CN114815584B - Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input - Google Patents
Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input Download PDFInfo
- Publication number
- CN114815584B CN114815584B CN202210376116.XA CN202210376116A CN114815584B CN 114815584 B CN114815584 B CN 114815584B CN 202210376116 A CN202210376116 A CN 202210376116A CN 114815584 B CN114815584 B CN 114815584B
- Authority
- CN
- China
- Prior art keywords
- jet
- inlet pressure
- natural gas
- input
- injection amount
- 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.)
- Active
Links
- 238000002347 injection Methods 0.000 title claims abstract description 164
- 239000007924 injection Substances 0.000 title claims abstract description 164
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 title claims abstract description 158
- 239000003345 natural gas Substances 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000008859 change Effects 0.000 claims abstract description 42
- 239000007789 gas Substances 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims description 20
- 230000000875 corresponding effect Effects 0.000 claims description 19
- 125000004122 cyclic group Chemical group 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000002485 combustion reaction Methods 0.000 description 14
- 230000004044 response Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 239000000446 fuel Substances 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000116 mitigating effect Effects 0.000 description 2
- TVMXDCGIABBOFY-UHFFFAOYSA-N octane Chemical compound CCCCCCCC TVMXDCGIABBOFY-UHFFFAOYSA-N 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
-
- 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
- Y02T10/30—Use of alternative fuels, e.g. biofuels
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a circulating air injection amount feedforward PID closed-loop control method and a system taking natural gas ejector inlet pressure fluctuation as input, wherein the method comprises the following steps: installing a pressure sensor at the air inlet end of the natural gas injection valve, and acquiring an inlet pressure signal; taking the inlet pressure signal as jet quantity change information based on the fact that the change rate of the inlet pressure signal is the same as the jet quantity change rule of the ejector; establishing a jet quantity prediction model, and training the jet quantity prediction model by using jet quantity variation information to obtain a jet quantity calculation model; taking the current inlet pressure signal as the input of the air injection quantity calculation model, and solving the real-time air injection quantity; and comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, taking the error value as the input of a feedforward controller and a PID controller, performing feedforward compensation on the output of the PID, and performing comprehensive control on the natural gas circulating injection amount. The method is used for accurately controlling the circulating gas injection amount of the natural gas and is beneficial to maintaining the normal and stable operation of the natural gas engine.
Description
Technical Field
The invention relates to the technical field of power energy, in particular to a circulating air injection amount feedforward PID closed-loop control method taking natural gas ejector inlet pressure fluctuation as input.
Background
Burning alternative fuels in engines is one of the measures to improve the mitigation of emission pollution. Natural gas has gained wide attention due to its advantages of clean combustion, high octane number, abundant resources, low price, etc. The natural gas has high H/C ratio, and CO2 generated by combustion of unit mass is low, so that low-carbon combustion is realized; the density is less than that of air, the leakage can be diffused to a high place to reduce the tendency of explosion, and the safety is better; the natural gas has high octane number (up to 130), strong antiknock capability, and is beneficial to adopting higher compression ratio and supercharging pressure, improving power output and improving thermal efficiency; the natural gas has high low calorific value and generates more heat per unit mass; the ignition limit is wide, the lean-burn capability is strong, the higher lean-burn limit can be expanded, and the thermal efficiency is improved. Thus, natural gas engines emit lower amounts of CO2 at the same air-fuel ratio than diesel engines, but at the same time have similar thermal efficiency in the very lean state of the mixture.
In order to maintain the stable operation of the natural gas engine, the circulating gas injection amount of the natural gas needs to be accurately controlled. The existing control method mainly uses the reaction after the combustion of the fuel gas to identify the change of the circulating gas injection amount and compensate. Since these methods all require passing through the combustion stage, both the response speed and the degree of discernability of the control are affected.
Disclosure of Invention
The present invention is directed to solving, at least in part, one of the technical problems in the related art.
To this end, it is an object of the present invention to provide a cyclic injection quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as an input, which does not require combustion mitigation, and which has a fast response speed and discernability without impact.
Another objective of the present invention is to provide a cyclic injection quantity feed forward PID closed loop control system with natural gas injector inlet pressure fluctuations as input.
In order to achieve the above object, an embodiment of the present invention provides a feedforward PID closed-loop control method for a cycle injection amount with natural gas injector inlet pressure fluctuation as an input, including the following steps: step S1, installing a pressure sensor at the air inlet end of a natural gas injection valve, and acquiring an inlet pressure signal; s2, taking the inlet pressure signal as air injection quantity change information based on the one-to-one correspondence relationship between the lowest point of the inlet pressure signal and the air injection quantity change rule of the ejector; s3, establishing a jet quantity prediction model by using a RBF neural network, and training the jet quantity prediction model by using the jet quantity variation information to obtain a jet quantity calculation model; s4, solving a real-time gas injection amount by taking the current inlet pressure signal as the input of the gas injection amount calculation model; and S5, comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, taking the error value as the input of a feedforward controller and a PID (proportion integration differentiation) controller, performing feedforward compensation on the PID output, and performing comprehensive control on the natural gas circulating injection amount.
According to the feedforward PID closed-loop control method for the circulating injection quantity by taking the natural gas injector inlet pressure fluctuation as input, the circulating injection quantity change is identified by the reaction after gas combustion, and the control method for compensation is adopted, so that the response speed is improved, the integral structures of the natural gas injector and the combustion chamber of the engine are not required to be damaged, only a pressure sensor is required to be additionally arranged on a high-pressure oil pipe, the equipment is simple, and the out-of-cylinder measurement can be realized.
In addition, the feedforward PID closed-loop control method for the circulating jet quantity with the natural gas injector inlet pressure fluctuation as the input according to the embodiment of the invention can also have the following additional technical characteristics:
further, in an embodiment of the present invention, in the step S3, a corresponding relationship between a jet volume change, a jet pressure at a jet starting point, and a maximum drop value of an inlet pressure is determined according to the jet volume change information, the jet pressure and the maximum drop value of the inlet pressure are used as inputs of the jet volume prediction model, and the jet volume change is used as an output of the jet volume prediction model, where the corresponding relationship is that the jet volume, the jet pressure, and the inlet pressure drop value are positively correlated.
Further, in an embodiment of the present invention, the step S3 specifically includes: step S301, normalizing the jet volume change, the jet pressure at the jet starting point and the maximum drop value of the inlet pressure; step S302, selecting an activation function of a hidden layer in an RBF neural network to construct the air injection amount prediction model; step S303, dividing the normalized air injection quantity change, the air injection pressure at the air injection starting point and the maximum inlet pressure drop value into a training set and a testing set, training the air injection quantity prediction model by using the training set to obtain the air injection quantity calculation model, and verifying by using the testing set.
Further, in an embodiment of the present invention, the compensation process in step S5 specifically includes:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i In order to be a coefficient of the integration time,k d is a differential time coefficient, K q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
In order to achieve the above object, another embodiment of the present invention provides a feedforward PID closed-loop control system for circulating injection air quantity with natural gas injector inlet pressure fluctuation as input, including: the acquisition module is used for installing a pressure sensor at the air inlet end of the natural gas injection valve and acquiring an inlet pressure signal; the determining module is used for taking the inlet pressure signal as jet quantity change information based on the one-to-one correspondence relationship between the lowest point of the inlet pressure signal and the jet quantity change rule of the ejector; the training module is used for establishing a jet quantity prediction model by using a RBF neural network and training the jet quantity prediction model by using the jet quantity variation information to obtain a jet quantity calculation model; the solving module is used for solving the real-time air injection amount by taking the current inlet pressure signal as the input of the air injection amount calculation model; and the compensation module is used for comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, taking the error value as the input of the feedforward controller and the PID controller, performing feedforward compensation on the PID output, and performing comprehensive control on the natural gas circulating injection amount.
According to the circulating injection quantity feedforward PID closed-loop control system taking the natural gas injector inlet pressure fluctuation as input, the circulating injection quantity change is identified by the reaction after gas combustion, and the control method of compensation is carried out, so that the response speed is improved, the integral structures of the natural gas injector and the combustion chamber of the engine are not required to be damaged, only a pressure sensor is required to be additionally arranged on a high-pressure oil pipe, the equipment is simple, and the out-of-cylinder measurement can be realized.
In addition, the cyclic injection quantity feedforward PID closed-loop control system taking the natural gas injector inlet pressure fluctuation as the input according to the embodiment of the invention can also have the following additional technical characteristics:
further, in an embodiment of the present invention, in the training module, according to a corresponding relationship between the jet volume change, the jet pressure at the jet starting point, and the maximum inlet pressure drop value, the jet pressure and the maximum inlet pressure drop value are used as inputs of the jet volume prediction model, and the jet volume change is used as an output of the jet volume prediction model, where the corresponding relationship is that the jet volume and the jet pressure are positively correlated to the inlet pressure drop value.
Further, in an embodiment of the present invention, the training module specifically includes: the normalization unit is used for performing normalization processing on the jet flow variation, the jet pressure at the jet starting point and the maximum inlet pressure drop value; the construction unit is used for selecting an activation function of a hidden layer in the RBF neural network to construct the air injection amount prediction model; and the training and verifying unit is used for dividing the jet quantity change after normalization, the jet pressure at the jet starting point and the maximum drop value of the inlet pressure into a training set and a testing set, training the jet quantity prediction model by using the training set to obtain the jet quantity calculation model, and verifying by using the testing set.
Further, in an embodiment of the present invention, the compensation process in the compensation module specifically includes:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference value between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i Is the integral time coefficient, k d Is a differential time coefficient, k q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
In another aspect, the present invention provides a feedforward PID closed-loop control method for the circulating injection amount using the pressure fluctuation of the inlet of the natural gas injector as the input, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the feedforward PID closed-loop control method for the circulating injection amount using the pressure fluctuation of the inlet of the natural gas injector as the input is implemented.
Yet another aspect embodiment of the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program that when executed by a processor implements a cyclic injection quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as input as described in the previous embodiment.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a cyclic injection quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as input according to one embodiment of the invention;
FIG. 2 is a schematic diagram of the structure of a natural gas control device according to one embodiment of the present invention;
FIG. 3 is a graph showing the variation of the maximum value of the fuel injection amount and the air pressure drop according to the embodiment of the present invention;
FIG. 4 is a block diagram of an RBF neural network according to one embodiment of the present invention;
FIG. 5 is a block diagram of a feed forward PID control of one embodiment of the invention;
FIG. 6 is a detailed flow chart of a method for controlling the injection quantity of the natural gas recycle according to an embodiment of the invention;
FIG. 7 is a schematic diagram of a cyclic injection quantity feed-forward PID closed-loop control system with natural gas injector inlet pressure fluctuations as inputs, according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes a method and a system for loop-forward PID closed-loop control of the injection quantity with natural gas injector inlet pressure fluctuation as input according to an embodiment of the present invention with reference to the accompanying drawings, and first, a method for loop-forward PID closed-loop control of the injection quantity with natural gas injector inlet pressure fluctuation as input according to an embodiment of the present invention will be described with reference to the accompanying drawings.
FIG. 1 is a flow chart of a cyclic injection quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as input according to an embodiment of the invention.
As shown in FIG. 1, the feedforward PID closed-loop control method for the circulating injection amount by taking the natural gas injector inlet pressure fluctuation as input comprises the following steps:
in step S1, a pressure sensor is attached to the intake end of the natural gas injection valve, and an inlet pressure signal is acquired.
Specifically, as shown in fig. 2, a pressure sensor is installed at the air inlet end of the natural gas injection valve, the output signal of the sensor is amplified by a charge amplifier, and the inlet pressure is acquired by a data acquisition card; the inlet of the ejector is selected as a pressure detection point, so that the channel effect of the pressure signal can be avoided to the maximum extent under the condition of not damaging the ejector, and the pressure signal of the sensor is approximately equal to the pressure signal in the pressure accumulation gallery. Therefore, the maximum value of the pressure drop of the pressure accumulation cavity in the inlet pressure signal can be selected as the signal characteristic of the air injection quantity identification. The control unit controls the output electric signal, namely controls the air injection duration of the ejector by controlling the on-off of the electromagnetic valve of the ejector, and the acquisition system acquires the electric signal, the rail pressure and the inlet pressure signal of the ejector and transmits the electric signal, the rail pressure and the inlet pressure signal to the upper computer.
In step S2, the inlet pressure signal is used as the jet flow variation information based on the one-to-one correspondence relationship between the lowest point of the inlet pressure signal and the jet flow variation law of the ejector.
In step S3, an air injection quantity prediction model is established by using the RBF neural network, and the air injection quantity prediction model is trained by using the air injection quantity change information to obtain an air injection quantity calculation model.
Further, in an embodiment of the present invention, in step S3, a corresponding relationship between the jet volume change, the jet pressure at the jet starting point, and the maximum drop value of the inlet pressure is determined according to the jet volume change information, the jet pressure and the maximum drop value of the inlet pressure are used as inputs of the jet volume prediction model, and the jet volume change is used as an output of the jet volume prediction model, wherein the corresponding relationship is that the jet volume and the jet pressure are positively correlated with the inlet pressure drop value.
Further, in an embodiment of the present invention, step S3 specifically includes:
step S301, carrying out normalization processing on the variation of the air injection quantity, the air injection pressure at the air injection starting point and the maximum drop value of the inlet pressure;
step S302, selecting an activation function of a hidden layer in an RBF neural network to construct a gas injection amount prediction model;
and S303, dividing the normalized air injection quantity change, the air injection pressure at the air injection starting point and the maximum drop value of the inlet pressure into a training set and a testing set, training the air injection quantity prediction model by using the training set to obtain an air injection quantity calculation model, and verifying by using the testing set.
Specifically, as shown in fig. 2, the variation of the jet amount and the jet pressure (P) at the jet start point inj ) And the maximum value (delta P) of the air pressure drop has strong corresponding relation. The precise mapping relation between the two can be quickly established by a neural network method. The method selects a Radial Basis Function (RBF) neural network to establish a gas injection quantity prediction model. Compared with other neural networks, the RBF neural network has the advantages of simple structure, concise training, high training speed and strong nonlinear mapping capability. As shown in fig. 3, and is therefore denoted by P inj And Δ P as input to the neural network to measure the jet (m) cyc ) As an output, the network is trained to establish feed forward adjustments. Wherein the training set is set to 70% of the total samples, the validation set and the test sum are 15% of the samples. The training function selects L-M.
In step S4, the current inlet pressure signal is used as an input of the air injection quantity calculation model, and the real-time air injection quantity is solved.
In step S5, the real-time gas injection amount is compared with the expected gas injection amount to obtain an error value, which is used as the input of a feedforward controller and a PID controller to perform feedforward compensation on the PID output and perform comprehensive control on the natural gas circulating injection amount.
Specifically, based on the measured inlet pressure change of the natural gas ejector, a basic PID controller is modified, a feedforward compensation link is added to enable the feedforward compensation link to be changed into composite control, namely, the feedforward neural network and the feedback PID are combined to control the natural gas circulating gas injection amount, and the combined feedforward PID control (and compensation) is formed, wherein the compensation process specifically comprises the following steps:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference value between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i As integral time coefficient, k d Is a differential time coefficient, k q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
Thus, as shown in fig. 4-6, the working principle of the embodiment of the present invention is: firstly, driving a natural gas injector to supply natural gas by a control unit according to an expected reference gas injection amount; simultaneously measuring the pressure change of an inlet of the gas injector, and taking the pressure change and the injection pressure as the input of a neural network to correspondingly obtain the natural gas circulating injection quantity; the actual natural gas injection quantity is compared with the expected gas injection quantity, the error between the actual natural gas injection quantity and the expected gas injection quantity is transmitted to the PID controller, the power-on and power-off time of the gas injection electromagnetic valve is changed, namely the gas injection duration is changed, the natural gas circulating injection quantity is further changed, and the accurate control of the natural gas circulating injection quantity is realized. Compared with the traditional PID control algorithm comprising three control links of proportion, integral and differential, the method has the advantages of simple operation, good robustness, easy learning and the like, and can not influence both stability and accuracy due to the value change of the proportionality coefficient P.
According to the feedforward PID closed-loop control method for the circulating injection quantity by taking the natural gas injector inlet pressure fluctuation as input, disclosed by the embodiment of the invention, the circulating injection quantity change is identified by the reaction after gas combustion, and the control method for compensation is carried out, so that the response speed is improved, the integral structures of the natural gas injector and a combustion chamber of an engine are not required to be damaged, only a pressure sensor is required to be additionally arranged on a high-pressure oil pipe, the equipment is simple, and the out-of-cylinder measurement can be realized.
Next, a cyclic injection quantity feedforward PID closed-loop control system taking natural gas injector inlet pressure fluctuation as input is provided according to the embodiment of the invention and is described with reference to the accompanying drawings.
FIG. 7 is a configuration of a cyclic injection quantity feed forward PID closed loop control system with natural gas injector inlet pressure fluctuations as input, in accordance with an embodiment of the invention.
As shown in fig. 7, the system 10 includes: acquisition module 100, determination module 200, training module 300, solution module 400, and compensation module 500.
The collecting module 100 is used for installing a pressure sensor at the air inlet end of the natural gas injection valve and collecting an inlet pressure signal. The determining module 200 is configured to use the inlet pressure signal as the jet quantity variation information based on a one-to-one correspondence relationship between a lowest point of the inlet pressure signal and a jet quantity variation rule of the ejector. The training module 300 is configured to establish a jet quantity prediction model by using the RBF neural network, and train the jet quantity prediction model by using the jet quantity variation information to obtain a jet quantity calculation model. The solving module 400 is configured to solve the real-time injection amount by using the current inlet pressure signal as an input of the injection amount calculation model. The compensation module 500 is used for comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, and the error value is used as the input of a feedforward controller and a PID controller to perform feedforward compensation on the PID output and perform comprehensive control on the natural gas circulating injection amount.
Further, in an embodiment of the present invention, in the training module, according to a corresponding relationship between the jet volume variation, the jet pressure at the jet starting point, and the maximum drop value of the inlet pressure, the jet pressure and the maximum drop value of the inlet pressure are used as inputs of a jet volume prediction model, and the jet volume variation is used as an output of the jet volume prediction model, where the corresponding relationship is that the jet volume and the jet pressure are positively correlated to the drop value of the inlet pressure.
Further, in an embodiment of the present invention, the training module specifically includes: the normalization unit is used for performing normalization processing on the air injection quantity change, the air injection pressure at the air injection starting point and the maximum drop value of the inlet pressure; the construction unit is used for selecting an activation function of a hidden layer in the RBF neural network to construct a gas injection amount prediction model; and the training and verifying unit is used for dividing the normalized air injection quantity change, the air injection pressure at the air injection starting point and the maximum drop value of the inlet pressure into a training set and a testing set, training the air injection quantity prediction model by using the training set to obtain an air injection quantity calculation model, and verifying by using the testing set.
Further, in an embodiment of the present invention, the compensation process in the compensation module specifically includes:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference value between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i As integral time coefficient, k d Is a differential time coefficient, k q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
It should be noted that the foregoing explanation of the embodiment of the feedforward PID closed-loop control of the cycle injection amount using the pressure fluctuation of the natural gas system as the input is also applicable to the system of the embodiment, and is not repeated here.
According to the circulating injection quantity feedforward PID closed-loop control system taking the natural gas injector inlet pressure fluctuation as input provided by the embodiment of the invention, the circulating injection quantity change is identified by the reaction after the combustion of the fuel gas, and the control method of compensation is carried out, so that the response speed is improved, the integral structures of the natural gas injector and the combustion chamber of the engine are not required to be damaged, only a pressure sensor is required to be additionally arranged on a high-pressure oil pipe, the equipment is simple, and the out-of-cylinder measurement can be realized.
In order to achieve the above embodiments, the present invention further provides a feedforward PID closed-loop control device of a cycle injection amount using pressure fluctuation of a natural gas system as an input, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the feedforward PID closed-loop control device of the cycle injection amount using pressure fluctuation of a natural gas injector inlet as an input implements the feedforward PID closed-loop control method of the cycle injection amount using pressure fluctuation of the natural gas injector inlet as an input according to the foregoing embodiments.
In order to achieve the above embodiments, the present invention also proposes a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a cyclic injection gas quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as input as described in the previous embodiments.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A cyclic jet quantity feedforward PID closed-loop control method taking natural gas injector inlet pressure fluctuation as input is characterized by comprising the following steps:
step S1, installing a pressure sensor at the air inlet end of a natural gas injection valve, and acquiring an inlet pressure signal;
s2, based on the one-to-one correspondence relationship between the lowest point of the inlet pressure signal and the jet quantity variation rule of the ejector, taking the inlet pressure signal as jet quantity variation information;
s3, establishing a jet quantity prediction model by using a RBF neural network, and training the jet quantity prediction model by using the jet quantity variation information to obtain a jet quantity calculation model;
s4, solving a real-time gas injection amount by taking the current inlet pressure signal as the input of the gas injection amount calculation model;
and S5, comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, taking the error value as the input of a feedforward controller and a PID (proportion integration differentiation) controller, performing feedforward compensation on the output of the PID, and performing comprehensive control on the natural gas circulating injection amount.
2. A feedforward PID closed-loop control method of a cyclic injection quantity with natural gas injector inlet pressure fluctuation as an input according to claim 1, wherein in the step S3, a corresponding relationship between an injection quantity change, an injection pressure at an injection start point and a maximum drop value of the inlet pressure is determined according to the injection quantity change information, the injection pressure and the maximum drop value of the inlet pressure are used as an input of the injection quantity prediction model, and the injection quantity change is used as an output of the injection quantity prediction model, wherein the corresponding relationship is that the injection quantity and the injection pressure are positively correlated with the drop value of the inlet pressure.
3. The feedforward PID closed-loop control method for the circulating injection amount with the natural gas injector inlet pressure fluctuation as the input according to claim 2, wherein the step S3 specifically comprises:
step S301, normalizing the jet volume change, the jet pressure at the jet starting point and the maximum drop value of the inlet pressure;
step S302, selecting an activation function of a hidden layer in an RBF neural network to construct the air injection amount prediction model;
step S303, dividing the normalized air injection quantity change, the air injection pressure at the air injection starting point and the maximum inlet pressure drop value into a training set and a testing set, training the air injection quantity prediction model by using the training set to obtain the air injection quantity calculation model, and verifying by using the testing set.
4. The feedforward PID closed-loop control method for the cycle injection amount with the natural gas injector inlet pressure fluctuation as the input according to claim 1, wherein the compensation process in the step S5 is specifically as follows:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference value between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i As integral time coefficient, k d Is a differential time coefficient, K q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
5. A cyclic injection quantity feed forward PID closed loop control system with natural gas injector inlet pressure fluctuations as input, comprising:
the acquisition module is used for installing a pressure sensor at the air inlet end of the natural gas injection valve and acquiring an inlet pressure signal;
the determining module is used for taking the inlet pressure signal as air injection quantity change information based on the one-to-one correspondence relationship between the lowest point of the inlet pressure signal and the air injection quantity change rule of the ejector;
the training module is used for establishing a gas injection amount prediction model by using a RBF neural network, and training the gas injection amount prediction model by using the gas injection amount change information to obtain a gas injection amount calculation model;
the solving module is used for solving the real-time air injection amount by taking the current inlet pressure signal as the input of the air injection amount calculation model;
and the compensation module is used for comparing the real-time gas injection amount with the expected gas injection amount to obtain an error value, taking the error value as the input of the feedforward controller and the PID controller, performing feedforward compensation on the PID output, and performing comprehensive control on the natural gas circulating injection amount.
6. The feedforward PID closed-loop control system of claim 5, wherein the training module takes the jet pressure and the maximum inlet pressure drop value as the input of the jet prediction model and the jet change as the output of the jet prediction model according to the corresponding relationship among the jet change, the jet pressure at the jet starting point and the maximum inlet pressure drop value, wherein the corresponding relationship is that the jet and the jet pressure are positively correlated with the inlet pressure drop value.
7. The feed-forward PID closed-loop control system for cyclic injection quantity with natural gas injector inlet pressure fluctuations as input of claim 6, wherein the training module specifically comprises:
the normalization unit is used for performing normalization processing on the jet flow variation, the jet pressure at the jet starting point and the maximum inlet pressure drop value;
the construction unit is used for selecting an activation function of a hidden layer in the RBF neural network to construct the air injection amount prediction model;
and the training and verifying unit is used for dividing the normalized air injection quantity change, the air injection pressure at the air injection starting point and the maximum drop value of the inlet pressure into a training set and a testing set, training the air injection quantity prediction model by using the training set to obtain the air injection quantity calculation model, and verifying by using the testing set.
8. The feed-forward PID closed-loop control system for cycle injection gas quantity with natural gas injector inlet pressure fluctuation as input according to claim 5, wherein the compensation process in the compensation module is specifically as follows:
wherein u (t) is the jet duration of the ejector and the corresponding jet amount, e (t) is the difference between the expected jet amount and the real-time jet amount, and k p Is a proportionality coefficient, k i As integral time coefficient, k d Is a differential time coefficient, k q For the feedforward coefficient, q (t) is the feedforward value derived from the injector inlet pressure signal.
9. A cyclic injection quantity feedforward PID closed-loop control device taking natural gas system pressure fluctuation as input, which is characterized by comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the computer program, the cyclic injection quantity feedforward PID closed-loop control method taking natural gas injector inlet pressure fluctuation as input is realized according to any one of claims 1 to 4.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements a cyclic injection quantity feed forward PID closed loop control method with natural gas injector inlet pressure fluctuations as input as claimed in any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376116.XA CN114815584B (en) | 2022-04-11 | 2022-04-11 | Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376116.XA CN114815584B (en) | 2022-04-11 | 2022-04-11 | Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114815584A CN114815584A (en) | 2022-07-29 |
| CN114815584B true CN114815584B (en) | 2022-12-27 |
Family
ID=82533828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210376116.XA Active CN114815584B (en) | 2022-04-11 | 2022-04-11 | Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114815584B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6882992B1 (en) * | 1999-09-02 | 2005-04-19 | Paul J. Werbos | Neural networks for intelligent control |
| WO2010109667A1 (en) * | 2009-03-27 | 2010-09-30 | 本田技研工業株式会社 | Controller for plant |
| JP2014004911A (en) * | 2012-06-25 | 2014-01-16 | Tokyo Univ Of Marine Science & Technology | Method for maintaining water route of ship with nonlinear auto-regressive model |
| CN106483850A (en) * | 2016-11-23 | 2017-03-08 | 沈阳航天新光集团有限公司 | The Fuzzy Self-adaptive PID method for designing that a kind of aero-engine is feedovered based on RBF neural |
| US11879656B2 (en) * | 2018-04-04 | 2024-01-23 | International Business Machines Corporation | Initialization of radial base function neural network nodes for reinforcement learning incremental control system |
| CN111273544B (en) * | 2020-04-01 | 2022-11-15 | 河海大学常州校区 | Radar pitching motion control method based on prediction RBF feedforward compensation type fuzzy PID |
-
2022
- 2022-04-11 CN CN202210376116.XA patent/CN114815584B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114815584A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104975956B (en) | In response to the internal combustion engine control of gas recirculation system condition | |
| US7383816B2 (en) | Virtual fuel quality sensor | |
| US20100199951A1 (en) | Adaptive control of fuel delivery in direct injection engines | |
| JP2005214201A (en) | METHOD AND DEVICE FOR MICRO PILOT FUEL INJECTION CONTROL FOR KEEPING NOx AND UHC EMISSION MINIMUM | |
| Kumar et al. | In-cylinder pressure-based air-fuel ratio control for lean burn operation mode of SI engines | |
| CN101965447A (en) | Fuel control system for diesel engine | |
| CN102797569A (en) | Adaptation control of lean nox trap regeneration with biodiesel during engine transient operation | |
| US11112333B2 (en) | Sensor failure diagnostic apparatus | |
| US8425224B2 (en) | Mass air flow compensation for burner-based exhaust gas generation system | |
| CN101825027B (en) | Method and apparatus for controlling fuel rail pressure using fuel pressure sensor error | |
| US9845757B2 (en) | Controller for diesel engine | |
| CN105283651A (en) | System and method for controlling the performance of an engine | |
| US6968827B2 (en) | Diesel engine comprising a device for controlling the flow of injected fuel | |
| US10280849B2 (en) | Combustion system control device | |
| CN114815584B (en) | Circulating air injection amount feedforward PID closed-loop control method and system taking natural gas ejector inlet pressure fluctuation as input | |
| CN114839869B (en) | ADRC gas injection amount closed-loop control method based on high-pressure natural gas circulating gas injection amount real-time detection | |
| US9494102B2 (en) | Method for operating a fuel injection system of an internal combustion engine | |
| Tan et al. | Exhaust gas recirculation control through extremum seeking in a low temperature combustion diesel engine | |
| US10132318B2 (en) | Turbocharger control | |
| US9328691B2 (en) | Setpoint bank control architecture | |
| JP2013024199A (en) | Extremely lean zone responsiveness diagnostic method of lambda sensor and common rail type fuel injection control device | |
| US7124017B2 (en) | Method of operating an internal combustion engine | |
| US20120279291A1 (en) | System and method for establishing a mass flow rate of air entering an engine | |
| JP2021148073A (en) | Injection condition creation device and vehicle | |
| Peng et al. | Characteristics of Rail Pressure Fluctuations under Two-Injection Conditions and the Control Strategy Based on ANN |
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 |