Peak reaching path planning method suitable for ship building and repairing enterprises and related equipment

Abstract

The invention provides a peak reaching path planning method suitable for a ship building and repairing enterprise and related equipment, and is applied to the technical field of data processing. According to the method, to-be-assessed enterprise information is processed, and peak-reaching driving parameter information of a to-be-assessed enterprise is generated; processing the regional information of the enterprise to be evaluated, and generating peak reaching measure parameter information of a target region and energy conservation and emission reduction parameter information of the target region; processing the carbon emission information of the to-be-evaluated enterprise in a preset time period, and generating a peak-reaching prediction feature vector; processing a preset peak accounting planning model based on the training sample set with the target feature information to generate a target peak accounting planning model; and processing the peak reaching prediction feature vector, the peak reaching driving parameter information of the to-be-evaluated enterprise, the peak reaching measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area based on a target peak reaching accounting planning model to generate target peak reaching path planning information.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a peak path planning method and related equipment suitable for a shipbuilding and repairing enterprise. Background Art

[0002] In actual application scenarios, energy-saving and low-carbon strategies are diverse, covering multiple fields such as energy efficiency improvement, clean energy substitution, production process optimization, carbon capture and storage, and each field contains many specific technologies and methods.

[0003] There is a widespread problem of information asymmetry in energy-saving technologies and energy-saving equipment in the shipbuilding and repair industry. First, enterprises do not know what energy-saving technologies and equipment are available in the industry. Second, even if the technology is installed, it does not match the current situation of the enterprise and cannot be used. Third, although enterprises have applied individual energy-saving technologies, they lack the design of systematic applications and long-term carbon reduction routes. Various energy-saving technologies such as efficient energy conversion technology, advanced energy storage technology, smart grid technology, and waste heat recovery technology in industrial production are constantly emerging; low-carbon technologies include various clean energy power generation technologies (such as solar energy, wind energy, hydropower, nuclear energy, etc.), low-carbon building materials technology, low-carbon transportation technology, and carbon capture, utilization and storage (CCUS) technology. These technologies have significant differences in principles, application scenarios, technical maturity, cost-effectiveness, etc. In this context, for enterprises that urgently need to plan a scientific carbon reduction path, it is crucial to scientifically and effectively formulate carbon emission execution routes and peak time execution routes for the actual enterprises.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a peak path planning method and related equipment and systems suitable for shipbuilding and repair enterprises, at least to a certain extent, to overcome the problems existing in the prior art, by obtaining the enterprise information to be evaluated, regional information, carbon emission information, preset models and training sample sets. Then, the enterprise information is processed to obtain the peak driving parameter information, the regional information is processed to obtain the peak measures and energy conservation and emission reduction parameter information, and the carbon emission information is processed to obtain the prediction subtask. Then, the feature vector is extracted from the prediction subtask, and the training sample set is processed to obtain a sample set with target feature information. Finally, based on the target peak accounting planning model, the peak prediction feature vector, enterprise and regional related parameters are integrated to generate the energy and industrial structure adjustment path, and then the preset peak path, peak time, peak value and target peak path planning information are obtained.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a peak path planning method suitable for shipbuilding and repair enterprises is provided, including: obtaining information of the enterprise to be evaluated, regional information of the enterprise to be evaluated, carbon emission information of the enterprise to be evaluated within a preset time period, a preset peak accounting planning model and a training sample set; processing the information of the enterprise to be evaluated to generate peak driving parameter information of the enterprise to be evaluated; processing the regional information of the enterprise to be evaluated to generate peak measure parameter information of the target area and energy conservation and emission reduction parameter information of the target area; processing the carbon emission information of the enterprise to be evaluated within a preset time period to generate an interval peak prediction subtask and a sequential access peak prediction subtask; The task and the sequential access peak prediction subtask are processed to generate a peak prediction feature vector; the training sample set is processed to generate a training sample set with target feature information, wherein the target feature information is used to characterize the risk factors of abnormal emission reduction effect; based on the training sample set with target feature information, the preset peak accounting planning model is processed to generate a target peak accounting planning model; based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate target peak path planning information.

[0008] Another aspect of the present application is a peak path planning device suitable for a shipbuilding and repairing enterprise, characterized in that it includes: an acquisition module for acquiring information of the enterprise to be evaluated, regional information of the enterprise to be evaluated, carbon emission information of the enterprise to be evaluated within a preset time period, a preset peak accounting planning model and a training sample set; a processing module for processing the information of the enterprise to be evaluated to generate peak driving parameter information of the enterprise to be evaluated; processing the regional information of the enterprise to be evaluated to generate peak measure parameter information of the target area and energy-saving and emission reduction parameter information of the target area; processing the carbon emission information of the enterprise to be evaluated within a preset time period to generate an interval peak prediction subtask and a sequential access peak prediction subtask; The interval peak prediction subtask and the sequential access peak prediction subtask are processed to generate a peak prediction feature vector; the training sample set is processed to generate a training sample set with target feature information, wherein the target feature information is used to characterize the risk factors of abnormal emission reduction effects; based on the training sample set with target feature information, the preset peak accounting planning model is processed to generate a target peak accounting planning model; based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate target peak path planning information.

[0009] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned peak path planning method applicable to shipbuilding and repairing enterprises by executing the executable instructions.

[0010] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the above-mentioned peak path planning method applicable to a shipbuilding and repairing enterprise is implemented.

[0011] The present application provides a peak path planning method and related equipment suitable for shipbuilding and repair enterprises, in which the server obtains the enterprise information to be evaluated, regional information, carbon emission information, preset model and training sample set. Then, the enterprise information is processed to obtain the peak driving parameter information, the regional information is processed to obtain the peak measures and energy conservation and emission reduction parameter information, and the carbon emission information is processed to obtain the prediction subtask. Then, the feature vector is extracted from the prediction subtask, and the training sample set is processed to obtain a sample set with target feature information. Finally, based on the target peak accounting planning model, the peak prediction feature vector, enterprise and regional related parameters are integrated to generate the energy and industrial structure adjustment path, and then the preset peak path, peak time, peak value and target peak path planning information are obtained.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flow chart showing a peak path planning method applicable to a shipbuilding and repairing enterprise provided by an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a peak path planning device applicable to a shipbuilding and repairing enterprise provided by an embodiment of the present application is shown;

[0015] Figure 3 A peak curve effect diagram provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] Combine the following Figure 1 To describe the peak path planning method applicable to a shipbuilding and repairing enterprise according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0018] In one embodiment, the present application also proposes a peak path planning method and related equipment suitable for shipbuilding and repair enterprises. Figure 1 The following schematically shows a flow chart of a peak path planning method applicable to a shipbuilding and repairing enterprise according to an embodiment of the present application. Figure 1 As shown, the method is applied to a server, comprising:

[0019] S101, obtaining information of the enterprise to be evaluated, regional information of the enterprise to be evaluated, carbon emission information of the enterprise to be evaluated within a preset time period, a preset peak accounting planning model and a training sample set.

[0020] In one implementation, an example of the basic profile information of an enterprise is as follows: Enterprise name: XX Shipbuilding and Repair Factory, type is manufacturing industry (shipbuilding and repair). Enterprise scale: 2,000 employees, covering an area of ​​500,000 square meters, annual turnover of 1 billion yuan, located in coastal areas, close to ports, convenient transportation, but facing pressure from marine ecological protection. Production capacity: 50 ships can be built and 200 ships repaired each year, with diverse products. The complexity of the construction and repair processes of different ships varies, which affects energy consumption and carbon emissions. Equipment situation: There are 5 large docks, 20 cranes, 100 sets of welding equipment, 30 sets of painting equipment, etc. The energy consumption characteristics of each equipment are different, and the energy consumption and carbon emissions of each process of shipbuilding and repair are different, such as high energy consumption in steel pretreatment and VOCs emissions in the painting process.

[0021] Examples of regional information are as follows: Climate: Subtropical monsoon climate, high temperature and heavy rain in summer, mild and little rain in winter, which affects the energy demand of enterprises, such as high energy consumption for cooling in summer and precipitation affecting wastewater treatment. Energy: Rich wind energy resources and scarce traditional energy sources prompt enterprises to consider the use of renewable energy. Geographical location: Located in a developed coastal area, close to ports and transportation hubs, but subject to marine environmental regulations, surrounded by oceans, wetlands and a small amount of forest ecosystems, enterprises need to avoid damaging the ecology during production. The local government has strict marine ecological protection policies, and enterprises need to take environmental protection measures. The flat terrain is conducive to construction and transportation, but there is a risk of sea level rise, and flood control and moisture prevention need to be considered. Developed transportation leads to increased transportation energy consumption and carbon emissions, and enterprises need to optimize logistics. Examples of carbon emission information are as follows: Total amount trend: The total amount of carbon emissions has fluctuated and increased in the past five years, reaching 500,000 tons of carbon dioxide equivalent in 2018 and 600,000 tons in 2022. Carbon emission composition: Direct carbon emissions mainly come from energy combustion in shipbuilding and repair, with diesel combustion accounting for 70%, welding gas emissions accounting for 15%, and coating solvent volatilization accounting for 10%. Indirect carbon emissions mainly come from electricity consumption, accounting for about 30% of total carbon emissions, and are on the rise. The carbon emission intensity per unit of output value is also rising, and enterprises need to strengthen energy conservation and emission reduction.

[0022] The peak accounting planning model is preset. Taking the mixed integer linear programming model as an example, the model can optimize the decision variables (such as energy usage, industrial development scale, etc.) under certain constraints to achieve specific goals (such as the shortest peak time, the lowest peak value, etc.). The carbon emission peak problem of the enterprise is described by constructing the objective function and constraints. The objective function can be set to minimize the peak time or peak value, and the constraints include energy balance constraints (ensuring that energy supply meets demand), industrial development constraints (such as production capacity constraints, market demand constraints, etc.), emission reduction potential constraints (based on the enterprise's technical level and measure implementation capabilities), environmental capacity constraints (in compliance with regional environmental emission standards), etc. For example, the objective function (where is the peak time, is the peak value, and is the weight coefficient, which is determined according to the enterprise's emphasis on the peak time and peak value), and the constraints are such as (indicates that the energy supply in each time period must meet the energy demand of the enterprise, and is the use of the th energy in the th time period).

[0023] Examples of model input and output variables are as follows: Input variables: including enterprise energy consumption data (such as consumption of different energy types), production process parameters (such as production efficiency, energy utilization efficiency, etc.), regional energy supply (such as renewable energy exploitable volume, energy price, etc.), emission reduction measures cost and effect data (such as investment cost and expected emission reduction of a certain energy-saving technology), etc. Output variables: mainly peak time, peak value, and energy use structure at each stage (such as the proportion of coal, electricity, and clean energy used in different time periods), industrial development scale (such as different product output or business segment scale), emission reduction measures implementation plan (such as energy-saving technology or emission reduction projects implemented each year), etc.

[0024] The following is an example of a training sample set: Data of enterprises in the same industry: The relevant data of 100 shipbuilding and repair enterprises are collected. These enterprises are distributed in different regions and of different sizes, covering various types from small shipyards to large shipbuilding enterprises, and are highly representative. Historical data accumulation: including detailed production and operation data, energy consumption data, carbon emission data, and records of energy-saving and emission reduction measures taken by the enterprise in the past 10 years. These historical data can reflect the characteristics and changing trends of the enterprise itself at different stages of development, and provide rich internal information for model training. Enterprise scale characteristics: such as the number of employees, total assets, annual turnover, etc. These characteristics can reflect the production capacity and economic strength of the enterprise, and have an important impact on the carbon emissions and peak path of the enterprise. For example, large enterprises usually have more production equipment and higher energy consumption, but they also have advantages in technology research and development and capital investment, and may be more capable of implementing large-scale energy-saving and emission reduction projects.

[0025] Technical level characteristics: including the advancement of production technology, energy utilization efficiency, and degree of equipment automation. Advanced production technology and efficient equipment can often reduce energy consumption and carbon emissions per unit product. The investment and achievements of enterprises in technological innovation can be reflected through these characteristics, which are also key factors affecting the peak path. Regional characteristics: such as the energy resource endowment of the region where the enterprise is located (the abundance of resources such as coal, natural gas, and renewable energy), the strictness of environmental policies (such as carbon emission standards, environmental protection tax collection standards, etc.), and the level of economic development (regional GDP, per capita income, etc.). Regional characteristics will affect the energy procurement costs, environmental pressures, and market demand of enterprises, thereby affecting the peak strategy of enterprises. Carbon emission-related characteristics: including total carbon emissions, carbon emission intensity, carbon emission source structure, etc. These are the core target characteristics of model training. By analyzing the relationship between these characteristics and other sample characteristics, the model can learn the key factors and laws that affect carbon emissions, thereby predicting the peak path of enterprises under different circumstances.

[0026] S102: Process the enterprise information to be evaluated to generate peak driving parameter information of the enterprise to be evaluated.

[0027] In one implementation, the information of the enterprise to be evaluated is processed to generate the attribute information of the enterprise to be evaluated, wherein the attribute information of the enterprise to be evaluated includes equipment list information, production capacity data information, energy consumption parameters, and production process parameters. An example of equipment list information is as follows: Large docks: 5 in number, with specifications of 300 meters in length, 50 meters in width, and 10 meters in depth, built between 2010 and 2015, using advanced hydraulic systems to control the lifting of docks, the main energy consumption is electricity, which is used for pumping and equipment operation, and the maximum displacement of a single dock is 100,000 tons. Cranes: Types include gantry cranes and tower cranes, a total of 20 units, of which the maximum lifting weight of gantry cranes is 500 tons, and the maximum lifting height of tower cranes is 100 meters, with service life ranging from 5 to 15 years, and energy consumption is mainly electricity, and some old cranes have low energy efficiency. Welding equipment: mainly manual arc welding machines, gas shielded welding machines and submerged arc welding machines, totaling 100 sets. Different welding machines have different welding current and voltage ranges, and are suitable for different welding materials and processes. The energy consumption is electricity. Compared with the old models, the new welding machines have improved energy saving and welding quality. Coating equipment: including 30 sets of high-pressure airless sprayers, electrostatic spraying equipment, etc. The maximum spraying area can reach 500 square meters per hour. The service life of the equipment is 3-10 years. The main energy consumption is electricity. The utilization rate of some equipment needs to be improved, and volatile organic compounds (VOCs) will be generated during operation.

[0028] The following is an example of capacity data information: Shipbuilding capacity: 50 ships of various types can be built each year, including 20 bulk carriers, 15 container ships, 10 tankers, and 5 other special ships. The construction period of different types of ships is different. The average construction period of bulk carriers is 12 months, container ships is 10 months, and tankers is 15 months. The construction period of special ships varies from 18 to 24 months according to specific design and process requirements. Ship repair capacity: 200 ships can be repaired each year, and the main repair business includes hull structure repair, power system maintenance, ship painting renovation, etc. Depending on the degree of damage to the ship and the complexity of the repair, the average repair time for each ship is 1 to 3 months.

[0029] Examples of energy consumption parameters are as follows, energy types and consumption ratios: Electricity consumption accounts for 60% of total energy consumption, mainly used for production equipment operation (such as dock pumping, crane operation, welding equipment power supply, painting equipment drive, etc.), workshop lighting and office electricity. Diesel consumption accounts for 40% of total energy consumption, mainly used for ship trials, transport vehicles and some emergency power generation equipment. Energy consumption intensity: Calculated by energy consumption per unit of output value, in the past year, for every 1 million yuan of output value created by the enterprise, 100,000 kWh of electricity and 50 tons of diesel were consumed. In different production links, the energy consumption intensity varies greatly. For example, the welding link in the shipbuilding process has a higher electricity consumption intensity, while the diesel consumption intensity is higher during the ship trial stage.

[0030] The following are examples of production process parameters: Steel pretreatment process: Shot blasting and paint pretreatment methods are used. The shot blasting speed of the shot blasting equipment is 10-15 meters per minute, and the paint thickness is controlled at 100-200 microns. The energy consumption of this process is mainly concentrated in the motor drive of the shot blasting equipment and the air compression link of the paint spraying equipment. At the same time, a certain amount of waste steel shots and paint residues will be generated. Segment manufacturing process: The ship is assembled and welded in sections at different stations using an assembly line operation method. The welding process mainly uses a combination of gas shielded welding and submerged arc welding. The welding speed is between 30-60 cm per minute according to the plate thickness and weld requirements. The key to quality control of this process lies in the precise adjustment of welding parameters, such as welding current, voltage, welding speed, etc. The energy consumption mainly comes from welding equipment. Slipway closing process: The sections are hoisted to the slipway by a large crane for closing, and high-precision measuring equipment such as a total station is used for positioning and precision control. The energy consumption during the closing process is mainly the operating energy consumption of the crane. At the same time, the construction accuracy and process requirements are high to ensure the overall structural strength and watertightness of the ship. Outfitting process: including the installation of internal equipment, pipeline laying, cable laying and other work. Modular outfitting technology is used to improve outfitting efficiency. However, the installation and commissioning of some complex equipment requires experienced technicians to operate. Energy consumption is relatively low, mainly concentrated in lighting and small power tools. Painting process: a combination of high-pressure airless spraying and electrostatic spraying is used. The coating thickness is between 200-500 microns according to the ship's use environment and anti-corrosion requirements. The environmental impact of the painting process is relatively large, and VOCs emissions are the main problem. At the same time, the utilization rate of the paint and the drying process have a certain impact on energy consumption. For example, the use of hot air drying will consume a lot of electricity.

[0031] The equipment list information, capacity data information, energy consumption parameters and production process parameters are processed to generate the target parameter information of the enterprise to be evaluated and the weight information matching the target parameter information. Examples of target parameter information are as follows: Equipment energy efficiency parameters: According to the equipment type and service life in the equipment list information, combined with energy consumption parameters, the energy utilization efficiency of each equipment is calculated. For example, the energy utilization efficiency of a new crane is 80% (that is, 80% of the input energy is converted into effective working energy), while the energy utilization efficiency of an old crane may be only 60%. For welding equipment, the energy utilization efficiency of different models ranges from 50% to 70%. By statistics and analysis of these equipment energy efficiency parameters, the energy utilization level of the overall equipment of the enterprise can be determined, providing a basis for evaluating the energy conservation and emission reduction potential of the enterprise. Capacity and energy consumption association parameters: Combine capacity data information with energy consumption parameters to calculate the energy consumption per unit product. For example, each construction of a bulk carrier consumes 500,000 kWh of electricity and 200 tons of diesel; each repair of a ship consumes 100,000 kWh of electricity and 50 tons of diesel. These parameters can reflect the energy consumption intensity of enterprises in different production activities, help analyze the relationship between enterprise production efficiency and energy consumption, and provide a reference for formulating targeted energy-saving and emission reduction measures. Process carbon emission parameters: Based on the production process parameters and energy consumption parameters, calculate the carbon dioxide emissions of each production process link. For example, in the steel pretreatment process, the carbon dioxide emissions generated by the shot blasting and rust removal due to electricity consumption are 100 tons per year, and the carbon dioxide emissions generated by the solvent volatilization and energy consumption in the painting process are 200 tons per year; in the slipway assembly process, the carbon dioxide emissions generated by diesel combustion during the crane lifting and segmenting process are 300 tons per year. Through the analysis of process carbon emission parameters, the main sources of carbon emissions of enterprises can be identified, providing direction for optimizing production processes and reducing carbon emissions.

[0032] Example of weight information in Japanese (weights are determined using the analytic hierarchy process), construct a judgment matrix: through data analysis, compare the relative importance of each target parameter information to the enterprise's peak drive, and construct a judgment matrix. Calculate the weight vector: solve the maximum eigenvalue of the judgment matrix and its corresponding eigenvector, and perform normalization to obtain the weight vector. After calculation, the weight of the equipment energy efficiency parameter is 0.25, the weight of the capacity and energy consumption correlation parameter is 0.25, and the weight of the process carbon emission parameter is 0.5. These weights reflect the relative importance of each target parameter information in affecting the enterprise's peak drive, and will play an important role in the subsequent calculation of the peak drive parameter information.

[0033] The target parameter information of the enterprise to be evaluated and the weight information matching the target parameter information are processed to generate the peak driving parameter information of the enterprise to be evaluated. The peak driving parameter calculation example is as follows: Comprehensive parameter calculation: According to the target parameter information and weight information, the peak driving comprehensive parameters of the enterprise are calculated. For example, if the peak driving comprehensive parameter is, then the equipment energy efficiency parameter, the capacity and energy consumption related parameter, and the process carbon emission parameter. If the equipment energy efficiency parameter of an enterprise is 0.7 (indicating that the overall equipment energy utilization efficiency is high), the capacity and energy consumption related parameter is 0.6 (indicating that the unit product energy consumption is at a medium level), and the process carbon emission parameter is 0.8 (indicating that the process carbon emission is relatively high), then the peak driving comprehensive parameter. Driving factor contribution analysis: By calculating the contribution of each target parameter information to the peak driving comprehensive parameter, the key driving factors of the enterprise's peak are analyzed. In the above example, the contribution of the equipment energy efficiency parameter to is, the contribution of the capacity and energy consumption related parameter is, and the contribution of the process carbon emission parameter is. It can be seen that process carbon emission parameters have the greatest impact on the company's peak drive. When formulating peak strategies, companies should focus on optimizing production processes and reducing carbon emissions, such as adopting more environmentally friendly painting processes, improving the energy efficiency of welding processes, etc. At the same time, improving equipment energy efficiency and reasonably matching production capacity and energy consumption are also of great significance, which can be achieved through measures such as equipment renewal and transformation and production process optimization.

[0034] S103, processing the regional information of the enterprise to be evaluated to generate peaking measure parameter information of the target area and energy conservation and emission reduction parameter information of the target area.

[0035] In one implementation, the regional information of the enterprise to be evaluated is processed to generate the natural environment factor information of the target area, the ecosystem factor information of the target area, and the geographical factor information of the target area. Example of natural environment factor information (taking a coastal area as an example), climate conditions: the area belongs to the subtropical monsoon climate, with an annual average temperature of about 22°C, an average temperature of 30°C in summer, and an average temperature of 10°C in winter. The annual precipitation is abundant, with an average precipitation of 1,800 mm, and precipitation is mainly concentrated in summer (May-September), accounting for about 70% of the annual precipitation. The prevailing wind direction changes significantly with the seasons, with southeast winds in summer and northwest winds in winter, with an average wind speed of 3-5 meters per second. This climatic condition has a significant impact on the energy demand of the enterprise. The high temperature in summer prompts the enterprise to increase the cooling energy consumption, while the abundant wind energy resources provide potential for the development of renewable energy. Natural resources: The natural resources in the region are rich and diverse, among which water resources are relatively abundant. There are many rivers running through it, and the annual runoff is about 5 billion cubic meters, which provides a certain guarantee for the production water of the enterprise, but also puts forward requirements for the wastewater discharge and water resource management of the enterprise. In terms of energy resources, in addition to conventional coal, oil and other traditional energy sources that need to be imported from outside, wind and solar energy resources have great potential. It is estimated that the wind energy capacity that can be developed in coastal areas is about 10 million kilowatts, and the annual effective utilization hours can reach more than 2,000 hours; the total annual solar energy radiation is about 5,000 megajoules / square meter, which has good conditions for large-scale development and utilization of solar energy.

[0036] The following is an example of information on ecosystem factors: The types of surrounding ecosystems: There are mainly marine ecosystems, wetland ecosystems and terrestrial forest ecosystems around the area where the enterprise is located. The marine ecosystem is an important ecological asset in the region, with a coastline of 200 kilometers and rich marine biodiversity, inhabited by a variety of fish, shellfish and marine mammals. The wetland ecosystem is distributed at the mouth of the river and the coastal mudflats, covering an area of ​​about 500 square kilometers, and has important ecological functions such as regulating climate, purifying water quality and providing habitats. The terrestrial forest ecosystem is mainly distributed in mountainous areas, with a forest coverage rate of about 30%, which plays a key role in maintaining water and soil, conserving water sources and maintaining regional ecological balance. Ecological protection requirements: Based on the rich ecosystem resources, the local government has introduced strict ecological protection policies. In terms of marine ecological protection, marine ecological protection areas have been delineated, and any activities that may damage the marine ecology are prohibited in the protection areas, such as prohibiting sewage discharge, limiting fishing intensity, and controlling the speed of ships to reduce interference with marine life. For wetland ecosystems, wetland restoration and protection projects have been implemented, requiring enterprises to strictly control wastewater discharge, ensure that the water quality meets the requirements of wetland ecosystems, and avoid damage to wetland ecology. In terms of terrestrial forest ecological protection, a forest felling quota system is implemented. When enterprises carry out infrastructure construction or production activities, if they need to occupy forest land, they must go through strict approval and take corresponding ecological compensation measures.

[0037] Examples of geographical factor information are as follows: Topography: The terrain of this region is mainly plains and hills, with a relatively flat terrain and an altitude between 0 and 500 meters. There are some tidal flats and shallow sea areas in the coastal areas, which are suitable for building ports and developing marine industries. The plain areas have convenient transportation, which is conducive to the construction of factories and logistics transportation for enterprises, but there are also certain flood risks, especially in the rainy season, and enterprises need to strengthen the construction of flood control facilities. The hilly areas are rich in forest resources, but the development and construction are relatively difficult, which has a certain impact on the infrastructure construction and production operation layout of enterprises. Transportation network: The transportation network in the region is well developed, and highways, railways and water transportation are interconnected. The total mileage of highways reaches 5,000 kilometers, and expressways run through the entire territory, connecting major surrounding cities. The railway trunk line connects major domestic railway hubs, with an annual freight volume of 50 million tons. There are many coastal ports, with multiple berths of 10,000 tons or more, and an annual cargo throughput of 200 million tons, which is an important channel for enterprises to import raw materials and export products. The convenient transportation network provides good logistics conditions for the development of enterprises, but it also leads to traffic congestion and increased energy consumption and carbon emissions during transportation. Enterprises need to optimize logistics management and improve transportation efficiency.

[0038] The natural environmental factor information of the target area is processed to generate the assessment information of regional renewable energy resources. The wind energy resource assessment example is as follows: Wind energy resource distribution: Based on meteorological data and field measurements, a wind energy resource distribution map is drawn in the region. The coastal area is determined to be a wind energy resource-rich area with a high annual average wind speed and a wind power density between 300-500 watts / square meter; the wind speed in the inland hilly area is relatively low, and the wind power density is between 100-300 watts / square meter. By analyzing the distribution of wind energy resources, a basis is provided for the site selection of wind power plants. Wind energy development potential estimation: Combined with topography, land use planning and environmental impact assessment, the wind energy installed capacity that can be developed in the region is estimated. Considering that coastal tidal flats and some hilly areas are suitable for the construction of large wind turbines, the total installed capacity that can be developed is expected to be 8 million kilowatts. At the same time, the utilization efficiency of wind energy resources in different wind speed ranges is analyzed to determine the optimal wind turbine selection and layout plan to improve the economic and environmental benefits of wind energy development.

[0039] Examples of solar energy resource assessment are as follows: Analysis of solar radiation: Using meteorological station observation data and satellite remote sensing data, analyze the temporal and spatial distribution characteristics of solar radiation in the region. It is determined that the areas with high total solar radiation throughout the year are mainly concentrated in open areas of plains and hills, with an annual total radiation of 4500-5500 MJ / m2. According to the solar radiation in different regions, the solar energy resource level is divided to provide a reference for the planning of solar photovoltaic power generation projects. Calculation of solar energy utilization potential: Combined with land resource and roof resource surveys, calculate the area that can be used for solar photovoltaic power generation in the region. For example, the roof area of ​​industrial plants is about 1 million square meters, the roof area of ​​residential houses is about 2 million square meters, and the area of ​​wasteland and idle land is about 50 square kilometers. Taking into account factors such as the conversion efficiency and installation inclination of solar panels, it is estimated that the potential annual power generation of solar photovoltaic power generation in the region is 2 billion kWh, which provides data support for enterprises to formulate renewable energy utilization plans.

[0040] The ecosystem factor information of the target area is processed to generate regional restriction parameter information, where the regional restriction parameter information includes industrial structure planning parameter information and enterprise energy conservation and emission reduction potential parameter information. The industrial structure planning parameter information is as follows: Industrial development direction: According to the regional resource endowment and ecological protection requirements, formulate an industrial structure adjustment plan. Clearly focus on the development of low-carbon and green industries such as marine high-end equipment manufacturing, new energy industries, energy-saving and environmental protection industries, and gradually eliminate high-energy-consuming and high-polluting traditional industries such as small-scale chemical industry, printing and dyeing industries. It is planned that in the next five years, the output value share of marine high-end equipment manufacturing industry will be increased from the current 20% to 30%, the output value share of new energy industry will be increased from 10% to 20%, and the output value share of high-energy-consuming industries will be reduced from 30% to below 20%. Industry access threshold: In order to control new carbon emissions, set a strict industry access threshold. For newly introduced projects, it is required that their unit output value energy consumption is lower than 50% of the regional average, and the unit output value carbon dioxide emissions are lower than 60% of the regional average. At the same time, enterprises are encouraged to adopt advanced production processes and technologies to improve resource utilization efficiency. For example, the energy utilization efficiency of new projects is required to reach more than 80% of the industry's advanced level, and the water resource reuse rate is required to reach more than 90%.

[0041] The following are examples of the parameter information of the energy conservation and emission reduction potential of enterprises: Technical improvement potential: Analyze the existing production processes and equipment of the enterprise, and evaluate the potential for energy conservation and emission reduction through technical improvement. Taking shipbuilding and repair enterprises as an example, if new welding technology is adopted, welding efficiency can be improved by 20% and energy consumption can be reduced by 15%; if the coating equipment is upgraded and low-VOCs coatings and efficient spraying processes are adopted, VOCs emissions can be reduced by more than 30%. According to the technical level and equipment conditions of different enterprises, the direction and potential of their technical improvement are determined to provide guidance for enterprises to formulate energy conservation and emission reduction measures. Management optimization potential: Evaluate the optimization space of enterprises in energy management, production management, etc. For example, establishing a sound energy management system can realize real-time monitoring and refined management of energy consumption, and it is expected to reduce energy consumption by 5%-10%. By optimizing the production process, arranging the production plan reasonably, and reducing the idling and standby time of equipment, the production efficiency can be improved by 10%-15%, while reducing energy consumption and carbon emissions. According to the current management status of the enterprise, formulate corresponding management optimization plans to tap the energy conservation and emission reduction potential of the enterprise.

[0042] Process the assessment information of regional renewable energy resources and the parameter information of industrial structure planning to generate the parameter information of peak measures for the target area. The following are examples of energy structure adjustment strategies: Renewable energy development goals: Based on the assessment information of regional renewable energy resources, formulate renewable energy development goals. It is planned to increase the proportion of renewable energy in the energy consumption structure from the current 10% to 30% in the next 10 years. Specific measures include building large offshore wind farms in coastal areas with a total installed capacity of 5 million kilowatts; promoting distributed solar photovoltaic power generation projects in plains and hilly areas with an installed capacity of 2 million kilowatts; at the same time, explore the development and utilization of other renewable energy sources such as biomass energy and geothermal energy, such as building biomass power generation projects and geothermal heating demonstration projects. Traditional energy substitution plan: gradually reduce dependence on traditional high-carbon energy such as coal and oil, and formulate a traditional energy substitution plan. Strengthen cooperation with energy suppliers and increase the supply ratio of clean energy such as natural gas. It is planned to increase the proportion of natural gas in industrial energy consumption from the current 20% to 30% in the next 5 years. Promote clean and efficient coal utilization technologies, such as coal washing and efficient combustion technologies, to reduce carbon emissions during coal use. At the same time, encourage enterprises to carry out energy transformation and use clean energy such as electricity and natural gas to replace coal as production energy.

[0043] Examples of support measures for industrial transformation are as follows: Policy support: The government has introduced a series of policies to support industrial transformation, including fiscal subsidies, tax incentives, and financial support. For enterprises investing in new energy industries and energy-saving and environmental protection industries, a fiscal subsidy of 10%-20% of the total investment will be given; for qualified enterprises, the "three exemptions and two reductions" policy for income tax will be implemented; a green industry development fund will be established to provide enterprises with low-interest loans and financing guarantees, and encourage enterprises to increase investment in low-carbon industries. Technological innovation support: Establish an industry-university-research cooperation platform, strengthen cooperation between enterprises and universities and scientific research institutions, and jointly carry out low-carbon technology research and development and innovation. For example, support enterprises and scientific research institutions to jointly carry out research and development of marine new energy equipment manufacturing technology to improve the independent innovation capabilities of enterprises. Establish a science and technology innovation reward fund to reward enterprises and individuals who have made outstanding achievements in energy-saving and emission reduction technology innovation to stimulate the enthusiasm of enterprises for innovation.

[0044] The geographical factor information of the target area and the parameter information of the energy conservation and emission reduction potential of the enterprise are processed to generate the parameter information of energy conservation and emission reduction in the target area. Examples of energy conservation and emission reduction potential under the influence of geographical factors are as follows: Energy conservation and emission reduction in transportation: formulate energy conservation and emission reduction measures for transportation according to the characteristics of the regional transportation network. Optimize traffic organization, promote intelligent transportation systems, improve traffic operation efficiency, reduce vehicle congestion and idling time, and it is expected to reduce traffic energy consumption by 5%-10%. Encourage the development of public transportation, increase bus routes and buses, and increase the share of public transportation travel. It is planned to increase the share of public transportation travel from the current 30% to 40% in the next three years. At the same time, promote the application of new energy vehicles in the fields of logistics and official vehicles, build supporting facilities such as charging piles, and gradually increase the proportion of new energy vehicles in transportation. Optimize industrial layout: Combine topography and traffic conditions to optimize industrial layout and reduce corporate logistics costs and energy consumption. For example, high-energy-consuming enterprises can be concentrated in areas with convenient energy supply, such as near ports or railway freight stations, to reduce the transportation distance of raw materials and products; low-energy-consuming, high-value-added enterprises can be located around cities or in areas with good ecological environment to form industrial cluster effects and improve resource utilization efficiency. Through the optimization of industrial layout, it is expected that the overall energy consumption of enterprises in the region can be reduced by 5%-8%.

[0045] The following is an example of comprehensive evaluation of the energy conservation and emission reduction potential of enterprises: Setting individual energy conservation and emission reduction targets for enterprises: According to the energy conservation and emission reduction potential parameter information of enterprises, set personalized energy conservation and emission reduction targets for each enterprise. For example, for shipbuilding and repair enterprises with high energy consumption, it is required to reduce energy consumption per unit of output value by 15% and carbon dioxide emissions by 20% in the next three years; for small and medium-sized manufacturing enterprises, according to their production scale and technical level, formulate corresponding energy conservation and emission reduction indicators, such as reducing energy consumption per unit of output value by 10% and carbon dioxide emissions by 15%. Overall planning of regional energy conservation and emission reduction: Comprehensively consider the energy conservation and emission reduction potential of all enterprises in the region, and formulate an overall planning of regional energy conservation and emission reduction. It is expected that through the implementation of the above energy conservation and emission reduction measures, in the next five years, the energy consumption per unit of GDP in the region will be reduced by 20%, and carbon dioxide emissions will be reduced by 25%, achieving the regional energy conservation and emission reduction targets, promoting the green development of the regional economy, and laying a solid foundation for achieving the peak of carbon emissions.

[0046] S104, processing the carbon emission information of the enterprise to be evaluated within a preset time period, and generating an interval peak prediction subtask and a sequential access peak prediction subtask.

[0047] In one embodiment, the carbon emission information of the enterprise to be evaluated within a preset time period is processed to generate a carbon emission trend factor, an interval peak assessment factor, carbon emission target node information, peak sequence information of the carbon emission target node, and peak time information of the carbon emission target node. An example of a carbon emission trend factor (taking the past 5 years as an example) is to perform a linear regression analysis on the carbon emission data of the enterprise in the past 5 years, assuming that the year is the independent variable and the total carbon emission is the dependent variable, and obtain a regression equation. If (unit: 10,000 tons of carbon dioxide / year) is calculated, this indicates that the carbon emission of the enterprise shows a linear growth trend of 50,000 tons of carbon dioxide per year. This coefficient is one of the carbon emission trend factors, reflecting the basic growth trend of the total carbon emission of the enterprise over time. Decompose the annual carbon emission data by quarter or month to observe whether there is obvious seasonal fluctuation. For example, it is found that in the second quarter of each year (April-June), due to the increase in production tasks, the carbon emissions of the enterprise are usually 10%-15% higher than other quarters. This seasonal fluctuation feature is also part of the carbon emission trend factor, which can be used to adjust carbon emissions in different time periods in subsequent forecasts.

[0048] The following is an example of the interval peak assessment factor, which considers the impact of national and local policies on enterprises. For example, the local government implemented a stricter carbon emission quota system in a certain year, requiring enterprises to reduce their carbon emission quotas by 5% each year. This policy factor will be used as an interval peak assessment factor, prompting enterprises to accelerate their emission reduction pace and affect the peak time forecast of enterprises. The energy-saving and emission reduction technology improvement measures taken by the enterprise itself will also affect the peak assessment. For example, if an enterprise invests in a new energy management system in a certain year, it is expected to reduce energy consumption by 10%, thereby reducing carbon emissions. The effect of this technical improvement measure (10% emission reduction) can be used as an interval peak assessment factor, reflecting the change in the enterprise's emission reduction capacity driven by technology, which has a positive impact on the peak forecast.

[0049] The following is an example of carbon emission target node information (taking shipbuilding and repair enterprises as an example), which takes the main production links such as steel pretreatment, block manufacturing, slipway assembly, outfitting, and painting in the shipbuilding process as carbon emission target nodes. For example, the painting link uses a large amount of paint, which will produce volatile organic compounds (VOCs) emissions, which is one of the important sources of carbon emissions for enterprises. Its carbon emissions account for about 20% of the total emissions of enterprises. Therefore, the painting link is taken as a key carbon emission target node, focusing on its emission reduction potential and peak situation. According to the energy consumption structure of the enterprise, electricity consumption and diesel consumption are taken as the main carbon emission target nodes. For example, the enterprise's electricity consumption accounts for 60% of the total energy consumption, which is mainly used for production equipment operation and lighting, and diesel consumption accounts for 40%, which is mainly used for ship trials and transportation vehicles. Analyzing the carbon emissions of these energy consumption nodes will help to formulate targeted energy-saving and emission reduction measures to achieve the peak target.

[0050] The peak sequence information of the carbon emission target nodes is as follows. The peak sequence is determined by analyzing the feasibility of emission reduction technology, cost-effectiveness and other factors of each carbon emission target node. For example, for shipbuilding and repair enterprises, it may start with the power consumption node, which is relatively easy to achieve emission reduction. By optimizing equipment operation and adopting energy-saving equipment, it is expected that the carbon emissions of the power consumption node will reach a peak and begin to decline in the next 2-3 years; for the painting link, due to complex issues such as process improvement and coating substitution, it may take 3-5 years to achieve carbon emission peak, so the power consumption node is ranked before the painting link to achieve peak. Combined with the order of the enterprise's production process, determine the peak sequence of carbon emission target nodes. For example, in the shipbuilding process, the steel pretreatment link is at the front end of the production process, and its carbon emission peak will affect the carbon emissions of subsequent production links. Therefore, priority is given to achieving the peak of the steel pretreatment link earlier, followed by segmented manufacturing, slipway assembly and other links, to ensure that the carbon emissions of the entire production process gradually reach the peak and decline in an orderly manner.

[0051] The peak time information of the carbon emission target node is as follows. Assuming that the company plans to comprehensively upgrade and transform the main production equipment in the next three years, it is expected that the energy efficiency of the equipment after the transformation can be improved by 20%, which will bring forward the peak time of some carbon emission target nodes (such as power consumption nodes). According to the equipment transformation plan and the expected emission reduction effect, it is calculated that the power consumption node may reach the carbon emission peak in 2 years, which is 1 year earlier than if the transformation plan was not implemented. If the company predicts that the market demand for environmentally friendly ships will increase in the future, it will prompt the company to accelerate the improvement of production processes and the implementation of emission reduction measures to meet market demand. For example, in order to enter the environmentally friendly ship market in advance, the company decided to replace all high-VOCs paints in the coating process with low-VOCs environmentally friendly paints in the next two years. This will bring forward the peak time of carbon emissions in the coating link to 1.5 years later, about 1 year earlier than originally planned.

[0052] The carbon emission trend factor and the interval peak assessment factor are processed to generate the interval peak prediction subtask. The prediction example based on the trend factor and the assessment factor is as follows. According to the carbon emission trend factor (such as the linear growth trend), it is assumed that in the absence of other major influencing factors, the future carbon emissions are predicted according to the current growth rate. For example, based on the trend of an increase of 50,000 tons of carbon dioxide per year in the past five years, the total carbon emissions in the next three years are predicted to be the current emissions plus,, and tons of carbon dioxide respectively. However, the impact of the interval peak assessment factor (such as the policy requirement to reduce the carbon emission quota by 5% each year) should be considered at the same time, and the prediction results should be adjusted. In this case, the total carbon emissions in the first year of the forecast are the current emissions plus 10,000 tons of carbon dioxide, and then multiplied by to obtain the adjusted forecast value. The forecast emissions for the next 2-3 years are calculated by analogy, thereby generating the interval peak prediction subtask, that is, focusing on how carbon emissions gradually approach the peak and achieve the peak target in each time period under the policy and the efforts of the enterprise itself, as well as the possible peak time range.

[0053] Consider the carbon emission trends and changes in evaluation factors under different scenarios. For example, set a baseline scenario (development in accordance with the existing trend), a policy strengthening scenario (the government introduces stricter policies), and a technological breakthrough scenario (the enterprise achieves a major breakthrough in energy conservation and emission reduction technology). In the policy strengthening scenario, assume that the reduction in carbon emission quotas increases from 5% to 8% per year, and recalculate the future carbon emission forecast; in the technological breakthrough scenario, assume that the enterprise adopts a new clean energy alternative technology that can reduce carbon emissions by 20%, and adjust the forecast results again. Through the analysis of different scenarios, multiple interval peak prediction subtasks are generated to provide a reference for enterprises to formulate peak strategies to deal with different situations. For example, in the policy strengthening scenario, enterprises need to speed up the implementation of emission reduction measures to adapt to stricter policy requirements; in the technological breakthrough scenario, enterprises can optimize the peak path according to the time nodes and effects of technology application.

[0054] The carbon emission target node information, the peak sequence information of the carbon emission target node, and the peak time information of the carbon emission target node are processed to generate a sequential access peak prediction subtask. The prediction example based on the target node information is as follows. According to the peak sequence information of the carbon emission target node, the peak time and peak value are predicted for each node in turn. Taking the steel pretreatment node as an example, combined with its current carbon emission level, emission reduction measures plan (such as the use of more efficient rust removal equipment) and peak time expectation (such as peaking in 2 years), the carbon emission change curve of the node in each time period in the future is predicted to determine its carbon emission peak value when it peaks. Then, according to the production process sequence, similar predictions are made for nodes such as segment manufacturing, slipway assembly, outfitting, and painting, and a sequential access peak prediction subtask is generated, that is, the process of simulating the peak of each key node in the production process of the enterprise in turn is achieved, and the mutual influence between the nodes and the feasibility of the overall peak path are analyzed.

[0055] Consider the interrelationships between carbon emission target nodes. For example, emission reduction measures in the painting process (such as the use of environmentally friendly paints) may affect the production efficiency and energy consumption of the outfitting process, thereby affecting its carbon emissions. When predicting the peak of the painting process, it is necessary to comprehensively consider this correlation effect. At the same time, when predicting the peak of the outfitting process, the impact of emission reduction measures in the painting process should also be included in the analysis. Through this node correlation analysis, the peak time and peak value of each node can be predicted more accurately, and a sequential access peak prediction subtask that is more in line with actual production conditions can be generated, which provides a basis for enterprises to formulate comprehensive and effective peak plans, ensuring that in the process of achieving the peak of each node, the overall carbon emissions of the enterprise can reach the peak in an orderly and efficient manner and achieve subsequent declines.

[0056] S105, processing the interval peak prediction subtask and the sequential access peak prediction subtask to generate a peak prediction feature vector.

[0057] In one implementation, feature extraction processing is performed on the interval peak prediction subtask to generate access time interval sequence features, access interval number features, and access interval information features. Generate an access time interval sequence feature example (assuming quarterly time intervals), assuming that the carbon emission data of the enterprise in the past five years (2018-2022) is counted quarterly, with the first quarter of 2018 as the starting point, and the time interval sequence is 1-20 (a total of 20 quarters). For each quarter, calculate the time interval with the starting point (such as the interval of 2 in the second quarter of 2018, the interval of 5 in the first quarter of 2019, etc.), and record the total carbon emissions of the quarter. For example, when the time interval is 2 (the second quarter of 2018), the total carbon emissions are 100,000 tons, and when the time interval is 5 (the first quarter of 2019), the total carbon emissions are 120,000 tons, etc. These time intervals and the corresponding total carbon emissions data constitute the access time interval sequence feature, which reflects the changes in carbon emissions at different intervals over time, and helps to analyze the long-term trend and seasonal fluctuations of carbon emissions.

[0058] The following is an example of generating access interval number features. Taking the above quarterly data as an example, an access interval number is assigned to each quarter, such as 1-4, which represents the four quarters of each year (1 is the first quarter, 2 is the second quarter, etc.). For each quarter's carbon emission data, in addition to recording its time interval series features, the quarter number to which it belongs is also recorded. For example, the access interval number for the first quarter of 2018 is 1, and the total carbon emissions are 80,000 tons; the access interval number for the second quarter of 2018 is 2, and the total carbon emissions are 100,000 tons, etc. The access interval number feature can help identify the regularity of carbon emission data in different seasons or specific time periods, such as whether there are quarterly differences (for example, some companies have higher carbon emissions during the peak production season in the second quarter, and the corresponding interval data numbered 2 may show higher values).

[0059] The following is an example of generating access interval information features. Access interval information features can contain more detailed information about carbon emissions in each time interval. In addition to the total carbon emissions, the growth rate of carbon emissions and the change compared with the previous interval can also be considered. For example, the growth rate of total carbon emissions in the second quarter of 2018 relative to the first quarter of 2018 is 25%, and the change is 10-8 = 20,000 tons; the growth rate of total carbon emissions in the first quarter of 2019 relative to the fourth quarter of 2018 is 33.3%, and the change is 12-9 = 30,000 tons, etc. These growth rate and change data combined with the time interval sequence and numbering features can more comprehensively describe the dynamic changes in corporate carbon emissions and provide richer information for subsequent analysis.

[0060] The access interval information features are processed to generate adjacent interval difference sequence information, difference sequence mean, and difference sequence variance. An example of generating adjacent interval difference sequence information is as follows. Based on the total carbon emission change data in the above access interval information features, the adjacent interval difference sequence is calculated. For example, the total carbon emission change between the second quarter and the first quarter of 2018 is 20,000 tons, and the total carbon emission change between the third quarter and the second quarter of 2018 is 15,000 tons (assuming), then the adjacent interval difference sequence is 2, 1.5, etc. This difference sequence reflects the increase and decrease trend of the total carbon emissions in adjacent time intervals, which helps to analyze the stability and rate of change of carbon emissions. For example, if the difference sequence fluctuates less, it means that the carbon emissions are growing more steadily, otherwise it means that the change is larger.

[0061] The following is an example of calculating the mean and variance of the difference sequence. The mean of the adjacent interval difference sequence is calculated. Assuming that the above difference sequence 2, 1.5, etc. has a total of 19 data (because there are 20 time intervals and 19 adjacent interval differences), these data are added and divided by 19 to get the mean. For example, the mean is 18,000 tons (assumed), which represents the average change in the total carbon emissions between adjacent quarters in the past five years, which can be used as an important indicator to measure the trend of carbon emissions. When calculating the variance, the average square of the difference between each difference and the mean is calculated according to the variance formula. The variance reflects the degree of dispersion of the adjacent interval differences. A small variance indicates that the change in the total carbon emissions between adjacent quarters is relatively stable, while a large variance indicates that the change is more drastic and may be affected by some special factors (such as production process adjustments, market demand fluctuations, etc.).

[0062] The sequential access peak prediction subtask is subjected to dimensionality reduction processing to generate a one-dimensional prediction feature vector. The one-dimensional prediction feature vector is subjected to feature extraction processing to generate target access list information, the mean of the adjacent access information similarity sequence, and the variance of the adjacent access information similarity sequence. An example of generating a one-dimensional prediction feature vector (using the principal component analysis PCA method) is given. Assume that in the sequential access peak prediction subtask, multiple characteristic variables of the enterprise in different production links (such as raw material procurement, production and processing, product transportation, etc.) are considered, such as energy consumption, raw material usage, pollutant emissions, production efficiency, etc. Each link has 5 characteristic variables, and there are 3 links in total. The original data is a 3×5 matrix. Through the PCA method, this multidimensional data is projected into a one-dimensional space to obtain a one-dimensional prediction feature vector. For example, after PCA calculation, the one-dimensional prediction feature vector obtained is [0.5, 0.3, 0.2] (assumption). This vector integrates the information of the original multiple characteristic variables and represents the overall characteristics of the enterprise in the production process in a new way, which is convenient for subsequent integration and analysis with other features. At the same time, it reduces the complexity of the data and highlights the main information.

[0063] Generate a target access list information example (taking the production link as an example), determine the key target access nodes or links according to the company's production process and carbon emissions, and form the target access list information. For example, for shipbuilding and repair companies, steel pretreatment, welding, painting and other links are identified as key target access nodes because these links have a greater impact on carbon emissions. Record the relevant information of these nodes in the target access list, such as the node name, the expected carbon emission peak (estimated based on historical data and prediction models, such as the steel pretreatment link is expected to reach a peak of 50,000 tons, the welding link is 30,000 tons, the painting link is 40,000 tons, etc.), and the peak time range (such as the steel pretreatment link is expected to peak in the next 2-3 years, and the welding link is expected to peak in 1-2 years, etc.). The target access list information provides a focus for subsequent analysis, which helps to formulate emission reduction measures and peak strategies in a more targeted manner.

[0064] Calculate the similarity between adjacent access nodes. For example, use the cosine similarity method to calculate the similarity between the steel pretreatment link and the welding link in terms of energy consumption, carbon emissions and other characteristics. Assume that the similarity between the two is calculated to be 0.6, and then calculate the similarity between the welding link and the painting link to be 0.4, etc., to form an adjacent access information similarity sequence [0.6, 0.4] (assumption). The mean of the similarity sequence is calculated to be 0.5 and the variance is 0.01 (assumption). The mean reflects the average level of similarity between adjacent access nodes, and the variance indicates the degree of dispersion of the similarity. A smaller variance indicates that the similarity between adjacent nodes in terms of characteristics is relatively stable, while a larger variance indicates that there are large differences between adjacent nodes. This helps to analyze the correlation and change patterns between different links in the enterprise production process, and provides a basis for optimizing the production process and emission reduction measures.

[0065] The visit time interval sequence features, visit interval number features, visit interval information features, target visit list information, the mean of the adjacent visit information similarity sequence and the variance of the adjacent visit information similarity sequence are processed to generate the peak prediction feature vector. The visit time interval sequence features (such as the total carbon emission of 100,000 tons when the time interval is 2), visit interval number features (such as quarterly numbers and corresponding carbon emission data), visit interval information features (such as carbon emission growth rate, change, etc.), target visit list information (such as key nodes and related parameters), and the mean (such as 0.5) and variance (such as 0.01) of the adjacent visit information similarity sequence generated above are integrated. For example, construct a vector [10, 2, 0.25, 5, 0.5, 0.01] (where 10 is the total carbon emissions at a time interval of 2, 2 is the corresponding quarter number, 0.25 is the carbon emissions growth rate of this quarter relative to the previous quarter, 5 is the expected carbon emissions peak value in the steel pretreatment stage, 0.5 is the mean of the similarity sequence of adjacent access information, and 0.01 is the variance). This vector is the peak prediction feature vector. It combines various key information extracted from the interval peak prediction subtask and the sequential access peak prediction subtask, and can fully reflect the characteristics and trends of corporate carbon emissions, providing an important data basis for model-based peak prediction and formulation of emission reduction strategies.

[0066] S106, processing the training sample set to generate a training sample set with target feature information, wherein the target feature information is used to characterize risk factors that indicate an abnormal emission reduction effect.

[0067] In one implementation, the training sample set is grouped to generate a grouped training sample set, wherein the grouped training sample set includes peak feature information of different regions and enterprises. The collected training samples are grouped according to different regions, for example, into the eastern coastal region, the central region and the western region. The eastern coastal region may have a developed economy, advanced technology and relatively strict environmental protection policies. The market competition faced by enterprises in the region is fierce, and the acceptance of energy-saving and emission reduction technologies is high, but the land and energy costs are also relatively high; the economic development in the central region is at a medium level, the industrial structure is being adjusted and optimized, and some enterprises face certain challenges in technology upgrading and energy conservation and emission reduction; the western region is rich in resources but the economy is relatively underdeveloped, and some enterprises may need to improve energy efficiency and environmental awareness. Through this regional division, the differences in the peak characteristics of enterprises in different regional environments can be analyzed. For example, enterprises in the eastern coastal region may be more inclined to adopt clean energy and advanced environmental protection technologies to achieve carbon emissions peak, and their peak time may be relatively early, while enterprises in the western region may be limited by economic and technical conditions, and the peak time is relatively late.

[0068] Enterprises are grouped according to their industry and size, such as large manufacturing enterprises (such as shipbuilding and repair, steel production, etc.), small manufacturing enterprises (such as mechanical processing, plastic products, etc.) and service industry enterprises (such as logistics and transportation, software development, etc.). The production and operation models and carbon emission characteristics of different types of enterprises are very different. Large manufacturing enterprises usually have large energy consumption and high total carbon emissions, but they also have strong financial and technical strength to implement energy-saving and emission reduction measures; although small manufacturing enterprises have relatively low total carbon emissions, they may have high carbon emissions per unit of output value due to limited technology and management level; carbon emissions of service industry enterprises are mainly concentrated in energy consumption (such as office electricity, transportation, etc.), which is different from the sources of carbon emissions and emission reduction methods of manufacturing enterprises. This grouping helps to formulate personalized peak strategies for different types of enterprises. For example, large manufacturing enterprises focus on improving production processes and adjusting energy structures, small manufacturing enterprises focus on improving management efficiency and adopting small energy-saving equipment, and service industry enterprises mainly start from optimizing operation management and promoting green office methods.

[0069] Taking large manufacturing enterprises in the eastern coastal areas as an example, this group of samples contains relevant data of multiple enterprises. For example, Enterprise A is a shipbuilding and repair enterprise. Its peak characteristic information includes that its total carbon emissions have shown a trend of rising first and then stabilizing in the past 10 years, reaching a relatively high plateau around 2015, and is currently striving to achieve carbon emissions peak through technological transformation and energy transformation; Enterprise B is a steel production enterprise, whose total carbon emissions have been at a high level for a long time in the past. In recent years, with the strengthening of environmental protection policies, it has gradually taken a series of emission reduction measures, such as waste heat recovery and the use of high-efficiency desulfurization and denitrification equipment, and is expected to achieve carbon emissions peak in the next few years. The peak characteristic information of these enterprises (carbon emission trends, implementation of emission reduction measures, peak expectations, etc.) constitutes the training sample set of this group of large manufacturing enterprises in the eastern coastal areas, providing a rich data basis for subsequent analysis, which can reflect the commonalities and characteristics of this region and enterprise type in the process of carbon emissions peaking.

[0070] The grouped training sample set is processed for feature extraction to generate the original feature library. The extracted features are as follows: Enterprise scale features: including total assets, number of employees, annual turnover, etc. Total assets reflect the economic strength and production scale of the enterprise. Enterprises with larger total assets usually have greater capabilities in equipment renewal, technology research and development, and energy conservation and emission reduction project investment; the number of employees affects the energy consumption and carbon emission levels of the enterprise. For example, labor-intensive enterprises may generate more carbon emissions in terms of commuting and office electricity consumption; annual turnover is closely related to the production and operation activities of the enterprise. Enterprises with high turnover may mean higher production intensity and energy demand, and also have stronger capital recovery capabilities to support energy conservation and emission reduction work. Energy consumption characteristics: involving total energy consumption, energy consumption structure (such as the proportion of different energy sources such as coal, oil, natural gas, and electricity), energy consumption per unit of output value, etc. The total energy consumption is directly related to the total carbon emissions and is an important indicator for measuring the carbon emission level of an enterprise. The energy consumption structure reflects the degree of dependence of an enterprise on different energy sources. For example, an energy structure dominated by coal usually leads to higher carbon emissions, while increasing the proportion of clean energy use will help reduce carbon emissions. Energy consumption per unit of output value reflects the energy utilization efficiency of the enterprise. Enterprises with low energy consumption per unit of output value have better performance in energy conservation and emission reduction, and are more likely to achieve carbon emissions peak earlier.

[0071] Production process characteristics: covers the advancement of production technology, the complexity of production process, the degree of automation of equipment, etc. Advanced production technology can often improve the utilization rate of raw materials, reduce energy consumption and reduce pollutant emissions. For example, the use of advanced intelligent manufacturing technology can achieve precise production, reduce energy waste and waste generation; the complexity of the production process affects the energy consumption and carbon emission distribution of the enterprise. Complex production processes may lead to more energy consumption and carbon emissions in the intermediate links; enterprises with high degree of equipment automation can more accurately control energy consumption in the production process, improve production efficiency, and reduce energy waste and carbon emissions caused by human factors. Regional environmental characteristics: including regional energy supply stability, strictness of environmental policies, and regional economic development level. The stability of regional energy supply affects the energy procurement cost and energy structure adjustment strategy of enterprises. Regions with stable and diversified energy supply are conducive to enterprises choosing cleaner and more efficient energy; the strictness of environmental policies is an important driving force for enterprises to implement energy conservation and emission reduction measures. Strict policies will prompt enterprises to increase environmental protection investment and improve production processes; the level of regional economic development is closely related to the market demand, technological innovation capabilities and environmental awareness of enterprises. Enterprises in economically developed regions usually pay more attention to sustainable development and have stronger initiative and ability in energy conservation and emission reduction.

[0072] The example of generating the original feature library is as follows: the above-mentioned various features extracted from different grouping samples are integrated to form the original feature library. For example, for the group of large manufacturing enterprises in the eastern coastal areas, the enterprise scale characteristics of enterprises A and B (such as enterprise A with total assets of 10 billion yuan, 5,000 employees, and annual turnover of 8 billion yuan; enterprise B with total assets of 20 billion yuan, 8,000 employees, and annual turnover of 12 billion yuan, etc.), energy consumption characteristics (enterprise A with a total energy consumption of 500,000 tons of standard coal, coal accounting for 30%, electricity accounting for 40%, and unit output value energy consumption of 0.6 tons of standard coal / 10,000 yuan; enterprise B with a total energy consumption of 800,000 tons of standard coal, coal accounting for 40%, electricity accounting for 30%, and unit output value energy consumption of 0.8 tons of standard coal / 10,000 yuan, etc.), production process characteristics (enterprise A with a production process advancement score of 7 points, a high degree of complexity in the production process, and a degree of equipment automation of 80%; enterprise B with a production process advancement score of 8 points, a high degree of complexity in the production process, and a degree of equipment automation of 90%, etc.) and regional environmental characteristics (the eastern coastal areas have stable energy supply, strict environmental policies, and a high level of economic development). The same feature extraction and integration are also performed on other groups (such as small manufacturing enterprises in the central region, service industry enterprises in the western region, etc.), and finally an original feature library containing the sample features of all groups is formed, providing comprehensive data support for subsequent model training and analysis.

[0073] The original feature library is processed to generate training sets and validation sets. Usually 70%-80% of the data is used as the training set, and 20%-30% of the data is used as the validation set. For example, in the original feature library with a total of 1,000 samples, 700 samples are randomly selected as the training set to train the prediction model so that the model can learn the relationship between the features and the emission reduction effect; the remaining 300 samples are used as the validation set to evaluate and adjust the model during the training process to prevent the model from overfitting, ensure that the model has good generalization ability, and can accurately predict the emission reduction effect of new data. When dividing the training set and validation set, it is necessary to ensure that the distribution of the data is representative, that is, the proportion of each type of sample (different regions, enterprise types, etc.) in the training set and validation set is roughly the same as the proportion in the original feature library. For example, in the original feature library, samples of large manufacturing enterprises in the eastern coastal areas account for 30%, samples of small manufacturing enterprises in the central region account for 40%, and samples of service industry enterprises in the western region account for 30%. Then in the training set and validation set after division, the proportions of these three types of samples should be as close to 30%, 40% and 30% as possible to ensure that the model can fully learn the characteristics and rules of different types of samples and improve the accuracy and reliability of the model.

[0074] Based on the classifier, the validation set is predicted and processed to generate prediction results. Based on the preset algorithm, the training set is trained and processed to generate prediction results for the validation set. The decision tree classifier is selected to perform prediction processing on the validation set. The decision tree classifier classifies data by constructing a tree structure, and makes judgments on the nodes of the tree according to the characteristic values ​​of the samples (such as enterprise scale characteristics, energy consumption characteristics, etc.), and gradually classifies the samples into different categories (such as good emission reduction effect, general, poor, etc.). For example, for an enterprise sample in the validation set, the decision tree classifier first judges based on its total energy consumption. If the total energy consumption is high (greater than a certain threshold), it further judges based on the proportion of coal in its energy consumption structure. If the proportion of coal is also high, it is judged based on the strictness of the environmental policy in the area where the enterprise is located. Finally, the enterprise sample is classified into the corresponding emission reduction effect category and the prediction result is generated. The prediction result can be expressed as the probability that each sample belongs to different emission reduction effect categories. For example, the probability that a certain enterprise sample belongs to the good emission reduction effect category is 0.3, the probability that it belongs to the general category is 0.5, and the probability that it belongs to the poor category is 0.2.

[0075] The training set is trained using the support vector machine algorithm. The support vector machine algorithm classifies the data by finding an optimal hyperplane, mapping the samples in the training set to a high-dimensional space, so that the intervals between samples of different categories are maximized. During the training process, the parameters of the hyperplane are adjusted according to the characteristics of the samples (such as enterprise scale, energy consumption, production process, and regional environment) and the corresponding emission reduction effect labels (such as emission reduction targets have been achieved, emission reduction targets have not been achieved, etc.), so that the hyperplane can accurately separate samples of different categories. For example, for the enterprise samples in the training set, the enterprise scale characteristics (total assets, number of employees, etc.), energy consumption characteristics (total amount, structure, unit output value consumption, etc.), production process characteristics (advancedness, complexity, degree of automation, etc.) and regional environmental characteristics (energy supply, policy, economic level, etc.) are used as input vectors, and the corresponding emission reduction effect labels are used as outputs. The parameters of the hyperplane are calculated by the support vector machine algorithm, so that a high classification accuracy can be achieved on the training set. After training, the trained model is used to predict the validation set, and the prediction results of the validation set are generated, which are compared and analyzed with the prediction results based on the classifier.

[0076] The prediction results and the validation set prediction results are processed to generate target feature information, which is used to characterize the risk factors of abnormal emission reduction effects. The prediction results based on the classifier (such as the decision tree classifier) ​​and the validation set prediction results based on the preset algorithm (such as the support vector machine algorithm) are compared. For example, it is found that for some enterprise samples, the decision tree classifier predicts that their emission reduction effect is good, but the support vector machine algorithm predicts that their emission reduction effect is average. Further analysis of the characteristics of these samples found that it may be because these enterprises have some special circumstances in terms of production process characteristics, such as the use of a new but not widely used energy-saving production process. When processing this new feature, the decision tree classifier may cause prediction deviation due to imperfect rules, while the support vector machine algorithm can better capture the complex relationship between this feature and emission reduction effect in high-dimensional space.

[0077] According to the difference analysis of the prediction results, the risk factors that characterize the abnormal state of emission reduction effect are determined as the target characteristic information. For example, for the above-mentioned enterprise samples that adopt new energy-saving production processes but have different prediction results, "uncertainty in the application and effect of new energy-saving production processes" is determined as a target characteristic information. In addition, if it is found that the emission reduction effect prediction of the enterprise is fluctuating greatly during the adjustment of the energy consumption structure (such as the transition from a high proportion of coal to a high proportion of clean energy), then "instability during the energy structure transformation process" can also be used as the target characteristic information. These target characteristic information can help enterprises and decision makers pay more attention to and solve key issues that may lead to abnormal emission reduction effects, such as strengthening the monitoring and evaluation of new energy-saving production processes, optimizing energy structure transformation strategies, etc., so as to improve the effectiveness and reliability of energy conservation and emission reduction work, which echoes the overall content of the document on using target characteristic information to improve the peak accounting planning model, and provides strong support for achieving scientific and reasonable carbon emission peaking and neutralization.

[0078] S107, processing the preset peak accounting planning model based on the training sample set with target feature information to generate a target peak accounting planning model.

[0079] In one embodiment, the training sample set with target feature information contains risk factors that can characterize the abnormal state of emission reduction effect. These risk factors are obtained by analyzing different prediction results, such as the characteristics corresponding to the prediction deviations that occur in certain enterprises during the adjustment of specific production processes or energy structures. When optimizing the preset peak accounting planning model, these target feature information can be used as a key reference basis, so that the model pays more attention to these factors that may affect the emission reduction effect, thereby improving the adaptability and accuracy of the model to complex actual situations.

[0080] It is assumed that the preset peak accounting planning model was originally a model based on linear regression, which is used to predict the peak time and peak emissions of enterprises. After introducing the training sample set with target feature information, it was found that during the energy structure transformation period (such as the transition from a high proportion of coal to a high proportion of clean energy), the prediction of the emission reduction effect of enterprises was greatly deviated from the actual situation, and "instability in the process of energy structure transformation" was identified as one of the target feature information. In view of this situation, the model is adjusted to increase nonlinear terms related to the energy structure transformation. For example, the square or cubic term of the energy structure change rate is introduced to better capture the nonlinear relationship in the process of energy structure transformation. At the same time, the weight of the model is redistributed according to the target feature information to increase the importance of characteristic variables related to the energy structure transformation (such as changes in the proportion of clean energy, the speed of energy transformation, etc.) in the model.

[0081] Using the adjusted model, the training sample set with target feature information is used for training again. During the training process, the model parameters are optimized by minimizing the prediction error (such as mean square error). After multiple iterations of training, the model is evaluated using the validation set. For example, the evaluation indicators may include accuracy (the proportion of samples predicted correctly by the model), recall (the proportion of samples that are actually positive and predicted as positive by the model), and F1 value (an indicator that comprehensively considers accuracy and recall), etc. If it is found that after the model is optimized, the accuracy of the emission reduction effect prediction for energy structure transformation enterprises has increased from the original 70% to 80%, the recall rate has increased from 60% to 70%, and the F1 value has increased from 0.65 to 0.75, it means that after considering the target feature information, the model's prediction ability for such enterprises has been significantly improved, and the model has been effectively optimized, thereby generating a more accurate and targeted target peak accounting planning model, which can better provide a reliable basis for enterprises to formulate peak path planning.

[0082] S108, based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate target peak path planning information.

[0083] In one implementation, based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area, and the energy conservation and emission reduction parameter information of the target area are processed to generate an energy structure adjustment path and an industrial structure transformation path. Figure 3From the content shown, it can be seen that, assuming that the current energy structure of the enterprise to be evaluated is mainly based on traditional fossil energy such as coal and diesel, coal accounts for 50% of the total energy consumption, diesel accounts for 30%, and electricity accounts for 20%. From the peak curve effect diagram, this energy structure leads to a high level of carbon emissions for enterprises and a significant growth trend. For example, in 2020 (corresponding to the starting time in the figure), the total carbon emissions are high and the slope is large. Based on the target peak accounting planning model, combined with the regional renewable energy resource assessment information (such as the rich wind and solar energy resources in the region), the energy structure adjustment path is formulated. It is planned to gradually increase the proportion of clean energy in the energy consumption structure in the next five years. Specific measures include: in the first two years, investing in the construction of solar photovoltaic power generation systems within the enterprise, which is expected to increase the proportion of solar power generation by 5% each year, while reducing the proportion of coal use by 3%; in the third and fourth years, cooperating with local energy suppliers to introduce wind power generation, gradually increase the proportion of wind power generation to 15%, and further reduce the proportion of coal and diesel use to 30% and 20% respectively; in the fifth year, continue to optimize the energy structure, so that the proportion of solar power generation reaches 20%, the proportion of wind power generation reaches 25%, the proportion of coal use drops to 20%, the proportion of diesel use drops to 10%, and the proportion of electricity (including solar power, wind power generation and external purchases) increases to 50%. Through such an adjustment path, it can be seen from the peak curve effect diagram that the growth trend of carbon emissions is gradually slowing down, and it is expected to reach a peak in carbon emissions and begin to decline in the later period.

[0084] The following is an example of the transformation path of the industrial structure. The enterprise to be evaluated is currently mainly engaged in traditional high-energy-consuming industries, such as steel production, with low industrial added value and high carbon emissions per unit of output value. From the peak curve effect diagram, it can be seen that this industrial structure makes the total carbon emissions of enterprises remain high, and under the current market and policy environment, it will be difficult to achieve the carbon emission peak target if the existing industrial structure is maintained. According to the industrial structure planning parameter information of the target area (such as the local government encourages the development of low-carbon industries such as new energy equipment manufacturing, energy-saving and environmental protection industries), the enterprise plans the transformation path of the industrial structure. In the next 3-5 years, some backward steel production capacity will be gradually eliminated, and steel production will be reduced by 10% each year. At the same time, the existing plant and equipment foundation will be used to transform and develop the new energy equipment manufacturing industry, such as wind turbine parts manufacturing. In the first two years, we will conduct technology research and development and talent reserve, invest funds and cooperate with scientific research institutions to develop manufacturing technology for key parts of wind turbines; in the third and fourth years, we will start small-scale production of wind turbine parts, gradually increase their proportion in the total output value of the enterprise, and it is expected to reach 30% in the fourth year; in the fifth year, we will further expand the scale of production, so that the output value of the new energy equipment manufacturing industry will account for more than 50%, and basically complete the transformation of the industrial structure. With the transformation of the industrial structure, it can be expected from the peak curve effect diagram that the total amount of carbon emissions will gradually decrease, the peak time is expected to be advanced, and the peak value will also decrease.

[0085] The energy structure adjustment path and the industrial structure transformation path are processed to generate several preset peak paths. Based on the above energy structure adjustment path and industrial structure transformation path, several preset peak paths are formed by considering different implementation progress and intensity. For example, path A: the energy structure adjustment adopts a rapid advancement strategy, increasing investment in solar and wind power generation in the first to third years, so that the proportion of clean energy reaches 40% in the third year, and the industrial structure transformation is also accelerated, and the output value of the new energy equipment manufacturing industry accounts for 20% in the third year; path B: the energy structure adjustment is carried out at a relatively steady pace, gradually increasing the proportion of clean energy in the first to fifth years, and the industrial structure transformation first conducts technology research and development and market research, and gradually releases production capacity in the third to fifth years, and the output value of the new energy equipment manufacturing industry accounts for 40% in the fifth year; path C: in the early stage of energy structure adjustment, focus on the development of solar power generation, so that the proportion of solar power generation reaches 15% in the first to third years, and then increase the introduction of wind power generation in the later stage, the industrial structure transformation is steadily promoted in the second to fifth years, and the output value of the new energy equipment manufacturing industry is increased by 10% each year. These different preset peak paths reflect the various options available to companies in achieving carbon emissions peak, and reflect the impact of different strategy combinations on the peak time and peak value.

[0086] Several preset peak paths are processed separately to generate the peak time and peak value of different preset peak paths. For path A, the curve of carbon emissions changing over time is calculated based on the enterprise energy consumption data, production plan, and energy structure and industrial structure adjustment plan, combined with the algorithm in the target peak accounting planning model. By analyzing the curve, it is found that the total carbon emissions reach a peak in the fourth year, that is, the peak time is 4 years. This is because in path A, the energy structure adjustment and industrial structure transformation measures that were rapidly promoted in the early stage began to play a significant emission reduction effect in the fourth year, so that the growth trend of carbon emissions was effectively curbed and began to decline. For path B, after a similar calculation process, the peak time is 5 years. Because its energy structure adjustment and industrial structure transformation are relatively robust, the emission reduction effect is sufficient to make carbon emissions reach a peak in the fifth year. For path C, the peak time is calculated to be 4.5 years. Its early focus on the development of solar power generation and the later introduction of wind power generation and the steady progress of industrial structure transformation measures have made the carbon emission peak appear in the 4.5th year.

[0087] When calculating the peak value of Path A, the total carbon emissions in the fourth year are calculated based on the assumption that the total carbon emissions of enterprises in that year are 800,000 tons of carbon dioxide equivalent (taking into account the comprehensive impact of energy structure adjustment and industrial structure transformation, such as clean energy replacing part of fossil energy to reduce carbon emissions, but there may be certain transition costs in the early stage of industrial transformation, resulting in carbon emissions not completely falling according to the ideal state). For Path B, the total carbon emissions are calculated to be 750,000 tons of carbon dioxide equivalent when the peak is reached in the fifth year. Because of its robust strategy, the downward trend of carbon emissions is relatively gentle and the peak is relatively low. When Path C peaks in the 4.5th year, the total carbon emissions are 780,000 tons of carbon dioxide equivalent, which is between Path A and Path B, reflecting the impact of its unique energy structure and industrial structure adjustment strategy on the peak.

[0088] The peak time and peak value of different preset peak paths are processed to generate the target peak path planning information. Taking into account the economic affordability, technical feasibility, market demand and regional environmental requirements of enterprises, the peak time and peak value of different preset peak paths are evaluated. Assuming that enterprises hope to achieve peak in a relatively short time in the current market competition environment to enhance their corporate image and competitiveness, but at the same time, they must also consider that the economic cost should not be too high. Comparing the three preset peak paths, although path A has the shortest peak time (4 years), the initial investment is large, which may cause great pressure on the company's cash flow; path B has a longer peak time (5 years), although the economic cost is relatively low, it may not meet the company's needs for rapid peaking; path C has a peak time of 4.5 years and a peak value of 780,000 tons of carbon dioxide equivalent. Its initial investment is relatively small compared to path A, and it can also better meet the company's needs in terms of peak time. After comprehensive evaluation, path C is selected as the target peak path.

[0089] The target peak path planning information includes detailed implementation steps and timetables. For example, in terms of energy structure adjustment, in the first and second years, the focus will be on investing in the construction of solar photovoltaic power generation systems, with a specific investment amount of 50 million yuan and an area of ​​20,000 square meters for installing solar panels. It is expected to reduce coal consumption by 10,000 tons and reduce carbon dioxide emissions by 25,000 tons per year; in the third and fourth years, wind power generation will be introduced, and cooperation agreements will be signed with energy suppliers to invest in the construction of supporting power transmission and transformation facilities. The investment amount is 80 million yuan, and it is expected to reduce coal consumption by 20,000 tons, diesel consumption by 10,000 tons, and carbon dioxide emissions by 60,000 tons per year. In terms of industrial structure transformation, in the first and second years, 20 million yuan will be invested in technology research and development and talent recruitment, and a research and development center will be established in cooperation with scientific research institutions; in the third and fourth years, trial production of wind turbine parts will be started, and the production scale will be gradually expanded. It is expected to increase the output value by 50 million yuan each year, while reducing carbon emissions from steel production by 30,000 tons; in the fifth year, the scale of the new energy equipment manufacturing industry will be further expanded, so that the output value will reach 200 million yuan, accounting for more than 50% of the total output value of the enterprise, and the total carbon emissions will continue to decline. In addition, the target peak path planning information also includes risk assessment and response measures during the implementation process, such as policy risks (such as changes in subsidy policies) and technical risks (such as power generation efficiency not meeting expectations) that new energy power generation projects may face, as well as corresponding response strategies (such as paying close attention to policy trends, strengthening technological research and development and monitoring, etc.), providing companies with comprehensive and feasible guidance plans for achieving carbon emissions peak.

[0090] In another embodiment, the method further includes a calculation formula for obtaining the peak time, and the calculation formula is: Among them, T0 represents the reference time, β i represents the technical impact coefficient, γ i Represents the implementation progress coefficient, ΔE i Represents carbon emission reduction, S i Represents the sensitivity of economic growth to carbon emissions, ρ i Represents the policy intensity coefficient.

[0091] Assume that we consider an energy-saving technology (i.e., n = 1), with 2020 as the base time (T0 = 2020). The technical impact coefficient of this energy-saving technology is β1 = 0.8, indicating that this technology is of great help in emission reduction; the implementation progress coefficient is γ1 = 0.5, assuming that the technology is half implemented at the current stage; it is estimated that the technology can reduce carbon emissions by 100 tons per year (ΔE1 = 100); the economic growth in the region where the enterprise is located is more sensitive to carbon emissions, S1 = 0.7; the local government has certain emission reduction policy support, and the policy intensity coefficient is ρ1 = 0.6.

[0092] Substituting into the formula we get: This means that in this case, the peak is expected to occur around 2115.

[0093] The method also includes a calculation formula for obtaining the peak value, which is:

[0094] Among them, P0 represents the initial carbon emission level, ω j represents the industrial structure coefficient, φ j Represents the industrial transformation progress coefficient, ΔI j represents the emission reduction brought about by industrial structure adjustment, Q j represents the energy structure coefficient, θ j Represents the progress coefficient of energy structure adjustment.

[0095] Assume that we consider an industrial restructuring situation (i.e. m = 1), with an initial carbon emission level of P0 = 500 tons. The industrial structure coefficient ω1 = 0.6, indicating that the industrial restructuring has a certain effect; the industrial transformation progress coefficient φ1 = 0.4, assuming that the industrial transformation has been carried out by 40%; it is expected that this industrial restructuring can reduce carbon emissions by 50 tons per year (ΔI1 = 50); the energy structure of the enterprise has a greater impact on carbon emissions, and the energy structure coefficient Q1 = 0.8; the energy structure adjustment progress coefficient θ1 = 0.3.

[0096] Substituting into the formula we get: This means that under this industrial restructuring scenario, the peak carbon emissions are expected to reach 25,500 tons.

[0097] This application obtains the information of the enterprise to be evaluated, regional information, carbon emission information, preset peak accounting planning model and training sample set. Then, key parameters and tasks are generated by processing these data: the enterprise information is processed to obtain the peak driving parameter information, which includes obtaining attribute information (such as equipment, production capacity, energy consumption and production process parameters, etc.) from the enterprise information, and then generating target parameter information and weight information, and finally obtaining the peak driving parameter information; the regional information is processed to obtain the peak measure parameter information and energy conservation and emission reduction parameter information of the target area, which involves extracting natural, ecological and geographical factor information from the regional information, and further generating renewable energy assessment information, regional restriction parameter information, etc.; the carbon emission information is processed to obtain the interval peak prediction subtask and the sequential access peak prediction subtask.

[0098] Next, feature vectors are extracted from the prediction subtasks, including feature extraction of interval peak prediction subtasks, dimension reduction of sequential access peak prediction subtasks, and other operations to obtain peak prediction feature vectors. The training sample set is processed to generate a training sample set with target feature information, including grouping, feature extraction, generation of training set and validation set, classifier prediction and algorithm training. Finally, based on the target peak accounting planning model, combined with the peak prediction feature vector, enterprise peak driving parameters, regional peak measures and energy conservation and emission reduction parameters, the energy and industrial structure adjustment path is generated, and the preset peak path, its peak time and peak value are further obtained, and the target peak path planning information is finally determined. Based on the embedded industry emission reduction technology database, optimization goals and constraints are established, energy-saving technologies cited by shipbuilding and repair enterprises are generated, and energy-saving technology reference conditions and judgment logic are generated. The optimal execution solution set and optimization plan are proposed, and the "adaptive" feature is used to realize autonomous optimization and intelligent optimization, and the optimal carbon emission execution route, the optimal peak cost execution route, the optimal economic benefit execution route, and the optimal peak time execution route are proposed. Digital integration of key energy-consuming links in enterprise production was carried out, and scientific reference conditions and judgment logic were proposed for the innovation of energy-saving technologies and energy-saving equipment applicable to the industry, successfully realizing the "integration, sharing and two-way matching" of energy-saving technology and energy-saving equipment information. Say goodbye to the "single and one-sided" situation, and have a systematic analysis and scientific diagnosis of the enterprise's carbon reduction route. While greatly improving the scientificity and systematicness of the enterprise's carbon reduction path, it also set an example for the industry's digital transformation.

[0099] In one embodiment, if Figure 2 As shown, the present application also provides a peak path planning device suitable for a shipbuilding and repairing enterprise, comprising:

[0100] An acquisition module 201 is used to acquire information of the enterprise to be evaluated, regional information of the enterprise to be evaluated, carbon emission information of the enterprise to be evaluated within a preset time period, a preset peak accounting planning model and a training sample set;

[0101] Processing module 202 is used to process the information of the enterprise to be evaluated and generate the peak driving parameter information of the enterprise to be evaluated; process the regional information of the enterprise to be evaluated and generate the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area; process the carbon emission information of the enterprise to be evaluated within a preset time period and generate an interval peak prediction subtask and a sequential access peak prediction subtask; process the interval peak prediction subtask and the sequential access peak prediction subtask to generate a peak prediction feature vector; process the training sample set to generate a training sample set with target feature information, wherein the target feature information is used to characterize the risk factors of the emission reduction effect being in an abnormal state; based on the training sample set with target feature information, process the preset peak accounting planning model to generate a target peak accounting planning model; based on the target peak accounting planning model, process the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area to generate target peak path planning information.

[0102] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for evaluating the peak path planning method, electronic device, electronic device, and readable storage medium embodiment applicable to shipbuilding and repair enterprises, since they are basically similar to the peak path planning method embodiment applicable to shipbuilding and repair enterprises described above, the description is relatively simple, and the relevant parts can be referred to the partial description of the peak path planning method embodiment applicable to shipbuilding and repair enterprises described above.

Claims

1. A peak path planning method suitable for shipbuilding and repairing enterprises, characterized in that: include: Obtain information on the enterprise to be assessed, regional information on the enterprise to be assessed, carbon emission information of the enterprise to be assessed within a preset time period, a preset peak accounting planning model and a training sample set; Processing the information of the enterprise to be evaluated to generate peak driving parameter information of the enterprise to be evaluated; Processing the regional information of the enterprise to be evaluated to generate peaking measure parameter information and energy conservation and emission reduction parameter information of the target area; Processing the carbon emission information of the enterprise to be evaluated within a preset time period to generate an interval peak prediction subtask and a sequential access peak prediction subtask; Processing the interval peak prediction subtask and the sequential access peak prediction subtask to generate a peak prediction feature vector; Processing the training sample set to generate a training sample set with target feature information, wherein the target feature information is used to characterize risk factors that indicate an abnormal emission reduction effect; Processing the preset peak accounting planning model based on the training sample set with target feature information to generate a target peak accounting planning model; Based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate target peak path planning information.

2. The method according to claim 1, characterized in that The information of the enterprise to be evaluated is processed to generate peak driving parameter information of the enterprise to be evaluated, including: Processing the information of the enterprise to be evaluated to generate attribute information of the enterprise to be evaluated, wherein the attribute information of the enterprise to be evaluated includes equipment list information, production capacity data information, energy consumption parameters, and production process parameters; Processing the equipment list information, the production capacity data information, the energy consumption parameters and the production process parameters to generate target parameter information of the enterprise to be evaluated and weight information matching the target parameter information; The target parameter information of the enterprise to be evaluated and the weight information matching the target parameter information are processed to generate the peak driving parameter information of the enterprise to be evaluated.

3. The method according to claim 1, characterized in that The regional information of the enterprise to be evaluated is processed to generate peaking measure parameter information and energy conservation and emission reduction parameter information of the target area, including: Processing the regional information of the enterprise to be evaluated to generate natural environment factor information of the target area, ecosystem factor information of the target area, and geographical factor information of the target area; Processing the natural environmental factor information of the target area to generate evaluation information of regional renewable energy resources; Processing the ecosystem factor information of the target area to generate regional restriction parameter information, wherein the regional restriction parameter information includes industrial structure planning parameter information and enterprise energy conservation and emission reduction potential parameter information; Processing the assessment information of the renewable energy resources in the region and the parameter information of the industrial structure planning to generate parameter information of peak measures for the target region; The geographical factor information of the target area and the energy-saving and emission-reduction potential parameter information of the enterprise are processed to generate the energy-saving and emission-reduction parameter information of the target area.

4. The method according to claim 1, characterized in that The carbon emission information of the enterprise to be evaluated within a preset time period is processed to generate an interval peak prediction subtask and a sequential access peak prediction subtask, including: Processing the carbon emission information of the enterprise to be assessed within a preset time period to generate a carbon emission trend factor, an interval peak assessment factor, carbon emission target node information, peak sequence information of the carbon emission target node, and peak time information of the carbon emission target node; Processing the carbon emission trend factor and the interval peak assessment factor to generate an interval peak prediction subtask; The carbon emission target node information, the peak sequence information of the carbon emission target nodes and the peak time information of the carbon emission target nodes are processed to generate a sequential access peak prediction subtask.

5. The method according to claim 4, characterized in that Processing the interval peak prediction subtask and the sequential access peak prediction subtask to generate a peak prediction feature vector includes: Performing feature extraction processing on the interval peak prediction subtask to generate access time interval sequence features, access interval number features and access interval information features; Processing the access interval information features to generate adjacent interval difference sequence information, difference sequence mean, and difference sequence variance; Performing dimensionality reduction processing on the sequential access peak prediction subtask to generate a one-dimensional prediction feature vector; Performing feature extraction processing on the one-dimensional prediction feature vector to generate target access list information, a mean of a similarity sequence of adjacent access information, and a variance of a similarity sequence of adjacent access information; The access time interval sequence feature, the access interval number feature, the access interval information feature, the target access list information, the mean of the adjacent access information similarity sequence and the variance of the adjacent access information similarity sequence are processed to generate a peak prediction feature vector.

6. The method according to claim 1, characterized in that Processing the training sample set to generate a training sample set with target feature information includes: Performing grouping processing on the training sample set to generate a grouped training sample set, wherein the grouped training sample set includes peak feature information of different regions and enterprises; Perform feature extraction on the grouped training sample set to generate an original feature library; Processing the original feature library to generate a training set and a verification set; Performing prediction processing on the verification set based on the classifier to generate a prediction result; Performing training processing on the training set based on a preset algorithm to generate prediction results for a validation set; The prediction results and the validation set prediction results are processed to generate target feature information, where the target feature information is used to characterize risk factors that indicate an abnormal emission reduction effect.

7. The method according to claim 1, characterized in that Based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate target peak path planning information, including: Based on the target peak accounting planning model, the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area are processed to generate an energy structure adjustment path and an industrial structure transformation path; Processing the energy structure adjustment path and the industrial structure transformation path to generate several preset peak paths; Processing several preset peak paths respectively to generate peak times and peak values ​​of different preset peak paths; The peak time and peak value of different preset peak paths are processed to generate target peak path planning information; The method also includes a calculation formula for obtaining the peak time, and the calculation formula is: Among them, T0 represents the reference time, β i represents the technical impact coefficient, γ i Represents the implementation progress coefficient, ΔE i Represents carbon emission reduction, S i Represents the sensitivity of economic growth to carbon emissions, ρ i represents the policy intensity coefficient; The method also includes a calculation formula for obtaining the peak value, which is: Among them, P0 represents the initial carbon emission level, ω j represents the industrial structure coefficient, φ j Represents the industrial transformation progress coefficient, ΔI j represents the emission reduction brought about by industrial structure adjustment, Q j represents the energy structure coefficient, θ j Represents the progress coefficient of energy structure adjustment.

8. A peak path planning device suitable for shipbuilding and repairing enterprises, characterized in that: The device comprises: An acquisition module is used to obtain information about the enterprise to be evaluated, regional information about the enterprise to be evaluated, carbon emission information about the enterprise to be evaluated within a preset time period, a preset peak accounting planning model, and a training sample set; A processing module is used to process the information of the enterprise to be evaluated and generate the peak driving parameter information of the enterprise to be evaluated; process the regional information of the enterprise to be evaluated and generate the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area; process the carbon emission information of the enterprise to be evaluated within a preset time period and generate an interval peak prediction subtask and a sequential access peak prediction subtask; process the interval peak prediction subtask and the sequential access peak prediction subtask to generate a peak prediction feature vector; process the training sample set to generate a training sample set with target feature information, wherein the target feature information is used to characterize the risk factors of the emission reduction effect being in an abnormal state; based on the training sample set with target feature information, process the preset peak accounting planning model to generate a target peak accounting planning model; based on the target peak accounting planning model, process the peak prediction feature vector, the peak driving parameter information of the enterprise to be evaluated, the peak measure parameter information of the target area and the energy conservation and emission reduction parameter information of the target area to generate target peak path planning information.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the peak path planning method applicable to a shipbuilding and repairing enterprise as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the peak path planning method applicable to a shipbuilding and repairing enterprise as described in any one of claims 1 to 7 is implemented.

Images