CN115115473A - Diesel generating set carbon emission quantitative calculation method based on BP neural network - Google Patents
Diesel generating set carbon emission quantitative calculation method based on BP neural network Download PDFInfo
- Publication number
- CN115115473A CN115115473A CN202210846393.2A CN202210846393A CN115115473A CN 115115473 A CN115115473 A CN 115115473A CN 202210846393 A CN202210846393 A CN 202210846393A CN 115115473 A CN115115473 A CN 115115473A
- Authority
- CN
- China
- Prior art keywords
- diesel generator
- carbon emission
- generator set
- diesel
- oil
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 144
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 144
- 238000004364 calculation method Methods 0.000 title claims abstract description 56
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000010248 power generation Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 5
- 239000003921 oil Substances 0.000 claims description 148
- 238000012360 testing method Methods 0.000 claims description 12
- 238000002485 combustion reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 239000000446 fuel Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 230000009467 reduction Effects 0.000 abstract description 4
- 230000005611 electricity Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000002283 diesel fuel Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Regulation And Control Of Combustion (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The invention discloses a quantitative calculation method for carbon emission of a diesel generator set based on a BP (back propagation) neural network, which aims to quantitatively calculate the carbon emission generated by different diesel generators burning different quality oil for power generation based on the BP neural network, and combines an online acquisition technology to realize quantitative dynamic calculation of the carbon emission of the diesel generator set and improve the calculation efficiency and accuracy; the invention provides a quantitative calculation method for carbon emission of a diesel generating set based on a BP neural network, which overcomes the technical problems that the carbon emission of the diesel generating set is difficult to calculate effectively, particularly the on-line dynamic calculation; the method has the advantages of simple flow, reasonable calculation model structure, BP neural network training calculation superposition, comprehensive calculation data quantity, clear intermediate structure meaning in the calculation process, strong practicability, contribution to use and popularization of carbon emission control calculation of the diesel generating set, contribution to mastering carbon emission rules of different types of diesel generating sets and support of carbon emission reduction of the diesel generating set.
Description
Technical Field
The invention relates to the field of power systems, in particular to the technical field of carbon emission quantitative calculation of diesel generating sets.
Background
The diesel oil is an oil mineral substance obtained after refining petroleum, is a mixture of hydrocarbon, can generate carbon dioxide emission when the diesel oil is combusted by the diesel engine to generate power, and is not beneficial to realizing the national carbon emission reduction target due to different carbon emissions generated in the operation process of different types of diesel engine units.
The diesel generator set burns diesel through the engine, converts heat energy into mechanical energy, and then drives the generator to cut a magnetic field through the rotation of the engine, and finally generates electric energy. At present, the diesel generator set mainly has the following application scenes: firstly, self-contained power, when the regional power supply that does not have the electric wire netting, like regions such as marine island, remote mountain area, desert, need diesel generating set to generate electricity, supply with electric power. And secondly, the emergency power supply is mainly configured with a certain number of diesel generator sets as the emergency power supply aiming at the accident conditions of power grid failure, power failure and the like, so that the continuity of power supply is guaranteed. And thirdly, a power supply is replaced, the power supply of the diesel generator set is replaced by the power supply in a short time mainly in order to make up the situation that the power supply capacity of a power grid is insufficient or the power generation of new energy is insufficient and the power supply of the power grid cannot meet the requirements of users. And the diesel generator set is portable, flexible and easy to operate, and the diesel generator set and a vehicle form the mobile power supply, so that the mobile power supply can be used in oil fields, field engineering exploration, steamships and other scenes. And fifthly, the power supply for fire fighting is used as a power supply for the diesel generator set which is commonly used for fire fighting and is equipped for building fire fighting equipment, and when the power supply of a power grid is cut off in case of fire, the diesel generator set generates power to provide power for the fire fighting equipment. In summary, the application scenarios of the diesel generating set are wide, the carbon emission generated by the operation of the diesel generating set is huge, but the carbon emission of the diesel generating set is less concerned by the existing research.
Disclosure of Invention
The invention aims to solve the technical problems that the carbon emission of a diesel generating set is difficult to calculate effectively, and particularly the on-line dynamic calculation is difficult;
aiming at the problems and different scenes, in order to master the carbon emission of the diesel generator set and support the carbon emission reduction of the diesel generator set, the method for quantitatively calculating the carbon emission of the diesel generator set based on the BP neural network is provided, and mainly comprises the following steps: the method comprises the following steps of acquiring the electrical and oil information of the diesel generator set, calculating models of carbon emission of the diesel generator sets of different types, constructing a carbon emission factor model of the diesel generator set based on a BP neural network, constructing a power generation carbon emission online calculating model of the diesel generator set, and quantitatively calculating the carbon emission of the diesel generator sets of different types;
the invention provides the following technical scheme:
the diesel generating set carbon emission quantitative calculation method based on the BP neural network comprises the following steps:
s1, acquiring electric oil information data of all different types of diesel generators in a diesel generator set to form a basic database;
s2, constructing a carbon emission calculation model under active/reactive power of the diesel generator set, calculating carbon emission data of the diesel generator set by using the electric oil information data collected in S1, updating a basic database to form electric oil carbon information data, and dividing a training set and a test set;
s3, constructing a carbon emission factor model under active/reactive power of the diesel generating set based on the BP neural network, training and testing by using a corresponding training set and a corresponding testing set in S2 to obtain the carbon emission factor model under the active/reactive power of the diesel generating set, and giving out the corresponding carbon emission factor under the unit active/reactive power of the diesel generating set when different qualities of oil are used according to the model;
s4, constructing a diesel generating set power carbon emission online calculation model;
s5, collecting the power generation power data of the diesel generator set on line, and distinguishing active power and reactive power; and combining the corresponding carbon emission factor obtained in the step S3, and dynamically calculating the corresponding generated power carbon emission of the diesel generator set on line according to the carbon emission on-line calculation model.
Preferably, for the collection technology based on the sensing device in S1, the current mature sensing device and the internet of things technology are used to collect electric oil information data of the diesel generator set, where the electric oil information data includes active and reactive data of the diesel generator set, different types of quality oil data, and oil consumption data of the diesel generator set;
the active and reactive data of the diesel generating set in the electric oil information data are shown in a formula (1):
in the formula:is composed ofThe active power vector of the diesel generator set at the moment,is composed ofThe time type isThe active power generated by the diesel generator of (1),;,,respectively represents three types of diesel generators, namely a high-speed diesel generator, a medium-speed diesel generator and a low-speed diesel generator;is composed ofAt the moment, the reactive power vector of the diesel generator set,is composed ofThe time type isThe reactive power generated by the diesel generating set,。
preferably, the processing is performed for different types of quality oil data in the electrical oil information data in S1 as shown in formula (2):
in the formula:the data are the vector data of the quality oil,respectively of type 30#, and,20#, 10#, 5#, 0#, -5#, -10#, -21#, and 35 #;
according to the different types of quality oil data, the oil consumption data of the diesel generating set in the electric oil information data is shown as a formula (3):
in the formula:is composed ofThe different types of diesel generating sets generate oil consumption data of different qualities of oil correspondingly consumed when the diesel generating sets are active,is composed ofOil consumption data of different qualities of oil correspondingly consumed when different types of diesel generator sets send out reactive power at any moment;is composed ofInstant diesel generator setWhen active, quality oil is producedOil consumption data of;is composed ofDiesel generator set at any momentQuality oil when it is idleThe number of fuel consumption.
Preferably, the calculation model of the carbon emission under active/reactive power for the diesel generator set constructed in S2 is as shown in formula (4):
in the formula:is composed ofInstant diesel generator setBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;standard quality oil for combustion unitThe amount of carbon emissions generated during the course of treatment,is a diesel generator setThe active oil consumption factor represents the combustion efficiency of the quality oil of the diesel generating set;Is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of;is composed ofDiesel generator set at any momentBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;is a diesel generator setThe idle oil consumption factor represents the combustion efficiency of the quality oil of the diesel generator set;is composed ofDiesel generator set at any momentWhen it is idleQuality oilThe amount of oil consumption.
Preferably, the model for the carbon emission factor under the active/reactive power of the diesel generator set based on the BP neural network in the S3 comprises an input layer, a hidden layer and an output layer; the input layer has 4 inputs; the output layer has 2 outputs;
the 4 inputs are:、、and(ii) a WhereinIs composed ofThe time type isThe active power generated by the diesel generating set,;is composed ofThe time type isThe reactive power generated by the diesel generator set,;Is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of the oil pump,is composed ofDiesel generator set at any momentQuality oil for emitting idle powerThe amount of oil consumption of; the 2 outputs are:andwhereinIs composed ofDiesel generator set at any momentBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;is composed ofDiesel generator set at any momentBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;
the hidden layer adopts a tansig function, and after training, the output carbon emission factor model of the BP neural network-based diesel generator set under active/reactive power is shown in a formula (5):
in the formula:for the trained carbon emission factor model of the active BP neural network of the diesel generating set,the model is a carbon emission factor model of the idle BP neural network of the diesel generating set after training.
Preferably, the carbon emission online calculation model for the power generation power of the diesel generating set constructed in the step S4 is shown in the formula (6):
in the formula:、are respectively asActive and reactive carbon emission of the diesel generator set on line at any moment;、are respectively asThe active power and the reactive power of the diesel generator set are on line at any moment;is composed ofDiesel generator set at any momentBurnup quality oilActive unit carbon emission factor of Internet;is composed ofDiesel generator set at any momentBurnup quality oilAnd the reactive unit carbon emission factor of the internet.
The invention further provides a carbon emission quantitative calculation system of the diesel generating set based on the BP neural network; comprises a network interface, a memory and a processor; the network interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor is used for executing the carbon emission quantitative calculation method of the diesel generating set based on the BP neural network when the computer program is run.
The invention further provides a computer storage medium, wherein the computer storage medium stores a program for quantitatively calculating the carbon emission of the diesel generating set based on the BP neural network, and the program for quantitatively calculating the carbon emission of the diesel generating set based on the BP neural network is executed by at least one processor to realize the method for quantitatively calculating the carbon emission of the diesel generating set based on the BP neural network;
it should be noted that the electrical and oil information acquisition technology of the present invention adopts the existing sensing device for acquisition, and the present invention is not specifically described nor limited herein;
compared with the prior art, the invention has the following beneficial effects:
the invention provides a quantitative calculation method for carbon emission of a diesel generating set based on a BP neural network, which overcomes the technical problems that the carbon emission of the diesel generating set is difficult to calculate effectively, particularly the on-line dynamic calculation; the method comprises the steps that specifically, through a diesel generator set electric oil information acquisition technology of a sensing device, electric oil information of all different types of diesel generators in a diesel generator set is acquired, and electric oil information data are divided into active power and reactive power; meanwhile, constructing a carbon emission calculation model under the active/reactive power of the diesel generator set; calculating carbon emission data of the diesel generating set by using the collected electric oil information data to form electric oil carbon information data, and dividing a training set and a test set; obtaining a carbon emission factor model under active/reactive power of the diesel generating set through training based on a BP neural network; giving out a carbon emission factor under active/reactive power of the diesel generator set; facilitating subsequent carbon emission calculations;
the method further constructs an on-line calculation model of the carbon emission of the generated power of the diesel generating set; the method has the advantages that the generated power data of the diesel generator set are collected on line, the corresponding carbon emission factors are combined, the carbon emission amount of the generated power corresponding to the diesel generator set is calculated dynamically on line, and the calculation efficiency and accuracy are improved greatly.
The invention distinguishes the generated power into active power and reactive power, avoids the interaction of the active power and the reactive power from influencing the carbon emission calculation, and improves the accuracy; the method has the advantages of simple flow, reasonable calculation model structure, BP neural network training calculation superposition, comprehensive calculation data quantity, clear intermediate structure meaning in the calculation process, strong practicability, contribution to use and popularization of carbon emission control calculation of the diesel generating set, contribution to mastering carbon emission rules of different types of diesel generating sets and support of carbon emission reduction of the diesel generating set.
Drawings
Fig. 1 is a schematic flow chart of a quantitative calculation method for carbon emission of a diesel generator set based on a BP neural network.
Fig. 2 is a schematic diagram of a BP neural network for calculating carbon emission factors of a diesel generating set in a quantitative calculation method for carbon emission of the diesel generating set based on the BP neural network.
Detailed Description
The technical solution of the present patent will be described in further detail with reference to the following embodiments.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention; the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; furthermore, unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, as they may be fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1, the method for quantitatively calculating carbon emission of a diesel generator set based on a BP neural network comprises the following steps:
s1, collecting electric oil information data of all different types of diesel generators in a diesel generator set to form a basic database;
in the electric oil acquisition technology of the diesel generator set in the embodiment, the currently mature sensing device and the internet of things technology are used for acquiring electric oil information data of the diesel generator set, wherein the electric oil information data comprise active data and reactive data of the diesel generator set, oil data of different types of quality and oil consumption data of the diesel generator set;
the active and reactive data processing of the diesel generating set in the electric oil information data is shown as a formula (1):
in the formula:is composed ofThe active power vector of the diesel generator set at the moment,is composed ofThe time type isThe active power generated by the diesel generator of (1),;,,respectively represents three types of diesel generators, namely a high-speed diesel generator, a medium-speed diesel generator and a low-speed diesel generator;is composed ofAt the moment, the reactive power vector of the diesel generator set,is composed ofThe time type isThe reactive power generated by the diesel generating set,。
the carbon emissions generated when different types of quality oil are combusted are different, so the invention analyzes the carbon emissions of the different types of quality oil; the processing of the different types of quality oil data of the electrical oil information data in the embodiment is shown as formula (2):
in the formula:the data are the vector data of the quality oil,respectively representing quality oils with types of 30#, 20#, 10#, 5#, 0#, -5#, -10#, -21#, and-35 #;
according to the different types of quality oil data, the oil consumption data of the diesel generating set in the electric oil information data is shown as a formula (3):
in the formula:is composed ofThe different types of diesel generating sets generate oil consumption data of different qualities of oil correspondingly consumed when the diesel generating sets are active,is composed ofDifferent types of diesel generators at different momentsThe oil consumption data of the oil with different qualities correspondingly consumed when the group sends out the idle work;is composed ofDiesel generator set at any momentWhen active, quality oil is producedOil consumption data of;is composed ofDiesel generator set at any momentQuality oil when it is idleOil consumption data of (c).
S2, constructing a carbon emission calculation model under active/reactive power of the diesel generator set, calculating carbon emission data of the diesel generator set by using the electric oil information data collected in S1, updating a basic database to form electric oil carbon information data, and dividing a training set and a test set;
the model for calculating the carbon emission under the active/reactive power of the diesel generator set constructed in the embodiment is shown as a formula (4):
in the formula:is composed ofInstant diesel generator setBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;for combustion of unit standard quality oilThe amount of carbon emissions generated during the course of treatment,is a diesel generator setThe active oil consumption factor represents the combustion efficiency of the quality oil of the diesel generator set;is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of;is composed ofDiesel generator set at any momentBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;is a diesel generator setThe idle oil consumption factor represents the combustion efficiency of the quality oil of the diesel generator set;is composed ofDiesel generator set at any momentQuality oil for emitting idle powerThe amount of oil consumption.
S3, constructing a carbon emission factor model under active/reactive power of the diesel generator set based on the BP neural network, training and testing by using a corresponding training and testing set in S2 to obtain the carbon emission factor model under the active/reactive power of the diesel generator set, and giving out corresponding carbon emission factors under unit active/reactive power of the diesel generator set under the condition of using different qualities of oil according to the model;
the application of the BP neural network has 3 main steps, which are respectively as follows: training data, a training network and a testing network are collected. The method adopts an off-line training neural network, namely, the neural network is trained according to active data and reactive data of different types of diesel generator sets and corresponding oil consumption data of different qualities of oil, connection weight values, threshold values, training functions and the like are obtained, and the active power, the reactive power and fuel carbon emission are associated;
as shown in fig. 2, the carbon emission factor model in the embodiment of the invention based on the BP neural network under the active/reactive power of the diesel generator set has an input layer, a hidden layer and an output layer; the input layer has 4 inputs; the output layer has 2 outputs;
the 4 inputs are:、、and(ii) a WhereinIs composed ofThe time type isThe active power generated by the diesel generating set,;is composed ofThe time type isDiesel generatorThe reactive power emitted by the group is,;is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of the oil pump,is composed ofDiesel generator set at any momentQuality oil for emitting idle powerThe amount of oil consumption of; the 2 outputs are:andwhereinIs composed ofDiesel generator set at any momentBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;is composed ofDiesel generator set at any momentBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;
the hidden layer adopts a tansig function, and after training, the output carbon emission factor model of the BP neural network-based diesel generator set under active/reactive power is shown as a formula (5):
in the formula:for the trained carbon emission factor model of the active BP neural network of the diesel generating set,the model is a carbon emission factor model of the idle BP neural network of the diesel generating set after training. The factor model outputs the carbon emission corresponding to the unit internet power, which is a unit value; the carbon emission on the internet at the back is calculated according to the power amount on the internet.
S4, constructing a diesel generating set power carbon emission online calculation model;
the diesel generator set power generation carbon emission online calculation model constructed in the S4 is shown in the formula (6):
in the formula:、respectively measuring the active and reactive carbon emissions of the diesel generator set on line at the moment t;、are respectively asThe active power and the reactive power of the diesel generator set are on line at any moment;is composed ofDiesel generator set at any momentBurnup quality oilActive unit carbon emission factor of Internet;is composed ofDiesel generator set at any momentBurnup quality oilAnd the reactive unit carbon emission factor of the internet.
S5, collecting the power generation power data of the diesel generator set on line, wherein the electricity and oil information data of the diesel generator set are collected by the current mature sensing device and the Internet of things technology through the electricity and oil collection technology of the diesel generator set; distinguishing active power and reactive power by utilizing power generation power data in the electric oil information data; and combining the corresponding carbon emission factor obtained in the step S3, and dynamically calculating the corresponding generated power carbon emission of the diesel generator set on line according to the carbon emission on-line calculation model.
The working principle of the invention is as follows: the invention collects the electric oil information of all different types of diesel generators in the diesel generator set by the electric oil information collection technology of the diesel generator set of the sensing device, and divides the electric oil information data into active power and reactive power; avoiding the interaction of active power and reactive power from influencing subsequent calculation, and constructing a calculation model of carbon emission under the active/reactive power of the diesel generator set; calculating carbon emission data of the diesel generating set by using the collected electric oil information data to form electric oil carbon information data, and dividing a training set and a test set; obtaining a carbon emission factor model under active/reactive power of the diesel generator set through training based on a BP neural network; giving out a carbon emission factor under active/reactive power of the diesel generator set; further, constructing a carbon emission online calculation model of the power generation power of the diesel generator set; the method has the advantages that the generated power data of the diesel generator set are collected on line, the corresponding carbon emission factors are combined, the carbon emission amount of the generated power corresponding to the diesel generator set is calculated dynamically on line, and the calculation efficiency and accuracy are improved.
Although the preferred embodiments of the present patent have been described in detail, the present patent is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present patent within the knowledge of those skilled in the art.
Claims (8)
1. A diesel generating set carbon emission quantitative calculation method based on a BP neural network is characterized by comprising the following steps:
s1, acquiring electric oil information data of all different types of diesel generators in a diesel generator set to form a basic database;
s2, constructing a carbon emission calculation model under active/reactive power of the diesel generator set, calculating carbon emission data of the diesel generator set by using the electric oil information data collected in S1, updating a basic database to form electric oil carbon information data, and dividing a training set and a test set;
s3, constructing a carbon emission factor model under active/reactive power of the diesel generating set based on the BP neural network, training and testing by using a corresponding training set and a corresponding testing set in S2 to obtain the carbon emission factor model under the active/reactive power of the diesel generating set, and giving out the corresponding carbon emission factor under the unit active/reactive power of the diesel generating set when different qualities of oil are used according to the model;
s4, constructing a diesel generating set generating power carbon emission online calculation model;
s5, collecting the power generation power data of the diesel generator set on line, and distinguishing active power and reactive power; and combining the corresponding carbon emission factor obtained in the step S3, and dynamically calculating the corresponding generated power carbon emission of the diesel generator set on line according to the carbon emission on-line calculation model.
2. The BP neural network-based quantitative carbon emission calculation method for a diesel generator set according to claim 1, wherein in step S1, a collection technology based on a sensing device is used to collect electrical and oil information data of all different types of diesel generators in the diesel generator set;
the active and reactive data of the diesel generator set in the electric oil information data are shown as a formula (1):
in the formula:is composed ofThe active power vector of the diesel generator set at the moment,is composed ofThe time type isThe active power generated by the diesel generator of (1),; ,,respectively represents three types of diesel generators, namely a high-speed diesel generator, a medium-speed diesel generator and a low-speed diesel generator;is composed ofAt the moment, the reactive power vector of the diesel generator set,is composed ofThe time type isThe diesel generator set generates reactive power.
3. The BP neural network-based diesel generator set carbon emission quantitative calculation method according to claim 2,
the different types of quality oil data in the electric oil information data are shown in formula (2):
in the formula:the data are the vector data of the quality oil,respectively representing quality oils with types of 30#, 20#, 10#, 5#, 0#, -5#, -10#, -21#, and-35 #;
according to the different types of quality oil data, the oil consumption data of the diesel generating set in the electric oil information data is shown as a formula (3):
in the formula:is composed ofAt no timeThe diesel generating sets of the same type correspondingly consume oil consumption data of different qualities of oil when generating active power,is composed ofOil consumption data of different qualities of oil correspondingly consumed when different types of diesel generator sets send out reactive power at any moment;is composed ofDiesel generator set at any momentWhen active, quality oil is producedOil consumption data of;is composed ofDiesel generator set at any momentQuality oil when it is idleThe number of fuel consumption.
4. The method for quantitatively calculating the carbon emission of the diesel generator set based on the BP neural network according to claim 3, wherein in the step S2, the model for calculating the carbon emission of the diesel generator set under the active/reactive power is constructed as shown in formula (4):
in the formula:is composed ofDiesel generator set at any momentBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;for combustion of unit standard quality oilThe amount of carbon emissions generated during the course of treatment,is a diesel generator setThe active oil consumption factor represents the combustion efficiency of the quality oil of the diesel generating set;is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of;is composed ofInstant diesel generator setBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;is a diesel generator setThe idle oil consumption factor represents the combustion efficiency of the quality oil of the diesel generator set;is composed ofDiesel generator set at any momentQuality oil for emitting idle powerThe amount of oil consumption.
5. The BP neural network-based quantitative calculation method for carbon emission of a diesel generator set according to claim 4, wherein in step S3, the BP neural network-based model for carbon emission factor under active/reactive power of the diesel generator set has an input layer, a hidden layer and an output layer; the input layer has 4 inputs; the output layer has 2 outputs;
the 4 inputs are:、、and(ii) a WhereinIs composed ofThe time type isThe active power generated by the diesel generator set;is composed ofThe time type isThe diesel generating set generates reactive power;is composed ofDiesel generator set at any momentProduce active time quality oilThe amount of oil consumption of the oil pump,is composed ofDiesel generator set at any momentQuality oil for emitting idle powerThe amount of oil consumption of; the 2 outputs are:andwhereinIs composed ofDiesel generator set at any momentBurning of quality oilWhen the power is generated, the carbon emission generated by the diesel generator set is reduced;is composed ofDiesel generator set at any momentBurning of quality oilCarbon emission generated by the diesel generator set when the engine generates idle work;
the hidden layer adopts a tansig function, and after training, the output carbon emission factor model of the BP neural network-based diesel generator set under active/reactive power is shown in a formula (5):
6. The method for quantitatively calculating the carbon emission of the diesel generator set based on the BP neural network as claimed in claim 5, wherein in the step S4, an on-line calculation model of the carbon emission of the generated power of the diesel generator set is constructed as shown in formula (6):
in the formula:、are respectively asActive and reactive carbon emission of the diesel generator set on line at any moment;、are respectively asThe active power and the reactive power of the diesel generator set are on line at any moment;is composed ofDiesel generator set at any momentCombustion quality oilActive unit carbon emission factor of Internet;is composed ofDiesel generator set at any momentCombustion quality oilAnd the reactive unit carbon emission factor of the internet.
7. The carbon emission quantitative calculation system of the diesel generating set based on the BP neural network is characterized by comprising a network interface, a memory and a processor; wherein the content of the first and second substances,
the network interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor is used for executing the method for quantitatively calculating the carbon emission of the diesel generator set based on the BP neural network according to any one of claims 2-6 when the computer program is run.
8. A computer storage medium, wherein the computer storage medium stores a program for BP neural network-based quantitative calculation of carbon emission of a diesel genset, and the program for BP neural network-based quantitative calculation of carbon emission of a diesel genset is executed by at least one processor to implement the BP neural network-based quantitative calculation method of carbon emission of a diesel genset according to any one of claims 2 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210846393.2A CN115115473B (en) | 2022-07-19 | 2022-07-19 | BP neural network-based carbon emission quantitative calculation method for diesel generator set |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210846393.2A CN115115473B (en) | 2022-07-19 | 2022-07-19 | BP neural network-based carbon emission quantitative calculation method for diesel generator set |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115115473A true CN115115473A (en) | 2022-09-27 |
CN115115473B CN115115473B (en) | 2023-05-12 |
Family
ID=83331742
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210846393.2A Active CN115115473B (en) | 2022-07-19 | 2022-07-19 | BP neural network-based carbon emission quantitative calculation method for diesel generator set |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115115473B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104362681A (en) * | 2014-11-18 | 2015-02-18 | 湖北省电力勘测设计院 | Island micro-grid capacity optimal-configuration method considering randomness |
CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
CN113887827A (en) * | 2021-10-25 | 2022-01-04 | 国网安徽省电力有限公司电力科学研究院 | Coal blending combustion optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
CN113886752A (en) * | 2021-09-10 | 2022-01-04 | 远景智能国际私人投资有限公司 | Method, device, terminal and storage medium for calculating carbon emission intensity |
CN113935125A (en) * | 2021-09-09 | 2022-01-14 | 西华大学 | BP neural network prediction model optimization method for diesel engine emission performance |
CN114202127A (en) * | 2021-12-18 | 2022-03-18 | 东南大学 | Electric vehicle load optimization method based on graph volume and deep confidence network |
CN114417571A (en) * | 2021-12-24 | 2022-04-29 | 国网湖北省电力有限公司电力科学研究院 | Method and system for realizing on-line monitoring of carbon emission of coal-fired generator set and storage medium |
CN114742294A (en) * | 2022-04-09 | 2022-07-12 | 广州网文三维数字技术有限公司 | Neural network algorithm for carbon emission prediction |
-
2022
- 2022-07-19 CN CN202210846393.2A patent/CN115115473B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104362681A (en) * | 2014-11-18 | 2015-02-18 | 湖北省电力勘测设计院 | Island micro-grid capacity optimal-configuration method considering randomness |
CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
CN113935125A (en) * | 2021-09-09 | 2022-01-14 | 西华大学 | BP neural network prediction model optimization method for diesel engine emission performance |
CN113886752A (en) * | 2021-09-10 | 2022-01-04 | 远景智能国际私人投资有限公司 | Method, device, terminal and storage medium for calculating carbon emission intensity |
CN113887827A (en) * | 2021-10-25 | 2022-01-04 | 国网安徽省电力有限公司电力科学研究院 | Coal blending combustion optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
CN114202127A (en) * | 2021-12-18 | 2022-03-18 | 东南大学 | Electric vehicle load optimization method based on graph volume and deep confidence network |
CN114417571A (en) * | 2021-12-24 | 2022-04-29 | 国网湖北省电力有限公司电力科学研究院 | Method and system for realizing on-line monitoring of carbon emission of coal-fired generator set and storage medium |
CN114742294A (en) * | 2022-04-09 | 2022-07-12 | 广州网文三维数字技术有限公司 | Neural network algorithm for carbon emission prediction |
Non-Patent Citations (1)
Title |
---|
郜新军: "《城市轨道交通***碳排放评估及集成优化控制方法研究》", 《工程科技Ⅰ辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115115473B (en) | 2023-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kenanoğlu et al. | Performance & emission analysis of HHO enriched dual-fuelled diesel engine with artificial neural network prediction approaches | |
Yang et al. | Machine learning prediction of specific capacitance in biomass derived carbon materials: Effects of activation and biochar characteristics | |
Laudan | Cognitive change in technology and science | |
TW200925015A (en) | Mixed type vehicle power system and method of forming multidimentional data of fuel consumption | |
CN105071389A (en) | Hybrid AC/DC microgrid optimization operation method and device considering source-grid-load interaction | |
Solmaz et al. | Comparison of artificial neural network and fuzzy logic approaches for the prediction of in-cylinder pressure in a spark ignition engine | |
CN112347694A (en) | Sea island micro-grid power supply planning method containing ocean current-offshore wind power-tidal current power generation | |
CN116482975A (en) | Virtual-real fusion ship energy management strategy verification method and platform | |
CN115115473A (en) | Diesel generating set carbon emission quantitative calculation method based on BP neural network | |
Gu et al. | Energy management strategy considering fuel economy and life of fuel cell for fuel cell electric vehicles | |
CN106451570A (en) | Method and device for dynamically distributing load of diesel power generation units of ships | |
CN106056168B (en) | The determination method of gas-steam combined circulating generation unit operating condition optimal value | |
CN112072651A (en) | Transient voltage instability and power angle instability identification method based on transient energy function | |
CN115099522B (en) | Active and reactive carbon emission prediction method for special transformer user based on BP neural network | |
CN116050858A (en) | Comprehensive energy service success evaluation method based on normal cloud model and application thereof | |
Horcasitas-Verdiguel et al. | Design and manufacture of ice test module to reduce gasoline consumption using oxyhydrogen gas from an alkaline electrolyzer | |
Guo et al. | Compressed air energy storage and future development | |
Prakash et al. | Multi-objective optimal economic dispatch of a fuel cell and combined heat and power based renewable integrated grid tied micro-grid using whale optimization algorithm | |
CN113949098A (en) | Island type hybrid micro-grid system reliability evaluation method considering FCV | |
CN112677752A (en) | New energy automobile electricity molecule fission driving system based on artificial intelligence | |
Tian et al. | Comprehensive cost-benefit assessment of offshore wind power based on improved VIKOR method | |
Wang et al. | Operation effect evaluation of grid side energy storage power station based on combined weight TOPSIS model | |
CN117312293B (en) | Electric power multisource heterogeneous data management and intelligent analysis method and system | |
Yongqi et al. | Comprehensive benefit analysis for integrated energy systems projects based on ahp-fuzzy | |
Khan et al. | Facts and popular perceptions on saving energy and the environment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |