CN114935423A - Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line - Google Patents
Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line Download PDFInfo
- Publication number
- CN114935423A CN114935423A CN202210383748.9A CN202210383748A CN114935423A CN 114935423 A CN114935423 A CN 114935423A CN 202210383748 A CN202210383748 A CN 202210383748A CN 114935423 A CN114935423 A CN 114935423A
- Authority
- CN
- China
- Prior art keywords
- ion current
- diesel engine
- neural network
- nozzle
- analog
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/14—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring the force of explosions; for measuring the energy of projectiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides an online detection device for the highest detonation pressure of a diesel engine nozzle position, wherein a nozzle body and an ion current detection probe provide bias voltage and generate ion current in the combustion process; the generated ion current is subjected to signal amplification and analog-to-digital conversion through a charge amplifier and an analog-to-digital converter; collecting ion current data through a data acquisition card of a PC (personal computer), and solving the size and the change rate of the ion current; constructing and training a BP neural network; inputting the obtained change rate of the ion current into a trained BP neural network for prediction to complete the measurement of the ion current; according to the invention, the circuit formed between the nozzle and the cathode is used for measuring and obtaining the ion current formed in the combustion process, so that the environment in the whole cylinder is ensured to be unchanged, and the measurement and the obtaining of the ion current are accurately realized.
Description
Technical Field
The invention belongs to the technical field of power energy, and particularly relates to a device and a method for detecting the highest detonation pressure of a nozzle of a diesel engine on line.
Background
With the development of the times, the diesel engine is popularized to a great extent in daily life, and the development of the diesel engine plays a key role in various aspects such as national defense and the like. Also, the development of engines is accompanied by problems of flame combustion performance, carbon emission, and the like. In order to improve the overall thermal efficiency of the diesel engine and reduce carbon emission, the highest detonation pressure of the nozzle position in the combustion process of the diesel engine needs to be detected on line to realize accurate and real-time data grasping.
In the current engine research process, the diesel engine still occupies a larger proportion, the detection of the highest explosion pressure at the nozzle position of the diesel engine can provide a corresponding theoretical basis for the research on the aspects of combustion, emission and the like, the research and development and the progress of the diesel engine can be promoted, and the overall performance of the diesel engine is improved.
In the aspect of engine electric control, realizing accurate and rapid real-time monitoring of parameters is always an important problem. The most common method is to add a sensor to detect various parameters in the cylinder in real time. Based on the method, the invention is further invented and perfected, and the measured parameters are processed and processed to finally obtain the final structure. When a sensor for detection is additionally arranged, the sensor is required to be ensured not to influence the environment of the whole experimental process too much, and after the environment is prevented from being changed, real data are changed to influence the measurement of the data.
In recent years, the development of neural network algorithms is fast, at present, neural networks have a plurality of calculation methods, and data can more accurately reach an actual value after being trained by the neural networks, so that the subsequent operation is facilitated. In the data acquisition process, the signal amplifier and the digital-to-analog converter are used, so that the acquired ion current can be integrally processed by a computer, and the data can be conveniently used. The relation between the ion current generated in the combustion process and the highest detonation pressure is processed in the whole research process, and the problem is converted into the solution of the ion current. And a neural network is adopted for the subsequent calculation of the highest burst pressure.
Disclosure of Invention
The invention provides an online detection device and method for the highest detonation pressure of a diesel engine nozzle position to solve the accuracy of overall data, wherein a neural network method is adopted to train the measured in-cylinder pressure, and after training, the maximum value in a pressure change curve can be quickly and accurately found, namely the highest detonation pressure is obtained; meanwhile, an ion detection probe technology is adopted to accurately detect the ion current; the method and the device realize online detection of the highest explosion pressure at the nozzle position in the combustion process of the diesel engine, ensure the highest explosion pressure at the nozzle position of the diesel engine at the detection position accurately and ensure the perfection of the whole system.
The invention is realized by the following technical scheme:
a diesel engine nozzle position highest detonation pressure on-line measuring device:
the online detection device comprises a nozzle body, an ion current detection probe, a charge amplifier, an analog-to-digital converter and a PC (personal computer);
the ion current detection probe is integrated inside a nozzle of the diesel engine and used as a positive electrode;
the nozzle body is used as a cathode of the ion current probe, and the nozzle body is connected with the ion current probe through an external lead;
the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
the charge amplifier and the analog-to-digital converter are used for carrying out signal amplification and analog-to-digital conversion on the ion current, and processed ion current data are collected through a data acquisition card of a PC (personal computer);
and the collected ion current data passes through a BP neural network model established by a PC (personal computer), and an explosion pressure curve at the nozzle body is obtained according to the relation between the ion current and the current attenuation speed and the explosion pressure, so that the measurement of the ion current is completed.
An online detection method for the highest detonation pressure of a diesel engine nozzle position;
step 1: the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
step 2: carrying out signal amplification and analog-to-digital conversion on the ion current generated in the step (1) through a charge amplifier and an analog-to-digital converter;
and step 3: collecting the ion current data processed in the step (2) through a data acquisition card of a PC (personal computer), and solving the size of the ion current and the change rate of the ion current;
and 4, step 4: constructing and training a BP neural network;
and 5: and (4) inputting the change rate of the ion current obtained in the step (3) into the BP neural network trained in the step (4) for prediction, and completing the measurement of the ion current.
Further, the air conditioner is provided with a fan,
in step 3, the ion current data obtained in step 2 is converted into a corresponding detonation pressure change curve through a formula (1):
wherein P is the desired burst pressure,the ion current decay rate is shown, and k and C are corresponding coefficients;
according to the relation between the ion current and the current decay speed and the detonation pressure, the detonation pressure curve can be obtained from the detected ion current.
Further, the air conditioner is provided with a fan,
in the step 4, the process is carried out,
the BP neural network is divided into three layers, namely an input layer, a hidden layer and an output layer, corresponding correction weights W1, W2, B1 and B2 are set, and the maximum value of the explosion pressure calculated by the formula (1) is obtained;
an activation layer is arranged in the hidden layer, a ReLU function is adopted, the maximum value of the explosion pressure is obtained aiming at the final output layer, and the maximum value of flexibility is selected as the output layer;
the flexibility maximum value calculation formula is as follows:
first calculate the weighted input
Then through the formula (3)
And the activation values are all positive numbers, and the maximum flexibility value is a probability distribution.
Further, the air conditioner is provided with a fan,
the best training results for the BP neural network were achieved when W1 was k, B1 was 0, W2 was 1, and B2 was C.
Further, the air conditioner is characterized in that,
the quality of output is measured through Cross Entropy loss Cross Entrophy Error, and the accuracy of a data result is ensured.
An electronic device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.
A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of any of the above methods.
The invention has the beneficial effects that
The invention processes the relation between the ionic current and the explosion pressure, and measures the ionic current formed in the combustion process by forming a circuit between the nozzle and the cathode, thereby ensuring that the environment in the whole cylinder is unchanged and accurately measuring the ionic current;
the method uses a neural network algorithm to carry out high-precision calculation, and correctly calculates the highest detonation pressure of the position of the diesel engine nozzle; compared with the existing method for measuring the detonation pressure of the diesel nozzle, the method has low cost, ensures that the measurement process can be carried out outside the cylinder by using an ionic current method, and prevents the influence of a corresponding sensor additionally arranged in the cylinder on the data change in the cylinder;
compared with other measuring methods, the neural network adopted by the method has certain advancement, the efficiency of the whole process is improved, the system correction and the method for detecting the highest detonation pressure of the position of the diesel engine nozzle are improved, and the research progress in the aspect can be promoted.
Drawings
FIG. 1 is a block diagram of an overall BP neural network according to the present invention;
FIG. 2 is a flowchart of the overall algorithm;
fig. 3 is an overall flow chart of system data processing.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
With reference to fig. 1 to 3.
An on-line detection device for the highest detonation pressure of a diesel engine nozzle,
the online detection device comprises a nozzle body, an ion current detection probe, a charge amplifier, an analog-to-digital converter and a PC (personal computer);
the ion current detection probe is integrated inside a nozzle of the diesel engine and used as a positive electrode;
the nozzle body is used as the cathode of the ion current probe, and the nozzle body is connected with the ion current probe through an external lead;
the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
the charge amplifier and the analog-to-digital converter (A/D converter) perform signal amplification and analog-to-digital conversion on the ion current, and the processed ion current data is collected by a data acquisition card of a PC (personal computer);
and the collected ion current data passes through a BP neural network model established by a PC (personal computer), and an explosion pressure curve at the nozzle body is obtained according to the relation between the ion current and the current attenuation speed and the explosion pressure, so that the measurement of the ion current is completed.
An online detection method for the highest detonation pressure of a diesel engine nozzle position;
step 1: the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
step 2: carrying out signal amplification and analog-to-digital conversion on the ion current generated in the step 1 through a charge amplifier and an analog-to-digital converter;
and step 3: collecting the ion current data processed in the step (2) by a data acquisition card of a PC (personal computer), and solving the size of the ion current and the change rate of the ion current;
and 4, step 4: constructing and training a BP neural network;
and 5: and (4) inputting the ion current change rate obtained in the step (3) into the BP neural network trained in the step (4) for prediction, and completing the measurement of the ion current.
In step 3, the ion current data obtained in step 2 is converted into a corresponding explosion pressure change curve through the formula (1):
where P is the desired burst pressure and where,the ion current decay rate is shown, and k and C are corresponding coefficients;
according to the relation between the ion current and the current decay speed and the detonation pressure, the detonation pressure curve can be obtained from the detected ion current.
In the step 4, the process is carried out,
the BP neural network is a multilayer feedforward network and is divided into three layers, namely an input layer, a hidden layer and an output layer, corresponding correction weights W1, W2, B1 and B2 are set, and the maximum value of the explosion pressure calculated by the formula (1) is obtained;
in order to ensure the corresponding accuracy of the data, an activation layer is arranged in the hidden layer, and a ReLU function is adopted, so that the original value of the data can be reserved in the primary operation process. Solving the maximum value of the explosion pressure aiming at the final output layer, and selecting the maximum flexible value as the output layer;
the flexibility maximum is to define a new output layer for the neural network. Initially, as with the S-type layer, the weighted input is first calculated
Then through the formula (3)
And the activation values are positive numbers, and the maximum flexibility value is a probability distribution.
The best training results for the BP neural network were achieved when W1 was k, B1 was 0, W2 was 1, and B2 was C. The structure diagram of the whole BP neural network is shown in figure 1, and the whole algorithm flow is shown in figure 2.
The quality of output is measured through Cross Entropy loss Cross Engine Error, and the accuracy of a data result is ensured.
An electronic device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.
A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of any of the above methods.
The device and the method for detecting the highest detonation pressure at the nozzle position of the diesel engine, which are provided by the invention, are introduced in detail, the principle and the implementation mode of the invention are explained, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. The utility model provides a highest detonation pressure on-line measuring device in diesel engine nozzle position which characterized in that:
the online detection device comprises a nozzle body, an ion current detection probe, a charge amplifier, an analog-to-digital converter and a PC (personal computer);
the ion current detection probe is integrated inside a nozzle of the diesel engine and used as a positive electrode;
the nozzle body is used as the cathode of the ion current probe, and the nozzle body is connected with the ion current probe through an external lead;
the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
the charge amplifier and the analog-to-digital converter are used for carrying out signal amplification and analog-to-digital conversion on the ion current, and the processed ion current data is collected through a data acquisition card of a PC (personal computer);
and the collected ion current data passes through a BP neural network model established by a PC (personal computer), and an explosion pressure curve at the nozzle body is obtained according to the relation between the ion current and the current attenuation speed and the explosion pressure, so that the measurement of the ion current is completed.
2. The method for detecting the highest detonation pressure of the position of a diesel engine nozzle on line is characterized by comprising the following steps of (1) detecting the highest detonation pressure of the position of the diesel engine nozzle on line;
step 1: the positive and negative electrode structure formed by the ion current detection probe and the nozzle body provides bias voltage for the whole online detection system, and meanwhile, the diesel engine generates ion current in the combustion process;
and 2, step: carrying out signal amplification and analog-to-digital conversion on the ion current generated in the step (1) through a charge amplifier and an analog-to-digital converter;
and step 3: collecting the ion current data processed in the step (2) by a data acquisition card of a PC (personal computer), and solving the size and the change rate of the ion current;
and 4, step 4: constructing and training a BP neural network;
and 5: and (4) inputting the change rate of the ion current obtained in the step (3) into the BP neural network trained in the step (4) for prediction, and completing the measurement of the ion current.
3. The method of claim 2, further comprising:
in step 3, the ion current data obtained in step 2 is converted into a corresponding detonation pressure change curve through the formula (1):
where P is the desired burst pressure and where,the ion current decay rate is shown, and k and C are corresponding coefficients;
the burst pressure curve can be obtained from the detected ion current according to the relationship between the ion current and the current decay rate and burst pressure.
4. The method of claim 3, wherein:
in the step 4, the process is carried out,
the BP neural network is divided into three layers, namely an input layer, a hidden layer and an output layer, corresponding correction weights W1, W2, B1 and B2 are set, and the maximum value of the explosion pressure calculated by the formula (1) is obtained;
an active layer is arranged in the hidden layer, a ReLU function is adopted, the maximum value of the burst pressure is obtained aiming at the final output layer, and the flexible maximum value is selected as the output layer;
the flexibility maximum value calculation formula is as follows:
first calculate the weighted input
Then the general formula (3)
And the activation values are positive numbers, and the maximum flexibility value is a probability distribution.
5. The method of claim 4, further comprising:
the best training result of the BP neural network is achieved when W1 is k, B1 is 0, W2 is 1 and B2 is C.
6. The method of claim 4, further comprising:
the quality of output is measured through Cross Entropy loss Cross Engine Error, and the accuracy of a data result is ensured.
7. An electronic device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 2 to 6 when executing the computer program.
8. A computer readable storage medium storing computer instructions, which when executed by a processor implement the steps of the method of any one of claims 2 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210383748.9A CN114935423A (en) | 2022-04-11 | 2022-04-11 | Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210383748.9A CN114935423A (en) | 2022-04-11 | 2022-04-11 | Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114935423A true CN114935423A (en) | 2022-08-23 |
Family
ID=82861795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210383748.9A Pending CN114935423A (en) | 2022-04-11 | 2022-04-11 | Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114935423A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07279743A (en) * | 1994-04-08 | 1995-10-27 | Honda Motor Co Ltd | Knocking detector for internal combustion engine |
JPH10122114A (en) * | 1996-06-10 | 1998-05-12 | Denso Corp | Glow plug, ionic current detecting device using it, and manufacture of glow plug |
US20050092287A1 (en) * | 2003-10-31 | 2005-05-05 | Woodward Governor Company | Method and apparatus for detecting ionization signal in diesel and dual mode engines with plasma discharge system |
CN105143649A (en) * | 2013-03-11 | 2015-12-09 | 韦恩州立大学 | Predictive correction in internal combustion engines |
CN112160842A (en) * | 2020-09-16 | 2021-01-01 | 同济大学 | Method for detecting and distinguishing pre-ignition and carbon deposition of engine based on ion current |
-
2022
- 2022-04-11 CN CN202210383748.9A patent/CN114935423A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07279743A (en) * | 1994-04-08 | 1995-10-27 | Honda Motor Co Ltd | Knocking detector for internal combustion engine |
JPH10122114A (en) * | 1996-06-10 | 1998-05-12 | Denso Corp | Glow plug, ionic current detecting device using it, and manufacture of glow plug |
US20050092287A1 (en) * | 2003-10-31 | 2005-05-05 | Woodward Governor Company | Method and apparatus for detecting ionization signal in diesel and dual mode engines with plasma discharge system |
CN105143649A (en) * | 2013-03-11 | 2015-12-09 | 韦恩州立大学 | Predictive correction in internal combustion engines |
CN112160842A (en) * | 2020-09-16 | 2021-01-01 | 同济大学 | Method for detecting and distinguishing pre-ignition and carbon deposition of engine based on ion current |
Non-Patent Citations (1)
Title |
---|
潘慕绚: "基于离子电流的脉冲爆震发动机压力建模及控制", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | SoC estimation of Lithium battery based on improved BP neural network | |
JP6430209B2 (en) | Fuel cell stack state diagnosis method and fuel cell system control method | |
CN106484026A (en) | Control method and device that a kind of maximum photovoltaic power point based on grey wolf algorithm is followed the tracks of | |
CN111062137A (en) | Lithium ion battery performance prediction model and construction method and application thereof | |
CN107728478A (en) | Fuel cell excess oxygen coefficient network response surface method | |
CN113132399A (en) | Industrial control system intrusion detection method based on time convolution network and transfer learning | |
CN112765902B (en) | Soft measurement modeling method for COD concentration in rural domestic sewage treatment process based on TentFWA-GD RBF neural network | |
CN112067999B (en) | Nondestructive acquisition system and method for open circuit potential curve of lithium ion battery anode | |
CN110597070A (en) | Method for identifying model parameters of thermal power generating unit system | |
CN106100582B (en) | Based on the recursive least-squares photovoltaic cell parameter identification method with forgetting factor | |
CN108647483A (en) | A kind of SCR inlet NO based on fuzzy tree modeling methodXThe flexible measurement method of concentration | |
CN114839542A (en) | Sample data set generation method and SOC estimation method for power lithium battery | |
CN114935423A (en) | Device and method for detecting highest detonation pressure of nozzle position of diesel engine on line | |
CN112580289B (en) | Hybrid capacitor power state online estimation method and system | |
CN114779103A (en) | Lithium ion battery SOC estimation method based on time-lag convolutional neural network | |
CN103899428B (en) | A kind of diesel combustion control gear based on ionic current | |
CN114280490B (en) | Lithium ion battery state of charge estimation method and system | |
Zhou et al. | Cell resistance slope combined with LVQ neural network for prediction of anode effect | |
Hu et al. | Research on the fault identification method of oil pumping unit based on residual network | |
CN112487748B (en) | Lithium ion battery fractional order model establishment method considering time-frequency domain characteristics | |
CN110705881A (en) | Boiler efficiency online calculation method and system based on artificial neural network | |
Tan et al. | Dynamic prediction of NOx emissions based on factor analysis and NARX neural network | |
Fu et al. | Transfer learning and vision transformer based state-of-health prediction of lithium-ion batteries | |
CN113555593B (en) | Proton exchange membrane fuel cell operation method based on physical field distribution heterogeneity | |
CN115061050B (en) | Intelligent monitoring method for battery electric quantity |
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 |