the modules of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] In order to solve the technical problem that the existing oil storage and transportation management system cannot predict market demand based on oil prices, macroeconomic indicators and seasonal factors, and thus cannot predict the usage time based on inventory, such as Figure 1 As shown, the following preferred technical solutions are provided:

[0040] The Internet-based intelligent management system for oil storage and transportation includes: business management module, vehicle management module, measurement management module, data analysis and prediction module, and user management and reporting module.

[0041] The business management module is used to coordinate oil product procurement, sales and inventory operations.

[0042] The business management module specifically includes a purchase order management unit, a sales order management unit and an inventory management unit;

[0043] The purchase order management unit is used to create, edit, review and query purchase orders; the sales order management unit is used to handle oil sales order-related business, including entering customer information, sales quantity, sales price and delivery date data, and managing the entire life cycle of sales orders, including order generation, delivery scheduling and payment confirmation, and real-time query of order progress and status; the inventory management unit dynamically updates the oil inventory information in the tank area based on the real-time measurement data of the oil tank and the in-and-out records.

[0044] The vehicle management module is used to coordinate vehicles during the storage and transportation of oil products.

[0045] The vehicle management module includes a vehicle entry management unit and a vehicle exit management unit; the vehicle entry management unit is connected to the vehicle identification system, identifies the license plate number of the entering vehicle through a high-definition camera, automatically obtains the basic information of the vehicle and matches it with the system database for registration, and records the entry time and the initial load of the vehicle; the vehicle exit management unit is used to identify the license plate again when the vehicle exits the site, and to check whether the vehicle load information and exit procedures are complete, calculate the actual cargo capacity of the vehicle based on the loading record and the vehicle entry information, and involve fee settlement, perform fee accounting in accordance with the standard and complete the settlement process, and record the exit time, actual cargo capacity and fee payment information.

[0046] The metering management module is used to provide accurate metering for oil storage and transportation.

[0047] The metering management module includes a self-service metering unit and a quantitative loading metering unit. The self-service metering unit automatically collects the level, temperature and pressure data of the oil through the sensors in the oil tank area, processes the data, and calculates the volume and quality of the oil in the tank based on the physical properties of the oil. The quantitative loading metering unit sets the target value according to the loading quantity required by the order during the loading process. , control the opening and flow of the loading valve.

[0048] During the loading process, the quantitative loading metering unit uses the PID control algorithm to adjust the valve opening and monitors the loading flow in real time through the flow meter. With cumulative total , the formula is , To control the output signal of the valve opening, is the deviation between the set value and the actual loading quantity, are the proportional coefficient, integral coefficient and differential coefficient respectively.

[0049] The data analysis and prediction module includes an oil price fluctuation analysis unit, an oil consumption growth prediction unit and a remaining oil prediction unit. The oil price fluctuation analysis unit is used to collect international oil price market data and adopts the ARIMA model in the time series analysis algorithm to model and predict the oil price data. The oil consumption growth prediction unit uses multiple linear regression to predict the oil consumption growth trend based on the local oil consumption historical data and macroeconomic indicators. The remaining oil prediction unit uses grey prediction and particle swarm optimization algorithms to predict the usage time of the remaining oil and the future trend of the remaining oil based on the real-time metering data of the oil tank, the oil product in and out of the warehouse records, the oil consumption growth forecast and the supply and demand relationship forecast under the influence of oil price fluctuations.

[0050] The steps for the oil price fluctuation analysis unit to model and predict oil price data are as follows:

[0051] S11. Collect international oil price market data to form oil price time series , perform a stationarity test on the collected oil price time series data. If the data is stable, proceed to the next step; if the data is not stable, perform a differential operation to make it stable;

[0052] S12. Calculate the higher-order statistics of oil price fluctuations, including kurtosis K and skewness S. Suppose the oil price fluctuation data sequence is , the sample mean is , the sample standard deviation is The calculation formula of kurtosis K is , the calculation formula of skewness S is , through the calculated kurtosis and skewness values, the asymmetric and peak-thick tail characteristics of oil price fluctuations are analyzed. If the kurtosis value is greater than 3, it indicates that the oil price fluctuation has obvious peak-thick tail characteristics, and extreme price fluctuations are more frequent; the positive and negative skewness values ​​reflect the asymmetry of oil price fluctuations on both sides of the mean. Positive skewness indicates that oil price increases may fluctuate more frequently or with greater amplitude, and negative skewness indicates that oil price decreases are more prominent.

[0053] S13. Calculate the autocorrelation function and partial autocorrelation function graph of oil price time series data, and determine the order of ARIMA based on the autocorrelation function and partial autocorrelation function graph , where p is the autoregressive order, determined by the partial autocorrelation function graph, d is the difference order, which has been determined in the stationarity test step. If the data is differentiated to make it stationary, d is the number of differences, and q is the moving average order, which is determined by the autocorrelation function graph; at the same time, according to the results of kurtosis and skewness analysis, the value range of d is optimized and adjusted. If the kurtosis value is large, the value range of d is appropriately increased, or the introduction of nonlinear models and ARIMA models for mixed modeling is considered; if the skewness value is not 0, consider using asymmetric data transformation methods in the data preprocessing stage;

[0054] S14. Use parameter estimation methods such as the least squares method to determine the parameters in the ARIMA model based on historical oil price data and The value of , , , ; For ARIMA model , substitute the current and historical oil price data into the established ARIMA model to predict the future oil price trend. When evaluating the prediction effect of the model, the mean square error is used in combination with the kurtosis and skewness values ​​of the predicted oil price data series and the degree of closeness to the actual data to optimize the model.

[0055] The steps for the oil consumption growth prediction unit to predict the oil consumption growth trend are as follows:

[0056] S21. Collect historical data on oil consumption from the company's internal systems and external related institutions, covering oil consumption information for different time periods, different oil types and different application fields. At the same time, collect data on related factors that may affect oil consumption, including macroeconomic indicators, seasonal factors and industry development trend data. Macroeconomic indicators include GDP growth rate and industrial added value. Seasonal factors are divided by month. Industry development trend data include transportation industry development index and industrial oil industry capacity expansion. Clean the collected data, remove erroneous data and missing data, and arrange the data in chronological order.

[0057] S22. Based on business knowledge and data analysis, factors that are significantly correlated with oil consumption are selected as feature variables, and the data set is divided into a training set and a test set. Usually, 70-80% of the data is used as the training set, and 20-30% of the data is used as the test set.

[0058] S23. Construct a multiple linear regression model: Assume that the oil consumption is The selected feature variables are , the model is ,in is the regression coefficient, is a random error term, and the regression coefficient is estimated by the least squares method using the training set data. The value of is to minimize the residual sum of squares ,in is the actual amount of oil used. is the oil consumption predicted by the regression model. After obtaining the regression model, the accuracy of the model is evaluated using the test set data.

[0059] The steps of the remaining fuel prediction unit for predicting the remaining fuel usage time and the future remaining fuel change trend are as follows:

[0060] S31. Obtain real-time measurement data of oil tanks and oil in and out records from the oil storage and transportation system, collect forecast data on oil consumption growth and forecast data on supply and demand relationship under the influence of oil price fluctuations, organize and pre-process the collected data to ensure the accuracy and consistency of the data;

[0061] S32. Construct a grey prediction model, assuming that the original remaining oil time series is , , perform first-order accumulation to generate a new sequence ,in , establish the grey prediction model The differential equation , a and u are the model parameters to be estimated, and the parameters a and u are solved by the least squares method. The formula is ,in , ;

[0062] S33. Assume that the size of the particle group is N, and the position vector of each particle represents the combination of parameters a and u of the grey prediction model, that is, , , the particle's velocity vector is , the particle updates its velocity and position according to the following formula:

[0063]

[0064]

[0065]

[0066]

[0067] in, is the inertia weight, and They are cognitive coefficient and social coefficient, and for A random number uniformly distributed in the interval, and are the values ​​of parameters a and u in the individual optimal position of the i-th particle, and is the value of the parameters a and u in the optimal position of the group. By continuously iteratively updating the speed and position of the particles, we can find the parameter combination that minimizes the prediction error of the grey prediction model.

[0068] S34. According to the grey prediction model combined with particle swarm optimization, the usage time of the remaining oil and the future trend of the remaining oil are predicted. The prediction results are analyzed to provide a decision-making basis for the inventory management, procurement planning and transportation scheduling of oil products, and to determine whether the oil inventory needs to be replenished and when to replenish it.

[0069] The user management and reporting module is used to manage users and generate various reports.

[0070] The user management and reporting module includes a user management unit and a report generation unit. The user management unit is used to manage the permissions of system users and divides user roles into administrators, operators, and data analysts. Administrators can perform account management, system configuration, data backup and recovery; operators are mainly responsible for daily business operations, such as order processing, metering operations, vehicle scheduling execution, etc.; data analysts focus on the construction and optimization of data analysis and prediction models, and can access and analyze system data, but do not have the authority to modify business data.

[0071] The report generation unit generates various reports according to user needs, including inventory reports, business reports, measurement reports and data analysis reports.

[0072] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0073] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Internet-based intelligent management system for oil storage and transportation, characterized by: include: Business management module, vehicle management module, metering management module, data analysis and prediction module, and user management and reporting module; The business management module is used to coordinate the purchase, sales and inventory of oil products; The vehicle management module is used to coordinate vehicles during the storage and transportation of oil products; The metering management module is used to provide accurate metering for oil storage and transportation; The data analysis and prediction module includes an oil price fluctuation analysis unit, an oil consumption growth prediction unit and a remaining oil prediction unit. The oil price fluctuation analysis unit is used to collect international oil price market data and use the ARIMA model in the time series analysis algorithm to model and predict the oil price data. The oil consumption growth prediction unit uses multiple linear regression to predict the oil consumption growth trend based on local oil consumption historical data and macroeconomic indicators. The remaining oil prediction unit uses gray prediction and particle swarm optimization algorithms to predict the use time of the remaining oil and the future remaining oil change trend based on the real-time metering data of the oil tank, the oil product in and out of the warehouse record, the oil consumption growth prediction and the supply and demand relationship prediction under the influence of oil price fluctuations. The user management and reporting module is used to manage users and generate various reports.

2. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The business management module specifically includes a purchase order management unit, a sales order management unit and an inventory management unit; The purchase order management unit is used to create, edit, review and query purchase orders; The sales order management unit is used to handle oil sales order-related business, including entering customer information, sales quantity, sales price and delivery date data, and managing the entire life cycle of sales orders, including order generation, delivery arrangement and payment confirmation, and real-time query of order progress and status; the inventory management unit dynamically updates the oil inventory information in the tank area based on the real-time measurement data of the oil tank and the in-and-out records.

3. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The vehicle management module includes a vehicle entry management unit and a vehicle exit management unit; the vehicle entry management unit is connected to the vehicle identification system, identifies the license plate number of the vehicle entering the site through a high-definition camera, automatically obtains the basic information of the vehicle and matches it with the system database, and records the entry time and the initial load of the vehicle; The vehicle exit management unit is used to identify the license plate again and verify whether the vehicle load information and exit procedures are complete when the vehicle leaves the site. It calculates the actual cargo capacity of the vehicle based on the loading record and vehicle entry information. For fee settlement, it calculates the fees according to the standards and completes the settlement process, and records the exit time, actual cargo capacity and fee payment information.

4. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The metering management module includes a self-service metering unit and a quantitative loading metering unit; the self-service metering unit automatically collects the level, temperature and pressure data of the oil through the sensors in the oil tank area, processes the data, and calculates the volume and quality of the oil in the tank according to the physical properties of the oil; the quantitative loading metering unit sets the target value according to the loading quantity required by the order during the loading process. , control the opening and flow of the loading valve.

5. The Internet-based intelligent management system for oil storage and transportation as claimed in claim 4, characterized in that: The quantitative loading metering unit uses a PID control algorithm to adjust the valve opening during the loading process, and monitors the loading flow in real time through a flow meter. With cumulative total , the formula is , To control the output signal of the valve opening, is the deviation between the set value and the actual loading quantity, are the proportional coefficient, integral coefficient and differential coefficient respectively.

6. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The steps of the oil price fluctuation analysis unit for modeling and predicting oil price data are as follows: S11. Collect international oil price market data to form oil price time series , perform a stationarity test on the collected oil price time series data. If the data is stable, proceed to the next step; if the data is not stable, perform a differential operation to make it stable; S12. Calculate the higher-order statistics of oil price fluctuations, including kurtosis K and skewness S. Suppose the oil price fluctuation data sequence is , the sample mean is , the sample standard deviation is The calculation formula of kurtosis K is , the calculation formula of skewness S is , through the calculated kurtosis and skewness values, the asymmetric and peak-thick tail characteristics of oil price fluctuations are analyzed. If the kurtosis value is greater than 3, it indicates that the oil price fluctuation has obvious peak-thick tail characteristics, and extreme price fluctuations are more frequent; the positive and negative skewness values ​​reflect the asymmetry of oil price fluctuations on both sides of the mean. Positive skewness indicates that oil price increases may fluctuate more frequently or with greater amplitude, and negative skewness indicates that oil price decreases are more prominent. S13. Calculate the autocorrelation function and partial autocorrelation function graph of oil price time series data, and determine the order of ARIMA based on the autocorrelation function and partial autocorrelation function graph , where p is the autoregressive order, determined by the partial autocorrelation function graph, d is the difference order, which has been determined in the stationarity test step. If the data is differentiated to make it stationary, d is the number of differences, and q is the moving average order, which is determined by the autocorrelation function graph; at the same time, according to the results of kurtosis and skewness analysis, the value range of d is optimized and adjusted. If the kurtosis value is large, the value range of d is appropriately increased, or the introduction of nonlinear models and ARIMA models for mixed modeling is considered; if the skewness value is not 0, consider using asymmetric data transformation methods in the data preprocessing stage; S14. Use parameter estimation methods such as the least squares method to determine the parameters in the ARIMA model based on historical oil price data and The value of , , , ; For ARIMA model , substitute the current and historical oil price data into the established ARIMA model to predict the future oil price trend. When evaluating the prediction effect of the model, the mean square error is used in combination with the kurtosis and skewness values ​​of the predicted oil price data series and the closeness to the actual data to optimize the model.

7. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The steps of predicting the oil consumption growth trend by the oil consumption growth prediction unit are as follows: S21. Collect historical data on oil consumption from the company's internal systems and external related institutions, covering oil consumption information for different time periods, different oil types and different application fields. At the same time, collect data on related factors that may affect oil consumption, including macroeconomic indicators, seasonal factors and industry development trend data. Macroeconomic indicators include GDP growth rate and industrial added value. Seasonal factors are divided by month. Industry development trend data include transportation industry development index and industrial oil industry capacity expansion. Clean the collected data, remove erroneous data and missing data, and arrange the data in chronological order. S22. Based on business knowledge and data analysis, factors that are significantly correlated with oil consumption are selected as feature variables, and the data set is divided into a training set and a test set. Usually, 70-80% of the data is used as the training set, and 20-30% of the data is used as the test set. S23. Construct a multiple linear regression model: Assume that the oil consumption is The selected feature variables are , the model is ,in is the regression coefficient, is a random error term, and the regression coefficient is estimated by the least squares method using the training set data. The value of is to minimize the residual sum of squares ,in is the actual amount of oil used. is the oil consumption predicted by the regression model. After obtaining the regression model, the accuracy of the model is evaluated using the test set data.

8. The Internet-based intelligent management system for oil storage and transportation according to claim 7, characterized in that: The steps of predicting the remaining fuel usage time and the future remaining fuel change trend of the remaining fuel prediction unit are as follows: S31. Obtain real-time measurement data of oil tanks and oil in and out records from the oil storage and transportation system, collect forecast data on oil consumption growth and forecast data on supply and demand relationship under the influence of oil price fluctuations, organize and pre-process the collected data to ensure the accuracy and consistency of the data; S32. Construct a grey prediction model, assuming that the original remaining oil time series is , , perform first-order accumulation to generate a new sequence ,in , establish the grey prediction model The differential equation , a and u are the model parameters to be estimated, and the parameters a and u are solved by the least squares method. The formula is ,in , ; S33. Assume that the size of the particle group is N, and the position vector of each particle represents the combination of parameters a and u of the grey prediction model, that is, , , the particle's velocity vector is , the particle updates its velocity and position according to the following formula: ， ， ， ， in, is the inertia weight, and They are cognitive coefficient and social coefficient, and for A random number uniformly distributed in the interval, and are the values ​​of parameters a and u in the individual optimal position of the i-th particle, and is the value of the parameters a and u in the optimal position of the group. By continuously iteratively updating the speed and position of the particles, we can find the parameter combination that minimizes the prediction error of the grey prediction model. S34. According to the grey prediction model combined with particle swarm optimization, the usage time of the remaining oil and the future trend of the remaining oil are predicted, and the prediction results are analyzed.

9. The Internet-based intelligent management system for oil storage and transportation according to claim 1, characterized in that: The user management and report module includes a user management unit and a report generation unit. The user management unit is used to manage the rights of system users and divides user roles into administrators, operators and data analysts. Administrators can perform account management, system configuration, data backup and recovery; operators are mainly responsible for daily business operations, such as order processing, metering operations, vehicle dispatch execution, etc. Data analysts focus on building and optimizing data analysis and predictive models. They can access and analyze system data but do not have the authority to modify business data.

10. The Internet-based intelligent management system for oil storage and transportation according to claim 9, characterized in that: The report generation unit generates various reports according to user needs, including inventory reports, business reports, measurement reports and data analysis reports.

Images