A new type of digital intelligence empowerment method, platform and equipment facilities for green passenger stations

Abstract

The present invention provides a new type of digital intelligence empowerment method, platform and equipment facilities for green passenger stations, the method comprising: receiving the full life cycle operation data of the passenger station; based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment in different areas and categories, extracting the corresponding energy consumption independent variables from the full life cycle operation data for the equipment in different areas and categories in the station, and obtaining the optimal energy consumption solution of the corresponding area and category of equipment based on the extracted energy consumption independent variables, so as to obtain the optimal power consumption of each area; based on the optimal power consumption, using the pre-trained time series prediction model to obtain the predicted power consumption of each area; by comparing the predicted power consumption of each area with the regional standard power consumption range, generating differentiated energy use strategies to realize the digital intelligence empowerment of green passenger stations. The present invention can formulate personalized energy-saving control strategies to achieve efficient utilization of energy and resources in passenger stations.

Description

Technical Field

[0001] The present invention relates to the field of energy management and control technology for new passenger stations, and in particular to a new digital intelligence enabling method, platform, and equipment and facilities for green passenger stations. Background Art

[0002] At present, the upgrade focus of railway passenger stations has shifted from business function integration and data integration to typical scenario intelligence, deep data mining and analysis, and the application of information technology. Although existing passenger stations have initially realized functions such as integrated planning and mobile operation command in passenger operations and production command, and subsystems such as electronic tickets, passenger services, passenger management, equipment management, and emergency command can realize data interaction, intelligent analysis and processing, and comprehensive evaluation through system interfaces, the current passenger stations basically only improve passenger business and passenger service needs, and have not unified the management and control of energy consumption data and energy efficiency data according to business scenarios. In short, there are still deficiencies in the current systematic research on green energy consumption and digitalization in passenger stations, and its limitations are mainly reflected in the following aspects:

[0003] 1) Lack of systematic and unified management of energy consumption data and insufficient digital and intelligent collaboration capabilities

[0004] In terms of energy consumption data monitoring and management, passenger stations involve a wide variety of equipment and facilities (such as travel service equipment, ticketing equipment, and electromechanical equipment, etc.), and the energy consumption of each passenger station, such as energy type, load, and usage, varies due to factors such as the geographical location of the passenger station, the size of the passenger station, passenger flow, equipment type, and operating environment, which greatly increases the difficulty of managing passenger station energy consumption data. At present, passenger stations basically adopt the traditional energy management method of single-point collection, decentralized management, and direct statistics, and disperse energy consumption data in subsystems such as power supply, building equipment monitoring system, and fire automation system, lacking data interaction and centralized management between systems.

[0005] Due to the lack of unified management of passenger station equipment, it is difficult to achieve coordinated scheduling of station resources and overall command of operation plans in emergency situations such as large-scale delays, large passenger flows, natural disasters, etc., resulting in weak circulation links within passenger stations, between passenger stations, and between passenger stations and external organizations, which is not conducive to the coordinated supply of resources.

[0006] 2) Weak energy efficiency analysis and low resource utilization efficiency

[0007] Passenger stations usually only monitor the energy consumption data of equipment that consumes a large proportion of daily operating energy (such as large waiting screens, platform screens, air conditioners, escalators, and lighting, etc.), and conduct periodic statistics and intuitive displays of the monitoring data. This management method lacks both comprehensive control of the energy consumption of equipment and facilities and effective analysis of energy consumption data. There is no statistical management by item, area, or time, which makes it unclear what the weak links in energy utilization are and what nodes need to be optimized, resulting in simple and rough energy-saving strategies and the lack of refined and dynamic management of energy resources.

[0008] Therefore, there is an urgent need for a new type of green passenger station digital empowerment method, which can achieve efficient utilization of passenger station energy and resources by unified management of passenger station equipment energy consumption and enhanced targeted analysis of passenger station equipment energy consumption and energy efficiency to formulate personalized energy-saving control strategies. Summary of the invention

[0009] In view of this, the embodiments of the present invention provide a new type of green passenger station digital empowerment method, platform and equipment facilities, which can comprehensively monitor, analyze and manage station energy-related information from multiple dimensions and angles, and improve the dynamic energy management of passenger stations and the targeted energy analysis, and realize digital applications of green passenger stations such as flexible customization of personalized energy use strategies and dynamic allocation of resources.

[0010] One aspect of the present invention provides a novel green passenger station digital intelligence empowerment method, the method comprising the following steps:

[0011] Receive the passenger station's full life cycle operation data, which includes: basic station information, environmental comfort information including seasonal climate, station equipment energy consumption information, multi-dimensional information on station equipment operation status, train reception and dispatching / passenger transport operation information, and station passenger information including passenger flow information, among which environmental comfort information, station equipment energy consumption information, multi-dimensional information on station equipment operation status, train reception and dispatching / passenger transport operation information, and station passenger information are associated with station areas and time periods;

[0012] Based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment in different areas and categories, the corresponding energy consumption independent variables are extracted from the full life cycle operation data for the equipment in different areas and categories in the station, and the optimal energy consumption solution of the equipment in the corresponding area and category is obtained based on the extracted energy consumption independent variables, so as to obtain the optimal power consumption of each area; wherein the dependent variable is the energy consumption information of the station equipment;

[0013] Based on the optimal power consumption, the pre-trained time series prediction model is used to obtain the predicted power consumption of each area;

[0014] By comparing the predicted power consumption of each area with the regional standard power consumption range, differentiated energy utilization strategies are generated to achieve digital empowerment of green passenger stations.

[0015] In some embodiments of the present invention, the basic information of the station includes some or all of the following information: the overall building structure, building materials, building orientation, geographical location and regional climate of the station;

[0016] Environmental comfort information includes part or all of the following information: weather information, seasonal climate, and station environment information including one or more of temperature, humidity, CO2 concentration, noise, and brightness;

[0017] The station energy consumption and energy efficiency information includes part or all of the following information: equipment historical energy consumption time series data, equipment energy consumption per unit time, energy consumption ratio between equipment and energy utilization rate;

[0018] The multi-dimensional information of the station equipment operation status includes some or all of the following information: basic equipment information, equipment service life, equipment operation status and equipment maintenance information;

[0019] Train reception and dispatch / passenger operation information includes part or all of the following information: passenger operation plan, train arrival and dispatch plan, train dispatch plan, water supply and sewage suction operation plan, personnel scheduling plan and equipment inspection plan;

[0020] Station passenger information includes some or all of the following information: passenger flow information, passenger identity information, passenger location information, and passenger inquiry and response information.

[0021] In some embodiments of the present invention, the pre-trained time series prediction model is obtained by:

[0022] Using the equipment's historical energy consumption time series data, passenger flow information during the corresponding period, and seasonal climate as training data sets, the pre-trained time series prediction model is obtained by iteratively training the time series prediction model;

[0023] After generating a differentiated energy usage strategy by comparing the predicted power consumption of each region with the regional standard power consumption range, the method further includes:

[0024] According to the set update frequency of the time series prediction model, the optimization model parameters are obtained from the cloud computing platform based on the comparison results of the real-time power consumption generated when the differentiated energy use strategy is executed and the regional standard power consumption range;

[0025] Based on the optimization model parameters, the corresponding parameters in the pre-trained time series prediction model are updated, so that the pre-trained time series prediction model is updated to the optimized time series prediction model, so that the predicted power consumption of each area can be obtained by using the optimized time series prediction model later;

[0026] Among them, the time series prediction model includes the autoregressive difference moving average model.

[0027] In some embodiments of the present invention, obtaining the optimal energy consumption solution of the corresponding area and category of equipment based on the extracted energy consumption independent variable, thereby obtaining the optimal power consumption of each area, includes:

[0028] Based on the multi-task learning algorithm and the extracted energy consumption independent variables corresponding to different areas and categories of equipment in the station, a multi-independent variable model of each category of equipment in different areas is constructed;

[0029] The multi-independent variable model is split to obtain multiple single-independent variable models of each category of equipment in different regions;

[0030] The non-dominated sorting genetic algorithm is used to obtain the optimal solution of each single independent variable model;

[0031] Based on the optimal solutions for the energy consumption of equipment in each area and category and the set impact weights corresponding to each optimal solution, the optimal power consumption of equipment in each area and category is obtained, thereby obtaining the optimal power consumption of each area.

[0032] In some embodiments of the present invention, the differentiated energy use strategy is:

[0033] If the predicted power consumption of the area exceeds the corresponding regional standard power consumption range, the power corresponding to the maximum value of the regional standard power consumption range is used as the allocated power of the area, and the power exceeding the maximum value of the regional standard power consumption range is used as the allocated power of the energy storage device; if the predicted power consumption of the area is within the corresponding regional standard power consumption range, the predicted power consumption is used as the allocated power of the area; if the predicted power consumption of the area is lower than the corresponding regional standard power consumption range, the power corresponding to the minimum value of the regional standard power consumption range is used as the allocated power of the area, and the power of the difference between the predicted power consumption and the minimum value of the regional standard power consumption range is obtained from the energy storage device;

[0034] The method further comprises: the area of ​​the passenger station is divided into a ticket sales area, a security inspection area, a ticket inspection area, a waiting area, a platform area, an exit area and a machine room area;

[0035] For the ticket sales area, security inspection area, ticket checking area and exit area, when the predicted power consumption of the area exceeds the standard power consumption range of the corresponding area, a dynamic resource allocation model for the corresponding area is generated based on the train reception and dispatching / passenger transport operation information, multi-dimensional information on the operation status of station equipment and passenger flow information, and a differentiated allocation plan for the area is generated based on the result of the dynamic resource allocation model to adjust the operation cycle of the resources and equipment in the area and the personnel scheduling plan; wherein the resources and equipment include at least gates, security inspection equipment and ticket sales equipment; the differentiated allocation plan is: if the result of the dynamic resource allocation model is a reduction in resources, then remove the idle resources and equipment in the area and / or reduce the staff scheduling; if the result of the dynamic resource allocation model is that the resources remain unchanged, then adjust the staff scheduling and / or the working hours of the resources and equipment in the area.

[0036] In some embodiments of the present invention, if the predicted power consumption of the area is lower than the corresponding regional standard power consumption range, the power corresponding to the minimum value of the regional standard power consumption range is used as the allocated power of the area, and the power of the difference between the predicted power consumption and the minimum value of the regional standard power consumption range is obtained from the energy storage device, which also includes:

[0037] Based on the energy-reducing devices in each area and the minimum power consumption of the energy-reducing devices, the power consumption of the corresponding area is reduced, so that the reduced power consumption is not less than the difference between the predicted power consumption and the minimum value of the regional standard power consumption range;

[0038] Among them, the energy reduction equipment in the security inspection area is the security inspection equipment, the energy reduction equipment in the platform area is the platform screen, the energy reduction equipment in the waiting area includes air conditioning, broadcasting and display screens, and the energy reduction equipment in the exit area is elevators and escalators.

[0039] In some embodiments of the present invention, generating a differentiated energy usage strategy by comparing the predicted power consumption of each region with the regional standard power consumption range also includes:

[0040] Based on the predicted power consumption of each area and the energy allocation ratio of equipment with different uses in the area, the predicted power consumption of equipment in each area and use is obtained;

[0041] By comparing the predicted power consumption of each region and purpose with the standard power consumption range of the corresponding region and purpose, a differentiated energy use strategy for energy sub-items is generated; among which, equipment for different purposes includes lighting and socket power equipment, air conditioning and heating power equipment, power power equipment and special power equipment; the regional standard power consumption range is obtained based on the standard power consumption range of each purpose in the region;

[0042] The differentiated energy use strategy for energy sub-items is as follows: if the predicted power consumption of the area and purpose exceeds the standard power consumption range of the corresponding area and purpose, the power corresponding to the maximum value of the corresponding standard power consumption range will be used as the allocated power of the area and purpose, and the power consumption exceeding the maximum value of the standard power consumption range of the corresponding area and purpose will be used as the allocated power of the energy storage device; if the predicted power consumption of the area and purpose is within the standard power consumption range of the corresponding area and purpose, the predicted power consumption will be used as the allocated power of the area and purpose; if the predicted power consumption of the area and purpose is lower than the standard power consumption range of the corresponding area and purpose, the power corresponding to the minimum value of the standard power consumption range of the corresponding area and purpose will be used as the allocated power of the area and purpose, and the power of the difference between the predicted power consumption of the area and purpose and the minimum value of the standard power consumption range of the corresponding area and purpose will be obtained from the energy storage device;

[0043] The method also includes: evaluating the execution effect of differentiated energy use strategies or differentiated energy use strategies of energy sub-items based on set evaluation indicators, and constructing a digital model of a green passenger station based on three-dimensional modeling technology to display the digital empowerment status of the passenger station in real time; wherein the evaluation indicators include some or all of the following indicators: environmental comfort index category, equipment and facility index category, data center index category, personnel-resource and equipment ratio index category, and digital intelligent means index category.

[0044] Another aspect of the present invention provides a new green passenger station digital intelligence empowerment platform, the new green passenger station digital intelligence empowerment platform includes a station-level platform for implementing the method described in any of the above embodiments;

[0045] The station-level platform sends the station equipment energy consumption information and multi-dimensional information of the station equipment operating status to its own bureau-level platform through the railway comprehensive information network and network transmission protocol, so that the bureau-level platform can send the periodic station equipment energy consumption information obtained by analyzing the station equipment energy consumption information and multi-dimensional information of the station equipment operating status to the national railway group-level platform.

[0046] In some embodiments of the present invention, the station-level platform includes:

[0047] The perception layer is used to obtain passenger station operation data throughout its life cycle from sensors;

[0048] The transport layer is used to transmit the real-time difference of passenger station operation data throughout its life cycle to the platform layer through the railway integrated information network;

[0049] The platform layer is used to generate differentiated energy use strategies or differentiated energy use strategies for energy sub-items;

[0050] The application layer is used to evaluate the execution effect of the differentiated energy use strategy or the differentiated energy use strategy of energy sub-items based on the set evaluation indicators;

[0051] The display layer is used to build a digital model of a green passenger station based on the full life cycle operation data of the passenger station and combined with 3D modeling technology to demonstrate the digital empowerment of the passenger station;

[0052] The platform layer includes:

[0053] The data aggregation module is used to receive the passenger station's full life cycle operation data and transmit it to the artificial intelligence module;

[0054] An artificial intelligence module, for obtaining the optimal power consumption of each region based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment of different regions and categories, obtaining the predicted power consumption of each region based on the optimal power consumption, and generating a differentiated energy consumption strategy by comparing the predicted power consumption of each region with the regional standard power consumption range, or generating a differentiated energy consumption strategy for energy sub-items by comparing the predicted power consumption of each region and purpose with the standard power consumption range of the corresponding region and purpose;

[0055] The control and coordination module is used to implement differentiated energy use strategies or differentiated energy use strategies for energy sub-items in combination with passenger operation plans, train arrival and departure plans, and personnel scheduling plans;

[0056] The carbon asset management module is used to obtain the comparison result by comparing the real-time power consumption when the differentiated energy use strategy is implemented with the standard power consumption range of the corresponding region, or by comparing the real-time power consumption when the differentiated energy use strategy of the energy sub-item is implemented with the standard power consumption range of the corresponding region and purpose;

[0057] The intelligent Internet of Things module is used to realize data transmission between the platform layer and the transport layer.

[0058] Another aspect of the present invention provides a new type of green guest station digital intelligence empowerment equipment and facility, including a processor, a memory and a computer program / instructions stored in the memory, wherein the processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the equipment and facility implements the steps of the method described in any of the above embodiments.

[0059] The present invention proposes a new type of green passenger station digital empowerment method, platform and equipment facilities, which are based on multi-dimensional energy consumption-related influencing factors, and realize efficient utilization of passenger station energy and resources by unified management of passenger station energy and formulating energy-saving control strategies with the characteristics of this station, thereby achieving the goals of carbon saving, consumption reduction, quality improvement and efficiency enhancement.

[0060] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0061] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0063] Figure 1 This is a schematic diagram of the three-level architecture of the new green passenger station digital intelligence empowerment platform in one embodiment of the present invention.

[0064] Figure 2 This is a flow chart of a new type of green passenger station digital intelligence empowerment method in one embodiment of the present invention.

[0065] Figure 3 This is a flow chart of a new type of green passenger station digital intelligence empowerment method in another embodiment of the present invention.

[0066] Figure 4 This is a schematic diagram of the data flow of the new green passenger station digital intelligence empowerment platform in one embodiment of the present invention.

[0067] Figure 5 This is a schematic diagram of the architecture of the station-level new green passenger station digital intelligence empowerment platform in one embodiment of the present invention.

[0068] Figure 6 This is a schematic diagram of platform-layer data transmission of the station-level new green passenger station digital intelligence empowerment platform in one embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0070] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0071] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0072] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0073] To simplify the expression, unless otherwise specified, the "empowerment platform" appearing below refers to the "Railway Green Passenger Station Digital Empowerment Platform".

[0074] At present, passenger stations are managed and controlled based on the three-level structure of "passenger station-railway bureau-national railway group". The existing energy of the station is not used reasonably and effectively, and no energy-saving control strategy with the characteristics of the station has been formulated. Therefore, it is impossible to essentially cater to the strategic layout of green development, and it is even more impossible to achieve carbon conservation, consumption reduction, quality improvement and efficiency enhancement, and thus it is impossible to fully realize the green transformation of railway passenger stations.

[0075] Based on this, the present invention designs and builds a railway green passenger station digital intelligence empowerment platform and supporting equipment and facilities to support the four major business directions of precise passenger service, coordinated production command, efficient and safe emergency response, and green energy conservation and environmental protection. In addition, with the empowerment platform as the core, a new green railway passenger station digital intelligence empowerment method is proposed, and a complete green and low-carbon digital intelligence information chain from green collection, green transmission, green data center, digital intelligence application to green ecology is constructed. Through the introduction and iterative upgrading of digital intelligence technology, its empowerment role for green passenger stations is fully utilized, and it is applied to precise passenger service, coordinated production command, efficient and safe emergency response, and green energy conservation and environmental protection. Multiple business scenarios to achieve the purpose of comprehensive green transformation of railway passenger stations. The empowerment platform realizes the "digital intelligence" application of green passenger stations such as all-round intelligent control of station energy consumption and energy efficiency information, flexible customization of personalized energy use, dynamic allocation of resources, and digital operation through comprehensive monitoring, flexible allocation and efficient management of passenger station energy, classification statistics of multi-dimensional energy consumption indicators of passenger stations, and monitoring and mining analysis of multi-modal energy consumption data.

[0076] In some embodiments of the present invention, Figure 1As shown in the figure, the green empowerment platform can be divided into a station-level platform (also known as the passenger station underlying service platform), a railway bureau-level platform (also known as the railway bureau center platform) and a national railway group-level platform (also known as the national railway group decision-making platform), which are deployed in stations, railway bureaus and national railway groups respectively. The station-level platform collects relevant information of equipment such as broadcasting, guidance, inquiry machines, air conditioners, escalators and fans through network communication units, intelligent gateways and intelligent sensors, and uses Wi-Fi, ultra-wideband wireless communication (Ultra Wide-Band, UWB) technology, Bluetooth and infrared and other transmission methods to complete the collection of passenger station full life cycle operation data. The passenger station full life cycle operation data collected by the station is uploaded to the railway bureau-level platform through edge computing and interface servers through firewalls according to the needs of the railway bureau-level platform using network transmission protocols such as message queues, TCP / IP, XML or WebService. The railway bureau-level platform statistically analyzes the data transmitted by the station-level platform, and transmits the statistical analysis results to the national railway group-level platform through the network transmission protocol and the railway comprehensive information network.

[0077] More specifically, the station-level platform generates differentiated energy use strategies and energy sub-item differentiated energy use strategies that meet the characteristics of the passenger station itself based on the passenger station's full life cycle operation data collected by the station's front-end digital collection terminal. Based on the transmission protocol, the station-level platform transmits passenger station full life cycle operation data, including equipment energy consumption information, station passenger information, and multi-dimensional information on the station equipment operating status, to the railway bureau-level platform to which it belongs through the railway comprehensive information network. The railway bureau-level platform statistically analyzes the energy consumption status of station equipment according to the time, space, and business dimensions, and coordinates the energy consumption of the station-level platforms under its jurisdiction based on the periodic station equipment energy consumption information obtained.

[0078] The railway bureau-level platform obtains the configuration of resources (people, equipment and trains) of each station under its jurisdiction (i.e., dynamic resource allocation plan), equipment energy consumption information (including comprehensive energy consumption, annual energy saving and regional GDP energy consumption and other energy consumption indicator data, energy consumption trend and energy consumption data comparison, etc.) and multi-dimensional information on the operation status of station equipment (including ventilation and air conditioning, fans, water pumps and elevators and escalators and other electromechanical equipment, ticket inspection gates, ticket machines and other passenger ticket equipment, as well as guidance screens, microphones, cameras, inquiry machines and other travel service equipment), and conducts multi-dimensional statistical analysis of "time + space + business". At the same time, it ensures unified regulation of energy and resources of each station under its jurisdiction in the event of sudden emergency situations such as large-scale delays or natural disasters, so that the railway bureau-level platform can have a macro control over the overall energy consumption of multiple passenger stations under its jurisdiction, and comprehensively display the energy consumption indicator data of each station based on the passenger transportation and operation processes of each station under its jurisdiction.

[0079] The railway bureau-level platform processes the data uploaded by the station-level platform to obtain periodic station equipment energy consumption information (periodic energy consumption status and resource usage of each railway bureau), and transmits it to the national railway group-level platform through the railway comprehensive information network in accordance with the established transmission method, so that the national railway group-level platform can adjust its energy ratio based on railway bureaus (or stations). In addition, the national railway group-level platform can also selectively display the functional points or operating processes that can reflect the railway bureaus under its jurisdiction according to the decision-making and command needs of the national railway group level, so as to intuitively display the energy consumption and overall planning results of railway bureaus and stations.

[0080] A station-level platform can only be governed by one railway bureau-level platform. A railway bureau-level platform can govern station-level platforms deployed in stations under the jurisdiction of the railway bureau where the railway bureau-level platform is deployed. The national railway group-level platform governs all railway bureau-level platforms.

[0081] The green passenger station digital empowerment method proposed in the present invention needs to rely on the digital empowerment platform deployed at the station. The following will take the station-level platform as an example to describe the specific process of implementing the railway passenger station digital empowerment method based on the station-level platform. Figure 2 FIG. 1 is a flow chart of a novel green passenger station digital intelligence empowerment method in one embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110-S140:

[0082] Step S110: receiving passenger station full life cycle operation data.

[0083] More specifically, before predicting power consumption and formulating personalized energy strategies (i.e., differentiated energy strategies), the station-level empowerment platform needs to obtain the full life cycle operation data of the passenger station. The full life cycle operation data of the passenger station includes: basic information of the station, environmental comfort information including seasonal climate, energy consumption information of station equipment, multi-dimensional information on the operation status of station equipment, train reception and dispatching / passenger transport operation information, and station passenger information including passenger flow information.

[0084] In some embodiments of the present invention, the basic information of the station includes one or more of the overall building structure of the station (such as the station building structure, peripheral structure and building height), passenger station scale, building materials, building orientation, geographical location and regional climate, which can be collected by scanning remote sensing equipment (such as mobile 3D scanning vehicles, AI intelligent robots, drones and GIS equipment, etc.).

[0085] Environmental comfort information includes weather conditions (including part or all of the information such as temperature, humidity, ultraviolet intensity, wind direction, cloudy or sunny, temperature, visibility, air pressure, wind force and wind speed), seasonal climate (for example, the seasonal climate is summer) and environmental information inside the station (including part or all of the information such as temperature, humidity, CO2 concentration, noise and brightness inside the station), which can be collected through devices such as network information collectors and environmental Internet of Things data recorders.

[0086] The multi-dimensional information of the station equipment operation status may include basic equipment information and / or equipment operation and maintenance information; wherein, the equipment operation and maintenance information includes one or more of the equipment operation cycle (referring to the equipment service cycle), equipment operation status (whether the equipment is operating normally and the fault status), and equipment maintenance information (such as the frequency of equipment failures, equipment failure repair cycle, equipment maintenance costs, and equipment failure alarm information); the basic equipment information includes one or more of the equipment name, equipment quantity, equipment model, equipment installation location in the passenger station, manufacturer and maintenance manufacturer. The multi-dimensional information of the station equipment operation status can be collected through inspection equipment (such as intelligent inspection robots and handheld data collection terminals, i.e., handheld PDAs, etc.).

[0087] The train reception and dispatching / passenger operation information includes one or more of the following information: passenger operation plan, train arrival and departure plan, train dispatching plan, personnel shift plan, water supply and sewage suction operation plan, equipment inspection plan and emergency events (such as large-scale delays), which can be obtained through the data interface between the ticket system and the dispatching system.

[0088] Station passenger information includes one or more of passenger flow information, passenger identity information (such as passenger facial information and passenger ID information), passenger location information, and passenger inquiry and response information. Among them, passenger flow information includes real-time passenger flow and passenger station crowd density.

[0089] The station energy consumption and energy efficiency information includes one or more of the following information: time series data of historical energy consumption of equipment, energy consumption of equipment per unit time, energy consumption ratio between equipment and energy utilization rate, which can be collected through equipment such as smart meters and digital intelligence collectors.

[0090] Step S120 includes: Step S121, based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment in different areas and categories, extracting the corresponding energy consumption independent variables from the full life cycle operation data for the equipment in different areas and categories in the station. Step S122, based on the extracted energy consumption independent variables, obtaining the optimal solution of the energy consumption of the equipment in the corresponding area and category, thereby obtaining the optimal power consumption of each area.

[0091] The energy consumption independent variable-dependent variable relationship pair mentioned in the present invention refers to a set of causal relationships corresponding to equipment in different regions and categories.

[0092] More specifically, in the artificial intelligence module of the empowerment platform, the energy consumption of the passenger station (i.e., the energy consumption and energy efficiency information of the station) can be used as the dependent variable, and other acquired passenger station full life cycle operation data (i.e., station basic information, environmental comfort information, multi-dimensional information on the operation status of station equipment, train reception and dispatching / passenger transport operation information, and station passenger information including passenger flow information) can be used as influencing factors (i.e., independent variables) to analyze the energy consumption of equipment in the passenger station. In addition, since the environmental comfort information, station equipment energy consumption information, multi-dimensional information on the operation status of station equipment, train reception and dispatching / passenger transport operation information, and station passenger information are associated with the station area and time period, the influencing factors of equipment energy consumption in different areas and time periods may be different, that is, the corresponding energy consumption independent variables extracted from the full life cycle operation data for equipment in different areas and categories in the station may be different.

[0093] According to the different functional characteristics of the passenger station, the passenger station area can be divided into ticket sales area, security inspection area, ticket checking area, waiting area, platform area, exit area and machine room area.

[0094] As an example, the energy consumption independent variables corresponding to the same equipment in the same area at different time periods may be different. For example, for the energy consumption of platform screens, the independent variables during the daytime period with more trains include passenger flow information and train arrival and departure plans and other train / passenger transport operation information, while the independent variables during the night period with fewer trains include multi-dimensional information on the operating status of station equipment.

[0095] Different devices in the same area may have different energy consumption independent variables in the same period. For example, for the energy consumption in the waiting area during the day, the independent variables of air conditioning energy consumption include environmental comfort and receiving and dispatching / passenger transportation information, and the independent variables of broadcasting energy consumption include receiving and dispatching / passenger transportation information and passenger flow information.

[0096] The energy consumption independent variables corresponding to the same equipment in different areas during the same period may be different. For example, for air conditioning energy consumption during the daytime, the independent variables of air conditioning energy consumption in the waiting area include environmental comfort and receiving and dispatching / passenger transportation operation information, and the independent variables of air conditioning energy consumption in the ticketing area include passenger flow information.

[0097] For example, during the daytime, the main equipment in the ticketing area includes ticketing equipment, so the factors affecting the ticketing area include passenger flow information and vehicle pickup and dispatch / passenger transport operation information;

[0098] The main equipment in the security inspection area includes security inspection equipment (such as security scanners, etc.) and gate equipment (including entry gates and ticket inspection gates). The influencing factors of the security inspection area include passenger flow information, train reception and dispatching / passenger transportation operation information, and multi-dimensional information on equipment operation status;

[0099] The main equipment in the ticket inspection area includes the integrated ticket inspection machine and ticket inspection screen. The factors affecting the ticket inspection area include passenger flow information, train reception and dispatching / passenger transportation operation information, and multi-dimensional information on equipment operation status;

[0100] The equipment in the waiting area includes a large screen for waiting at the station, a self-service inquiry machine, storage equipment, an intelligent inquiry desk and a pickup, etc. The factors affecting the waiting area include environmental comfort information, train / passenger transport operation information and passenger flow information, and multi-dimensional information on the equipment operation status;

[0101] The equipment in the platform area includes platform screens, channel screens, elevators, escalators, and water supply and sewage suction devices, etc. Its influencing factors include train reception and dispatching / passenger transportation operation information, passenger flow information, environmental comfort information, and multi-dimensional information on equipment operation status;

[0102] The equipment in the exit area includes exit screens, exit ticket gates, elevators, escalators, and service robots. The influencing factors of the exit area include multi-dimensional information on the operating status of station equipment, environmental comfort information, train reception and dispatching / passenger transport operation information, and passenger flow information;

[0103] The equipment in the computer room area includes broadcast interface machines, video servers, database servers, interface servers, network switches, routers, gateways, remote operation terminals and guide screen controllers, etc. Its influencing factors include multi-dimensional information on the operating status of station equipment and environmental comfort information.

[0104] In addition, the multi-dimensional information of the station equipment operation status and the information of receiving and dispatching trains / passenger transport operations can be used as internal factors, and the basic information of the station, environmental comfort information and passenger flow information can be used as external factors. According to the functions of different areas of the passenger station, the "independent variable-dependent variable" relationship pairs corresponding to different types of equipment in different areas of the station are sorted out (that is, the causal relationship set of energy consumption of equipment in different areas and categories of the station), and the causal relationship set can be presented in the form of knowledge graphs or decision trees.

[0105] As an example, the same influencing factors corresponding to different areas may be different. For example, the independent variable train / passenger transport operation information of the ticket inspection area, platform area and exit area is different: the ticket inspection area focuses on the departure time, train arrival time, train delay time, train timetable, train stop information and ticket purchase information; the exit area focuses on the train arrival time, train delay time, train stop information, passenger flow at the station and weather conditions; the platform area focuses on the train arrival and departure plan, train delay information, train stop information, passenger transfer information and weather conditions.

[0106] In step S122 , an optimal solution for the energy consumption of the corresponding area and category of equipment may be obtained based on the extracted energy consumption independent variable, thereby obtaining the optimal power consumption of each area.

[0107] The optimal power consumption is the ideal power consumption that meets the functions of the area, and is not necessarily the lowest power consumption.

[0108] In some embodiments of the present invention, obtaining the optimal solution of the energy consumption of the corresponding area and category of equipment based on the extracted energy consumption independent variable, thereby obtaining the optimal power consumption of each area, includes:

[0109] Based on the multi-task learning algorithm and extracting the energy consumption independent variables corresponding to different areas and categories of equipment in the station, a multi-independent variable model of each category of equipment in different areas is constructed;

[0110] Splitting the multi-independent variable model to obtain multiple single-independent variable models of equipment of each category in different areas;

[0111] The non-dominated sorting genetic algorithm is used to obtain the optimal solution of each single independent variable model;

[0112] Based on the optimal solution of the single independent variable model of the energy consumption of the equipment in each region and category and the set influence weight corresponding to each optimal solution, the optimal power consumption of the equipment in each region and category is obtained, thereby obtaining the optimal power consumption of each region. For example, the sum of the products of the optimal solution of the single independent variable model of the energy consumption of all categories of equipment in a region and the set influence weight corresponding to the optimal solution is the optimal power consumption of the region.

[0113] As an example, the optimal power consumption for each area can also be obtained as follows:

[0114] A set of influencing factors for different areas with safety, energy saving and comfort goals are selected from the extracted energy consumption independent variables, and the optimal power consumption of each area is obtained based on the influencing factor set and a constrained multi-objective optimization evolutionary algorithm.

[0115] More specifically, all influencing factors related to the safety target, all influencing factors related to the energy-saving target, and all influencing factors related to the comfort target are selected from the causal relationship set of the artificial intelligence module to form a set of safety influencing factors, a set of energy-saving influencing factors, and a set of comfort influencing factors for each area. Based on these three sets of influencing factors, the optimal power consumption of each area can be calculated using a constrained multi-objective optimization evolutionary algorithm.

[0116] It is assumed that the set of influencing factors in different areas for safety goals includes one or more of weather conditions, seasonal climate, equipment operation status, equipment maintenance status and emergency events (such as natural disasters or large-scale delays); the set of influencing factors in different areas for energy-saving goals includes one or more of equipment operation status, equipment maintenance status and passenger station scale; the set of influencing factors in different areas for comfort goals includes one or more of weather conditions, seasonal climate, real-time passenger flow, noise, brightness and other influencing factors.

[0117] There may be overlapping influencing factors in the safety influencing factor set, the energy-saving influencing factor set, and the comfort influencing factor set, but this does not affect the calculation of the optimal power consumption for a single target. The above examples of factors for safety, energy-saving, and comfort are only examples, and other influencing factors may also be included, and the present invention is not limited to this.

[0118] The optimal power consumption of each area is obtained based on a set of influencing factors and a constrained multi-objective optimization evolutionary algorithm, including:

[0119] Construct a multi-objective optimization model based on a set of factors for safety, energy saving and comfort goals;

[0120] Determine the constraints of each objective from the factor set, and construct the sub-objective functions corresponding to each constraint;

[0121] Based on the sub-objective functions and the weights corresponding to each sub-objective function, the optimization algorithm is used to obtain the optimal power consumption of the multi-objective optimization model in each area.

[0122] More specifically, for the set of safety influencing factors, the set of energy-saving influencing factors and the set of comfort influencing factors in each area, a multi-objective optimization model for each area is constructed; K influencing factors of each target in different areas are selected as constraints (K here is only an example, and does not mean that the number of constraints of each target in different areas is the same), and the corresponding range values ​​of these constraints are determined; based on the determined constraints, K sub-objective functions corresponding to the selected influencing factors are respectively constructed (the sub-objectives conflict with each other, and the improvement of one sub-objective performance may cause the performance of another sub-objective to decrease); based on the constructed K sub-objective functions and the corresponding weights of each sub-objective function (generally speaking, the sub-objective function with a larger weight ratio is more important to the optimal result, and the corresponding solution of the sub-objective function is also closest to the optimal solution), the optimization algorithm can be used to obtain the optimal power consumption of the multi-objective optimization model of each area.

[0123] As an example, for the waiting area, the process of obtaining the optimal power consumption of each area based on the set of comfort influencing factors and the constrained multi-objective optimization evolutionary algorithm includes the following two parts:

[0124] For the common waiting area, the brightness and real-time passenger flow are selected as constraints from the set of comfort influencing factors, and the corresponding range values ​​are determined (for example, the brightness range is 20W-40W, and the real-time passenger flow is 40-60 people / minute); based on the constraints (brightness is 20W-40W and real-time passenger flow is 40-60 people / minute), sub-objective functions for brightness and real-time passenger flow are constructed; based on the sub-objective functions and the weights of the corresponding sub-objective functions, the Pareto solution optimization algorithm can be used to obtain the optimal power consumption of the common waiting area;

[0125] For example, different passenger flows have different requirements for the illumination value setting of a station waiting room, but after a long period of operation, the final illumination stabilizes at a fixed value. Therefore, the random intercept model LMER can be used to construct the sub-objective function of real-time passenger flow.

[0126] For the VIP waiting area, weather conditions, noise and brightness are selected as constraints from the set of comfort influencing factors, and the corresponding range values ​​are determined (for example, temperature is 24-28℃, relative humidity is 45-65%, noise is 70-120dB, and brightness is 30W-45W); three sub-objective functions of noise, weather conditions and brightness are constructed based on the determined constraints; based on the constructed sub-objective functions and the corresponding weights of the sub-objective functions, the random intercept model can be used to obtain the optimal power consumption of the VIP waiting area.

[0127] By combining the optimal power consumption obtained for the ordinary waiting area and the VIP waiting area, the optimal power consumption for the station waiting area can be obtained.

[0128] As an example, setting the influence weights and the corresponding weights of the sub-objective functions can be obtained by a priori method (first assigning weights and then optimizing based on expert knowledge), asymptotic method (experts modify the weights during the optimization process based on the information fed back from the updated solution), or a posteriori method (once a set of candidate solutions are found, experts select a result and implicitly specify a set of weights).

[0129] The optimization algorithm includes a non-dominated sorting genetic algorithm (such as the NSGA-II algorithm), but other optimization algorithms can also be used to obtain the optimal power consumption of each area, such as a random intercept model for the waiting area, but the present invention is not limited to this.

[0130] Step S130: Based on the optimal power consumption, the energy consumption trend and energy usage pattern of the station are predicted using the pre-trained time series prediction model to obtain the predicted power consumption of all equipment in each area.

[0131] In some embodiments of the present invention, the pre-trained time series prediction model is obtained by:

[0132] The historical energy consumption time series data of station equipment (i.e. the historical energy consumption data within a certain period of time), the passenger flow information within the corresponding period of time and the seasonal climate are used as training data sets, and the pre-trained time series prediction model is obtained by iteratively training the time series prediction model.

[0133] As an example, the time series prediction model can be an Autoregressive Intergrated Moving Average (ARIMA) model. The basic idea is that since the label value at a point in time is affected by both the label value in the past period of time and the accidental events in the past period of time, the historical information of the data itself can be used to predict the future. Therefore, the ARIMA model usually assumes that: the label value fluctuates around the general trend of time, where the trend is affected by historical labels, the fluctuation is affected by accidental events in a period of time, and the general trend itself is not necessarily stable.

[0134] The training process of the ARIMA model is as follows: Based on the historical energy consumption time series data of station equipment, the autoregressive model in the ARIMA model is used to predict the energy consumption of a certain time series in the future. After correlation analysis, the moving average model in the ARIMA model is used to weighted accumulate the error terms of the energy consumption prediction results. The two models are accumulated and combined to obtain the ARIMA model to complete the long-term prediction of energy consumption. By performing autocorrelation analysis on the energy consumption data, combined with passenger flow information and seasonal climate, the appropriate time series model is judged and determined. The energy consumption is predicted by inputting the ARIMA model through MATLAB, the difference and predicted trend items are restored and superimposed, and finally the energy consumption results are obtained.

[0135] Furthermore, the pre-trained time series prediction model can be updated according to the set update frequency of the time series prediction model to obtain an optimized time series prediction model, thereby using the optimized time series prediction model to obtain the predicted power consumption of each area. The optimized time series prediction model is obtained in the following way:

[0136] After the differentiated energy strategy is generated, the optimization model parameters obtained based on the comparison results of the real-time power consumption generated when the differentiated energy strategy is executed and the regional standard power consumption range are obtained from the cloud computing platform according to the set update frequency of the time series prediction model;

[0137] Based on the optimized model parameters, the corresponding parameters in the pre-trained time series prediction model are updated, thereby updating the pre-trained time series prediction model to the optimized time series prediction model.

[0138] In addition, after generating predicted power consumption for each region based on the optimized time series model and then generating a differentiated energy usage strategy, the optimized time series prediction model may be updated again based on the real-time power consumption when the differentiated energy usage strategy is executed.

[0139] Specifically, the carbon asset management module in the empowerment platform can obtain the comparison results of the real-time power consumption when the differentiated energy consumption strategy generated by the artificial intelligence module of the empowerment platform is executed and the standard power consumption range of each region, and upload the comparison results to the cloud computing platform; the cloud computing platform generates optimization model parameters based on the comparison results, and sends the model parameters to the artificial intelligence module; the artificial intelligence module updates the current time series prediction model in the artificial intelligence module according to the optimization model parameters sent by the cloud computing platform to obtain the optimized time series prediction model.

[0140] In step S130, other time series prediction models may also be selected to predict the power consumption of each area, for example, a long short-term memory (LSTM) model, but the present invention is not limited thereto.

[0141] Step S140: Generate differentiated energy usage strategies by comparing the predicted power consumption of each area with the standard power consumption range to achieve digital empowerment.

[0142] The formulation of differentiated energy use strategies is based on the basic needs of passengers for safe, convenient and comfortable travel and the operational needs of healthy station operations. By monitoring and predicting the energy consumption of stations, analyzing the factors affecting station energy consumption, sorting out the causal relationship of station energy consumption problems, and obtaining energy use characteristics and preferences of different stations. For example, by simulating the energy use behavior characteristics of a single station using LSTM neural networks and other methods, establishing an energy use behavior portrait for the station, introducing energy use behavior similarity quantification, and quantifying the degree of fit with the differentiated energy use needs of station users, and formulating personalized energy use strategies and solutions for the station on this basis, it is possible to achieve a "green digital one-station one-solution" with the station's own characteristics and energy use characteristics, and fully tap the energy-saving potential of the station while ensuring the quality of passenger services.

[0143] In some embodiments of the present invention, the differentiated energy usage strategy may be generated by comparing the predicted power consumption of each region with the regional standard power consumption range, which is specifically:

[0144] If the predicted power consumption of the area exceeds the corresponding regional standard power consumption range, the power corresponding to the maximum value of the regional standard power consumption range is used as the distributed power energy of the area, and the power exceeding the maximum value of the regional standard power consumption range is used as the distributed power energy of the energy storage device;

[0145] If the predicted power consumption of the area is within the standard power consumption range of the corresponding area, the predicted power consumption is used as the allocated power energy of the area; and

[0146] If the predicted power consumption of the area is lower than the corresponding regional standard power consumption range, the power corresponding to the minimum value of the regional standard power consumption range is used as the allocated power of the area, and the power difference between the predicted power consumption and the minimum value of the regional standard power consumption range is obtained from the energy storage device.

[0147] In some embodiments of the present invention, after step S140, the method further includes step S150:

[0148] For the ticket sales area, security check area, ticket inspection area and exit area, if the predicted power consumption of a certain area exceeds the standard power consumption range of the corresponding area, a dynamic resource allocation model for the corresponding area is generated based on the train reception and dispatching / passenger transport operation information, multi-dimensional information on the operation status of station equipment and passenger flow information, and a differentiated allocation plan for the area is generated based on the results of the dynamic resource allocation model to adjust the operation cycle of the resource equipment in the area and the staff scheduling plan;

[0149] The resource equipment at least includes gate machines, security inspection equipment and ticketing equipment.

[0150] The differentiated deployment scheme is:

[0151] If the result of the dynamic resource allocation model corresponding to a certain area is a resource reduction, remove the idle resources and equipment in the area and / or reduce staff shifts;

[0152] If the result of the dynamic resource allocation model corresponding to a certain area is that the resources remain unchanged, the staff schedule and / or the working hours of the resource equipment in the area are adjusted;

[0153] If the result of the dynamic resource allocation model corresponding to a certain area is an increase in resources, the resource equipment and personnel scheduling in the area will not be adjusted.

[0154] More specifically, for the ticket sales area, security check area, ticket inspection area and exit area, when the predicted power consumption of a certain area exceeds the standard power consumption range of the area, and the result of the dynamic resource allocation model of the corresponding area is decreasing or unchanged, the "resource equipment-personnel" ratio will be adjusted according to the result of the dynamic resource allocation model. In other cases, there is no need to adjust the "resource equipment-personnel" ratio.

[0155] Taking into account the diversity and complexity of passenger flow at stations, a dynamic resource allocation model for the corresponding area is generated based on train dispatching / passenger operation information such as train operation scheduling, multi-dimensional information on the operation status of station equipment such as equipment operation status, and passenger flow information such as real-time passenger flow. A differentiated allocation plan is generated based on the results of the dynamic resource allocation model, so as to adjust the "resource equipment-personnel" ratio of gates, security inspection equipment, and ticket vending equipment. For example, for ticket gates with dense passenger flow, appropriate additional staff or increased number of ticket inspection equipment (referring to gates) can be opened. On the contrary, individual idle equipment can be appropriately closed. For emergencies such as large-scale delays, non-in-use equipment can be appropriately closed according to the real-time passenger flow in the station to avoid uneven "resource equipment-personnel" ratio and improper capacity allocation.

[0156] As an example, the differentiated deployment scheme may be:

[0157] 1) If the result of the dynamic resource allocation model is a reduction in resources, there are three different ways:

[0158] ① Reduced staff, unchanged resources and equipment: Since this method does not involve changes in power consumption, the ratio of “resources and equipment - staff” does not change;

[0159] ② The number of personnel remains the same, but the number of resources and equipment is reduced: some idle equipment in the area can be deactivated or moved to other areas to reduce equipment energy consumption;

[0160] ③ Reduction in staff, resources and equipment: Staff scheduling can be adjusted to reduce redundant human resources, and / or idle equipment in the area can be deactivated or removed.

[0161] 2) If the result of the dynamic resource allocation model is that the resources remain unchanged, then improve the equipment manufacturing process or select more energy-saving equipment materials, and appropriately shorten the equipment working hours; and / or optimize personnel scheduling to improve personnel operating proficiency and technical level.

[0162] In some embodiments of the present invention, when the predicted power consumption of a certain area is lower than the minimum value of the standard power consumption range of the corresponding area, the energy consumption of the corresponding area is reduced by using energy-reducing equipment in each area.

[0163] If the minimum power consumption of the energy reduction device is less than or equal to the minimum value of the regional standard power consumption range, the reduced power consumption shall not be less than the difference between the predicted power consumption and the minimum value of the regional standard power consumption range; if the minimum power consumption of the energy reduction device is greater than the minimum value of the regional standard power consumption range, the reduced power consumption is the difference between the minimum power consumption of the energy reduction device and the minimum value of the regional standard power consumption range, and the difference between the minimum power consumption of the energy reduction device and the predicted power consumption is obtained from the energy storage device.

[0164] Energy reduction equipment in each area refers to equipment that has its power consumption reduced first when the power allocated to the area cannot meet the needs of all equipment in the area. For example, the energy reduction equipment in the security inspection area may be security inspection equipment (energy reduction is achieved by reducing the number of security inspection equipment in operation or shortening the operating time), the energy reduction equipment in the platform area may be platform screens (energy reduction is achieved by reducing the brightness of the platform screens or turning off the corresponding platform screens during unplanned periods), the energy reduction equipment in the waiting area may include air conditioners, broadcasts and display screens (energy reduction is achieved by changing the air conditioner temperature, reducing the broadcast volume and reducing the brightness of the display screens), and the energy reduction equipment in the exit area may be elevators and escalators (energy reduction is achieved by reducing the number of elevators and escalators in operation or appropriately reducing the brightness of the exit guide screen). In addition, the minimum power consumption of the energy reduction equipment is the minimum power consumption required by the energy reduction equipment, which is pre-set and can maintain the functions of the corresponding area.

[0165] As an example, if the predicted power consumption of the security inspection area of ​​150lx is lower than the corresponding area standard power consumption range of 200-300lx, then based on the minimum power consumption of the energy-reducing equipment (i.e., security inspection equipment) in the security inspection area (assuming it is 100lx), shut down an appropriate number of security inspection equipment to reduce the power consumption of the security inspection area to 100lx or lower, so that the reduced power consumption is not less than the difference between the predicted power consumption of the security inspection area and the minimum value of the standard power consumption range of the security inspection area, which is 50lx.

[0166] For example, for the air conditioning equipment in the waiting area, assuming that the average air conditioning temperature in the waiting area in summer is 24°C, the adjustment strategy for the air conditioning power consumption in the waiting area is as follows:

[0167] If the temperature in the waiting area exceeds the average, first consider whether the ambient temperature is too hot (if the ambient temperature is too hot, it needs to be cooled down, which will inevitably increase the power consumption of the air conditioner. At this time, consider maintaining the temperature setting unchanged, increasing the number of ventilation channels opened, and using airflow to appropriately reduce the ambient temperature to improve comfort); secondly, consider the real-time passenger flow in the station (if the passenger flow is large, adopt diversion measures, such as accepting passengers waiting within a fixed time, appropriately opening some temporary waiting areas, etc., to disperse the passenger flow, and at the same time increase the number of ventilation openings, change the air conditioning mode to ventilation mode, etc.);

[0168] If the temperature in the waiting area is lower than the average, some air conditioners can be turned off or ventilation mode can be turned on to save energy while providing passengers with a more comfortable waiting experience.

[0169] For example, for security inspection equipment in the security inspection area, the use strategy of the security inspection equipment is adjusted according to the impact of the passenger traffic capacity of the security inspection area on the energy consumption of the security inspection equipment:

[0170] 1) If the security inspection area allows smooth entry for passengers, the average entry time is short, and the existing security inspection equipment can basically meet the passenger traffic capacity, the use of the existing security inspection equipment will not be changed;

[0171] 2) If there are group passengers or key passengers, the average time for passengers to enter the station is long, which is prone to congestion, causing the subsequent passengers to queue for a long time. At this time, the equipment at the security checkpoint has a long working time and relatively high energy consumption. Therefore, it is possible to consider adding security checkpoints and supporting personnel and equipment, or deploying the functions of different security check areas, concentrating group passengers or key passengers at one security checkpoint to complete security checks, dispersing security checks in congested areas, and appropriately reducing the average energy consumption;

[0172] 3) If there is a large-scale delay, in order to avoid congestion in the station and ensure the safety of personnel, only passengers within a fixed time period from departure will be allowed to enter the station, thereby reducing the use time of equipment and reducing energy consumption;

[0173] 4) In the event of a natural disaster, the personal safety of passengers and staff must be guaranteed. No further passengers will be allowed to enter the station, and passengers in the station must be evacuated outside the station.

[0174] For example, for ticket checking equipment in the ticket checking area, the energy consumption strategy of the ticket checking equipment can be adjusted according to the real-time passenger flow:

[0175] If the regional passenger flow is met and the energy consumption is high, you can check the ticket checking equipment that is idle but turned on for a long time, and transfer it to other areas; if the regional passenger flow is not met and the energy consumption is high, you need to check the ticket checking equipment for abnormalities and adjust the operation and maintenance strategy in time.

[0176] In some embodiments of the present invention, generating a differentiated energy usage strategy by comparing the power consumption predicted by each area with the standard power consumption range also includes:

[0177] Based on the predicted power consumption of each area and the energy allocation ratio of equipment with different uses in the area, the predicted power consumption of equipment in each area and use is obtained;

[0178] By comparing the predicted power consumption of each area and purpose with the standard power consumption range of the corresponding area and purpose, differentiated energy use strategies for energy sub-items are generated; among which, equipment for different purposes includes lighting and socket equipment, air-conditioning and heating equipment, power equipment and special equipment; the regional standard power consumption range is obtained based on the standard power consumption range of each purpose in the area.

[0179] As an example, assuming that the predicted power consumption of the waiting area obtained in step S130 is M, and according to the energy allocation ratio of the equipment with different uses in the waiting area set by the passenger station, that is, the lighting and socket power consumption of the waiting area: the air conditioning and heating power consumption: the power consumption: the special power consumption = 4:3:2:1, then the predicted power consumption of the equipment with different uses in the waiting area is 0.4M, 0.3M, 0.2M and 0.1M respectively. By comparing the predicted power consumption of the waiting area with the standard power consumption range of the waiting area with different uses, a differentiated energy consumption strategy for energy sub-items can be generated.

[0180] The standard power consumption range for different purposes refers to the standard power consumption range for lighting and sockets, the standard power consumption range for air conditioning and heating, the standard power consumption range for power, and the standard power consumption range for special power. The standard power consumption range for different purposes is set by the passenger station based on relevant standards and specifications, and the sum of the standard power consumption ranges for different purposes in each area can be used as the standard power consumption range for each area.

[0181] As an example, electricity consumption for lighting and sockets includes electricity consumption for indoor lighting and sockets, electricity consumption for lighting in public areas, electricity consumption for outdoor landscape lighting and electricity consumption for special sockets, etc.; electricity consumption for air conditioning and heating includes electricity consumption for cold and heat source systems, electricity consumption for air conditioning water systems and electricity consumption for air conditioning air systems, etc.; power consumption includes electricity consumption for elevators, water pumps and ventilators, etc.; special electricity consumption includes other uses such as information centers, laundries, kitchens and restaurants, gyms and advertising lighting.

[0182] The influencing factors of equipment with different uses in different areas of the passenger station may also be different. For example, the influencing factors of air conditioning and heating electricity consumption in the waiting area include: real-time ambient temperature, real-time passenger flow in the waiting hall of the station, station building scale, ventilation and air conditioning equipment configuration, seasonal climate, weather conditions and passenger experience; the influencing factors of lighting and socket electricity consumption in the platform area include: train arrival and departure schedules, stop information, platform lighting circuit settings, train operation timetables and illumination regulations for the area (i.e. standard power consumption range); the influencing factors of lighting and socket electricity consumption in the exit area include: natural lighting conditions in the passage, train arrival and departure schedules, stop information and illumination regulations for the area.

[0183] In some embodiments of the present invention, the differentiated energy use strategy for energy sub-items may be generated by comparing the predicted power consumption of different regions and uses with the standard power consumption range of the corresponding regions and uses, specifically:

[0184] If the predicted power consumption of a certain area and purpose exceeds the standard power consumption range of the corresponding area and purpose, the power corresponding to the maximum value of the corresponding standard power consumption range will be used as the allocated power for the area and purpose, and the power consumption exceeding the maximum value of the standard power consumption range of the corresponding area and purpose will be used as the allocated power for the energy storage device;

[0185] If the predicted power consumption of a certain area and purpose is within the standard power consumption range of the corresponding area and purpose, the predicted power consumption is used as the allocated power for the area and purpose; and

[0186] If the predicted power consumption of a certain area and purpose is lower than the standard power consumption range of the corresponding area and purpose, the power corresponding to the minimum value of the standard power consumption range of the corresponding area and purpose will be used as the allocated electric energy for the area and purpose, and the difference between the predicted power consumption of the area and purpose and the minimum value of the standard power consumption range of the corresponding area and purpose will be obtained from the energy storage device.

[0187] In some embodiments of the present invention, the method further includes step S160: evaluating the execution effect of the differentiated energy use strategy or the differentiated energy use strategy of the energy sub-item based on the set evaluation index; wherein the evaluation index includes part or all of the following indicators: environmental comfort index class, equipment and facility index class, data center index class, personnel-resource equipment ratio index class and digital intelligent means index class; and

[0188] A digital model of the green passenger station is built based on three-dimensional modeling technology to display the digital empowerment of the passenger station in real time.

[0189] In a specific embodiment of the present invention, taking lighting equipment as an example, each area of ​​the station generates a differentiated energy use strategy according to the railway passenger station digital intelligence empowerment method, such as Figure 3 As shown, it specifically includes steps S01-S06:

[0190] Step S01: Obtain the passenger station full life cycle operation data of the station ticket area, security inspection area, ticket checking area, waiting area, platform area, exit area and machine room area, and perform data preprocessing on it. Data preprocessing includes one or more preprocessing methods such as data review, data sorting, data cleaning, data transformation and data reduction.

[0191] Step S02: Based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the lighting equipment in different areas, the energy consumption independent variables (i.e., energy consumption influencing factors) for the lighting equipment in different areas are extracted from the pre-processed passenger station full life cycle operation data.

[0192] For example, the energy consumption independent variables of the lighting equipment in the waiting area of ​​the station include one or more of the following influencing factors: train arrival and departure plans including train schedules, passenger flow information, weather information, seasonal climate and emergency events (such as natural disasters); the energy consumption independent variables of the lighting equipment in the platform area of ​​the station include one or more of the following influencing factors: train arrival and departure plans, weather information and seasonal climate; the energy consumption independent variables of the lighting equipment in the machine room area of ​​the station include one or more of the following influencing factors: personnel scheduling plans and equipment operating conditions.

[0193] Furthermore, the extracted independent variables can be represented by A~G, for example, A represents train arrival and departure schedule, B represents passenger flow information, C represents weather information, D represents seasonal climate, E represents emergency events, F represents personnel scheduling plan, and G represents equipment operating status.

[0194] Step S03: Based on the multi-task learning algorithm, establish the influencing factor models of lighting equipment in different areas, and split the influencing factor models of lighting equipment in each area, so as to convert the optimal solution problem of multiple influencing factors into the optimal solution problem of a single factor.

[0195] For example, the influencing factor model of the waiting area lighting equipment can be expressed as L1{A, B, C, D, E}, the influencing factor model of the platform area lighting equipment can be expressed as L2{A, C, D}, and the influencing factor model of the computer room area lighting equipment can be expressed as L3{F, G}.

[0196] The multi-independent variable model L1{A, B, C, D, E} can be split into single-independent variable models L1{A}, L1{B}, L1{C}, L1{D} and L1{E}. The multi-independent variable model L2{A, C, D} can be split into single-independent variable models L2{A}, L2{C} and L2{D}. The multi-independent variable model L3{F, G} can be split into single-independent variable models L3{F} and L3{G}.

[0197] Step S04: Use the non-dominated sorting genetic algorithm to obtain the Pareto optimal solution of each single independent variable model (i.e., the optimal power consumption of the lighting equipment in the area). Add the set influence weights corresponding to each independent variable of the lighting equipment in a certain area and the product of the optimal solution corresponding to each independent variable to obtain the optimal power consumption of the area.

[0198] For example, the optimal power consumption of the lighting equipment in the waiting area can be expressed as L1 = a1*A1′+b1*B1′+c1*C1′+d1*D1+e1*E1′, the optimal power consumption of the lighting equipment in the platform area can be expressed as L2 = a2*A2′+c2*C2′+d2*D2, and the optimal power consumption of the lighting equipment in the machine room area can be expressed as L3 = f3*F3′+g3*G3′. Among them, a1 represents the set influence weight of the train arrival and departure plan in the waiting area, and A1′ represents the Pareto optimal solution of the train arrival and departure plan in the waiting area.

[0199] In addition, the set influence weights corresponding to the same independent variables of the lighting equipment in the waiting area and the platform area may be different, that is, a1 and a2 may be different or the same.

[0200] Step S05: Based on the optimal power consumption of the lighting equipment in each area, the predicted power consumption of the lighting equipment in each area is obtained using the pre-trained ARIMA model or the optimized ARIMA model. That is, the predicted power consumption L1′ of the lighting equipment in the waiting area, the predicted power consumption L2′ of the lighting equipment in the platform area, and the predicted power consumption L3′ of the lighting equipment in the machine room area are obtained using the pre-trained ARIMA model or the optimized ARIMA model.

[0201] Step S06: Generate a differentiated energy use strategy by comparing the predicted power consumption of each area with the regional standard power consumption range.

[0202] For example, the standard power consumption range of illumination in the waiting area may be 1501x to 2001x, the standard power consumption range of illumination in the platform area may be 1001x to 1501x, and the standard power consumption range of illumination in the machine room area may be 501x ​​to 1001x. Taking the lighting equipment in the waiting area as an example, if the predicted power consumption L1′ exceeds 1501x to 2001x, 2001x will be used as the allocated power in the waiting area; if the predicted power consumption L1′ is between 1501x and 2001x, L1′ will be used as the allocated power in the waiting area; if the predicted power consumption L1′ is lower than 1501x to 2001x, 1501x will be used as the allocated power in the waiting area, and (150-L1′) of power will be obtained from the energy storage device.

[0203] As an example, the station can also replenish electricity by purchasing electricity or using photovoltaic conversion equipment instead of energy storage equipment.

[0204] like Figure 4 As shown, the present invention proposes a new type of green passenger station digital intelligence empowerment platform, which includes a station-level platform, a railway bureau-level platform and a national railway group-level platform. The station-level platform includes a perception layer, a transmission layer, a platform layer, an application layer and a display layer. The perception layer of the underlying service platform of the passenger station collects the passenger station's full life cycle operation data, and transmits it to the platform layer through the transmission layer according to the real-time performance of the passenger station's full life cycle operation data. The platform layer generates differentiated energy use strategies through multi-dimensional analysis of the passenger station's full life cycle operation data. The application layer of the underlying service platform of the passenger station executes differentiated energy use strategies through digital twins and evaluates its execution effect based on the constructed evaluation system. The passenger station's full life cycle operation data collected by the station-level platform can select part of the data and upload it to the railway bureau-level platform and the national railway group-level platform according to the needs of the railway bureau and the national railway group's decision-making and command, so that the railway bureau-level platform and the national railway group-level platform can comprehensively display the passenger station's energy consumption, and the railway bureau-level platform can also uniformly allocate computing resources to the passenger stations under its jurisdiction.

[0205] The cloud computing platform that interacts with the empowerment platform is responsible for continuously accumulating and storing energy consumption data during station operations (obtained from the data aggregation module at the platform layer), integrating the computing resources, network resources and storage resources of all passenger stations, and all energy consumption and efficiency and resource allocation models are deployed on the railway bureau-level platform after training. In addition, the cloud computing platform can also update the parameters of the time series prediction model based on the set update frequency of the time series prediction model and the current operation status of the station; when updating the model parameters, it is necessary to dispatch computing resources for calculation, and the process includes:

[0206] Based on data such as the scale of each station, resource demand and resource type, the network throughput (the amount of data transmitted per second / network bandwidth), the storage capacity of data resources (that is, the amount of data that a device or system can store, also called storage capacity, number of storage units × storage word length / 8), and the memory and CPU of system resources are estimated from the three aspects of network resources, computing and storage. At the same time, combined with load balancing, scheduling algorithms based on genetics, scheduling algorithms based on greedy algorithms and other computing power resource scheduling methods, the optimal computing power resource scheduling plan is selected, and the actual data resources and network resource usage and occupancy of each station are monitored irregularly. The computing capacity of each station is dynamically adjusted according to the formulated resource scheduling plan, and the future computing power resource requirements of each station are predicted to complete the dynamic allocation and scheduling planning of computing power resources to avoid resource waste.

[0207] In some embodiments of the present invention, Figure 5 As shown, the station-level platform includes:

[0208] The perception layer is used to obtain passenger station operation data throughout its life cycle from sensors;

[0209] The transmission layer is used to transmit the real-time difference of the information collected by the perception layer to the platform layer through the railway integrated information network;

[0210] The platform layer is used to generate differentiated energy use strategies or differentiated energy use strategies for energy sub-items;

[0211] The application layer is used to evaluate the execution effect of the differentiated energy use strategy or the differentiated energy use strategy of energy sub-items based on the set evaluation indicators (it can also be evaluated by combining the equipment inspection plan, ticket checking plan and other passenger operations and production command processes to evaluate the execution effect of the differentiated energy use strategy or the differentiated energy use strategy of energy sub-items); among them, the evaluation indicators include: environmental comfort index category, equipment and facility index category, data center index category, personnel-resource ratio index category and digital intelligent means index category;

[0212] The display layer is used to build a digital model of a green passenger station based on the passenger station's full life cycle operation data and combined with 3D modeling technology to demonstrate the digital empowerment of the passenger station.

[0213] More specifically, the overall architecture of the station-level green empowerment platform is divided into perception layer, transmission layer, platform layer, application layer and display layer.

[0214] The perception layer can collect passenger station operation data throughout its life cycle through a variety of perception methods such as handheld mobile terminals, security scanners and sensors, and monitor multimodal energy consumption data (including station basic information, environmental comfort information, station equipment energy consumption information, multi-dimensional information on station equipment operating status, train reception and dispatching / passenger transport operation information and station passenger information including passenger flow information). In addition, the collected passenger station operation data throughout its life cycle can be transferred through the railway comprehensive information network in the three-level architecture of "station-railway bureau-China Railway Group".

[0215] The passenger station full life cycle operation data collected and pre-processed by the perception layer can be transmitted to the data aggregation module (also known as the data aggregation and sharing module) of the platform layer through the transmission layer according to the real-time difference transmission. Among them, the transmission layer mainly includes the railway integrated information network. For example, for the relevant data of the train reception and dispatching / passenger operation information with high real-time requirements, the platform calls the data interface through WebService to request data in real time; for environmental comfort information and station equipment operation and maintenance information, the enabling platform requests it every 30 minutes through Webservice to obtain interface data; for station basic information and equipment history information, it requests it when it changes, and changes the corresponding data records; for station passenger information, the platform requests it once every hour through Webservice or XML and other protocols to obtain and access the corresponding records; for station energy consumption and energy efficiency information, the platform requests it once every 2 hours through Webservice or XML and other protocols to obtain interface data.

[0216] The application layer builds a green digital passenger station evaluation system based on the digital application of green passenger stations and the results of energy consumption and energy efficiency analysis to evaluate the differentiated energy use effects of green passenger stations. The evaluation indicators of green passenger stations in the operation stage include: environmental comfort indicators (such as temperature, humidity, CO2 concentration, NO xConcentration and brightness, etc.), equipment and facility indicators (such as equipment operating status, basic equipment information and equipment layout, etc.), data center indicators (such as server occupancy, switches, clusters, data resource usage and allocation), personnel-resource ratio indicators (personnel scheduling and equipment usage configuration) and digital intelligent means indicators (such as hybrid networking methods for data transmission, green collection methods, model algorithm usage and green storage methods). According to the evaluation results, the accuracy, completeness and robustness of relevant strategies, models and algorithms can be reversed and optimized to provide a basis for the subsequent promotion and construction of green intelligent passenger stations. In addition, the application layer includes a digital twin module, which can verify the application effect of differentiated energy use strategies under different operation flow lines through digital twins. For differentiated energy use strategies with unsatisfactory optimization effects, they are fed back to the cloud computing platform, and the cloud computing platform re-updates the parameters of the time series prediction model.

[0217] The display layer can display the application effects in four directions: precise passenger service, coordinated production command, efficient and safe emergency response, and green energy conservation and environmental protection. The digital model of the green passenger station built with Unity3D technology can intuitively display the station building structure, area division, hardware resource configuration, equipment history, personnel history, operation plan, plan configuration and other dynamic and static parameter information in the form of data association, pop-up boxes, jumps, etc., and display the specific energy consumption / energy efficiency of the station in different statistical periods and time nodes in various forms such as bar charts, pie charts, curves, broken lines, knowledge graphs, etc., and intuitively display the effects of energy consumption, efficiency improvement, operation optimization, etc. along with the production / passenger operation process. Holographic simulation, precise simulation and diagnosis predict the status of the physical entity of the station in the real environment, realize the collaborative interaction and parallel operation of the two, and the real-time operation status of all equipment can be judged by connecting to the comprehensive video auxiliary, so as to facilitate the rapid location of weak links through decision-making command and then feedback to modify or adjust related functions, processes, models and algorithms.

[0218] In some embodiments of the present invention, Figure 6 As shown in the figure, the platform layer in the station-level platform includes:

[0219] The data aggregation module is used to collect the passenger station full life cycle operation data transmitted by the transport layer and transmit it to the artificial intelligence module;

[0220] The artificial intelligence module is used to obtain the optimal power consumption of each area based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment in different areas and categories, obtain the predicted power consumption of each area based on the optimal power consumption, and generate differentiated energy consumption strategies by comparing the predicted power consumption of each area with the standard power consumption range of the area, or generate differentiated energy consumption strategies for energy sub-items by comparing the predicted power consumption of each area and purpose with the standard power consumption range of the corresponding area and purpose.

[0221] The control and coordination module is used to generate differentiated energy use strategies or differentiated energy use strategies for energy sub-items by combining passenger operation plans, train arrival and departure plans, and personnel scheduling plans;

[0222] The carbon asset management module (also known as the carbon asset and energy efficiency management module) is used to obtain the implementation status of the differentiated energy usage strategy from the management and control and coordinated linkage module, and obtain the comparison results by comparing the real-time power consumption when the differentiated energy usage strategy is executed with the corresponding regional standard power consumption range, or by comparing the real-time power consumption when the differentiated energy usage strategy of the energy sub-item is executed with the standard power consumption range of the corresponding region and purpose, so as to manage the differentiated energy usage strategy; in addition, the carbon asset management module can also manage the overall energy-saving plan of the station according to the differentiated energy usage strategy.

[0223] The intelligent Internet of Things module is used to realize data transmission between the platform layer and the transport layer, and provide connection and data management services for terminal devices, personnel and environment.

[0224] More specifically, the data aggregation module obtains the passenger station full life cycle operation data transmitted by the transmission layer through the intelligent Internet of Things module and performs data preprocessing, and then transmits it to the artificial intelligence module, management and coordination module and carbon asset management module of the platform layer.

[0225] The control and coordination module generates the energy consumption plan of the equipment by region and accompanies the generation, automatic issuance and synchronization of passenger operation, equipment operation and maintenance / inspection and train arrival and departure plans, based on the multi-dimensional information of the station equipment operation status related to production and operation in the data aggregation module, the information of train reception and departure / passenger operation, the algorithm and model of the artificial intelligence platform and the differentiated energy consumption strategy, combined with the passenger operation plan, equipment operation and maintenance / inspection plan, train arrival and departure plan and personnel scheduling plan, and links various systems, equipment facilities and personnel to complete the application of energy consumption, energy efficiency models and differentiated energy consumption strategies. For emergency events such as large-scale delays and natural disasters, the energy consumption plan for special circumstances is formed along with the generation of emergency plans, and the energy consumption plan for special circumstances is executed synchronously with the emergency disposal process. The control and coordination module can also transmit the execution of energy consumption plans and differentiated energy consumption strategies to the carbon asset management module.

[0226] The carbon asset management module models the statistical multidimensional energy consumption and energy efficiency data through sample selection, data table construction, data completion and data correction. From the perspectives of energy organization, energy efficiency ratio and operation scenarios, the module comprehensively analyzes the statistical laws among the multidimensional energy consumption indicators of the station in the "time + space" dimension and queries them (e.g., according to the time dimensions such as year, month, day and hour, retrieve the energy consumption statistical report of each energy consumption node of the station building, conduct year-on-year analysis or month-on-month analysis, or conduct analysis and query according to energy consumption area, functional area, station building structure and equipment conditions, etc.) to support green production and operation. Subsequent applications involving the full life cycle management of energy consumption in railway passenger stations include operation (such as integrated and coordinated planning, centralized energy deployment, active equipment operation and maintenance, fault prediction and early warning, and other cost-saving and consumption-reducing applications, and quality-enhancing and efficiency-enhancing applications such as one-click station switching, energy coupling, and flexible resource allocation), comprehensive energy management, equipment operation and maintenance management (such as digital preventive maintenance, differentiated operation and maintenance, virtualized inspection, etc.), and carbon asset management, to achieve the interconnection, sharing, interaction, and intercommunication between management decisions and operations, continuously improve the energy utilization efficiency and management level of stations, maximize the economic and social benefits of stations, and achieve green and sustainable development. In addition to energy consumption management, the carbon asset management module can also perform carbon asset management such as carbon trajectory tracking, carbon asset measurement decision-making, and carbon performance assessment.

[0227] Furthermore, the artificial intelligence module combs through the acquired information on influencing factors, and uses BP neural networks, LSTM multimodal expected trajectory algorithms, etc. to perform adaptive training and predict energy consumption trends, as well as the changing trends of the "equipment-resource" resource ratios in each area of ​​the station, based on historical energy consumption data and multi-dimensional influencing factors of energy consumption. The artificial intelligence module includes common models and individual models. The common model is the energy consumption prediction model, including the BP neural network prediction model (based on the peak value, valley value, mean value, mean square error, energy consumption fluctuation intensity and influencing factor information, the energy consumption prediction model is constructed using the BP neural network series algorithm), the unit GDP energy consumption prediction model (based on the total energy consumption of the station, the annual gross domestic product of the station and the energy saving rate, the energy demand of the station is predicted on an annual basis) and hybrid models such as the ARMIMA-GARCH model (based on the environmental temperature, humidity and real-time passenger flow and other factors related to air conditioning, lighting and other systems The correlation between influencing factors and operating characteristic parameters and energy consumption is achieved by hybrid optimization of parameters and network structure of artificial intelligence methods such as RBF neural network, TSA algorithm and LSTM neural network to make up for the shortcomings of single model algorithm and improve prediction accuracy, robustness and prediction precision); the personalized model is a model with the energy consumption characteristics of the station itself, including time series prediction model (such as ARIMA model), resource dynamic allocation model and energy consumption sub-item measurement model (electricity consumption is measured sub-item according to the characteristics of electricity consumption, which is divided into lighting socket electricity consumption, air conditioning electricity consumption, power electricity consumption and special electricity consumption).

[0228] Based on the common and individual models of the above artificial intelligence modules, on the basis of real-time monitoring and analysis of passenger station energy consumption, corresponding differentiated energy consumption strategies can be provided according to the energy consumption characteristics of different stations, equipment types, physical areas, and regional climates. The data generated by the models and algorithms of the artificial intelligence modules during operation can be transmitted to the data aggregation module for storage.

[0229] Furthermore, if Figure 1 As shown in the figure, the passenger station life cycle operation data collected by the perception layer of the station-level platform also includes ticket information (which can be obtained from the automatic ticketing database server through the interface of the ticket system) and comprehensive video information (which can be collected through smart cameras). Ticket information includes some or all of the following information: ticket sales / ticket collection / refund status and the operating status of the ticketing equipment (i.e., whether the ticketing equipment is operating normally); comprehensive video information includes some or all of the following information: end crossing video information, platform white line crossing video information, entrance congestion video information, crowd gathering video information in key areas, and operation video information in key areas.

[0230] Passenger ticket information is transmitted between the three-level architecture of "station-railway bureau-China Railway Group" through the passenger ticket network, and comprehensive video information is transmitted between the station-level platform, railway bureau-level platform and China Railway Group-level platform through the comprehensive video network. Due to the high real-time requirements of passenger ticket information, the empowerment platform can call the data interface through Webservice to request data in real time; the comprehensive video information in the station can request data every 10 minutes. The green empowerment platform can grasp the station ticket sales status and real-time passenger flow information in real time based on the passenger ticket information; the empowerment platform can extract real-time monitoring videos of key areas in the station such as the waiting area, platform area, ticket checking area, and ticket sales area from the comprehensive video information, thereby assisting in positioning and viewing the equipment operation status.

[0231] In summary, the enabling platform transmits all the basic data of the passenger station's entire life cycle to the platform layer through the perception layer for data analysis, aggregation and sharing, computing power balance matching, model algorithm construction, collaborative linkage interaction, digital display, and comprehensive management of energy consumption and energy efficiency. Through the application layer, the application is carried out in four directions: precise passenger service, collaborative production command, efficient and safe emergency response, and green energy conservation and environmental protection. The application effect is intuitively displayed through the display layer for better decision-making and command.

[0232] The green passenger station digital empowerment method and platform proposed in the present invention adopts a collaborative, integrated and sustainably upgradeable system architecture, upgrades the energy management dimension, and processes and analyzes the passenger station energy consumption data in an all-round, multi-level, multi-dimensional and multi-angle manner. With the help of the energy consumption analysis results, the energy consumption of the station operation process is explored, energy costs and energy consumption are reduced from multiple angles, and the energy-saving management space of the station is analyzed and deduced. Energy optimization operation plans are provided, and unified planning and design based on energy and resources, integrated organization and implementation, and digital intuitive display are realized, which gives full play to the synergistic linkage of all levels and enables the digital development of railway green passenger stations.

[0233] Corresponding to the above method, the present invention also provides a new type of green passenger station digital intelligence empowerment equipment and facilities, which includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the equipment and facilities implement the steps of the method described above.

[0234] The new green passenger station digital intelligence empowerment method, platform and equipment facilities proposed in this invention have the following advantages:

[0235] 1) Aiming at the existing energy ratio, equipment and facility conditions, production operation conditions and energy consumption of the passenger station, a comprehensive analysis and evaluation of the existing energy consumption indicators of the passenger station is carried out from multiple dimensions, angles, scales, levels and aspects to form diversified energy consumption analysis results. With the help of digital models, high-energy-consuming equipment and weak links in energy distribution are intuitively explored, and targeted digital solutions that are conducive to the green transformation of the passenger station are given to save energy, reduce carbon emissions, improve quality and increase efficiency.

[0236] 2) By obtaining the energy consumption of the load end in different areas of the station, an energy consumption influencing factor model with load end energy consumption characteristics is constructed, and the most important influencing factors are obtained according to the Pareto optimal solution, so as to adjust its energy consumption in a targeted manner, and revise the model parameters according to the actual operating conditions of the equipment, so as to adjust the corresponding energy consumption and ensure the differentiation of energy consumption strategies.

[0237] 3) Consider factors such as energy use, energy consumption areas and energy-consuming equipment, identify measures and plans to improve energy efficiency and energy conservation, consider reducing energy consumption and improving energy efficiency by improving equipment, optimizing processes, improving energy-consuming materials, etc., scientifically and reasonably plan station energy consumption and emission reduction paths based on the station's energy consumption situation, assist passenger station operation decisions, and implement differentiated energy adjustment strategies with station characteristics.

[0238] 4) Provide unified scheduling and management of energy and resources (computing, storage, network, graphics, etc.), flexibly deploy existing energy based on differentiated energy use strategies, solve the current problem of independent and decentralized energy consumption of railway passenger station equipment, and manage passenger station energy and energy consumption in a centralized, systematic and intuitive manner, so as to achieve flexible configuration of energy consumption of various loads and balanced allocation of passenger station energy.

[0239] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0240] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0241] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0242] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A new green passenger station digital intelligence empowerment method, characterized in that: The method comprises the following steps: Receiving the passenger station full life cycle operation data, the passenger station full life cycle operation data including: station basic information, environmental comfort information including seasonal climate, station equipment energy consumption information, multi-dimensional information on station equipment operation status, train reception and dispatching / passenger transport operation information, and station passenger information including passenger flow information, wherein the environmental comfort information, station equipment energy consumption information, multi-dimensional information on station equipment operation status, train reception and dispatching / passenger transport operation information, and station passenger information are associated with station areas and time periods; Based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment in different areas and categories, the corresponding energy consumption independent variables are extracted from the full life cycle operation data for the equipment in different areas and categories in the station, and the optimal energy consumption solution of the equipment in the corresponding area and category is obtained based on the extracted energy consumption independent variables, so as to obtain the optimal power consumption of each area; wherein the dependent variable is the energy consumption information of the station equipment; Based on the optimal power consumption, using a pre-trained time series prediction model to obtain predicted power consumption for each area; By comparing the predicted power consumption of each area with the regional standard power consumption range, a differentiated energy use strategy is generated to achieve digital empowerment of green passenger stations; The method of obtaining the optimal energy consumption solution of the corresponding area and category of equipment based on the extracted energy consumption independent variable, thereby obtaining the optimal power consumption of each area, includes: Based on the multi-task learning algorithm and the extracted energy consumption independent variables corresponding to different areas and categories of equipment in the station, a multi-independent variable model of each category of equipment in different areas is constructed; Splitting the multi-independent variable model to obtain multiple single-independent variable models of equipment of each category in different areas; Use optimization algorithms to find the optimal solution for each single independent variable model; Based on the optimal solutions for the energy consumption of equipment in each area and category and the set impact weights corresponding to each optimal solution, the optimal power consumption of equipment in each area and category is obtained, thereby obtaining the optimal power consumption of each area.

2. The method according to claim 1, characterized in that The basic information of the station includes part or all of the following information: the overall building structure, building materials, building orientation, geographical location and regional climate of the station; The environmental comfort information includes part or all of the following information: weather information, seasonal climate, and in-station environmental information including one or more of temperature, humidity, CO2 concentration, noise, and brightness; The station equipment energy consumption information includes part or all of the following information: equipment historical energy consumption time series data, equipment energy consumption per unit time, energy consumption ratio between equipment and energy utilization rate; The multi-dimensional information of the station equipment operation status includes part or all of the following information: basic information of the equipment, service life of the equipment, operation status of the equipment and maintenance information of the equipment; The train reception and dispatching / passenger transport operation information includes part or all of the following information: passenger transport operation plan, train arrival and dispatching plan, train dispatching plan, water supply and sewage suction operation plan, personnel scheduling plan and equipment inspection plan; The station passenger information includes part or all of the following information: passenger flow information, passenger identity information, passenger location information and passenger inquiry and response information.

3. The method according to claim 2, characterized in that The pre-trained time series prediction model is obtained in the following way: Using the equipment's historical energy consumption time series data, passenger flow information during the corresponding period, and seasonal climate as training data sets, the pre-trained time series prediction model is obtained by iteratively training the time series prediction model; After generating a differentiated energy usage strategy by comparing the predicted power consumption of each region with the regional standard power consumption range, the method further includes: According to the set update frequency of the time series prediction model, the optimization model parameters obtained based on the comparison result of the real-time power consumption generated when the differentiated energy use strategy is executed and the regional standard power consumption range are obtained from the cloud computing platform; Based on the optimization model parameters, the corresponding parameters in the pre-trained time series prediction model are updated, thereby updating the pre-trained time series prediction model to the optimized time series prediction model, so that the predicted power consumption of each area can be obtained by using the optimized time series prediction model later; Wherein, the time series prediction model includes an autoregressive difference moving average model.

4. The method according to claim 1, characterized in that: The optimization algorithm includes a non-dominated sorting genetic algorithm.

5. The method according to claim 1, characterized in that The differentiated energy use strategy is: If the predicted power consumption of the area exceeds the corresponding regional standard power consumption range, the power corresponding to the maximum value of the regional standard power consumption range is used as the distributed power energy of the area, and the power exceeding the maximum value of the regional standard power consumption range is used as the distributed power energy of the energy storage device; If the predicted power consumption of the area is within the standard power consumption range of the corresponding area, the predicted power consumption is used as the allocated power energy of the area; If the predicted power consumption of the area is lower than the corresponding regional standard power consumption range, the power corresponding to the minimum value of the regional standard power consumption range is used as the allocated power of the area, and the power of the difference between the predicted power consumption and the minimum value of the regional standard power consumption range is obtained from the energy storage device; The method further comprises: the area of ​​the passenger station is divided into a ticket sales area, a security inspection area, a ticket inspection area, a waiting area, a platform area, an exit area and a machine room area; For the ticket sales area, security inspection area, ticket checking area and exit area, when the predicted power consumption of the area exceeds the standard power consumption range of the corresponding area, a dynamic resource allocation model for the corresponding area is generated based on the train reception and dispatching / passenger transport operation information, multi-dimensional information on the operation status of station equipment and passenger flow information, and a differentiated allocation plan for the area is generated based on the result of the dynamic resource allocation model to adjust the operation cycle of the resources and equipment in the area and the personnel scheduling plan; wherein the resources and equipment include at least gates, security inspection equipment and ticket sales equipment; the differentiated allocation plan is: if the result of the dynamic resource allocation model is a reduction in resources, then remove the idle resources and equipment in the area and / or reduce personnel scheduling; if the result of the dynamic resource allocation model is that the resources remain unchanged, then adjust the personnel scheduling and / or the working hours of the resources and equipment in the area.

6. The method according to claim 5, characterized in that If the predicted power consumption of the area is lower than the corresponding regional standard power consumption range, the power corresponding to the minimum value of the regional standard power consumption range is used as the allocated power of the area, and the power of the difference between the predicted power consumption and the minimum value of the regional standard power consumption range is obtained from the energy storage device, and also includes: Based on the energy reduction equipment in each area and the minimum power consumption of the energy reduction equipment, the power consumption of the corresponding area is reduced, so that the reduced power consumption is not less than the difference between the predicted power consumption and the minimum value of the regional standard power consumption range; Among them, the energy reduction equipment in the security inspection area is the security inspection equipment, the energy reduction equipment in the platform area is the platform screen, the energy reduction equipment in the waiting area includes air conditioning, broadcasting and display screens, and the energy reduction equipment in the exit area is elevators and escalators.

7. The method according to claim 5, characterized in that The generating of a differentiated energy use strategy by comparing the predicted power consumption of each region with the regional standard power consumption range also includes: Based on the predicted power consumption of each area and the energy allocation ratio of equipment with different uses in the area, the predicted power consumption of equipment in each area and use is obtained; By comparing the predicted power consumption of each region and purpose with the standard power consumption range of the corresponding region and purpose, a differentiated energy use strategy for energy sub-items is generated; where the equipment for different purposes includes lighting and socket electrical equipment, air conditioning and heating electrical equipment, power electrical equipment and special electrical equipment; the regional standard power consumption range is obtained based on the standard power consumption range of each purpose in the region; The differentiated energy use strategy of the energy sub-items is as follows: if the predicted power consumption of the area and purpose exceeds the standard power consumption range of the corresponding area and purpose, the power corresponding to the maximum value of the corresponding standard power consumption range is used as the allocated power of the area and purpose, and the power consumption exceeding the maximum value of the standard power consumption range of the corresponding area and purpose is used as the allocated power of the energy storage device; if the predicted power consumption of the area and purpose is within the standard power consumption range of the corresponding area and purpose, the predicted power consumption is used as the allocated power of the area and purpose; if the predicted power consumption of the area and purpose is lower than the standard power consumption range of the corresponding area and purpose, the power corresponding to the minimum value of the standard power consumption range of the corresponding area and purpose is used as the allocated power of the area and purpose, and the power of the difference between the predicted power consumption of the area and purpose and the minimum value of the standard power consumption range of the corresponding area and purpose is obtained from the energy storage device; The method also includes: evaluating the execution effect of the differentiated energy utilization strategy or the differentiated energy utilization strategy of the energy sub-items based on the set evaluation indicators, and constructing a digital model of a green passenger station based on three-dimensional modeling technology to display the digital empowerment status of the passenger station in real time; wherein the evaluation indicators include some or all of the following indicators: environmental comfort index category, equipment and facility index category, data center index category, personnel-resource and equipment ratio index category, and digital intelligent means index category.

8. A new type of green passenger station digital intelligence empowerment platform, characterized by: The novel green passenger station digital intelligence empowerment platform includes a station-level platform for implementing the method described in any one of claims 1 to 7; The station-level platform sends the station equipment energy consumption information and multi-dimensional information on the station equipment operating status to its own railway bureau-level platform through the railway comprehensive information network and network transmission protocol, so that the railway bureau-level platform can send the periodic station equipment energy consumption information obtained by analyzing the station equipment energy consumption information and multi-dimensional information on the station equipment operating status to the national railway group-level platform.

9. The platform according to claim 8, characterized in that The station-level platform includes: The perception layer is used to obtain passenger station operation data throughout its life cycle from sensors; The transport layer is used to transmit the real-time difference of passenger station operation data throughout its life cycle to the platform layer through the railway integrated information network; The platform layer is used to generate differentiated energy use strategies or differentiated energy use strategies for energy sub-items; The application layer is used to evaluate the execution effect of the differentiated energy use strategy or the differentiated energy use strategy of energy sub-items based on the set evaluation indicators; The display layer is used to build a digital model of a green passenger station based on the full life cycle operation data of the passenger station and combined with 3D modeling technology to demonstrate the digital empowerment of the passenger station; Wherein, the platform layer includes: The data aggregation module is used to receive the passenger station's full life cycle operation data and transmit it to the artificial intelligence module; An artificial intelligence module, for obtaining the optimal power consumption of each area based on the pre-established energy consumption independent variable-dependent variable relationship pairs corresponding to the equipment of different areas and categories, obtaining the predicted power consumption of each area based on the optimal power consumption, and generating a differentiated energy consumption strategy by comparing the predicted power consumption of each area with the regional standard power consumption range, or generating a differentiated energy consumption strategy for energy sub-items by comparing the predicted power consumption of each area and purpose with the standard power consumption range of the corresponding area and purpose; The control and coordination module is used to implement differentiated energy use strategies or differentiated energy use strategies for energy sub-items in combination with passenger operation plans, train arrival and departure plans, and personnel scheduling plans; A carbon asset management module, for obtaining a comparison result by comparing the real-time power consumption when the differentiated energy use strategy is executed with the standard power consumption range of the corresponding region, or by comparing the real-time power consumption when the differentiated energy use strategy of the energy sub-item is executed with the standard power consumption range of the corresponding region and purpose; The intelligent Internet of Things module is used to realize data transmission between the platform layer and the transport layer.

10. A new type of green passenger station digital intelligence empowerment equipment and facilities, characterized by: The device comprises a processor, a memory and a computer program / instruction stored in the memory, wherein the processor is used to execute the computer program / instruction, and when the computer program / instruction is executed, the device implements the steps of the method as described in any one of claims 1 to 7.

Images