Production Task Scheduling Method and System Based on Carbon Emission Prediction

Abstract

The present invention relates to information technology specifically applicable to administrative management or supervision purposes, and particularly to a production task scheduling method and system based on carbon emission prediction; it includes the following steps: S1, obtaining carbon emission parameters; S2, constructing a multi-dimensional parameter set; S3, constructing a feature vector; S4, constructing a feature vector parameter set; S5, constructing a carbon emission fitting prediction formula; S6, carbon emission prediction; by constructing a feature vector and calculating the vector value and vector angle, the present invention avoids large-scale direct adjustment of a single parameter, reduces the impact on production, enables users to independently coordinate multiple parameters to obtain the target vector value or vector angle, and improves the system stability; by means of parameter fitting for carbon emission prediction, the training difficulty is reduced and the usability is improved; through the method of emission verification, it is examined whether the adjusted parameters meet the emission requirements, the prediction accuracy is improved, and ineffective interference with production is avoided.

Description

Technical Field

[0001] The present invention relates to information technology (G06Q) specifically applicable to administrative management or supervision purposes, and particularly relates to a production task scheduling method and system based on carbon emission prediction. Background Art

[0002] Greenhouse gas emissions cause the greenhouse effect and lead to a rise in global temperatures. While the Earth absorbs solar radiation, it also radiates heat into outer space, mainly in the form of long-wave infrared rays with wavelengths of 3 - 30 μm. When such long-wave radiation enters the atmosphere, it is easily absorbed by certain gas molecules with larger molecular weights and stronger polarities. Since the energy of infrared rays is relatively low and insufficient to break molecular bond energies, there is no chemical reaction when gas molecules absorb infrared radiation. Instead, it simply blocks the escape of heat from the Earth to outer space, acting as an insulating layer between the Earth and outer space, i.e., the "greenhouse" effect. The phenomenon where certain trace components in the atmosphere absorb the Earth's long-wave radiation and keep the near-surface heat, resulting in a rise in global temperatures, is called the greenhouse effect.

[0003] The sources of greenhouse gas emissions are mainly from the development of the world's heavy industries, vehicle exhaust, etc. Once greenhouse gases exceed the atmospheric standards, they will cause the greenhouse effect, leading to a rise in global temperatures and threatening human survival. Therefore, controlling greenhouse gas emissions has become a major issue faced by all mankind. Carbon emissions refer to the release of carbon dioxide and other greenhouse gases during the process of energy conversion or utilization. These greenhouse gases can include carbon dioxide, methane, nitrous oxide, etc., among which carbon dioxide is one of the main greenhouse gases.

[0004] The prior art discloses relevant technologies for carbon emission prediction and management:

[0005] Chinese Patent No. CN115099142A discloses an energy optimization scheduling method for carbon emission control enterprises based on model prediction, specifically including: establishing an energy-output prediction model and an energy-carbon emission prediction model for carbon emission control enterprises; predicting the output and carbon emissions in a future period according to the energy-output prediction model and the energy-carbon emission prediction model; establishing an energy optimization scheduling objective function for carbon emission control enterprises; using the energy optimization scheduling objective function as the fitness function of the particle swarm, and solving the optimal energy scheduling using the particle swarm algorithm; realizing the energy optimization scheduling of carbon emission control enterprises, improving enterprise production efficiency and reducing carbon emissions.

[0006] A Chinese patent with the publication number CN115471098A discloses a method, device, computer equipment and storage medium for obtaining carbon emissions, specifically discloses: The method includes: obtaining the net purchased electricity of the target cement enterprise and the cement production data of the target cement enterprise; obtaining the carbon emission characteristic factor data for the target cement enterprise according to the cement production data; obtaining the target electro-carbon monitoring model matching the target cement enterprise from multiple pre-trained electro-carbon monitoring models, and inputting the carbon emission characteristic factor data into the target electro-carbon monitoring model, and outputting the electro-carbon index corresponding to the target cement enterprise through the target electro-carbon monitoring model; obtaining the carbon emissions of the target cement enterprise according to the net purchased electricity and the electro-carbon index; using this method does not require obtaining the carbon emissions of the cement enterprise through an accounting method, thereby improving the accuracy of obtaining the carbon emissions of the cement enterprise.

[0007] A Chinese patent with the publication number CN116094068A discloses a power grid dispatching method, device and medium based on a carbon emission prediction mechanism; specifically discloses: obtaining carbon emission data related to power plants; preprocessing the carbon emission data related to power plants, and using the preprocessed data as sample data; dividing the sample data into a training set and a test set; training an improved BP neural network using the training set and the test set to obtain a trained improved BP neural network; predicting the future carbon emissions of power plants using the trained improved BP neural network; inputting the future carbon emissions of power plants into an objective function with the optimization goal of minimizing carbon emissions, and outputting the start-stop and output plans of power plants. The power grid dispatching method, device and medium based on a carbon emission prediction mechanism provided by the present invention accurately grasps the per-kWh carbon emission capacity of thermal power plant units in the future state through an improved BP neural network, realizes low-carbon dispatching of large power grids under the background of dual carbon, and provides data support and auxiliary decision-making for low-carbon operation work.

[0008] A Chinese patent with the publication number CN115409403A discloses a carbon asset management method and system based on organizational carbon emission prediction; specifically discloses: by obtaining the actual carbon emissions and corresponding actual industrial values of an organization's multiple historical carbon verifications, determining the carbon emission intensity of the organization, obtaining the planned industrial value of the organization within a preset time period, predicting the carbon emissions of the organization within the preset time period, calculating the carbon emissions generated by the organization from the start time node of the preset time period to the current year, obtaining the current carbon emissions, and combining the organization's current carbon quota, voluntary emission reduction issuance volume as of the preset time period, current carbon emissions and the carbon emissions of the organization within the preset time period, determining the remaining carbon assets of the organization as of the preset time period. By predicting the carbon emissions of an organization in a future preset time period in advance, the prediction of the organization's remaining carbon assets is realized, thereby helping the organization to optimize the allocation of carbon assets in advance, reduce the carbon quota compliance cost, and realize the preservation and appreciation of carbon assets.

[0009] However, the above-mentioned existing technologies still have the following problems:

[0010] 1. Existing carbon emission prediction methods require the training of artificial intelligence models, which need a large amount of samples, have complex training models, and once the model is trained, it has a large adjustability and cannot adapt to the situation of large-scale production parameter scheduling.

[0011] 2. Existing carbon emission prediction methods mainly directly predict carbon emissions using a single parameter, are greatly affected by individual parameters, it is difficult to determine the main factors, and lack the consideration of the synergy between parameters, prone to prediction inaccuracies. Summary of the Invention

[0012] To achieve the object of the present invention, the present invention is realized through the following technical solutions: A production task scheduling method based on carbon emission prediction, including the following steps:

[0013] S1. Obtain carbon emission parameters; obtain the equipment parameters, process parameters, material parameters and carbon emission time-domain parameters of the target factory area;

[0014] S2. Construct a multi-dimensional parameter set; construct a multi-dimensional feature parameter set based on the equipment parameters, process parameters, material parameters and carbon emission time-domain parameters ; satisfying:

[0015]

[0016]

[0017]

[0018]

[0019] Wherein, , and are respectively the equipment parameter subset, process parameter subset and material parameter subset of the multi-dimensional feature parameter set ; is the time-domain change amount of carbon emissions; and , and , and are respectively the equipment parameter serial number and equipment parameter dimension, process parameter serial number and process parameter dimension, material parameter serial number and material parameter dimension; to are respectively the items of the equipment parameters, and is the time variable; to are respectively the items of the process parameters, and is the time variable; to are the items of material parameters, which are time variables;

[0020] S3. Construct feature vectors; construct the feature vectors of the equipment parameter subset, process parameter subset, and material parameter subset respectively based on the equipment parameter subset, process parameter subset, and material parameter subset , the process parameter feature vector and the material parameter feature vector , satisfying:

[0021]

[0022]

[0023]

[0024] S4. Construct the feature vector parameter set; calculate the vector values and vector angles of the feature vectors of the equipment parameter subset , the process parameter feature vector and the material parameter feature vector respectively, and construct the feature vector parameter set , satisfying:

[0025]

[0026] Among them, are the vector values and vector angles of the feature vectors of the equipment parameter subset , the process parameter feature vector and the material parameter feature vector respectively;

[0027] S5. Construct the carbon emission fitting prediction formula; based on the time parameter , match and fit the time-domain change amount of the carbon emissions with the feature vector parameter set to obtain the carbon emission fitting prediction formula, satisfying:

[0028]

[0029] S6. Carbon emission prediction and production task scheduling; based on the carbon emission fitting prediction formula, predict the future carbon emissions and schedule the production tasks.

[0030] Furthermore, step S6 includes:

[0031] S61. Determine the carbon emission limit; based on the carbon emission target, determine the carbon emission limit , among which, represents the future time;

[0032] S62. Construct a set of factors influencing the trend of carbon emissions , satisfying:

[0033]

[0034]

[0035]

[0036]

[0037]

[0038]

[0039]

[0040] S63. Determine the main factors affecting carbon emissions; arrange the set of factors influencing the trend of carbon emissions in descending order to obtain a sequence of main factors affecting carbon emissions, namely the first main factor, the second main factor, the third main factor, the fourth main factor, the fifth main factor, and the sixth main factor;

[0041] S64. Determine the control factors; according to the sequence of main factors, determine the first main factor from the set of characteristic vector parameters as the control object.

[0042] Further, after step S64, it further includes:

[0043] S65. Control verification; substitute the adjusted set of characteristic vector parameters into the carbon emission fitting prediction formula to determine whether the carbon emission limit is met, that is, to judge whether the emission requirement is satisfied:

[0044]

[0045] wherein, represents the target time for carbon emission control.

[0046] Further, after step S65, it further includes:

[0047] S66. If the emission requirement is met, perform production scheduling according to the adjusted set of characteristic vector parameters : adjust the actual production parameters to the adjusted set of characteristic vector parameters , and carry out production according to the adjusted parameters;

[0048] S67. If the emission requirement is not met, perform control on the second main factor and execute step S65;

[0049] S68. Execute steps S65 - S67 in a loop and check whether the emission requirements are met.

[0050] Furthermore, the subset of device parameters includes: device number, number of devices, device type, energy consumption per unit time of the device, carbon emissions per unit time of the device.

[0051] Furthermore, the subset of process parameters includes: number of process steps, process step time, number of transfers, transfer time, carbon emissions of process steps, flexible time of process steps, topological relationship of process steps.

[0052] Furthermore, the subset of material parameters includes: types of incoming materials, incoming batches, quantity of incoming materials, quantity of intermediate materials, intermediate material batches, types of outgoing materials, outgoing batches, quantity of outgoing materials, quantity of waste materials.

[0053] The present invention also provides a production task scheduling system based on carbon emissions prediction for implementing the production task scheduling method based on carbon emissions prediction, including:

[0054] A parameter acquisition unit, including device sensors, process sensors, and material sensors, for implementing step S1;

[0055] A main operation unit, for implementing steps S2 - S5;

[0056] A prediction and verification unit, for implementing step S6.

[0057] The beneficial effects of the present invention are as follows:

[0058] 1. By constructing feature vectors and calculating vector values and vector angles, the present invention avoids large-scale direct adjustment of a single parameter, reduces the impact on production, and enables users to independently coordinate multiple parameters to obtain the target vector value or vector angle, improving the system stability.

[0059] 2. By using the method of parameter fitting for carbon emissions prediction, the present invention reduces the training difficulty and improves the usability compared with the method of artificial intelligence models.

[0060] 3. By means of emission verification, the present invention examines whether the adjusted parameters meet the emission requirements, improves the accuracy of prediction, and avoids ineffective interference with production. Description of the Drawings

[0061] Figure 1 It is a schematic flow chart of the method of the present invention. Detailed Embodiments

[0062] To deepen the understanding of the present invention, the following will further elaborate on the present invention in conjunction with embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0063] Embodiment 1

[0064] According to Figure 1 As shown, this embodiment provides a production task scheduling method based on carbon emission prediction, including the following steps:

[0065] S1. Obtain carbon emission parameters; obtain the equipment parameters, process parameters, material parameters, and carbon emission time-domain parameters of the target plant area;

[0066] S2. Construct a multi-dimensional parameter set; construct a multi-dimensional feature parameter set based on the equipment parameters, process parameters, material parameters, and carbon emission time-domain parameters ; satisfying:

[0067]

[0068]

[0069]

[0070]

[0071] Among them, 、 and are respectively the equipment parameter subset, process parameter subset, and material parameter subset of the multi-dimensional feature parameter set ; is the time-domain change amount of carbon emissions; and 、 and 、 and are respectively the equipment parameter serial number and equipment parameter dimension, process parameter serial number and process parameter dimension, material parameter serial number, and material parameter dimension; to are respectively the items of the equipment parameters, and is the time variable; to are respectively the items of the process parameters, and is the time variable; to are respectively the items of the material parameters, and is the time variable;

[0072] S3. Construct feature vectors; respectively construct the equipment parameter subset feature vector 、process parameter feature vector and material parameter feature vector , satisfying:

[0073]

[0074]

[0075]

[0076] S4. Construct a feature vector parameter set; calculate the vector values and vector angles of the feature vectors of the equipment parameter subset , the process parameter feature vector and the material parameter feature vector respectively, and construct a feature vector parameter set , satisfying:

[0077]

[0078] wherein, are the vector values and vector angles of the feature vectors of the equipment parameter subset , the process parameter feature vector and the material parameter feature vector respectively;

[0079] S5. Construct a carbon emission fitting prediction formula; based on the time parameter , match and fit the time-domain change amount of the carbon emissions with the feature vector parameter set to obtain a carbon emission fitting prediction formula, satisfying:

[0080]

[0081] The fitting adopts one of the least squares method, kernel method, spline method, maximum likelihood estimation method, and tangent method.

[0082] S6. Carbon emission prediction and production task scheduling; based on the carbon emission fitting prediction formula, predict the future carbon emissions and schedule the production tasks.

[0083] Further, step S6 includes:

[0084] S61. Determine the carbon emission limit; based on the carbon emission target, determine the carbon emission limit , wherein, represents the future time;

[0085] S62. Construct a set of carbon emission trend factors , satisfying:

[0086]

[0087]

[0088]

[0089]

[0090]

[0091]

[0092]

[0093] S63. Determine the main factors affecting carbon emissions; arrange the set of carbon emission trend factors in descending order to obtain the main factor sequence affecting carbon emissions, namely the first main factor, the second main factor, the third main factor, the fourth main factor, the fifth main factor, and the sixth main factor;

[0094] S64. Determine the control factors; according to the main factor sequence, determine the first main factor from the characteristic vector parameter set as the control object.

[0095] Further, after step S64, it further includes:

[0096] S65. Control verification; substitute the adjusted characteristic vector parameter set into the carbon emission fitting prediction formula to determine whether the carbon emission limit is met, that is, to judge whether the emission requirement is satisfied:

[0097]

[0098] Among them, represents the target time for carbon emission control.

[0099] Further, after step S65, it further includes:

[0100] S66. If the emission requirement is met, perform production scheduling according to the adjusted characteristic vector parameter set : adjust the actual production parameters to the adjusted characteristic vector parameter set and carry out production according to the adjusted parameters;

[0101] S67. If the emission requirement is not met, control the second main factor and execute step S65;

[0102] S68. Loop and execute steps S65 - S67 and check whether the emission requirement is satisfied.

[0103] Further, the subset of device parameters includes: device number, number of devices, device type, energy consumption per unit time of the device, and carbon emissions per unit time of the device.

[0104] Further, the subset of process parameters includes: number of process steps, process step time, number of transfers, transfer time, carbon emissions of process steps, flexible time of process steps, and topological relationship of process steps.

[0105] Further, the subset of material parameters includes: types of incoming materials, incoming batches, quantity of incoming materials, quantity of intermediate materials, intermediate material batches, types of outgoing materials, outgoing batches, quantity of outgoing materials, and quantity of waste materials. Specific Embodiment 2

[0107] A production task scheduling system based on carbon emissions prediction for implementing the production task scheduling method based on carbon emissions prediction, including:

[0108] A parameter acquisition unit, including device sensors, process sensors, and material sensors, for implementing step S1;

[0109] A main operation unit for implementing steps S2 - S5;

[0110] A prediction and verification unit for implementing step S6.

[0111] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A production task scheduling method based on carbon emission prediction, characterized in that It includes the following steps: S1. Obtain carbon emission parameters; obtain the equipment parameters, process parameters, material parameters and carbon emission time-domain parameters of the target plant area; S2. Construct a multi-dimensional parameter set; Construct a multi-dimensional feature parameter set based on the device parameters, process parameters, material parameters, and carbon emission time-domain parameters ; Satisfying: Among them, , and are respectively the subsets of equipment parameters, process parameters, and material parameters of the multi-dimensional feature parameter set ; is the time-domain change amount of carbon emissions; and , and , and are respectively the equipment parameter serial number and equipment parameter dimension, process parameter serial number and process parameter dimension, material parameter serial number, and material parameter dimension; to are respectively the items of equipment parameters and are time variables; to are respectively the items of process parameters and are time variables; to are respectively the items of material parameters and are time variables; S3. Construct feature vectors; respectively construct the feature vectors of the equipment parameter subset, the process parameter subset, and the material parameter subset based on the equipment parameter subset, the process parameter subset, and the material parameter subset , the process parameter feature vector and the material parameter feature vector , satisfying: S4. Construct a feature vector parameter set; calculate the feature vectors of the device parameter subset, the process parameter feature vector, and the material parameter feature vector respectively, and construct a feature vector parameter set that satisfies: Among them, are the vector values and vector angles of the feature vectors of the subsets of device parameters , the feature vectors of process parameters and the feature vectors of material parameters respectively; S5. Construct a fitting prediction formula for carbon emissions; based on the time parameter , match and fit the time-domain change amount of carbon emissions with the feature vector parameter set , and the fitting adopts one of the least squares method, kernel method, spline method, maximum likelihood estimation method, and tangent method to obtain a fitting prediction formula for carbon emissions, satisfying: S6. Carbon emission prediction and production task scheduling; based on the carbon emission fitting prediction formula, predict the future carbon emissions and schedule the production tasks; specifically including: S61. Determine the carbon emission limit; based on the carbon emission target, determine the carbon emission limit , where represents a future time S62. Construct a set of factors influencing the trend of carbon emissions , satisfying: S63. Determine the main factors affecting carbon emissions; and arrange the set of carbon emission trend factors in descending order to obtain the main factor sequence affecting carbon emissions, namely the first main factor, the second main factor, the third main factor, the fourth main factor, the fifth main factor, and the sixth main factor respectively; S64. Determine the regulatory factors; according to the main factor sequence, determine the first main factor as the regulatory object from the characteristic vector parameter set therein; S65. Regulation verification: The regulated feature vector parameter set is substituted into the carbon emission fitting prediction formula to determine whether the carbon emission limit is met, that is, to judge whether the emission requirement is satisfied: Among them, represents the target moment for carbon emission regulation; S66. If the emission requirements are met, production scheduling is carried out according to the adjusted characteristic vector parameter set : The actual production parameters are adjusted to the adjusted characteristic vector parameter set , and production is carried out according to the adjusted parameters; S67. If the emission requirements are not met, adjust the second main factor and execute step S65; S68. Loop and execute steps S65 - S67, and determine whether the emission requirements are met.

2. The production task scheduling method based on carbon emission prediction according to claim 1, wherein: The equipment parameter subset includes: equipment number, equipment quantity, equipment type, unit time energy consumption of the equipment, unit time carbon emission of the equipment.

3. The production task scheduling method based on carbon emission prediction according to claim 1, wherein: The process parameter subset includes: number of process steps, process step time, number of transfers, transfer time, carbon emission of process steps, elastic time of process steps, topological relationship of process steps.

4. The production task scheduling method based on carbon emission prediction according to claim 1, wherein: The material parameter subset includes: types of incoming materials, incoming batches, quantity of incoming materials, quantity of intermediate materials, intermediate material batches, types of outgoing materials, outgoing batches, quantity of outgoing materials, quantity of waste materials.

5. A production task scheduling system based on carbon emission prediction, which is used to implement the production task scheduling method based on carbon emission prediction according to any one of claims 1-4, and is characterized in that: It includes: A parameter acquisition unit, including equipment sensors, process sensors, and material sensors, for implementing step S1; A main operation unit, for implementing steps S2 - S5; A prediction and verification unit, for implementing step S6.

Images