CN112963256A - HCCI/SI combustion mode switching process control method - Google Patents

HCCI/SI combustion mode switching process control method Download PDF

Info

Publication number
CN112963256A
CN112963256A CN202110317167.0A CN202110317167A CN112963256A CN 112963256 A CN112963256 A CN 112963256A CN 202110317167 A CN202110317167 A CN 202110317167A CN 112963256 A CN112963256 A CN 112963256A
Authority
CN
China
Prior art keywords
combustion mode
output
imep
engine
hcci
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
Application number
CN202110317167.0A
Other languages
Chinese (zh)
Other versions
CN112963256B (en
Inventor
郑太雄
杨萃
杨新琴
张良斌
贺吉
刘星
吴泽林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN202110317167.0A priority Critical patent/CN112963256B/en
Publication of CN112963256A publication Critical patent/CN112963256A/en
Application granted granted Critical
Publication of CN112963256B publication Critical patent/CN112963256B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02D—CONTROLLING COMBUSTION ENGINES
    • F02D43/00—Conjoint electrical control of two or more functions, e.g. ignition, fuel-air mixture, recirculation, supercharging or exhaust-gas treatment
    • F02D43/02—Conjoint electrical control of two or more functions, e.g. ignition, fuel-air mixture, recirculation, supercharging or exhaust-gas treatment using only analogue means
    • 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
    • Y02T10/12—Improving ICE efficiencies

Abstract

The invention relates to a control method for an HCCI/SI combustion mode switching process, which belongs to the technical field of engine control and is characterized in that an IMEP predicted value output by a switched combustion mode at the next moment on a switched combustion mode LSTM neural network black box model prediction time sequence is established according to a rotation speed, a combustion mode, an air-fuel ratio, an oil injection quantity, an intake valve opening timing, an exhaust valve closing timing and an ignition advance angle in an SI combustion mode; designing a BP neural network controller, inputting variables of a rotating speed, a combustion mode at the next moment and an IMEP expected value, obtaining an air-fuel ratio, an oil injection quantity, an inlet valve opening timing, an exhaust valve closing timing and an ignition advance angle which enable an error between a predicted value and the expected value to be smaller than an error threshold value through training the neural network, and at the moment, modifying relevant parameters of an engine to control variable values obtained through training to realize stable switching of the combustion mode of the engine.

Description

HCCI/SI combustion mode switching process control method
Technical Field
The invention belongs to the field of engine control, and relates to a control method for HCCI/SI combustion mode switching process.
Background
The sharp increase of the automobile holding capacity brings environmental problems of aggravation of air pollution and the like, and the normal development of the automobile society in China is severely restricted. HCCI (Homogeneous Charge Compression Ignition), a new combustion mode that provides high thermal efficiency and low NO by compressing a Homogeneous fuel/air mixture until reaching an auto-Ignition pointxAnd PM emission while effectively reducing fuel consumption. These advantages make it possible to satisfy both the restrictions of shortage of crude oil resources and the strict environmental emission regulations, which are the main development directions of engine technology in the future.
HCCI combustion, in addition to its almost outright advantages, presents some inherent challenges. The problem of narrow operating condition range caused by knocking at high load and misfire at low load in the HCCI combustion mode is a prominent problem in the wide application of the HCCI combustion mode in the automotive industry. For this purpose, it is necessary to operate the engine in a full operating range by means of combustion mode switching (HCCI/SI).
Because the combustion conditions in the cylinders of the two combustion modes are completely different, the switching of the combustion modes under the same combustion conditions can cause great sudden change of the dynamic property of the output of the engine, and the stable operation of the engine in the full working condition range is seriously influenced. Therefore, the abrupt change range of the dynamic output of the engine after the combustion mode is switched is stabilized in a smaller range by changing the relevant combustion conditions at the switching moment, and the engine can be ensured to stably run in the full working condition range. The engine dynamic output is characterized by the magnitude of the output IMEP.
Considering that the combustion mode is frequently switched when the engine is always in a working state with variable working conditions in the actual running process, the engine output IMEP is greatly fluctuated, and the engine cannot normally run. The traditional control method comprises the following steps: PID control, model predictive control sliding film control and the like can realize the control of output IMEP of the HCCI engine under a constant working condition, and the control effect under a variable working condition is poor. Therefore, further investigation into the problem of HCCI engine control over varying operating conditions is needed.
Disclosure of Invention
In view of the above, the present invention provides a HCCI/SI combustion mode switching process control method, which includes firstly establishing an LSTM neural network engine black box model to predict an output IMEP at a next time; secondly, designing a BP neural network controller, and adjusting an air-fuel ratio AFR and an oil injection quantity m according to the rotating speed of the engine, the combustion mode and the expected IMEP output valuefuel, intake valve opening timing thetaivoExhaust valve closing timing thetaevcAngle of ignition advance alphaign) And the control of the dynamic and smooth output of the engine in the switching process of the HCCI/SI combustion mode is realized.
In order to achieve the purpose, the invention provides the following technical scheme:
a HCCI/SI combustion mode switching process control method, comprising the steps of:
s1: for engine speed N, combustion mode M, air-fuel ratio AFR and fuel injection quantity MfuelIntake valve opening timing thetaivoAnd exhaust valve closing timing thetaevcSampling as an original input data set; in the combustion mode M, the SI combustion mode is defined as M1, the HCCI combustion mode M is defined as 2, and when M is 1, the ignition advance angle α is also sampledign；
S2: building a black box prediction model of the switched combustion mode LSTM neural network engine, and predicting IMEP output values IMEP of the upper and lower moments of a time sequencePre；
S3: the rotating speed N in the running process of the engine, the combustion mode M at the next moment and the expected value IMEP of the IMEP at the next moment are calculatedExpAs inputs, the air-fuel ratio AFR and the fuel injection quantity mfuelIntake valve opening timing thetaivoAnd exhaust valve closing timing thetaevcAnd ignition advance angle alpha in SI combustion modeignDesigning a BP neural network controller as a control variable; obtaining IMEP predicted value and IMEP expected value IMEP of the combustion mode after switching at the next moment through learning of a neural networkExpError e betweentLess than error threshold elControl variable value ofThis controls smooth switching of the two combustion modes.
Further, in step S1, IMEP related variables including N, M, AFR, M are determined according to the characteristics of the engine combustion process and the two combustion modesfuel、θivo、θevc、αign(ii) a Under various automobile operating conditions, data are collected once per cycle, namely, each crankshaft rotation angle rotates by 720 degrees, and an original input data set is obtained.
Further, the LSTM neural network engine black box model described in step S2 includes an input and feedback layer, a hidden layer, and an output layer; the LSTN memory unit is provided with a forgetting gate, an input gate and an output gate;
first, the output value of LSTM cells was calculated using the forward propagation algorithm: the forgetting gate outputs h according to the last moment by using sigmoid activation functiont-1And current time input xtDetermining information that passed a forgotten door at a previous time
Figure BDA0002986988630000021
The input gate determines the state of the unit which is input at the current moment and reserved to the current moment through the sigmoid activation function
Figure BDA0002986988630000022
The output gate obtains the output of the model through the sigmoid function and the tanh function
Figure BDA0002986988630000023
And then calculating an error term of each LSTM cell by using a back propagation algorithm, and updating the weight by using a gradient descent method.
Further, in step S2, according to the formula
Figure BDA0002986988630000024
Determining the state of the unit passing through the forgetting gate; according to the formula
Figure BDA0002986988630000025
Calculating the unit state of the output gate; according to the formula
Figure BDA0002986988630000026
Calculating new memory to obtain the unit state of the current input to the current moment; according to the formula
Figure BDA0002986988630000027
And obtaining model output.
Further, in step S3, the BP neural network input layer includes 3 neuron nodes, the hidden layer includes 4 neuron nodes, and the output layer includes 5 neuron nodes; the excitation function of the hidden layer is
Figure BDA0002986988630000031
The neuron threshold of the hidden layer is ajThe connection weight from the input layer to the hidden layer is wij(ii) a The excitation function of the output layer is psi (·), and the neuron threshold is bkThe connection weight from the hidden layer to the output layer is wjk。
Further, in step S3, the BP neural network is based on a formula
Figure BDA0002986988630000032
Calculating output signal H of jth neuron node of hidden layerj(ii) a According to the formula
Figure BDA0002986988630000033
And calculating an output signal y of a neuron node of an output layer, and realizing the adjustment of engine parameters in the combustion mode switching process through an output vector to realize the stability of the combustion mode switching process.
The invention has the beneficial effects that: the neural network has strong nonlinear mapping capability, the neural network controller is established by utilizing the nonlinear function between the analog input and the output of the neural network, the output IMEP control of the HCCI engine under variable working conditions is realized, and the control of the dynamic stable output of the engine in the HCCI/SI combustion mode switching process is realized. .
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a schematic diagram of the steps of an LSTM neural network algorithm;
FIG. 2 is a diagram of a BP neural network architecture;
FIG. 3 is a control diagram of an HCCI/SI combustion mode switching process.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
Referring to fig. 1 to 3, HCCI-SI combustion mode switching process control methods provided by the present invention are illustrated.
The air-fuel ratio refers to the mass ratio of air to fuel in the mixed gas, the concentration of the mixed gas can be well represented, and within a certain range, the concentration of the mixed gas is increased, the mass of the fuel is increased, and the dynamic property of an engine is improved. Intake and exhaust valve timing can change the chemical composition of the mixture in the engine cylinder, mixture concentration, and temperature, thereby affecting engine dynamics. The invention defines the opening time of the air inlet valve and the exhaust valve of the engine as the time when the piston moves to the bottom dead center, and realizes the timing control of the air inlet valve and the exhaust valve by controlling the opening time of the air inlet valve and the closing time of the exhaust valve. The volume of fuel and air in the cylinder is determined by the fuel injection quantity and the timing of the intake valve and the exhaust valve, the concentration of the mixed gas is directly influenced, and further the dynamic property of the engine is influenced. For a gasoline engine, an optimal ignition advance angle exists for obtaining optimal power performance, so when the combustion mode is switched to the SI combustion mode, the ignition advance angle is controlled to realize smooth switching from the HCCI combustion mode to the SI combustion mode. In conclusion, the air-fuel ratio, the fuel injection amount, and the intake/exhaust valve timing have a large influence on the engine dynamics, and therefore the engine dynamics output can be controlled as the control variables. It should be noted that the spark advance angle should also be added to the control variable when switching from HCCI to SI combustion mode.
The invention utilizes an LSTM neural network engine black box model to predict the output IMEP of the combustion mode after HCCI/SI switching at the next moment. A BP neural network controller is designed, and the IMEP output in the switching process is controlled according to the combustion mode, the engine speed and the IMEP expected value. The invention ensures the accuracy of the predicted value, realizes the stable output of the switching process of the two combustion modes, and ensures that the HCCI engine can operate in the full working condition range.
When the LSTM engine black box prediction model is established, a large amount of data needs to be collected to train the model so as to fit the relation between input and output. Since the magnitude and the unit of the collected sample data are different, the collected data needs to be standardized first. The invention adopts a Z-score standardization method to process data, and the formula is as follows:
Figure BDA0002986988630000041
wherein x isiA sequence of sample data is represented which,
Figure BDA0002986988630000051
obtaining a new sequence yiThe mean of the new sequence is 0, the variance is 1, and there is no dimension.
The LSTM neural network engine black box prediction model is built as follows.
Using the engine speed N, the combustion mode M, the air-fuel ratio AFR and the fuel injection quantity MfuelIntake valve opening timing thetaivoExhaust valve closing timing thetaevcAngle of ignition advance alphaign) For input, the IMEP value at the time of the combustion mode is output. The LSTN memory cell includes a forgetting gate, an input gate, and an output gate. The forgetting gate outputs h according to the last moment by utilizing sigmoid activation functiont-1And current time input xtDetermining the information of passing through the forgetting door at the last moment; the input gate determines the input x at the current moment through the sigmoid activation functiontThe unit state of the current moment is reserved; and the output gate obtains the output of the model through the sigmoid function and the tanh function. The algorithm used to obtain the output of LSTM cells is a forward propagation algorithm. And secondly, calculating an error term of each LSTM cell by using a back propagation algorithm, and updating the weight by using a gradient descent method.
(1) The output values of LSTM cells were calculated using the forward propagation algorithm:
calculation input gate:
Figure BDA0002986988630000052
calculating a forgetting gate:
Figure BDA0002986988630000053
calculating an output gate:
Figure BDA0002986988630000054
calculating new memory:
Figure BDA0002986988630000055
calculating the final memory:
Figure BDA0002986988630000056
calculating an output value:
Figure BDA0002986988630000057
(2) the error for each cell is calculated using a back propagation algorithm:
the loss function is defined as:
Figure BDA0002986988630000058
and updating the weight by adopting a gradient descent method until the error function value is smaller than a preset value.
The BP neural network controller is established as follows:
when a BP neural network controller in the HCCI/SI combustion mode switching process is established, the input variables are the engine speed N, the combustion mode M at the next moment and the expected IMEP output valueExpThe control variables are air-fuel ratio AFR and fuel injection quantity mfuelIntake valve opening timing thetaivoExhaust valve closing timing thetaevc、(αign) Establishing three-layer BP neural network controlAnd (5) manufacturing a device. Error e is obtained by training neural networktLess than a set error threshold elAnd modifying the relevant parameters of the engine to the trained control variable values at the next moment to realize stable switching process.
FIG. 2 is a diagram of a BP neural network structure, x1Is the engine speed N, x2For the next combustion mode M, x3Expecting an output value IMEP for IMEPExp. The hidden layer includes 4 neuron nodes (1, 2,3,4),
Figure BDA0002986988630000061
as a function of excitation of the hidden layer, ajNeuron threshold, w, for the hidden layerijThe connection weight from the input layer to the hidden layer; the output vector is ykPhi (-) is the excitation function of the output layer, the neuron threshold of the output layer is bkThe connection weight from the hidden layer to the output layer is wjk. The training process of the BP neural network is mainly divided into two stages, wherein the first stage is forward propagation of signals from an input layer to an output layer through a hidden layer to obtain an output vector. The second stage is the back propagation of the error from the output layer to the input layer through the hidden layer, and the weight and the threshold value from the hidden layer to the output layer and the weight and the threshold value from the input layer to the hidden layer are adjusted in sequence.
The output signal of the hidden layer neuron node is:
Figure BDA0002986988630000062
the output signal of the output layer neuron node is:
Figure BDA0002986988630000063
the error formula is taken as follows:
Figure BDA0002986988630000064
wherein, YkTo expect the output, note:
Yk-yk＝ek(12)
obtaining:
Figure BDA0002986988630000065
updating the weight by using a gradient descent method to enable the error function to reach a minimum value, and updating the weight from the hidden layer to the output layer:
Figure BDA0002986988630000066
the formula for updating the weights from the hidden layer to the output layer can be obtained as follows:
ωjk＝ωjk+ηHjek (15)
weight update from input layer to hidden layer:
Figure BDA0002986988630000071
wherein the content of the first and second substances,
Figure BDA0002986988630000072
Figure BDA0002986988630000073
then the weight update formula from the input layer to the hidden layer is:
Figure BDA0002986988630000074
hidden layer neuron threshold update:
Figure BDA0002986988630000075
wherein the content of the first and second substances,
Figure BDA0002986988630000076
Figure BDA0002986988630000077
the hidden layer neuron threshold update formula can be derived as:
Figure BDA0002986988630000078
output layer neuron threshold update:
Figure BDA0002986988630000079
the formula for updating the neuron threshold value of the obtained output layer is as follows:
bk＝bk+ηek (25)
where η is the learning rate.
Firstly, an LSTM neural network black box prediction model is established to predict IMEP output values of the switched combustion modes at the next moment. And secondly, establishing a BP neural network controller to obtain an air-fuel ratio, an oil injection quantity, an opening timing of an intake valve, a closing timing of an exhaust valve and an ignition advance angle, wherein the error between the IMEP predicted value and the expected value is smaller than an error threshold value, through training. Smooth switching of the HCCI/SI combustion mode is achieved by modifying engine-related parameters.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.

Claims (6)

1. A HCCI/SI combustion mode switching process control method, characterized by: the method comprises the following steps:
s1: for engine speed N, combustion mode M, air-fuel ratio AFR and fuel injection quantity MfuelIntake valve opening timing thetaivoAnd exhaust valve closing timing thetaevcSampling as an original input data set; in the combustion mode M, the SI combustion mode is defined as M1, the HCCI combustion mode M is defined as 2, and when M is 1, the ignition advance angle α is also sampledign；
S2: building a black box prediction model of the switched combustion mode LSTM neural network engine, and predicting IMEP output values IMEP of the upper and lower moments of a time sequencePre；
S3: the rotating speed N in the running process of the engine, the combustion mode M at the next moment and the expected value IMEP of the IMEP at the next moment are calculatedExpAs inputs, the air-fuel ratio AFR and the fuel injection quantity mfuelIntake valve opening timing thetaivoAnd exhaust valve closing timing thetaevcAnd ignition advance angle alpha in SI combustion modeignDesigning a BP neural network controller as a control variable; obtaining IMEP predicted value and IMEP expected value IMEP of the combustion mode after switching at the next moment through learning of a neural networkExpError e betweentLess than error threshold elThereby controlling smooth switching of the two combustion modes.
2. The HCCI/SI combustion mode switching process control method of claim 1, wherein: in step S1, IMEP related variables including N, M, AFR, M are determined based on characteristics of the engine combustion process and the two combustion modesfuel、θivo、θevc、αign(ii) a Under various automobile operating conditions, data are collected once per cycle, namely, each crankshaft rotation angle rotates by 720 degrees, and an original input data set is obtained.
3. The HCCI/SI combustion mode switching process control method of claim 1, wherein: the LSTM neural network engine black box model in the step S2 comprises an input and feedback layer, a hidden layer and an output layer; the LSTN memory unit is provided with a forgetting gate, an input gate and an output gate;
first, the output value of LSTM cells was calculated using the forward propagation algorithm: the forgetting gate outputs h according to the last moment by using sigmoid activation functiont-1And current time input xtDetermining the information F of passing the forgetting gate at the last momentt 1(ii) a The input gate determines the state of the unit which is input at the current moment and reserved to the current moment through the sigmoid activation function
Figure FDA0002986988620000011
The output gate obtains the output of the model through the sigmoid function and the tanh function
Figure FDA0002986988620000012
And then calculating an error term of each LSTM cell by using a back propagation algorithm, and updating the weight by using a gradient descent method.
4. The HCCI/SI combustion mode switching process control method of claim 3, wherein: in step S2, according to formula Ft 0＝Wfxt+Ufht-1Determining the state of the unit passing through the forgetting gate; according to the formula
Figure FDA0002986988620000013
Calculating the unit state of the output gate; according to the formula
Figure FDA0002986988620000014
Calculating new memory to obtain the unit state of the current input to the current moment; according to the formula
Figure FDA0002986988620000021
And obtaining model output.
5. The HCCI/SI combustion mode switching process control method of claim 1, wherein: in step S3, the BP neural network input layer includes 3 neuron nodes, the hidden layer includes 4 neuron nodes, and the output layer includes 5 neuron nodes; the excitation function of the hidden layer is
Figure FDA0002986988620000022
The neuron threshold of the hidden layer is ajThe connection weight from the input layer to the hidden layer is wij(ii) a The excitation function of the output layer is psi (·), and the neuron threshold is bkThe connection weight from the hidden layer to the output layer is wjk。
6. The HCCI/SI combustion mode switching process control method of claim 5, wherein: in step S3, the BP neural network is based on a formula
Figure FDA0002986988620000023
Calculating output signal H of jth neuron node of hidden layerj(ii) a According to the formula
Figure FDA0002986988620000024
And calculating an output signal y of a neuron node of an output layer, and realizing the adjustment of engine parameters in the combustion mode switching process through an output vector to realize the stability of the combustion mode switching process.
CN202110317167.0A 2021-03-22 2021-03-22 HCCI/SI combustion mode switching process control method Active CN112963256B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110317167.0A CN112963256B (en) 2021-03-22 2021-03-22 HCCI/SI combustion mode switching process control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110317167.0A CN112963256B (en) 2021-03-22 2021-03-22 HCCI/SI combustion mode switching process control method

Publications (2)

Publication Number Publication Date
CN112963256A true CN112963256A (en) 2021-06-15
CN112963256B CN112963256B (en) 2022-09-30

Family

ID=76278838

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110317167.0A Active CN112963256B (en) 2021-03-22 2021-03-22 HCCI/SI combustion mode switching process control method

Country Status (1)

Country Link
CN (1) CN112963256B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11459962B2 (en) * 2020-03-02 2022-10-04 Sparkcognitton, Inc. Electronic valve control

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1416143A1 (en) * 2002-10-29 2004-05-06 STMicroelectronics S.r.l. Virtual sensor for the exhaust emissions of an endothermic motor and corresponding injection control system
US20040182359A1 (en) * 2003-03-17 2004-09-23 Stewart Daniel W. Individual cylinder-switching in a multi-cylinder engine
WO2007096064A1 (en) * 2006-02-21 2007-08-30 Fev Motorentechnik Gmbh Direct-injection spark ignition internal combustion engine with scr catalyst
US20080051975A1 (en) * 2006-08-28 2008-02-28 Ker Stephan Method of Real Time-Estimation of Indicators of the Combustion State of an Internal-Combustion Engine
EP1990527A2 (en) * 2007-05-09 2008-11-12 Hitachi, Ltd. Engine controller
JP2011202590A (en) * 2010-03-25 2011-10-13 Honda Motor Co Ltd Control device for internal combustion engine
EP2418368A2 (en) * 2010-08-10 2012-02-15 General Electric Company Method for compensating for combustion efficiency in fuel control system
CN103085649A (en) * 2007-04-12 2013-05-08 福特环球技术公司 Control Strategy For Multi-mode Vehicle Propulsion System
US20160025028A1 (en) * 2014-07-22 2016-01-28 The Regents Of The University Of Michigan Adaptive Machine Learning Method To Predict And Control Engine Combustion
US20170300018A1 (en) * 2016-04-19 2017-10-19 General Electric Company Asset degradation model baselinening system and method
CN107472038A (en) * 2017-07-21 2017-12-15 重庆邮电大学 Hybrid vehicle energy management method based on hcci engine
US20180229713A1 (en) * 2017-02-10 2018-08-16 Motrec International Inc. Range extender for industrial electric vehicle
JP6547992B1 (en) * 2019-04-18 2019-07-24 トヨタ自動車株式会社 Oxygen storage amount estimation device, oxygen storage amount estimation system, control device for internal combustion engine, data analysis device, and oxygen storage amount estimation method
CN110259590A (en) * 2019-06-28 2019-09-20 重庆邮电大学 Hcci engine burning timing control system under complex working condition
CN110552804A (en) * 2019-09-05 2019-12-10 重庆邮电大学 method for estimating combustion timing of mixed fuel HCCI (homogeneous charge compression ignition) engine based on LSTM (localized fuel transfer model)
WO2020040014A1 (en) * 2018-08-21 2020-02-27 日立オートモティブシステムズ株式会社 Internal combustion engine control device and internal combustion engine control method
JP6708292B1 (en) * 2019-08-30 2020-06-10 トヨタ自動車株式会社 Internal combustion engine state determination device, internal combustion engine state determination system, data analysis device, and internal combustion engine control device

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1416143A1 (en) * 2002-10-29 2004-05-06 STMicroelectronics S.r.l. Virtual sensor for the exhaust emissions of an endothermic motor and corresponding injection control system
US20040182359A1 (en) * 2003-03-17 2004-09-23 Stewart Daniel W. Individual cylinder-switching in a multi-cylinder engine
WO2007096064A1 (en) * 2006-02-21 2007-08-30 Fev Motorentechnik Gmbh Direct-injection spark ignition internal combustion engine with scr catalyst
US20080051975A1 (en) * 2006-08-28 2008-02-28 Ker Stephan Method of Real Time-Estimation of Indicators of the Combustion State of an Internal-Combustion Engine
CN103085649A (en) * 2007-04-12 2013-05-08 福特环球技术公司 Control Strategy For Multi-mode Vehicle Propulsion System
EP1990527A2 (en) * 2007-05-09 2008-11-12 Hitachi, Ltd. Engine controller
JP2011202590A (en) * 2010-03-25 2011-10-13 Honda Motor Co Ltd Control device for internal combustion engine
EP2418368A2 (en) * 2010-08-10 2012-02-15 General Electric Company Method for compensating for combustion efficiency in fuel control system
US20160025028A1 (en) * 2014-07-22 2016-01-28 The Regents Of The University Of Michigan Adaptive Machine Learning Method To Predict And Control Engine Combustion
US20170300018A1 (en) * 2016-04-19 2017-10-19 General Electric Company Asset degradation model baselinening system and method
US20180229713A1 (en) * 2017-02-10 2018-08-16 Motrec International Inc. Range extender for industrial electric vehicle
CN107472038A (en) * 2017-07-21 2017-12-15 重庆邮电大学 Hybrid vehicle energy management method based on hcci engine
WO2020040014A1 (en) * 2018-08-21 2020-02-27 日立オートモティブシステムズ株式会社 Internal combustion engine control device and internal combustion engine control method
JP6547992B1 (en) * 2019-04-18 2019-07-24 トヨタ自動車株式会社 Oxygen storage amount estimation device, oxygen storage amount estimation system, control device for internal combustion engine, data analysis device, and oxygen storage amount estimation method
CN110259590A (en) * 2019-06-28 2019-09-20 重庆邮电大学 Hcci engine burning timing control system under complex working condition
JP6708292B1 (en) * 2019-08-30 2020-06-10 トヨタ自動車株式会社 Internal combustion engine state determination device, internal combustion engine state determination system, data analysis device, and internal combustion engine control device
CN110552804A (en) * 2019-09-05 2019-12-10 重庆邮电大学 method for estimating combustion timing of mixed fuel HCCI (homogeneous charge compression ignition) engine based on LSTM (localized fuel transfer model)

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
周能辉等: "基于神经网络的汽油HCCI发动机空燃比控制策略", 《农业机械学报》 *
田国弘等: "HCCI/SI燃烧模式转换过程关键因素的研究", 《2007年APC联合学术年会论文集》 *
田国弘等: "缸内直喷汽油机SI-HCCI-SI燃烧模式切换的研究", 《内燃机学报》 *
郑太雄等: "Study of Fuel Film Parameter Identification in Gasoline Engine Transient Conditions Based on Weighted Recursive Instrumental Variable Method", 《2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA)》 *
郑太雄等: "基于黑箱模型和RBF-PID的HCCI发动机燃烧正时控制", 《仪器仪表学报》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11459962B2 (en) * 2020-03-02 2022-10-04 Sparkcognitton, Inc. Electronic valve control

Also Published As

Publication number Publication date
CN112963256B (en) 2022-09-30

Similar Documents

Publication Publication Date Title
Aliramezani et al. Modeling, diagnostics, optimization, and control of internal combustion engines via modern machine learning techniques: A review and future directions
Bendu et al. Multi-objective optimization of ethanol fuelled HCCI engine performance using hybrid GRNN–PSO
Li et al. Multi-objective energy management for Atkinson cycle engine and series hybrid electric vehicle based on evolutionary NSGA-II algorithm using digital twins
Zareei et al. Optimization and study of performance parameters in an engine fueled with hydrogen
CN101432726B (en) Airflow estimation method and apparatus for internal combustion engine
Zhao et al. Optimization and matching for range-extenders of electric vehicles with artificial neural network and genetic algorithm
US20060016438A1 (en) HCCI engine combustion control
Yap et al. Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle
Duan et al. Regression prediction of hydrogen enriched compressed natural gas (HCNG) engine performance based on improved particle swarm optimization back propagation neural network method (IMPSO-BPNN)
Yu et al. Internal combustion engine calibration using optimization algorithms
CN112963256B (en) HCCI/SI combustion mode switching process control method
Li et al. Multi-objective optimization of the Atkinson cycle gasoline engine using NSGA Ⅲ coupled with support vector machine and back-propagation algorithm
CN107472038B (en) Hybrid electric vehicle energy management method based on HCCI engine
CN110552804B (en) Method for estimating combustion timing of mixed fuel HCCI (homogeneous charge compression ignition) engine based on LSTM (localized fuel transfer model)
Dang et al. Optimization control of hydrogen engine ignition system based on ACO-BP
Sun et al. Multi-objective optimization for combustion, thermodynamic and emission characteristics of Atkinson cycle engine using tree-based machine learning and the NSGA II algorithm
Bozza et al. Steady-state and transient operation simulation of a “downsized” turbocharged SI engine
Jansri et al. Enhanced model and fuzzy strategy of air to fuel ratio control for spark ignition engines
Chiang et al. Constrained control of homogeneous charge compression ignition (HCCI) engines
CN110259590B (en) HCCI (homogeneous charge compression ignition) engine combustion timing control system under complex working conditions
Flärdh et al. Optimal air path control during load transients on a spark ignited engine with variable geometry turbine and variable valve timing
CN108563844A (en) A kind of supercharged diesel engine Optimum EGR rate determines method
CN114934848B (en) Fuzzy neural network modeling method for optimizing control of combustion performance of diesel engine
Lezhnev et al. Boosted gasoline direct injection engines: Comparison of throttle and VGT controllers for homogeneous charge operation
Larimore et al. Adaptive control of a recompression four-cylinder HCCI engine

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