CN108268359A - The optimization method of air compression station based on deep learning - Google Patents
The optimization method of air compression station based on deep learning Download PDFInfo
- Publication number
- CN108268359A CN108268359A CN201711486859.8A CN201711486859A CN108268359A CN 108268359 A CN108268359 A CN 108268359A CN 201711486859 A CN201711486859 A CN 201711486859A CN 108268359 A CN108268359 A CN 108268359A
- Authority
- CN
- China
- Prior art keywords
- compression station
- air compression
- deep learning
- optimization method
- air
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The present invention provides a kind of optimization method of the air compression station based on deep learning, the optimization method of the air compression station based on deep learning includes the following steps:(A1) using Internet of Things is monitored, the operating parameter of each air compressor machine in air compression station is obtained;(A2) using operating parameter described in deep learning Algorithm Analysis, the operational mode characteristic model of each air compressor machine in air compression station is extracted;(A3) using operational mode characteristic model described in genetic algorithm optimization, unlatching number of units and the opening time of air compressor machine are obtained.The present invention has the advantages that power consumption is low etc..
Description
Technical field
The present invention relates to the optimization methods of air compression station, the more particularly to air compression station based on deep learning.
Background technology
Compressed air is widely used in the every field in industrial production as a kind of energy of clean environment firendly.But as two
The secondary energy, the power consumption of compressed air in itself are huge.According to statistics, the 10% of China's commercial power is used for air compressor machine.But one
Since straight, enterprise does not have the energy consumption of compressed air system enough attention, causes the operation of air compressor machine energy consumption unreasonable, compression
The energy waste of air system.It for enterprise, is generally all supplied by the way of air compression station, air compression station has multiple air compressors group
Into.
At present, all it is by the original control mode of machine (the included control of limits pressure up and down), substantially on air-compressor set
Joint control is not carried out, can only check the operating parameter of separate unit air compressor machine.Compressed air main application sets cushion gas, instrument is used
Gas, purging etc..If cushion gas is being mainly used for gas equipment, if cushion gas is by after oil removing, water removal and dust, specializing in instrument
With gas, other purposes then include purging, cleaning etc..
The air compressor system planning of most of enterprise is less reasonable, effective coordination control is lacked between unit, there are bright
Aobvious waste, main problem include:
1. air compressor machine is opened arbitrarily, high efficiency does not efficiently use.
2. the variation of environment is not accounted for, the influence for pneumatics engine efficiency.If to the air-compressor set of air compression station into
The power consumption of enterprise will be greatly decreased in row optimal control.
Invention content
In order to solve the deficiency in above-mentioned prior art, the present invention provides a kind of air compression stations based on deep learning
Optimization method, be effectively improved the operational efficiency of air compressor machine, and reduce energy consumption.
A kind of optimization method of the air compression station based on deep learning, the optimization method of the air compression station based on deep learning
Include the following steps:
(A1) using Internet of Things is monitored, the operating parameter of each air compressor machine in air compression station is obtained;
(A2) using operating parameter described in deep learning Algorithm Analysis, the operational mode for extracting each air compressor machine in air compression station is special
Levy model;
(A3) using operational mode characteristic model described in genetic algorithm optimization, unlatching number of units and the unlatching of air compressor machine are obtained
Time.
According to the optimization method of the above-mentioned air compression station based on deep learning, optionally, the sky based on deep learning
The optimization method at pressure station further comprises the steps:
(A4) Internet of Things and Hadoop framework of increasing income, structure air compression station optimization operating system are utilized.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that the operating parameter includes:Operation
Time, admission pressure, outlet pressure, air compression station environment temperature, inlet temperature, outlet temperature, flow and power.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that the deep learning algorithm utilizes
Depth autocoder, the depth autocoder include:Encoder, decoder and hidden layer;
The encoder is encoded using following relational expression:
H=f (x)=Sf(Wx+bj)
Wherein, the feature vector that x is made of operating parameter, weights of the W for input vector, bjRepresent j-th of neuron
Threshold value or be known as bias, the hidden layer value that h is;
Decoder is decoded using following relational expression:
Y=g (h)=Sg(Wh+bh)
Wherein, h for hidden layer vector, here as input, W be corresponding weight vector, bhFor threshold value, SgIt is decoder
Activation primitive;
Training process to depth autocoder is that parameter W, b are found on training sample set Dj, bhThe minimum of composition
Reconstructed error, the expression formula of reconstructed error are:
Wherein, x is the input of above-mentioned formula, and g (f (x)) is that the decoder of above-mentioned formula exports, and L is reconstructed error function.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that described to depth autocoder
Training process include the following steps:
(B1) operating parameter of the input as training, it is unsupervised to train first self-encoding encoder;
(B2) using the output of first self-encoding encoder as the input of next self-encoding encoder, second own coding is trained
Device;
(B3) step (B2) is repeated, until completing the training of preset quantity hidden layer;
(B4) using the power H of air compression station as output, increase a reverse transmittance nerve network on the last one hidden layer
Prediction model realizes the weight fine tuning to the prediction model.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that in step (A3), optimization includes
Following steps:
(C1) grid and valuation functions of the operating parameter of structure air compressor machine, valuation functions use
(C2) to the unlatching number of units of air compressor machine, opening sequence, using air compression station initial launch number of units and operation order as just
Initial value assesses fitness individual corresponding to every chromosome, using the power H of air-compressor set as fitness;
(C3) principle higher in accordance with fitness, bigger select probability P, selected from population two individual as it is paternal with
Maternal;
(C4) chromosome of parent both sides is extracted, is intersected, generates filial generation.
(C5) to the chromosome of filial generation into row variation.
(C6) step (C2)-(C4) is repeated, until the generation of new population, when iterations reach setting number, acquisition is empty
Press opens number of units, opening time.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that in step (A3), utilize heredity
Algorithm is solved in the case of air compression station power minimum, obtains the unlatching number of units and sequence of air compressor machine.
Compared with prior art, the device have the advantages that being:
By way of wireless internet of things, air-compressor set Optimal Control System is built, while utilize depth and genetic algorithm,
Optimize air compressor machine and open number of units, operation duration, so as to optimize air-compressor set entirety efficiency, energy saving, environmental protection.
Description of the drawings
With reference to attached drawing, the disclosure will be easier to understand.Skilled addressee readily understands that be:This
A little attached drawings are used only for the technical solution illustrated the present invention, and are not intended to and protection scope of the present invention is construed as limiting.
In figure:
Fig. 1 is the flow chart of the optimization method of the air compression station according to embodiments of the present invention based on deep learning.
Specific embodiment
Fig. 1 and following description describe the present invention optional embodiment with instruct those skilled in the art how to implement and
Reproduce the present invention.In order to instruct technical solution of the present invention, simplified or some conventional aspects be omitted.Those skilled in the art should
The understanding is originated from the modification of these embodiments or replacement will within the scope of the invention.Under those skilled in the art should understand that
Stating feature can combine to form multiple modifications of the invention in various ways.The invention is not limited in following optional as a result,
Embodiment, and be only limited by the claims and their equivalents.
Embodiment:
Fig. 1 schematically illustrates the flow of the optimization method of the air compression station based on deep learning of the embodiment of the present invention
Figure, as shown in Figure 1, the optimization method of the air compression station based on deep learning includes the following steps:
(A1) using Internet of Things is monitored, the operating parameter of each air compressor machine in air compression station is obtained, such as run time, air inlet pressure
Power, outlet pressure, air compression station environment temperature, inlet temperature, outlet temperature, flow and power;
(A2) using operating parameter described in deep learning Algorithm Analysis, the operational mode for extracting each air compressor machine in air compression station is special
Levy model;Specially:
The deep learning algorithm utilizes depth autocoder, and the depth autocoder includes:Encoder, decoding
Device and hidden layer;
The encoder is encoded using following relational expression:
H=f (x)=Sf(Wx+bj)
Wherein, the feature vector that x is made of operating parameter, weights of the W for input vector, bjRepresent j-th of neuron
Threshold value or be known as bias, the hidden layer value that h is;
Decoder is decoded using following relational expression:
Y=g (h)=Sg(Wh+bh)
Wherein, h for hidden layer vector, here as input, W be corresponding weight vector, bhFor threshold value, sgIt is decoder
Activation primitive;
Training process to depth autocoder is that parameter W, b are found on training sample set Dj, bhThe minimum of composition
Reconstructed error, the expression formula of reconstructed error are:
Wherein, x is the input of above-mentioned formula, and g (f (x)) is that the decoder of above-mentioned formula exports, and L is reconstructed error function.
According to the optimization method of the above-mentioned air compression station based on deep learning, it is preferable that described to depth autocoder
Training process include the following steps:
(B1) operating parameter of the input as training, it is unsupervised to train first self-encoding encoder;
(B2) using the output of first self-encoding encoder as the input of next self-encoding encoder, second own coding is trained
Device;
(B3) step (B2) is repeated, until completing the training of preset quantity hidden layer;
(B4) using the power H of air compression station as output, increase a reverse transmittance nerve network on the last one hidden layer
Prediction model realizes the weight fine tuning to the prediction model;
(A3) using operational mode characteristic model described in genetic algorithm optimization, in the case of obtaining air compression station power minimum,
The unlatching number of units of air compressor machine and opening time, specially:
(C1) grid and valuation functions of the operating parameter of structure air compressor machine, valuation functions use
(C2) to the unlatching number of units of air compressor machine, opening sequence, using air compression station initial launch number of units and operation order as just
Initial value assesses fitness individual corresponding to every chromosome, using the power H of air-compressor set as fitness;
(C3) principle higher in accordance with fitness, bigger select probability P, selected from population two individual as it is paternal with
Maternal;
(C4) chromosome of parent both sides is extracted, is intersected, generates filial generation.
(C5) to the chromosome of filial generation into row variation.
(C6) step (C2)-(C4) is repeated, until the generation of new population, when iterations reach setting number, acquisition is empty
Press opens number of units, opening time;
(A4) Internet of Things and Hadoop framework of increasing income, structure air compression station optimization operating system are utilized.
Claims (7)
1. a kind of optimization method of the air compression station based on deep learning, the optimization method packet of the air compression station based on deep learning
Include following steps:
(A1) using Internet of Things is monitored, the operating parameter of each air compressor machine in air compression station is obtained;
(A2) using operating parameter described in deep learning Algorithm Analysis, the operational mode character modules of each air compressor machine in air compression station are extracted
Type;
(A3) using operational mode characteristic model described in genetic algorithm optimization, when obtaining the unlatching number of units of air compressor machine and opening
Between.
2. the optimization method of the air compression station according to claim 1 based on deep learning, it is characterised in that:It is described to be based on deeply
The optimization method for spending the air compression station of study further comprises the steps:
(A4) Internet of Things and Hadoop framework of increasing income, structure air compression station optimization operating system are utilized.
3. the optimization method of the air compression station according to claim 1 based on deep learning, it is characterised in that:The operation ginseng
Number includes:Run time, admission pressure, outlet pressure, air compression station environment temperature, inlet temperature, outlet temperature, flow and work(
Rate.
4. the optimization method of the air compression station according to claim 1 based on deep learning, it is characterised in that:The depth
Algorithm is practised using depth autocoder, the depth autocoder includes:Encoder, decoder and hidden layer;
The encoder is encoded using following relational expression:
H=f (x)=Sf(Wx+bj)
Wherein, the feature vector that x is made of operating parameter, weights of the W for input vector, bjRepresent the threshold of j-th of neuron
Value is known as biasing, the hidden layer value that h is;
Decoder is decoded using following relational expression:
Y=g (h)=Sg(Wh+bh)
Wherein, h for hidden layer vector, here as input, W be corresponding weight vector, bhFor threshold value, SgIt is swashing for decoder
Function living;
Training process to depth autocoder is that parameter W, b are found on training sample set Dj, bhThe minimum reconstruct of composition
Error, the expression formula of reconstructed error are:
Wherein, x is the input of above-mentioned formula, and g (f (x)) is that the decoder of above-mentioned formula exports, and L is reconstructed error function.
5. the optimization method of the air compression station according to claim 4 based on deep learning, it is characterised in that:It is described to depth
The training process of autocoder includes the following steps:
(B1) operating parameter of the input as training, it is unsupervised to train first self-encoding encoder;
(B2) using the output of first self-encoding encoder as the input of next self-encoding encoder, second self-encoding encoder is trained;
(B3) step (B2) is repeated, until completing the training of preset quantity hidden layer;
(B4) using the power H of air compression station as output, increase a reverse transmittance nerve network prediction on the last one hidden layer
Model realizes the weight fine tuning to the prediction model.
6. the optimization method of the air compression station according to claim 1 based on deep learning, it is characterised in that:In step (A3)
In, optimization includes the following steps:
(C1) grid and valuation functions of the operating parameter of structure air compressor machine, valuation functions use
(C2) to the unlatching number of units of air compressor machine, opening sequence, using air compression station initial launch number of units and operation order as initial value,
Fitness individual corresponding to every chromosome is assessed, using the power H of air-compressor set as fitness;
(C3) principle higher in accordance with fitness, bigger select probability P selects two individuals as paternal and female from population
Side;
(C4) chromosome of parent both sides is extracted, is intersected, generates filial generation.
(C5) to the chromosome of filial generation into row variation.
(C6) step (C2)-(C4) is repeated, until the generation of new population, when iterations reach setting number, acquisition air compressor machine
Open number of units, opening time.
7. the optimization method of the air compression station according to claim 1 based on deep learning, it is characterised in that:In step (A3)
In, it is solved in the case of air compression station power minimum using genetic algorithm, obtains the unlatching number of units and sequence of air compressor machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711486859.8A CN108268359A (en) | 2017-12-30 | 2017-12-30 | The optimization method of air compression station based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711486859.8A CN108268359A (en) | 2017-12-30 | 2017-12-30 | The optimization method of air compression station based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108268359A true CN108268359A (en) | 2018-07-10 |
Family
ID=62772865
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711486859.8A Pending CN108268359A (en) | 2017-12-30 | 2017-12-30 | The optimization method of air compression station based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108268359A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109322816A (en) * | 2018-09-30 | 2019-02-12 | 西门子电力自动化有限公司 | Supply method, apparatus, equipment, medium and the program of compressed air |
WO2020165043A1 (en) * | 2019-02-14 | 2020-08-20 | Bayer Cropscience Lp | Machine learning based algorithmic procedure |
CN112901449A (en) * | 2021-03-17 | 2021-06-04 | 英赛孚工业智能科技(苏州)有限公司 | Air compressor system energy consumption optimization method based on machine learning |
CN113669242A (en) * | 2021-08-03 | 2021-11-19 | 新奥数能科技有限公司 | Power control method and device of air compressor system and computer equipment |
CN113670642A (en) * | 2021-08-25 | 2021-11-19 | 广东鑫钻节能科技股份有限公司 | Cloud automatic detection system and method based on air compression station protection device |
CN113807015A (en) * | 2021-09-17 | 2021-12-17 | 南方电网科学研究院有限责任公司 | Parameter optimization method, device, equipment and storage medium for compressed air energy storage system |
CN114893402A (en) * | 2022-04-06 | 2022-08-12 | 合肥工业大学 | Parallel air compressor energy consumption regulation and control method and system based on artificial intelligence |
CN117311430A (en) * | 2023-11-29 | 2023-12-29 | 广东鑫钻节能科技股份有限公司 | Energy-saving digital energy air compression station control system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130173615A1 (en) * | 2011-12-29 | 2013-07-04 | Yu Xu | Techniques for fast loading of data from an external distributed file system to a database management system |
CN105867347A (en) * | 2016-03-29 | 2016-08-17 | 全球能源互联网研究院 | Trans-space cascade fault detection method based on machine learning technology |
CN106127304A (en) * | 2016-06-30 | 2016-11-16 | 国网山东省电力公司无棣县供电公司 | One is applicable to power distribution network Network Topology Design method |
CN106570237A (en) * | 2016-10-25 | 2017-04-19 | 浙江理工大学 | Method and system for monitoring stator blade thickness of turbine of blast furnace gas waste heat recovery device |
CN107229972A (en) * | 2017-03-10 | 2017-10-03 | 东莞理工学院 | A kind of global optimization based on Lamarch inheritance of acquired characters principle, search and machine learning method |
-
2017
- 2017-12-30 CN CN201711486859.8A patent/CN108268359A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130173615A1 (en) * | 2011-12-29 | 2013-07-04 | Yu Xu | Techniques for fast loading of data from an external distributed file system to a database management system |
CN105867347A (en) * | 2016-03-29 | 2016-08-17 | 全球能源互联网研究院 | Trans-space cascade fault detection method based on machine learning technology |
CN106127304A (en) * | 2016-06-30 | 2016-11-16 | 国网山东省电力公司无棣县供电公司 | One is applicable to power distribution network Network Topology Design method |
CN106570237A (en) * | 2016-10-25 | 2017-04-19 | 浙江理工大学 | Method and system for monitoring stator blade thickness of turbine of blast furnace gas waste heat recovery device |
CN107229972A (en) * | 2017-03-10 | 2017-10-03 | 东莞理工学院 | A kind of global optimization based on Lamarch inheritance of acquired characters principle, search and machine learning method |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109322816B (en) * | 2018-09-30 | 2020-04-07 | 西门子电力自动化有限公司 | Method, device, apparatus and medium for supplying compressed air |
CN109322816A (en) * | 2018-09-30 | 2019-02-12 | 西门子电力自动化有限公司 | Supply method, apparatus, equipment, medium and the program of compressed air |
WO2020165043A1 (en) * | 2019-02-14 | 2020-08-20 | Bayer Cropscience Lp | Machine learning based algorithmic procedure |
CN112901449B (en) * | 2021-03-17 | 2023-03-03 | 英赛孚工业智能科技(苏州)有限公司 | Air compressor system energy consumption optimization method based on machine learning |
CN112901449A (en) * | 2021-03-17 | 2021-06-04 | 英赛孚工业智能科技(苏州)有限公司 | Air compressor system energy consumption optimization method based on machine learning |
CN113669242A (en) * | 2021-08-03 | 2021-11-19 | 新奥数能科技有限公司 | Power control method and device of air compressor system and computer equipment |
CN113670642B (en) * | 2021-08-25 | 2023-12-19 | 广东鑫钻节能科技股份有限公司 | Cloud automatic detection system and method based on air compression station protection device |
CN113670642A (en) * | 2021-08-25 | 2021-11-19 | 广东鑫钻节能科技股份有限公司 | Cloud automatic detection system and method based on air compression station protection device |
CN113807015A (en) * | 2021-09-17 | 2021-12-17 | 南方电网科学研究院有限责任公司 | Parameter optimization method, device, equipment and storage medium for compressed air energy storage system |
CN113807015B (en) * | 2021-09-17 | 2023-12-26 | 南方电网科学研究院有限责任公司 | Parameter optimization method, device, equipment and storage medium for compressed air energy storage system |
CN114893402A (en) * | 2022-04-06 | 2022-08-12 | 合肥工业大学 | Parallel air compressor energy consumption regulation and control method and system based on artificial intelligence |
CN117311430A (en) * | 2023-11-29 | 2023-12-29 | 广东鑫钻节能科技股份有限公司 | Energy-saving digital energy air compression station control system |
CN117311430B (en) * | 2023-11-29 | 2024-02-20 | 广东鑫钻节能科技股份有限公司 | Energy-saving digital energy air compression station control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108268359A (en) | The optimization method of air compression station based on deep learning | |
CN104915805B (en) | A kind of river ecosystem restoration effect evaluation method | |
CN103514398B (en) | A kind of real-time online log detection method and system | |
CN108985632A (en) | A kind of electricity consumption data abnormality detection model based on isolated forest algorithm | |
CN109978287B (en) | Intelligent polycrystalline silicon production method and system | |
WO2004104817A3 (en) | Sharing method and apparatus using directed graphs | |
CN112000771B (en) | Judicial public service-oriented sentence pair intelligent semantic matching method and device | |
CN110827791B (en) | Edge-device-oriented speech recognition-synthesis combined modeling method | |
CN106127304B (en) | One kind is applied to power distribution network Network Topology Design method | |
CN107248740A (en) | A kind of household electricity machine utilization Forecasting Methodology | |
CN105574589A (en) | Transformer oil chromatogram fault diagnosis method based on ecological niche genetic algorithm | |
CN106779071A (en) | A kind of neutral net adaptive speed regulation method for Mine Ventilator | |
CN110321947A (en) | A kind of multiplexing electric abnormality pre-judging method based on convolutional neural networks | |
US20240062039A1 (en) | Design method of polymeric seawater desalination membrane based on graph neural network | |
CN109740722A (en) | A kind of network representation learning method based on Memetic algorithm | |
CN103793747A (en) | Sensitive information template construction method in network content safety management | |
CN114632624B (en) | Electric dust removal operation optimization system and optimization method | |
CN113919635A (en) | Park comprehensive energy system evaluation method based on energy efficiency-economy-environment | |
CN104680259B (en) | The energy conservation optimizing method of oil extractor operating parameter | |
CN103970985A (en) | Population global optimization method based on local abstract convexity estimation | |
Long et al. | Is financial development good for ecological footprint? A Bayesian multilevel mixed-effects analysis in ASEAN countries | |
CN1317677C (en) | Genetic algorithm based human face sample generating method | |
Zhang et al. | A decision tree scoring model based on genetic algorithm and k-means algorithm | |
CN108460501B (en) | Wind power station output power prediction method based on combined model | |
CN105427583A (en) | LZW-coding-based road traffic data compression method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180710 |
|
WD01 | Invention patent application deemed withdrawn after publication |