CN109184931A - The active control system and method for biogas internal combustion engine generator group - Google Patents
The active control system and method for biogas internal combustion engine generator group Download PDFInfo
- Publication number
- CN109184931A CN109184931A CN201811346181.8A CN201811346181A CN109184931A CN 109184931 A CN109184931 A CN 109184931A CN 201811346181 A CN201811346181 A CN 201811346181A CN 109184931 A CN109184931 A CN 109184931A
- Authority
- CN
- China
- Prior art keywords
- internal combustion
- combustion engine
- engine generator
- generator group
- biogas
- 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
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims abstract description 15
- 239000007789 gas Substances 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 6
- 238000007791 dehumidification Methods 0.000 claims description 6
- 239000003546 flue gas Substances 0.000 claims description 6
- 239000003921 oil Substances 0.000 claims description 6
- 238000010248 power generation Methods 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 238000010304 firing Methods 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000000779 smoke Substances 0.000 claims description 5
- 239000002516 radical scavenger Substances 0.000 claims description 4
- 239000010687 lubricating oil Substances 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims 1
- 238000010977 unit operation Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000295 complement effect Effects 0.000 description 2
- 238000005474 detonation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 238000000855 fermentation Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000010815 organic waste Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 150000004767 nitrides Chemical class 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000003584 silencer Effects 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/0025—Controlling engines characterised by use of non-liquid fuels, pluralities of fuels, or non-fuel substances added to the combustible mixtures
- F02D41/0027—Controlling engines characterised by use of non-liquid fuels, pluralities of fuels, or non-fuel substances added to the combustible mixtures the fuel being gaseous
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D29/00—Controlling engines, such controlling being peculiar to the devices driven thereby, the devices being other than parts or accessories essential to engine operation, e.g. controlling of engines by signals external thereto
- F02D29/06—Controlling engines, such controlling being peculiar to the devices driven thereby, the devices being other than parts or accessories essential to engine operation, e.g. controlling of engines by signals external thereto peculiar to engines driving electric generators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D35/00—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for
- F02D35/0015—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for using exhaust gas sensors
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D35/00—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for
- F02D35/02—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for on interior conditions
- F02D35/025—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for on interior conditions by determining temperatures inside the cylinder, e.g. combustion temperatures
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D35/00—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for
- F02D35/02—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for on interior conditions
- F02D35/027—Controlling engines, dependent on conditions exterior or interior to engines, not otherwise provided for on interior conditions using knock sensors
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/22—Safety or indicating devices for abnormal conditions
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/22—Safety or indicating devices for abnormal conditions
- F02D2041/224—Diagnosis of the fuel system
- F02D2041/225—Leakage detection
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
- F02D2200/021—Engine temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
- F02D2200/023—Temperature of lubricating oil or working fluid
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
- F02D2200/04—Engine intake system parameters
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
- F02D2200/06—Fuel or fuel supply system parameters
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Output Control And Ontrol Of Special Type Engine (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
Present disclose provides the active control systems and method of a kind of biogas internal combustion engine generator group.Wherein, a kind of active control system of biogas internal combustion engine generator group, comprising: environment sensing sensor group is configured as the environment sensing data of acquisition unit and is sent to active controller;Active controller is also connected with biogas internal combustion engine generator group ECU controller, and active controller is configured as the internal operation data of acquisition biogas internal combustion engine generator group ECU controller;Active controller is also configured to that corresponding active safety executing agency is driven to act according to the environment sensing data of unit;The inside real-time running data of biogas internal combustion engine generator group ECU controller is input to the biogas internal combustion engine generator group fault prediction model of training completion, exports the failure predication result of biogas internal combustion engine generator group;Pass through the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two complementation active control biogas internal combustion engine generator group, to improve the stability of biogas internal combustion engine generator group operation.
Description
Technical field
The disclosure belongs to biogas internal combustion engine generator technical group field more particularly to a kind of active of biogas internal combustion engine generator group
Control system and method.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
Biogas internal combustion engine generator group is to integrate the comprehensive utilization of energy new system of environmental protection and energy conservation, it using it is industrial,
A large amount of organic wastes in agricultural or urban life handle a large amount of biogas generated through anaerobic fermentation, and biogas is in combustion in IC engine
Room burning generates the power generation of heat-driven internal combustion engine generator group, and the waste heat of generating set can be made full use of to realize supply of cooling, heating and electrical powers system
System, overall efficiency generate good economic, energy conservation and environmental benefit up to 70-80% or so.
But generated fire damp concentration difference is big at a temperature of different organic waste raw material and different fermentations, fluctuates
Property it is big, to biogas internal combustion engine generator group it is efficient, stable, safe operation propose huge challenge.Especially biogas internal combustion generates electricity
Units' installation operates near bionethanation system, will be to unit and natural pond if operational safety problem such as occurs in biogas internal combustion engine generator group
Gas system generates huge security risk.
Summary of the invention
According to the one aspect of one or more other embodiments of the present disclosure, a kind of active of biogas internal combustion engine generator group is provided
Control system can be improved the stability and reliability of the operation of biogas internal combustion engine generator group.
A kind of active control system of biogas internal combustion engine generator group of the disclosure, comprising:
Environment sensing sensor group is configured as the environment sensing data of acquisition unit and is sent to active controller;
The active controller is also connected with biogas internal combustion engine generator group ECU controller, and the active controller is configured as acquisition natural pond
The internal operation data of gas internal combustion engine generator group ECU controller;
The active controller is also configured to
Corresponding active safety executing agency is driven to act according to the environment sensing data of unit;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is input to the biogas internal combustion of training completion
Generating set fault prediction model exports the failure predication result of biogas internal combustion engine generator group;
Judged by the judgement of unit external data and the prediction of internal operation mechanism model, in the two complementation active control biogas
Generating set is fired, to improve the stability of biogas internal combustion engine generator group operation.
In one or more embodiments, the active controller acquires environment using RS485 bus and Modbus agreement
Data that detecting sensor group is perceived simultaneously store in the database.
In one or more embodiments, the environment sensing sensor group, comprising: leak detector, gas are dense
Spend sensor, smoke sensor device, pressure sensor, flowmeter, vibrating sensor, sound transducer, Temperature Humidity Sensor and figure
As collector.
In one or more embodiments, the environment sensing sensor group, further includes:
Generating set grounding detector, is used to detect whether generating set earthed system to work normally;
Alternating current powers off sensor, is used to detect whether alternating current to power off.
In one or more embodiments, the active safety executing agency, comprising: scavenger fan, biogas valve, alarm
Device, emergency lighting system and dehumidification system.
In one or more embodiments, the active controller is also configured to
Biogas internal combustion engine generator group fault prediction model is constructed using deep learning convolutional neural networks;
It determines the input variable and output variable of biogas internal combustion engine generator group fault prediction model, and is normalized;
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and is tested in biogas using test set
The output result precision for firing generating set fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion
The training of generating set fault prediction model.
In one or more embodiments, the input variable of biogas internal combustion engine generator group fault prediction model includes: biogas
Data, air data, flue gas data, jacket water data and lubricating oil data;
The output variable of biogas internal combustion engine generator group fault prediction model includes: the pinking of biogas internal combustion engine generator group operation
Sensing data, oxygen sensor data, exhaust gas temperature, oil temperature, burning cylinder temperature and cylinder sleeve coolant-temperature gage.
According to the other side of one or more other embodiments of the present disclosure, a kind of master of biogas internal combustion engine generator group is provided
The control method of autocontrol system can be improved the stability and reliability of the operation of biogas internal combustion engine generator group.
A kind of control method of the active control system of biogas internal combustion engine generator group of the disclosure, comprising:
Compare unit environment sensing data and default safety condition, when the environment sensing data of unit do not meet default peace
When full condition, corresponding active safety executing agency is driven to act;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is received, and is input to trained completion
Biogas internal combustion engine generator group fault prediction model, export biogas internal combustion engine generator group failure predication result;
Judged by the judgement of unit external data and the prediction of internal operation mechanism model, in the two complementation active control biogas
Generating set is fired, to improve the stability of biogas internal combustion engine generator group operation.
In one or more embodiments, the inside real-time running data of biogas internal combustion engine generator group ECU controller is defeated
Enter to before the biogas internal combustion engine generator group fault prediction model of training completion, further includes:
Biogas internal combustion engine generator group fault prediction model is constructed using deep learning convolutional neural networks;
It determines the input variable and output variable of biogas internal combustion engine generator group fault prediction model, and is normalized;
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and is tested in biogas using test set
The output result precision for firing generating set fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion
The training of generating set fault prediction model.
In one or more embodiments, biogas internal combustion is sent out using the data normalization method based on Sigmoid function
The input variable and output variable of motor group fault prediction model are normalized.
The beneficial effect of the disclosure is:
(1) disclosure drives corresponding active safety executing agency to act according to the environment sensing data of unit, to reach
Directly judge and implement the purpose of active safety control;By the inside real time execution number of biogas internal combustion engine generator group ECU controller
According to the biogas internal combustion engine generator group fault prediction model for being input to training completion, the failure predication of biogas internal combustion engine generator group is exported
As a result;Fault prediction model based on data unit operation is to excavate the potential of inside based on unit internal operation mechanism model
Danger simultaneously implements active safety control;By the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two is mutual
Active control biogas internal combustion engine generator group is mended, to improve the stability and reliability of the operation of biogas internal combustion engine generator group.
(2) ambient condition information and data unit operation of the disclosure based on biogas internal combustion engine generator group is established in difference
The dynamic mathematical models of the operation characteristic of accurate description biogas internal combustion engine generator group under biogas ingredient, multi-state see clearly its complexity
Moving law and failure predication, the ambient condition information of unit is actively seen clearly, and establish active safety control mechanism, from basic
The upper safety and stability performance for improving unit, fundamentally ensure entire bionethanation system and generating set system operation stability and
Reliability.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is a kind of structural schematic diagram of the active control system of biogas internal combustion engine generator group of the disclosure.
Fig. 2 is a kind of control method flow chart of the active control system of biogas internal combustion engine generator group of the disclosure.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Fig. 1 is a kind of structural schematic diagram of the active control system of biogas internal combustion engine generator group of the disclosure.
As shown in Figure 1, a kind of active control system of biogas internal combustion engine generator group of the disclosure, comprising: environment sensing passes
Sensor group, active controller, biogas internal combustion engine generator group ECU controller and active safety executing agency.
The active control system of biogas internal combustion engine generator group is analyzed in detail below:
(1) environment sensing sensor group
Environment sensing sensor group is configured as the environment sensing data of acquisition unit and is sent to active controller.
In specific implementation, the environment sensing sensor group, including but not limited to: leak detector, gas are dense
Spend sensor, smoke sensor device, pressure sensor, flowmeter, vibrating sensor, sound transducer, Temperature Humidity Sensor and figure
As collector.
The environment sensing sensor group, further includes:
Generating set grounding detector, is used to detect whether generating set earthed system to work normally;
Alternating current powers off sensor, is used to detect whether alternating current to power off.
Such as:
1) explosion-proof type biogas leak detection device: whether the biogas for detecting biogas pipeline leaks;
2) explosion-proof type gas concentration lwevel sensor: it is for detecting the flue in biogas internal combustion engine generator group computer room
No leakage;
3) explosion-proof type CO concentration sensor: whether abundant for detecting the burning of biogas internal combustion engine generator group;
4) smoke alarm: for detecting whether biogas internal combustion engine generator group computer room has smog alarm;
5) biogas pipeline pressure: for detecting biogas pipeline supply gas pressure, if meet pressure demand;
6) biogas flowmeter: for detecting whether biogas pipeline blocks;
7) explosion-proof unit vibrating sensor: for detect biogas internal combustion engine generator group whether normal combustion;
8) sensor noise: for detecting whether biogas internal combustion engine generator group silencer works normally;
9) cable temperature detector: for detect generating set power output cable whether excess load;
10) generating set earthed system: for detecting whether generating set earthed system works normally;
11) flue pressure sensor: for detecting flue pressure, judge whether flue blocks;
12) flue gas Nox sensor: for detecting the concentration of nitride
13) unit indoor temperature transmitter: for detecting the temperature in computer room.
14) unit indoor humidity sensor: for detecting the humidity in air, excessive will cause of humidity is caught fire.
15) operator's automatic identification camera: for automatic equipment whether unit operations staff;
16) alternating current powers off sensor: for detecting whether alternating current powers off.
Element model in environment sensing sensor group, as shown in table 1.
Element model in 1 environment sensing sensor group of table
(2) biogas internal combustion engine generator group ECU controller
Biogas internal combustion engine generator group active controller provides RS485 interface and RJ45 interface and biogas internal combustion engine generator group
ECU communication, the internal operation data N of the biogas internal combustion engine generator group ECU of acquisitioniInclude:
Ni=[HCH4,HQ2,CZS,CBZ,TPY,PJY,TJY,PZQ,JTQ,TG,TGT,DZG];
Wherein, HCH4For CH in biogas4Content (%), HQ2For oxygen sensor data value (%), CZSFor biogas internal combustion engine
Tachometer value (rpm), CBZFor detonation sensor data value (%), TPYFor biogas internal combustion engine generator group exhaust gas temperature value (DEG C), PJY
For the oil pressure force value (kPa) of biogas internal combustion engine generator group, TJYFor oil temperature (DEG C), the P of biogas internal combustion engine generator groupZQFor
The intake manifold pressure value (kPa) of biogas internal combustion engine generator group, JTQFor ignition advance angle (°), the T of biogas internal combustion engine generator groupG
For burning cylinder temperature (DEG C), the T of biogas internal combustion engine generator groupGTSFor cylinder sleeve coolant-temperature gage (DEG C), the D of biogas internal combustion engine generator groupZG
For the generated output (kW) of biogas internal combustion engine generator group.
(3) active safety executing agency
Specifically, the active safety executing agency, including but not limited to: scavenger fan, alarm, is answered at biogas valve
Anxious lighting system and dehumidification system.
In the present embodiment, the active safety executing agency of biogas internal combustion engine generator group include: electric control exhaust fan, it is automatically controlled
Biogas valve, alarm lamp, alarm, emergency lighting system and dehumidification system, concrete model, as shown in table 2.
The model of 2 active safety executing agency of table
(4) active controller
Active controller is also configured to
Corresponding active safety executing agency is driven to act according to the environment sensing data of unit;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is input to the biogas internal combustion of training completion
Generating set fault prediction model exports the failure predication result of biogas internal combustion engine generator group;
Judged by the judgement of unit external data and the prediction of internal operation mechanism model, in the two complementation active control biogas
Generating set is fired, to improve the stability of biogas internal combustion engine generator group operation.
Specifically, the active controller acquires environment sensing sensor group institute using RS485 bus and Modbus agreement
The data of perception simultaneously store in the database.
The active controller of the present embodiment operates on X86 platform and uses linux real time operating system.
The function of the active controller of the present embodiment are as follows:
Acquire biogas internal combustion engine generator group external sensor data;
The internal operation data read by RS485 communication module and ECU communication;
Operation history data is stored in data platform;
Run active safety control method;
It exports active safety control signal and runs active safety executing agency.
The environment and safe operation data platform of biogas internal combustion engine generator group, the data platform is using RJ45 interface and actively
Controller connection, the data platform establish the environment and safe operation number of SQL Server database purchase biogas internal combustion engine generator
According to.
In specific implementation, active controller drives corresponding active safety to execute machine according to the environment sensing data of unit
The process of structure movement, as shown in Figure 2:
Active controller detects any one alarm, active controller in biogas leakage alarm detector and smoke alarm
It then increases scavenger fan power and starts alarm, active controller and biogas internal combustion engine generator group ECU are communicated, and make generating set
Reduce generated output and with power grid off-network, generating set is shut down after off-network.Finally, active controller closes biogas valve.
As active controller detects that any one in gas concentration lwevel, CO concentration, temperature and flue gas NOx is more than setting
Value, then active controller increases exhaust fan power then to improve the air circulation in computer room, while starting alarm.Such as 2 minutes
Interior, gas concentration lwevel, carbonomonoxide concentration or temperature and flue gas NOx are lower than setting value, then close alarm, and keep air draft
The operation power of fan.Otherwise, active controller and biogas internal combustion engine generator group ECU are communicated, and reduce generating set by generated output
And with power grid off-network, after off-network, generating set is shut down, and closes biogas valve.
Active controller such as detects that humidity value is more than setting value, then active controller starts dehumidification system to reduce computer room
Interior humidity, while starting alarm.If humidity value is lower than setting value, then alarm and closed dehumidification system are closed.
The recognition of face camera of active controller such as detects unlicensed operation personnel, then active controller starting alarm
Device and alarm lamp, and play safety instruction voice;
Active controller such as detects alternating current power-off and generating set ground fault, and active controller starts alarm and report
Warning lamp and emergency lighting system, and communicated with biogas internal combustion engine generator group ECU, make generating set and power grid off-network, after off-network, sends out
Electric compressor emergency shutdown simultaneously closes biogas valve;
As detected, biogas pressure is lower than the biogas pressure value that unit is allowed to active controller, then active controller starts
Alarm, and being communicated with biogas internal combustion engine generator group ECU, make generating set reduce load and with power grid off-network, after off-network, power generation
Unit is idle, until biogas pressure reach the pressure value that unit allowed increase load and with power grid it is grid-connected.Such as biogas pressure
Power is unable to reach biogas pressure setting value in 10 minutes, then generating set is shut down.
Active controller such as detects that noise is more than setting value 10%, then active controller starts alarm, and and biogas
Internal combustion engine generator group ECU communication reduces generating set by load and with power grid off-network, compressor emergency shutdown after off-network.
In specific implementation, the inside real-time running data of biogas internal combustion engine generator group ECU controller is input to training
The process of the biogas internal combustion engine generator group fault prediction model of completion includes:
(1) it is primarily based on environmental data and operation data, biogas internal combustion is established using deep learning convolutional neural networks and sends out
The fault prediction model of motor group;
Determine the input variable I of biogas internal combustion engine generator group failure predication modelingiWith output variable Oi;
The input variable I of biogas internal combustion engine generator group fault prediction modeliIt include: biogas data, air data, flue gas number
According to, jacket water data, lubricating oil data;Determine the input variable I of biogas internal combustion engine generator group modelingi(i=1 ... .9): Ii=
[HCH4,LZQ,YZQ,LKQ,JTQ,CZS,DYG,DWG,TJF];
Wherein, LZQFor the flow value (m of biogas3/h);YZQFor the pressure value (kPa) of biogas;TJFFor the temperature value in computer room
(℃);
The output variable O of biogas internal combustion engine generator group fault prediction modeliIt include: the quick-fried of biogas internal combustion engine generator group operation
Shake sensing data, oxygen sensor data, exhaust gas temperature, oil temperature, burning cylinder temperature, cylinder sleeve coolant-temperature gage;Determine biogas
The output variable O of internal combustion engine generator group Holistic modelingi(i=1 ... .8): Oi=[CBZ,HQ2,TJY,TG,TGTS,LGTS,TYQ,LYQ,
TRHY]。
(2) method for normalizing based on Sigmoid function is used, by input variable IiWith output variable OiData normalization;
Using the data normalization method based on Sigmoid function, this method can effectively expand the power generation of biogas internal combustion
The otherness of the state acquisition system operation data of unit, normalized function are as follows:
Wherein, NIi(i=1 ... 9) is based on the data after Sigmoid function normalization, NOi(i=1 ... 8) for based on
Data after Sigmoid function normalization.
(3) convolutional neural networks (Convolutional Neural Network, CNN) based on deep learning are constructed,
According to input variable IiData and output variable O after data normalizationiData training convolutional neural networks, obtain biogas in
Fire generating set fault prediction model.
Convolutional neural networks (Convolutional Neural Network, CNN), are a kind of feedforward neural network, people
Work neuron can respond surrounding cells, can carry out large data calculation process.Convolutional neural networks mainly include input layer,
Convolutional layer, pond layer and full articulamentum.
Modeling procedure are as follows:
Step 1: the input layer of this method is 1200*9*10 three-dimensional vector, wherein 1200 be 1200 groups of operation datas, and 9 are
9 influence factors, 10 be time dimension;
Step 2: this method convolutional layer is 3 layers, and convolutional layer sets the number of convolution kernel as 128, the area size of convolution kernel
For 4*4;
Step 3: pond layer uses Max-Pooling (maximum pond sample level), and the area size of sample level is 2*2;
Step 4: the activation primitive that this method uses is hyperbolic tangent function tanh, mathematic(al) representation are as follows:
Step 5: the optimization algorithm used utilizes gradient for Adam (Adaptive Moment Estimation) method
Single order moments estimation and second order moments estimation dynamic adjust the learning rate of each parameter.The Optimum learning rate Lr=0.05 of selection.
Step 6: full articulamentum is set as 256 neurons, sets Dropout parameter as 0.5.
Step 7: setting the output layer of biogas internal combustion engine generator group fault prediction model as the two-dimensional vector of 8*10, wherein 8
It is time dimension for predicted vector, 10;
Step 8: obtain optimal weight matrix W, obtain biogas internal combustion engine generator group based on deep learning convolutional Neural
The fault prediction model of network.
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and is tested in biogas using test set
The output result precision for firing generating set fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion
The training of generating set fault prediction model.
(4) the biogas internal combustion engine generator group fault prediction model completed based on training, the model of unit real time execution is defeated
Enter data and be input to failure operation model to obtain the model output data of fault prediction model, as detonation sensor data, oxygen pass
Sensor data, exhaust gas temperature, oil temperature, burning cylinder temperature, cylinder sleeve coolant-temperature gage deviation be greater than 5%, active safety control
Device starts alarm and alarm lamp, and reduces unit load, and with power grid off-network, shut down after off-network and close biogas valve, such as
Shown in Fig. 2.
The disclosure drives corresponding active safety executing agency to act according to the environment sensing data of unit, to reach direct
Judge and implement the purpose of active safety control;The inside real-time running data of biogas internal combustion engine generator group ECU controller is defeated
Enter the biogas internal combustion engine generator group fault prediction model completed to training, exports the failure predication knot of biogas internal combustion engine generator group
Fruit;Fault prediction model based on data unit operation is to excavate internal potential danger based on unit internal operation mechanism model
Simultaneously implement active safety control in danger;By the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two is complementary
Active control biogas internal combustion engine generator group, to improve the stability and reliability of the operation of biogas internal combustion engine generator group.
A kind of control method of the active control system of biogas internal combustion engine generator group of the disclosure, comprising:
Compare unit environment sensing data and default safety condition, when the environment sensing data of unit do not meet default peace
When full condition, corresponding active safety executing agency is driven to act;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is received, and is input to trained completion
Biogas internal combustion engine generator group fault prediction model, export biogas internal combustion engine generator group failure predication result;
Judged by the judgement of unit external data and the prediction of internal operation mechanism model, in the two complementation active control biogas
Generating set is fired, to improve the stability of biogas internal combustion engine generator group operation.
In one or more embodiments, the inside real-time running data of biogas internal combustion engine generator group ECU controller is defeated
Enter to before the biogas internal combustion engine generator group fault prediction model of training completion, further includes:
Biogas internal combustion engine generator group fault prediction model is constructed using deep learning convolutional neural networks;
It determines the input variable and output variable of biogas internal combustion engine generator group fault prediction model, and is normalized;
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and is tested in biogas using test set
The output result precision for firing generating set fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion
The training of generating set fault prediction model.
Specifically, using the data normalization method based on Sigmoid function to biogas internal combustion engine generator group failure predication
The input variable and output variable of model are normalized.
The disclosure drives corresponding active safety executing agency to act according to the environment sensing data of unit, to reach direct
Judge and implement the purpose of active safety control;The inside real-time running data of biogas internal combustion engine generator group ECU controller is defeated
Enter the biogas internal combustion engine generator group fault prediction model completed to training, exports the failure predication knot of biogas internal combustion engine generator group
Fruit;Fault prediction model based on data unit operation is to excavate internal potential danger based on unit internal operation mechanism model
Simultaneously implement active safety control in danger;By the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two is complementary
Active control biogas internal combustion engine generator group, to improve the stability and reliability of the operation of biogas internal combustion engine generator group.
Although above-mentioned be described in conjunction with specific embodiment of the attached drawing to the disclosure, model not is protected to the disclosure
The limitation enclosed, those skilled in the art should understand that, on the basis of the technical solution of the disclosure, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within the protection scope of the disclosure.
Claims (10)
1. a kind of active control system of biogas internal combustion engine generator group characterized by comprising
Environment sensing sensor group is configured as the environment sensing data of acquisition unit and is sent to active controller;It is described
Active controller is also connected with biogas internal combustion engine generator group ECU controller, and the active controller is configured as in acquisition biogas
Fire the internal operation data of generating set ECU controller;
The active controller is also configured to
Corresponding active safety executing agency is driven to act according to the environment sensing data of unit;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is input to the biogas internal combustion power generation of training completion
Unit fault prediction model exports the failure predication result of biogas internal combustion engine generator group;
Pass through the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two complementation active control biogas internal combustion hair
Motor group, to improve the stability of biogas internal combustion engine generator group operation.
2. a kind of active control system of biogas internal combustion engine generator group as described in claim 1, which is characterized in that the active
Controller is using RS485 bus and the Modbus agreement data that are perceived of acquisition environment sensing sensor group and is stored in database
In.
3. a kind of active control system of biogas internal combustion engine generator group as described in claim 1, which is characterized in that the environment
Detecting sensor group, comprising: leak detector, gas concentration sensor, smoke sensor device, pressure sensor, flowmeter,
Vibrating sensor, sound transducer, Temperature Humidity Sensor and image acquisition device.
4. a kind of active control system of biogas internal combustion engine generator group as claimed in claim 3, which is characterized in that the environment
Detecting sensor group, further includes:
Generating set grounding detector, is used to detect whether generating set earthed system to work normally;
Alternating current powers off sensor, is used to detect whether alternating current to power off.
5. a kind of active control system of biogas internal combustion engine generator group as described in claim 1, which is characterized in that the active
Safety and firing mechanism, comprising: scavenger fan, biogas valve, alarm, emergency lighting system and dehumidification system.
6. a kind of active control system of biogas internal combustion engine generator group as described in claim 1, which is characterized in that the active
Controller is also configured to
Biogas internal combustion engine generator group fault prediction model is constructed using deep learning convolutional neural networks;
It determines the input variable and output variable of biogas internal combustion engine generator group fault prediction model, and is normalized;
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and biogas internal combustion hair is tested using test set
The output result precision of motor group fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion power generation
The training of unit fault prediction model.
7. a kind of active control system of biogas internal combustion engine generator group as claimed in claim 6, which is characterized in that biogas internal combustion
The input variable of generating set fault prediction model includes: biogas data, air data, flue gas data, jacket water data and profit
Lubricating oil data;
The output variable of biogas internal combustion engine generator group fault prediction model includes: the pinking sensing of biogas internal combustion engine generator group operation
Device data, oxygen sensor data, exhaust gas temperature, oil temperature, burning cylinder temperature and cylinder sleeve coolant-temperature gage.
8. a kind of controlling party of such as active control system of biogas internal combustion engine generator group of any of claims 1-7
Method characterized by comprising
Compare unit environment sensing data and default safety condition, preset safe item when the environment sensing data of unit are not met
When part, corresponding active safety executing agency is driven to act;
The inside real-time running data of biogas internal combustion engine generator group ECU controller is received, and is input to the natural pond of training completion
Gas internal combustion engine generator group fault prediction model exports the failure predication result of biogas internal combustion engine generator group;
Pass through the judgement of unit external data and the prediction judgement of internal operation mechanism model, the two complementation active control biogas internal combustion hair
Motor group, to improve the stability of biogas internal combustion engine generator group operation.
9. the control method of the active control system of biogas internal combustion engine generator group as claimed in claim 8, which is characterized in that will
The inside real-time running data of biogas internal combustion engine generator group ECU controller is input to the biogas internal combustion engine generator group event of training completion
Before barrier prediction model, further includes:
Biogas internal combustion engine generator group fault prediction model is constructed using deep learning convolutional neural networks;
It determines the input variable and output variable of biogas internal combustion engine generator group fault prediction model, and is normalized;
By normalized input variable and output variable building sample set and test set;
Biogas internal combustion engine generator group fault prediction model is trained using sample set, and biogas internal combustion hair is tested using test set
The output result precision of motor group fault prediction model, when output result precision reaches preset requirement, completion biogas internal combustion power generation
The training of unit fault prediction model.
10. the control method of the active control system of biogas internal combustion engine generator group as claimed in claim 9, which is characterized in that
Using the data normalization method based on Sigmoid function to the input variable of biogas internal combustion engine generator group fault prediction model and
Output variable is normalized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811346181.8A CN109184931B (en) | 2018-11-13 | 2018-11-13 | Active control system and method for methane internal combustion generator set |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811346181.8A CN109184931B (en) | 2018-11-13 | 2018-11-13 | Active control system and method for methane internal combustion generator set |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109184931A true CN109184931A (en) | 2019-01-11 |
CN109184931B CN109184931B (en) | 2024-01-19 |
Family
ID=64939583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811346181.8A Active CN109184931B (en) | 2018-11-13 | 2018-11-13 | Active control system and method for methane internal combustion generator set |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109184931B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112069724A (en) * | 2020-07-21 | 2020-12-11 | 上海宇航系统工程研究所 | Rocket health degree evaluation method based on long-time and short-time memory self-encoder |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201401236Y (en) * | 2009-04-30 | 2010-02-10 | 福建绿色大地环保科技有限公司 | Novel control system of marsh gas generating set |
CN105226613A (en) * | 2015-10-23 | 2016-01-06 | 河南柴油机重工有限责任公司 | A kind of refuse landfill gas generating set supervisory control system and method |
CN105257408A (en) * | 2015-10-23 | 2016-01-20 | 河南柴油机重工有限责任公司 | Waste landfill gas engine monitoring device and method |
CN105760617A (en) * | 2016-03-07 | 2016-07-13 | 华北电力大学(保定) | Calculation method applied to multi-parameter fault prediction and judgment indexes of wind generating set |
CN105927399A (en) * | 2016-06-16 | 2016-09-07 | 山东大学 | Digital integrated controller of small biomass gas internal combustion generator unit and method |
CN205830707U (en) * | 2016-07-26 | 2016-12-28 | 天津市灥嘉科技发展有限公司 | A kind of domestic animal ecologic breeding control system |
CN108319150A (en) * | 2018-04-25 | 2018-07-24 | 山东交通学院 | The full running state information perception of bionethanation system and optimal control system and method |
KR101903528B1 (en) * | 2018-01-24 | 2018-10-25 | 주식회사 하나티이씨 | Optimal control system of landfill gas and biogas plant using deep running technique |
-
2018
- 2018-11-13 CN CN201811346181.8A patent/CN109184931B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201401236Y (en) * | 2009-04-30 | 2010-02-10 | 福建绿色大地环保科技有限公司 | Novel control system of marsh gas generating set |
CN105226613A (en) * | 2015-10-23 | 2016-01-06 | 河南柴油机重工有限责任公司 | A kind of refuse landfill gas generating set supervisory control system and method |
CN105257408A (en) * | 2015-10-23 | 2016-01-20 | 河南柴油机重工有限责任公司 | Waste landfill gas engine monitoring device and method |
CN105760617A (en) * | 2016-03-07 | 2016-07-13 | 华北电力大学(保定) | Calculation method applied to multi-parameter fault prediction and judgment indexes of wind generating set |
CN105927399A (en) * | 2016-06-16 | 2016-09-07 | 山东大学 | Digital integrated controller of small biomass gas internal combustion generator unit and method |
CN205830707U (en) * | 2016-07-26 | 2016-12-28 | 天津市灥嘉科技发展有限公司 | A kind of domestic animal ecologic breeding control system |
KR101903528B1 (en) * | 2018-01-24 | 2018-10-25 | 주식회사 하나티이씨 | Optimal control system of landfill gas and biogas plant using deep running technique |
CN108319150A (en) * | 2018-04-25 | 2018-07-24 | 山东交通学院 | The full running state information perception of bionethanation system and optimal control system and method |
Non-Patent Citations (2)
Title |
---|
苑希民等: "天然橡胶价格波动研究 规律发现、市场关联与形成机制", 北京航空航天大学出版社, pages: 156 - 157 * |
赵峰: "冷热电联供系统的优化控制方法及应用研究", 《中国博士学位论文全文数据库(工程科技Ⅱ辑)》, 15 August 2017 (2017-08-15) * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112069724A (en) * | 2020-07-21 | 2020-12-11 | 上海宇航系统工程研究所 | Rocket health degree evaluation method based on long-time and short-time memory self-encoder |
CN112069724B (en) * | 2020-07-21 | 2023-06-20 | 上海宇航系统工程研究所 | Rocket health degree assessment method based on long-short-time memory self-encoder |
Also Published As
Publication number | Publication date |
---|---|
CN109184931B (en) | 2024-01-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN204925745U (en) | Roots blower intelligent monitoring system | |
CN110137539A (en) | A kind of fuel cell system and its blowing method that shuts down | |
CN110618610A (en) | Gas turbine NOx standard exceeding early warning method and device based on LSTM deep learning | |
CN110752391B (en) | Semi-physical simulation platform for fuel cell | |
CN109269087A (en) | Gas water-heating furnace and its monitoring adjusting method, heating system | |
CN105840326A (en) | System and method for model based and map based throttle position derivation and monitoring | |
CN1240521A (en) | Method for blade temp. estimation in a steam turbine | |
CN109184931A (en) | The active control system and method for biogas internal combustion engine generator group | |
CN109272174A (en) | Combustion turbine exhaustion system condition prediction technique based on Recognition with Recurrent Neural Network | |
CN110068004A (en) | A kind of power boiler burning intelligence control system and application method | |
Cervantes-Bobadilla et al. | Experimental implementation of a new control approach using an inverse neural network to on-demand hydrogen production | |
Barelli et al. | Diagnosis of a turbocharging system of 1 MW internal combustion engine | |
CN103411234A (en) | Quantitative air distribution economic combustion energy saving control system | |
CN206315655U (en) | A kind of kitchen pernicious gas processing system | |
CN202817796U (en) | Fuel cell stand-by power supply system with hydrogen circulating apparatus | |
KR102239721B1 (en) | Optimal control system of plant using deep running technique | |
CN208655008U (en) | A kind of domestic gas alarm system based on Internet of Things | |
CN111723331A (en) | Equity distribution calculation method for combined cycle two-in-one unit steam turbine load | |
CN108758355A (en) | A kind of hydrogen power generation device hydrogen gas leakage monitoring protection device and method | |
CN109260639B (en) | Fire control system and control method for wind turbine generator room | |
CN204962783U (en) | Msw incineration control system | |
CN103711548A (en) | Method and system for preventing diesel engine particle trap from melting | |
CN207780576U (en) | A kind of domestic gas table and pipeline telesecurity monitoring system | |
Radziszewski et al. | Application of a genetic-fuzzy system to diesel engine pressure modeling | |
CN110705881A (en) | Boiler efficiency online calculation method and system based on artificial neural network |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 250023 No. 5 Jiao Tong Road, Tianqiao District, Shandong, Ji'nan Applicant after: Shandong Jiaotong University Address before: No. 5001, Haitang Road, Science Park, Changqing University, Jinan City, Shandong Province, 250023 Applicant before: Shandong Jiaotong University |
|
GR01 | Patent grant | ||
GR01 | Patent grant |