Data acquisition system and method for gas station and diesel delivery vehicle

Abstract

The invention relates to the technical field of Internet of Things, in particular to a data acquisition system and method for a gas station and a diesel delivery vehicle, and the system comprises a data acquisition module, a path optimization module, a demand prediction module, a risk monitoring module, an unmanned vehicle management module and a fault alarm module. According to the system, comprehensive intelligent management of the gas station and the diesel delivery vehicle is realized, the efficiency is improved, and the cost is reduced. And the data acquisition module efficiently combines and cleans real-time data, so that the availability and accuracy of the data are enhanced. And the path optimization module selects the distribution path with the lowest cost and time consumption based on the comprehensive data set, so that the distribution efficiency is greatly improved, and the time cost is reduced. And the demand prediction module carries out accurate market demand prediction to prevent resource waste. The risk monitoring module monitors environmental risks and path safety in real time, and safety accidents are avoided. The unmanned vehicle management module and the fault alarm module improve the coping capacity through operation optimization and fault early warning.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a data acquisition system and method for gas stations and diesel delivery vehicles. Background Technology

[0002] The Internet of Things (IoT) is an extension and expansion of information networks. It refers to a network that connects to the Internet through information sensing devices, such as radio frequency identification (RFID) devices, infrared sensors, global positioning systems (GPS), and laser scanners, to exchange and communicate information in order to achieve intelligent identification, positioning, tracking, monitoring, and management.

[0003] The data acquisition system for gas stations and diesel delivery vehicles is a comprehensive monitoring system for petroleum distribution. It primarily collects and manages all data related to fuel sales, distribution, and consumption. The system typically includes a series of sensors and monitoring devices, such as fuel level gauges, flow meters, thermometers, and pressure gauges. These devices are installed in the fuel storage tanks of gas stations and the fuel tanks of diesel delivery vehicles to monitor the storage, transportation, and sales of fuel in real time. The main goal is to achieve transparent management of the entire petroleum distribution process, optimize storage and distribution, improve energy efficiency, ensure fuel safety, and reduce operating costs. Through this system, companies can obtain accurate inventory data, optimize inventory, avoid fuel waste, promptly detect and handle fuel leaks, and reduce environmental pollution risks.

[0004] Traditional gas station and diesel delivery systems lack effective data integration and optimization capabilities, resulting in an inability to flexibly adjust routes during delivery, optimize based on real-time traffic conditions, and achieve the lowest possible cost and time. Furthermore, for demand forecasting, previous systems relied solely on experience and historical data, lacking scientific forecasting models, thus requiring improvement in accuracy and real-time performance. In risk monitoring and autonomous vehicle management, traditional systems can only monitor in real-time, lacking early warning and predictive capabilities, making their ability to identify and prevent risks relatively weak. Regarding fault alarms, traditional systems only report faults after they occur, lacking predictive and preventative capabilities, and failing to handle and respond to fault situations promptly and effectively. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the existing technology by proposing a data acquisition system and method for gas stations and diesel delivery vehicles.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: the data acquisition system for gas stations and diesel delivery vehicles includes a data acquisition module, a route optimization module, a demand forecasting module, a risk monitoring module, an unmanned vehicle management module, and a fault alarm module;

[0007] The data acquisition module uses real-time data from gas stations and diesel delivery vehicles, employs data fusion technology to integrate and clean the data, and updates it in real time to generate a comprehensive dataset.

[0008] The path optimization module, based on a comprehensive dataset, uses genetic algorithms and recurrent neural networks to generate, evaluate, and optimize routes, thereby generating the optimal path solution.

[0009] The demand forecasting module is based on a comprehensive dataset and uses a long short-term memory network algorithm to perform market trend analysis and demand forecasting, generating a demand forecasting report.

[0010] The risk monitoring module, based on a comprehensive dataset and optimal route plan, uses sensors and a geographic information system to monitor risks and generate risk monitoring reports.

[0011] The unmanned vehicle management module uses the AdaBoost algorithm based on the optimal route plan and risk monitoring report to optimize unmanned vehicle navigation and fleet scheduling, and generates an unmanned vehicle scheduling plan.

[0012] The fault alarm module, based on a comprehensive dataset and unmanned vehicle scheduling plan, uses artificial neural network fault diagnosis technology to perform fault mode recognition and prediction, and generates fault alarm signals.

[0013] As a further aspect of the present invention, the comprehensive dataset includes traffic conditions, weather forecasts, vehicle performance, and fuel sales data; the optimal route plan is specifically a delivery route with the lowest cost and time consumption; the demand forecast report is specifically a predictive analysis of fuel demand and sales trends; the risk monitoring report is specifically a monitoring data analysis of environmental risks and route safety; the unmanned vehicle scheduling plan is specifically an operation and maintenance plan for autonomous vehicles; and the fault alarm signal includes timely alarms and maintenance suggestions.

[0014] As a further embodiment of the present invention, the data acquisition module includes a data receiving submodule, a data processing submodule, a data storage submodule, a data verification submodule, and a data forwarding submodule;

[0015] The path optimization module includes a path planning submodule, an algorithm application submodule, a cost analysis submodule, and a path testing submodule;

[0016] The demand forecasting module includes a trend analysis submodule, a model training submodule, a forecast validation submodule, and a report generation submodule.

[0017] The risk monitoring module includes a sensor monitoring submodule, a risk analysis submodule, an emergency response plan submodule, and a report summary submodule;

[0018] The unmanned vehicle management module includes a navigation optimization submodule, a fleet monitoring submodule, a maintenance scheduling submodule, and a safety management submodule;

[0019] The fault alarm module includes a fault detection submodule, a diagnostic analysis submodule, an alarm issuance submodule, and a maintenance suggestion submodule.

[0020] As a further aspect of the present invention, the data receiving submodule generates a real-time dataset based on real-time data from gas stations and diesel delivery vehicles through a data receiving server;

[0021] The data processing submodule is based on a real-time dataset and uses data fusion technology to integrate and clean the data, generating a cleaned dataset.

[0022] The data storage submodule generates a stored dataset based on the cleaned dataset using a database storage method.

[0023] The data verification submodule generates a verification dataset based on the stored dataset and using a data verification algorithm.

[0024] The data forwarding submodule generates a comprehensive dataset based on the verification dataset via an FTP / file sharing server.

[0025] As a further embodiment of the present invention, the path planning submodule generates a preliminary path plan based on a comprehensive dataset and using a genetic algorithm.

[0026] The algorithm application submodule, based on the initial path plan, uses a recurrent neural network to perform route depth evaluation and optimization, and generates an optimized path plan;

[0027] The cost analysis submodule generates a cost-benefit report based on the optimized path scheme and using cost-benefit analysis methods.

[0028] The path testing submodule generates optimized path solutions based on cost-benefit reports and using simulation testing technology.

[0029] As a further aspect of the present invention, the trend analysis submodule, based on a comprehensive dataset, employs a time series analysis method to perform market trend analysis and generate a market trend analysis report.

[0030] The model training submodule generates a prediction model based on a market trend analysis report and using a long short-term memory network algorithm.

[0031] The prediction verification submodule generates the verified prediction results based on the prediction model and using the cross-validation method.

[0032] The report generation submodule generates a demand forecast report based on the verified prediction results and using report compilation technology.

[0033] As a further aspect of the present invention, the sensor monitoring submodule, based on a comprehensive dataset and an optimal path scheme, employs sensor technology and a geographic information system to perform risk monitoring and generate risk monitoring data.

[0034] The risk analysis submodule generates a risk analysis report based on risk monitoring data and using statistical analysis and machine learning techniques.

[0035] The emergency response plan submodule generates emergency response plan documents based on the risk analysis report and using risk management technology;

[0036] The report aggregation submodule aggregates information based on the emergency response plan document and generates a risk monitoring report.

[0037] As a further aspect of the present invention, the navigation optimization submodule uses the AdaBoost algorithm based on the optimal path scheme and risk monitoring report to optimize the navigation of the unmanned vehicle and generate an optimized navigation scheme.

[0038] The fleet monitoring submodule generates a fleet monitoring report based on the optimized navigation scheme and using real-time monitoring technology.

[0039] The maintenance scheduling submodule generates a maintenance scheduling plan based on the fleet monitoring report and using a priority scheduling algorithm.

[0040] The safety management submodule generates an unmanned vehicle scheduling plan based on the maintenance scheduling plan and adopts a safety management strategy.

[0041] As a further aspect of the present invention, the fault detection submodule uses sensor monitoring technology based on a comprehensive dataset and an unmanned vehicle scheduling plan to perform fault detection and generate fault detection data.

[0042] The diagnostic analysis submodule uses artificial neural network fault diagnosis technology based on fault detection data to analyze the causes of faults and generate a fault analysis report.

[0043] The alarm issuing submodule generates a fault alarm signal based on the fault analysis report and using the GPS vehicle alarm management system.

[0044] The maintenance suggestion submodule generates maintenance suggestion schemes based on fault alarm signals and using a fault prediction and maintenance decision optimization algorithm.

[0045] A data acquisition method for gas stations and diesel delivery vehicles, wherein the electric vehicle status monitoring method is executed based on the aforementioned data acquisition system for gas stations and diesel delivery vehicles, includes the following steps:

[0046] S1: Based on real-time data from gas stations and diesel delivery vehicles, real-time data acquisition technology is used to collect, store, and process data to generate a real-time dataset;

[0047] S2: Based on the real-time dataset, data fusion and cleaning algorithms are used to standardize the format and generate a processed dataset;

[0048] S3: Based on the processed dataset, a database management system is used to archive and store the data, and secure encryption is performed to generate a stored dataset;

[0049] S4: Based on the stored dataset, a data consistency verification algorithm is used and corrected to generate a verification dataset;

[0050] S5: Based on the verification dataset, perform data synchronization using FTP / file sharing technology to generate a comprehensive dataset;

[0051] S6: Based on the comprehensive dataset, a genetic algorithm is used to perform preliminary path planning, efficiency evaluation, and generate a preliminary path scheme.

[0052] S7: Based on the preliminary path scheme, a recurrent neural network is used to perform route depth evaluation and optimization, and performance testing is conducted to generate an optimized path scheme;

[0053] S8: Based on the optimized path scheme, cost-benefit analysis is used to estimate costs and conduct simulation tests to generate the optimal path scheme;

[0054] S9: Based on the optimal path scheme and the comprehensive dataset, first use the Long Short-Term Memory Network algorithm to predict demand and obtain a demand prediction report; then, based on the demand prediction report and the comprehensive dataset, use artificial neural network fault diagnosis technology to perform fault mode recognition and prediction, and generate fault alarm signals.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0056] This invention enables comprehensive intelligent management of gas stations and diesel delivery vehicles, improving efficiency and reducing costs. The data acquisition module efficiently merges and cleans real-time data, enhancing its usability and accuracy. The route optimization module selects the delivery route with the lowest cost and time consumption based on a comprehensive dataset, significantly improving delivery efficiency and reducing time costs. The demand forecasting module provides accurate market demand predictions, helping to further optimize resource allocation and prevent waste. The risk monitoring module monitors environmental risks and route safety in real time, avoiding potential safety accidents and ensuring transportation safety. The unmanned vehicle management module and fault alarm module further improve the operational effectiveness and fault response capabilities of unmanned vehicles through operational optimization and fault warnings, preventing delays in fuel delivery due to malfunctions. Attached Figure Description

[0057] Figure 1 This is a system flowchart of the present invention;

[0058] Figure 2 This is a schematic diagram of the system framework of the present invention;

[0059] Figure 3 This is a flowchart of the data acquisition module of the present invention;

[0060] Figure 4 This is a flowchart of the path optimization module of the present invention;

[0061] Figure 5 This is a flowchart of the demand forecasting module of the present invention;

[0062] Figure 6 This is a flowchart of the risk monitoring module of the present invention;

[0063] Figure 7 This is a flowchart of the unmanned vehicle management module of the present invention;

[0064] Figure 8 This is a flowchart of the fault alarm module of the present invention;

[0065] Figure 9 This is a schematic diagram of the method steps of the present invention. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0067] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0068] Example 1

[0069] Please see Figure 1 The present invention provides a technical solution: a data acquisition system for gas stations and diesel delivery vehicles includes a data acquisition module, a route optimization module, a demand forecasting module, a risk monitoring module, an unmanned vehicle management module, and a fault alarm module;

[0070] The data acquisition module uses real-time data from gas stations and diesel delivery vehicles, employs data fusion technology to integrate and clean the data, and updates it in real time to generate a comprehensive dataset.

[0071] The path optimization module uses a comprehensive dataset and employs genetic algorithms and recurrent neural networks to generate, evaluate, and optimize routes, ultimately producing the optimal path solution.

[0072] The demand forecasting module uses a long short-term memory network algorithm based on a comprehensive dataset to perform market trend analysis and demand forecasting, and generates a demand forecasting report.

[0073] The risk monitoring module uses sensors and geographic information systems to monitor risks and generate risk monitoring reports based on a comprehensive dataset and optimal route plan.

[0074] The autonomous vehicle management module uses the AdaBoost algorithm based on the optimal route plan and risk monitoring report to optimize autonomous vehicle navigation and fleet scheduling, and generate an autonomous vehicle scheduling plan.

[0075] The fault alarm module is based on a comprehensive dataset and the unmanned vehicle scheduling plan. It uses artificial neural network fault diagnosis technology to perform fault mode recognition and prediction, and generate fault alarm signals.

[0076] The comprehensive dataset includes traffic conditions, weather forecasts, vehicle performance, and fuel sales data. The optimal route plan is the delivery route with the lowest cost and time consumption. The demand forecast report is a forecast analysis of fuel demand and sales trends. The risk monitoring report is a monitoring data analysis of environmental risks and route safety. The unmanned vehicle scheduling plan is an operation and maintenance plan for autonomous vehicles. The fault alarm signals include timely alerts and maintenance suggestions.

[0077] This system, through its data acquisition module, can acquire real-time data from gas stations and diesel delivery vehicles, and then integrate, clean, and update the data. This ensures the accuracy and completeness of the comprehensive dataset, providing reliable data support for subsequent route optimization, demand forecasting, and risk monitoring. Based on the comprehensive dataset, the route optimization module uses genetic algorithms and recurrent neural networks to generate, evaluate, and optimize routes, producing delivery routes with the lowest cost and time consumption. This reduces transportation costs and time, improves delivery efficiency, and thus enhances the company's competitiveness. The demand forecasting module uses a long short-term memory network algorithm to analyze market trends and predict fuel demand and sales trends. This helps companies rationally plan fuel supply, avoid overstocking or understocking, and improve the efficiency and reliability of the supply chain. The risk monitoring module combines sensors and a geographic information system to monitor environmental risks and route safety, generating corresponding risk monitoring reports. This helps companies promptly identify potential risk factors and take appropriate risk management measures to ensure the safe operation of vehicles. The unmanned vehicle management module uses the AdaBoost algorithm to analyze the optimal route plan and risk monitoring reports, optimizing unmanned vehicle navigation and fleet scheduling, and generating unmanned vehicle scheduling plans. This can improve the operational efficiency and safety of autonomous vehicles, reducing human error and accidents. The fault alarm module uses artificial neural network fault diagnosis technology to perform fault mode recognition and prediction on the comprehensive dataset and autonomous vehicle scheduling plan, and generate fault alarm signals. This can help enterprises to promptly identify and resolve faults, reduce downtime and maintenance costs, and improve equipment reliability and stability.

[0078] In summary, this data acquisition system, through its functions such as real-time data integration and updating, optimal route generation, market demand forecasting and analysis, risk monitoring and management, unmanned vehicle navigation optimization and fleet scheduling, and fault mode identification and early warning, can improve the operational efficiency of gas stations and diesel delivery vehicles, reduce transportation costs, enhance service quality, and reduce risks and malfunctions, thereby bringing economic benefits and competitive advantages to enterprises.

[0079] Please see Figure 2 The data acquisition module includes a data receiving submodule, a data processing submodule, a data storage submodule, a data verification submodule, and a data forwarding submodule.

[0080] The path optimization module includes a path planning submodule, an algorithm application submodule, a cost analysis submodule, and a path testing submodule.

[0081] The demand forecasting module includes a trend analysis submodule, a model training submodule, a forecast validation submodule, and a report generation submodule.

[0082] The risk monitoring module includes a sensor monitoring submodule, a risk analysis submodule, an emergency response plan submodule, and a report summary submodule;

[0083] The autonomous vehicle management module includes a navigation optimization submodule, a fleet monitoring submodule, a maintenance scheduling submodule, and a safety management submodule.

[0084] The fault alarm module includes a fault detection submodule, a diagnostic analysis submodule, an alarm issuance submodule, and a maintenance suggestion submodule.

[0085] In the data acquisition module, the data receiving submodule is responsible for receiving real-time data from gas stations and diesel delivery vehicles; the data processing submodule integrates and cleans the received data and updates it in real time; the data storage submodule stores the processed data; the data verification submodule verifies the stored data to ensure its accuracy; and the data forwarding submodule forwards the verified data to other modules for use.

[0086] In the route optimization module, the route planning submodule generates a preliminary delivery route plan based on the comprehensive dataset; the algorithm application submodule uses genetic algorithms and recurrent neural networks to evaluate and optimize the preliminary plan; the cost analysis submodule performs cost analysis on the optimal route plan; and the route testing submodule performs actual testing on the optimal route plan to ensure its feasibility.

[0087] In the demand forecasting module, the trend analysis submodule analyzes market trends; the model training submodule trains the demand forecasting model based on a comprehensive dataset and a long short-term memory network algorithm; the forecast verification submodule verifies the forecast results to ensure the accuracy of the forecast; and the report generation submodule generates a demand forecasting report based on the verified forecast results.

[0088] In the risk monitoring module, the sensor monitoring submodule monitors environmental risks and path safety through sensors; the risk analysis submodule analyzes the monitored data to identify potential risk factors; the emergency plan submodule formulates corresponding emergency plans to deal with possible risk events; and the report summary submodule summarizes the risk analysis results and emergency plans into a risk monitoring report.

[0089] In the autonomous vehicle management module, the navigation optimization submodule optimizes the navigation of autonomous vehicles based on the optimal route plan; the fleet monitoring submodule monitors the autonomous vehicle fleet in real time to ensure its normal operation; the maintenance scheduling submodule performs maintenance scheduling according to the autonomous vehicle operation and maintenance plan; and the safety management submodule is responsible for the safety management of autonomous vehicles.

[0090] In the fault alarm module, the fault detection submodule uses artificial neural network fault diagnosis technology to identify fault modes in the comprehensive dataset and the unmanned vehicle scheduling plan; the diagnostic analysis submodule analyzes the identified fault modes to determine the cause of the fault; the alarm issuance submodule issues timely alarms based on the diagnostic analysis results; and the maintenance suggestion submodule provides corresponding maintenance suggestions to solve the fault problem.

[0091] Please see Figure 3 The data receiving submodule generates a real-time dataset based on real-time data from gas stations and diesel delivery vehicles through a data receiving server.

[0092] The data processing submodule is based on real-time datasets and uses data fusion technology to integrate and clean the data, generating a cleaned dataset.

[0093] The data storage submodule generates a stored dataset based on the cleaned dataset using a database storage method.

[0094] The data validation submodule generates a validation dataset based on the stored dataset and using a data validation algorithm.

[0095] The data forwarding submodule generates a comprehensive dataset based on the verification dataset via an FTP / file sharing server.

[0096] The data receiving submodule generates a real-time dataset based on real-time data from gas stations and diesel delivery vehicles via a data receiving server. This submodule communicates with gas stations and diesel delivery vehicles to acquire their generated real-time data and transmits it to the data receiving server.

[0097] The data processing submodule, based on the real-time dataset, employs data fusion technology to integrate and clean the data, generating a cleaned dataset. In this step, the submodule processes the real-time dataset received from the data receiving server. First, it integrates data from different sources to ensure data consistency and integrity. Then, it cleans the data, removing noise and outliers to guarantee accuracy and reliability.

[0098] The data storage submodule generates a stored dataset based on the cleaned dataset using a database storage method. In this step, the submodule stores the cleaned dataset into the database. Database tables are designed according to certain rules and structures, and the cleaned data is inserted into the database tables in the appropriate format. This facilitates subsequent querying and analysis operations.

[0099] The data validation submodule generates a validation dataset based on the stored dataset and employs data validation algorithms. In this step, the submodule validates the dataset stored in the database. Several validation algorithms are used to check the correctness and completeness of the data. For example, it can check for missing or outlier values ​​and generate a corresponding validation report.

[0100] The data forwarding submodule generates a comprehensive dataset based on the verified dataset via an FTP / file sharing server. In this step, the submodule forwards the verified dataset via FTP or file sharing server, allowing other systems or users to access and use this data. Furthermore, the submodule can perform further processing and transformation on the data as needed to meet specific requirements.

[0101] In summary, this solution process includes data reception, processing, storage, verification, and forwarding. It ensures that real-time data from gas stations and diesel delivery vehicles is effectively collected, processed, and applied.

[0102] Please see Figure 4 The path planning submodule generates preliminary path schemes based on a comprehensive dataset and using a genetic algorithm.

[0103] The algorithm application submodule, based on the initial path plan, uses a recurrent neural network to perform in-depth route evaluation and optimization, and generates an optimized path plan;

[0104] The cost analysis submodule generates a cost-benefit report based on the optimized path scheme and using cost-benefit analysis methods.

[0105] The path testing submodule generates optimized path solutions based on cost-benefit reports and using simulation testing technology.

[0106] The path planning submodule uses a genetic algorithm to generate preliminary path schemes based on a comprehensive dataset. First, this submodule extracts relevant information from the comprehensive dataset, such as the starting point, destination, and road network. Then, it sets the parameters of the genetic algorithm based on this information, such as population size, crossover probability, and mutation probability. Next, the genetic algorithm iteratively searches according to certain rules to generate a set of preliminary path schemes.

[0107] The algorithm application submodule, based on the initial route plan, uses a recurrent neural network (RNN) for in-depth route evaluation and optimization to generate an optimized route plan. In this step, the submodule takes the initial route plan as input data and performs in-depth evaluation and optimization through a trained RNN model. The RNN scores each road segment based on historical data and real-time traffic conditions, and adjusts the route plan according to the scoring results. Finally, the submodule outputs the optimized route plan.

[0108] The cost analysis submodule generates a cost-benefit report based on the optimized route plan and employs cost-benefit analysis methods. In this step, the submodule performs a cost-benefit analysis on the optimized route plan. Considering factors such as distance, traffic conditions, and tolls for different road segments, it calculates the cost and benefits of each route. Then, the submodule generates a cost-benefit report based on the comparison results of the costs and benefits.

[0109] The route testing submodule generates optimized route plans based on the cost-benefit report and using simulation testing technology. In this step, the submodule uses simulation testing to verify and test the optimized route plans. Different traffic scenarios and conditions can be simulated, and the performance of the optimized route plans can be observed. Based on the test results, the submodule can further adjust and improve the optimized route plans.

[0110] In summary, this detailed solution process includes route planning, algorithm application, cost analysis, and route testing. It ensures that route planning schemes for gas stations and diesel delivery vehicles are effectively generated, evaluated, and optimized.

[0111] Please see Figure 5 The trend analysis submodule uses a time series analysis method based on a comprehensive dataset to conduct market trend analysis and generate a market trend analysis report.

[0112] The model training submodule uses a long short-term memory network algorithm based on a market trend analysis report to generate a predictive model.

[0113] The prediction validation submodule generates validated prediction results based on the prediction model and using cross-validation.

[0114] The report generation submodule generates a demand forecast report based on the verified forecast results and using report compilation techniques.

[0115] The trend analysis submodule uses a comprehensive dataset and time series analysis methods to analyze market trends and generate a market trend analysis report. First, this submodule extracts relevant market data from the comprehensive dataset, such as sales volume and demand. Then, it constructs a time series model based on this data, such as an ARIMA model or an exponential smoothing model. Next, the submodule uses the selected time series model to analyze and predict market data, and generates a market trend analysis report.

[0116] The model training submodule uses a market trend analysis report and a Long Short-Term Memory (LSTM) network algorithm to generate a predictive model. In this step, the submodule takes the market trend analysis report as input data and trains it using a pre-trained LSM network model. The LSM network learns and builds a predictive model based on historical data and relevant factors. Finally, the submodule outputs the trained predictive model.

[0117] The prediction validation submodule generates validated prediction results based on the prediction model using cross-validation. In this step, the submodule uses cross-validation to validate and evaluate the prediction model. The dataset is divided into training and test sets. The prediction model is trained using the training set and then validated using the test set. Based on the validation results, the submodule can further adjust and improve the prediction model.

[0118] The report generation submodule generates a demand forecast report based on the validated forecast results, using report compilation techniques. In this step, the submodule prepares a demand forecast report based on the validated forecast results and other relevant information. The report may include market demand trends, the reasons for changes, and influencing factors. Furthermore, the submodule can use charts, tables, and other methods to visually present the forecast results.

[0119] In summary, this detailed solution process includes trend analysis, model training, forecast validation, and report generation. It ensures that demand forecasts for gas stations and diesel delivery vehicles are effectively analyzed and reported.

[0120] Please see Figure 6 The sensor monitoring submodule, based on a comprehensive dataset and optimal route plan, uses sensor technology and geographic information system to conduct risk monitoring and generate risk monitoring data.

[0121] The risk analysis submodule generates risk analysis reports based on risk monitoring data and employs statistical analysis and machine learning techniques.

[0122] The emergency response plan submodule generates emergency response plan documents based on risk analysis reports and using risk management techniques.

[0123] The report summary submodule summarizes information based on the emergency response plan document and generates a risk monitoring report.

[0124] The sensor monitoring submodule, based on a comprehensive dataset and optimal route plan, employs sensor technology and a geographic information system (GIS) for risk monitoring, generating risk monitoring data. First, this submodule extracts relevant information from the comprehensive dataset, such as vehicle location and road conditions. Then, it determines the road segments and areas requiring monitoring based on the optimal route plan. Next, the submodule uses sensor technology to monitor the selected areas in real time and records relevant data, such as traffic flow and weather conditions. Finally, the submodule integrates this monitoring data into a risk monitoring data report.

[0125] The risk analysis submodule generates a risk analysis report based on risk monitoring data, employing statistical analysis and machine learning techniques. In this step, the submodule analyzes and processes the risk monitoring data. Statistical analysis methods, such as frequency distribution and correlation analysis, are applied to identify potential risk factors. Simultaneously, the submodule can also use machine learning algorithms, such as decision trees and random forests, to predict and assess the probability and impact of different risk events. Finally, the submodule generates a detailed risk analysis report.

[0126] The emergency response plan submodule generates emergency response plan documents based on the risk analysis report and employs risk management techniques. In this step, the submodule develops corresponding emergency response plans based on the risk assessment results in the risk analysis report. The plans may include measures to address different risk events, division of responsibilities, and resource allocation. The submodule also considers practical considerations and feasibility to ensure the effectiveness and operability of the plans. Finally, the submodule compiles the developed emergency response plans into a single document.

[0127] The report aggregation submodule, based on the emergency response plan document, summarizes information and generates a risk monitoring report. In this step, the submodule integrates and aggregates the reports generated by various submodules, organizing and summarizing relevant information such as risk monitoring data reports, risk analysis reports, and emergency response plan documents. The submodule can also add summary content and suggestions to provide a more comprehensive risk monitoring report. Finally, the submodule outputs a complete risk monitoring report.

[0128] In summary, this detailed plan includes sensor monitoring, risk analysis, emergency response planning, and report compilation. It ensures that the risks associated with gas stations and diesel delivery vehicles are effectively monitored, analyzed, and addressed.

[0129] Please see Figure 7 The navigation optimization submodule uses the AdaBoost algorithm based on the optimal path scheme and risk monitoring report to optimize the autonomous vehicle navigation and generate an optimized navigation scheme.

[0130] The fleet monitoring submodule is based on the optimized navigation scheme and uses real-time monitoring technology to generate fleet monitoring reports;

[0131] The maintenance scheduling submodule generates a maintenance scheduling plan based on fleet monitoring reports and using a priority scheduling algorithm.

[0132] The safety management submodule generates an unmanned vehicle scheduling plan based on the maintenance scheduling plan and adopts safety management strategies.

[0133] The navigation optimization submodule uses the AdaBoost algorithm to optimize autonomous vehicle navigation based on the optimal route and risk monitoring report, generating an optimized navigation plan. First, this submodule takes the optimal route as input data and combines it with the risk assessment results from the risk monitoring report. Then, according to the principles of the AdaBoost algorithm, it optimizes and adjusts the route. The AdaBoost algorithm assigns a weight to each road segment based on its risk level and adjusts the route accordingly. Finally, the submodule outputs the optimized navigation plan.

[0134] The fleet monitoring submodule generates a fleet monitoring report based on the optimized navigation scheme and real-time monitoring technology. In this step, the submodule uses real-time monitoring technology to monitor and manage the autonomous vehicle fleet. It acquires information such as the location, speed, and status of each autonomous vehicle in real time and analyzes and processes this information. Simultaneously, the submodule can also track and record the fleet's driving status according to the optimized navigation scheme. Finally, the submodule integrates the monitoring data into a single fleet monitoring report.

[0135] The maintenance scheduling submodule generates a maintenance scheduling plan based on fleet monitoring reports and using a priority scheduling algorithm. In this step, the submodule formulates a corresponding maintenance scheduling plan based on the vehicle status and maintenance requirements in the fleet monitoring reports. The priority scheduling algorithm determines the priority order of maintenance tasks based on factors such as vehicle importance and fault severity. The submodule also considers factors such as the availability of maintenance resources and time windows to ensure the feasibility and effectiveness of the maintenance scheduling plan. Finally, the submodule outputs a detailed maintenance scheduling plan.

[0136] The safety management submodule generates an autonomous vehicle (RV) scheduling plan based on the maintenance scheduling plan and employs safety management strategies. In this step, the submodule formulates a corresponding RV scheduling plan according to the maintenance tasks and schedules in the maintenance scheduling plan. Safety management strategies may include safety checks and emergency handling. The submodule also considers external factors such as traffic conditions and weather to ensure the safety and reliability of the RV scheduling plan. Finally, the submodule outputs a complete RV scheduling plan.

[0137] In summary, this detailed solution process includes navigation optimization, fleet monitoring, maintenance scheduling, and safety management. It ensures effective navigation optimization, monitoring, and management of the unmanned fleets of gas stations and diesel delivery vehicles.

[0138] Please see Figure 8 The fault detection submodule uses sensor monitoring technology based on a comprehensive dataset and unmanned vehicle scheduling plan to detect faults and generate fault detection data.

[0139] The diagnostic analysis submodule uses artificial neural network fault diagnosis technology based on fault detection data to analyze the causes of faults and generate a fault analysis report.

[0140] The alarm issuing submodule generates fault alarm signals based on the fault analysis report and using the GPS vehicle alarm management system.

[0141] The maintenance suggestion submodule generates maintenance suggestion schemes based on fault alarm signals and using a fault prediction and maintenance decision optimization algorithm.

[0142] The fault detection submodule, based on a comprehensive dataset and an autonomous vehicle scheduling plan, employs sensor monitoring technology to detect faults and generate fault detection data. First, this submodule extracts relevant information from the comprehensive dataset, such as vehicle status and sensor data. Then, it determines the vehicles and time periods requiring monitoring based on the autonomous vehicle scheduling plan. Next, the submodule uses sensor monitoring technology to monitor the selected vehicles in real time and records relevant data, such as temperature and pressure. Finally, the submodule integrates the monitoring data into a fault detection data report.

[0143] The diagnostic analysis submodule uses artificial neural network fault diagnosis technology to analyze the causes of faults based on fault detection data and generates a fault analysis report. In this step, the submodule analyzes and processes the fault detection data, applying artificial neural network algorithms such as multilayer perceptrons and convolutional neural networks to identify potential fault causes. Simultaneously, the submodule can also combine historical vehicle data and maintenance records to further analyze and confirm the fault causes. Finally, the submodule generates a detailed fault analysis report.

[0144] The alarm issuance submodule generates a fault alarm signal based on the fault analysis report and using the GPS vehicle alarm management system. In this step, the submodule triggers the corresponding alarm mechanism based on the fault assessment results in the fault analysis report. The GPS vehicle alarm management system can track the vehicle's location using GPS positioning technology and send the fault alarm signal to relevant personnel or organizations. The alarm signal can include the fault type, location information, and urgency level. Ultimately, the submodule ensures that the fault alarm signal is delivered to relevant personnel in a timely and accurate manner.

[0145] The maintenance suggestion submodule generates suggested maintenance plans based on fault alarm signals using a fault prediction maintenance decision optimization algorithm. In this step, the submodule formulates corresponding maintenance suggestion plans based on the fault type and location information in the fault alarm signal, combined with factors such as the vehicle's maintenance records and the availability of maintenance resources. The fault prediction maintenance decision optimization algorithm can consider multiple factors, such as maintenance cost, maintenance time, and risk assessment, to determine the optimal maintenance plan. Finally, the submodule outputs a detailed maintenance suggestion plan.

[0146] In summary, this detailed solution process includes fault detection, diagnostic analysis, alarm issuance, and maintenance recommendations. It ensures that the unmanned fleet of gas stations and diesel delivery vehicles can promptly detect and address faults.

[0147] Please see Figure 9 The data collection method for gas stations and diesel delivery vehicles, and the electric vehicle status monitoring method are based on the aforementioned data collection system for gas stations and diesel delivery vehicles, and include the following steps:

[0148] S1: Based on real-time data from gas stations and diesel delivery vehicles, real-time data acquisition technology is used to collect, store, and process data to generate a real-time dataset;

[0149] S2: Based on real-time datasets, data fusion and cleaning algorithms are used to standardize the format and generate processed datasets;

[0150] S3: Based on the processed dataset, a database management system is used to archive and store the data, and secure encryption is performed to generate a stored dataset;

[0151] S4: Based on the stored dataset, a data consistency verification algorithm is used and corrected to generate a verification dataset;

[0152] S5: Based on the verification dataset, data is synchronized via FTP / file sharing technology to generate a comprehensive dataset;

[0153] S6: Based on the comprehensive dataset, use a genetic algorithm to perform preliminary path planning, evaluate efficiency, and generate preliminary path schemes;

[0154] S7: Based on the initial path plan, a recurrent neural network is used to perform in-depth route evaluation and optimization, and performance testing is conducted to generate an optimized path plan;

[0155] S8: Based on the optimized route plan, cost-benefit analysis is used to estimate costs and conduct simulation tests to generate the optimal route plan;

[0156] S9: Based on the optimal path scheme and the comprehensive dataset, first use the Long Short-Term Memory Network algorithm to predict demand and obtain a demand forecast report; then, based on the demand forecast report and the comprehensive dataset, use artificial neural network fault diagnosis technology to perform fault mode recognition and prediction, and generate fault alarm signals.

[0157] This method employs real-time data acquisition technology to obtain timely vehicle data, improving operational efficiency and safety. Secondly, it uses data fusion and cleaning algorithms to process the data, eliminating redundancy and errors, and improving data quality and accuracy. Thirdly, it uses a database management system for data archiving, storage, and secure encryption to protect sensitive information and maintain trade secrets. Fourthly, it uses data consistency verification algorithms to correct data, ensuring consistency and reliability. Fifthly, it uses FTP / file sharing technology to achieve data synchronization, promoting information flow and sharing. Sixthly, it uses genetic algorithms for route planning and efficiency evaluation, optimizing transportation routes and scheduling plans. Seventhly, it uses recurrent neural networks for in-depth route evaluation and optimization, improving driving efficiency and safety. Eighthly, it uses cost-benefit analysis methods for cost estimation and simulation testing, reducing operating costs and improving economic efficiency.

[0158] In conclusion, the implementation of this method can improve the operational efficiency, safety, and economic benefits of gas stations and diesel delivery vehicles.

[0159] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A data acquisition system for gas stations and diesel delivery vehicles, characterized in that: The system includes a data acquisition module, a path optimization module, a demand forecasting module, a risk monitoring module, an unmanned vehicle management module, and a fault alarm module. The data acquisition module uses real-time data from gas stations and diesel delivery vehicles, employs data fusion technology to integrate and clean the data, and updates it in real time to generate a comprehensive dataset. The path optimization module, based on a comprehensive dataset, uses genetic algorithms and recurrent neural networks to generate, evaluate, and optimize routes, thereby generating the optimal path solution. The demand forecasting module is based on a comprehensive dataset and uses a long short-term memory network algorithm to perform market trend analysis and demand forecasting, generating a demand forecasting report. The risk monitoring module, based on a comprehensive dataset and optimal route plan, uses sensors and a geographic information system to monitor risks and generate risk monitoring reports. The unmanned vehicle management module uses the AdaBoost algorithm based on the optimal route plan and risk monitoring report to optimize unmanned vehicle navigation and fleet scheduling, and generates an unmanned vehicle scheduling plan. The fault alarm module, based on a comprehensive dataset and unmanned vehicle scheduling plan, uses artificial neural network fault diagnosis technology to perform fault mode recognition and prediction, and generates fault alarm signals.

2. The data acquisition system for gas stations and diesel delivery vehicles according to claim 1, characterized in that: The comprehensive dataset includes traffic conditions, weather forecasts, vehicle performance, and fuel sales data. The optimal route plan is specifically the delivery route with the lowest cost and time consumption. The demand forecast report is specifically a predictive analysis of fuel demand and sales trends. The risk monitoring report is specifically a monitoring data analysis of environmental risks and route safety. The unmanned vehicle scheduling plan is specifically an operation and maintenance plan for autonomous vehicles. The fault alarm signals include timely alerts and maintenance suggestions.

3. The data acquisition system for gas stations and diesel delivery vehicles according to claim 1, characterized in that: The data acquisition module includes a data receiving submodule, a data processing submodule, a data storage submodule, a data verification submodule, and a data forwarding submodule; The path optimization module includes a path planning submodule, an algorithm application submodule, a cost analysis submodule, and a path testing submodule; The demand forecasting module includes a trend analysis submodule, a model training submodule, a forecast validation submodule, and a report generation submodule. The risk monitoring module includes a sensor monitoring submodule, a risk analysis submodule, an emergency response plan submodule, and a report summary submodule; The unmanned vehicle management module includes a navigation optimization submodule, a fleet monitoring submodule, a maintenance scheduling submodule, and a safety management submodule; The fault alarm module includes a fault detection submodule, a diagnostic analysis submodule, an alarm issuance submodule, and a maintenance suggestion submodule.

4. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The data receiving submodule generates a real-time dataset based on real-time data from gas stations and diesel delivery vehicles through a data receiving server. The data processing submodule is based on a real-time dataset and uses data fusion technology to integrate and clean the data, generating a cleaned dataset. The data storage submodule generates a stored dataset based on the cleaned dataset using a database storage method. The data verification submodule generates a verification dataset based on the stored dataset and using a data verification algorithm. The data forwarding submodule generates a comprehensive dataset based on the verification dataset via an FTP / file sharing server.

5. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The path planning submodule generates preliminary path schemes based on a comprehensive dataset and using a genetic algorithm. The algorithm application submodule, based on the initial path plan, uses a recurrent neural network to perform route depth evaluation and optimization, and generates an optimized path plan; The cost analysis submodule generates a cost-benefit report based on the optimized path scheme and using cost-benefit analysis methods. The path testing submodule generates optimized path solutions based on cost-benefit reports and using simulation testing technology.

6. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The trend analysis submodule uses a time series analysis method based on a comprehensive dataset to perform market trend analysis and generate a market trend analysis report. The model training submodule generates a prediction model based on a market trend analysis report and using a long short-term memory network algorithm. The prediction verification submodule generates the verified prediction results based on the prediction model and using the cross-validation method. The report generation submodule generates a demand forecast report based on the verified prediction results and using report compilation technology.

7. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The sensor monitoring submodule, based on a comprehensive dataset and optimal route plan, uses sensor technology and a geographic information system to perform risk monitoring and generate risk monitoring data. The risk analysis submodule generates a risk analysis report based on risk monitoring data and using statistical analysis and machine learning techniques. The emergency response plan submodule generates emergency response plan documents based on the risk analysis report and using risk management technology; The report aggregation submodule aggregates information based on the emergency response plan document and generates a risk monitoring report.

8. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The navigation optimization submodule optimizes the autonomous vehicle navigation based on the optimal path scheme and risk monitoring report, using the AdaBoost algorithm to generate an optimized navigation scheme. The fleet monitoring submodule generates a fleet monitoring report based on the optimized navigation scheme and using real-time monitoring technology. The maintenance scheduling submodule generates a maintenance scheduling plan based on the fleet monitoring report and using a priority scheduling algorithm. The safety management submodule generates an unmanned vehicle scheduling plan based on the maintenance scheduling plan and adopts a safety management strategy.

9. The data acquisition system for gas stations and diesel delivery vehicles according to claim 3, characterized in that: The fault detection submodule uses sensor monitoring technology based on a comprehensive dataset and an unmanned vehicle scheduling plan to detect faults and generate fault detection data. The diagnostic analysis submodule uses artificial neural network fault diagnosis technology based on fault detection data to analyze the causes of faults and generate a fault analysis report. The alarm issuing submodule generates a fault alarm signal based on the fault analysis report and using the GPS vehicle alarm management system. The maintenance suggestion submodule generates maintenance suggestion schemes based on fault alarm signals and using a fault prediction and maintenance decision optimization algorithm.

10. A data collection method for gas stations and diesel delivery vehicles, characterized in that, The data acquisition system for gas stations and diesel delivery vehicles according to any one of claims 1-9 includes the following steps: Based on real-time data from gas stations and diesel delivery vehicles, real-time data acquisition technology is used to collect, store, and process the data to generate a real-time dataset. Based on the real-time dataset, data fusion and cleaning algorithms are used to standardize the format and generate a processed dataset. Based on the processed dataset, a database management system is used to archive and store the data, and secure encryption is performed to generate a stored dataset. Based on the stored dataset, a data consistency verification algorithm is used and corrected to generate a verification dataset; Based on the aforementioned verification dataset, data synchronization is performed using FTP / file sharing technology to generate a comprehensive dataset; Based on the comprehensive dataset, a genetic algorithm is used to perform preliminary path planning, efficiency evaluation, and generate a preliminary path scheme. Based on the preliminary path scheme, a recurrent neural network is used to perform route depth evaluation and optimization, and performance testing is conducted to generate an optimized path scheme. Based on the optimized path scheme, a cost-benefit analysis method is used to estimate the cost and conduct simulation tests to generate the optimal path scheme. Based on the optimal path scheme and the comprehensive dataset, a long short-term memory network algorithm is first used to predict demand and generate a demand forecast report. Then, based on the demand forecast report and the comprehensive dataset, artificial neural network fault diagnosis technology is used to perform fault mode recognition and prediction, and generate fault alarm signals.

Images