CN111931413A - Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance - Google Patents
Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance Download PDFInfo
- Publication number
- CN111931413A CN111931413A CN202010570940.XA CN202010570940A CN111931413A CN 111931413 A CN111931413 A CN 111931413A CN 202010570940 A CN202010570940 A CN 202010570940A CN 111931413 A CN111931413 A CN 111931413A
- Authority
- CN
- China
- Prior art keywords
- extreme
- diesel engine
- altitude
- particle
- performance
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
A method for predicting the performance of an optimized extreme learning machine high-altitude diesel engine based on chaotic particle swarm with extreme disturbance is characterized by comprising the following steps of: the method comprises the following steps: firstly, acquiring high-altitude operation data of the diesel engine, wherein the high-altitude operation data comprises working condition parameters and performance parameters; optimizing the weight and the threshold of the extreme learning machine by using the algorithm of the chaotic particle swarm with extreme disturbance to obtain the optimal weight and threshold; a global optimal particle position; and thirdly, giving the optimal weight and the threshold value obtained in the second step to an ELM neural network, inputting the acquired data into an extreme learning machine, and training to establish an optimal diesel engine high-altitude ELM neural network performance prediction model. The method ensures that the diesel engine performance prediction model has the characteristics of high prediction precision and high training speed.
Description
Technical Field
The invention relates to the field of high-altitude performance prediction of diesel engines, in particular to a method for predicting the performance of an optimized extreme learning machine high-altitude diesel engine based on chaotic particle swarm with extreme disturbance.
Background
When the diesel engine runs at high altitude, the air supply speed is obviously lower than the oil supply speed due to the reduction of the atmospheric pressure air inlet flow, and the performance of the diesel engine is obviously deteriorated compared with that of the diesel engine on the plain due to the reduction of the air inlet flow. At present, the diesel engine supercharging technology is one of the technical measures for improving the plateau adaptability of the diesel engine, and the supercharging system research mainly focuses on control strategy design and multi-objective collaborative optimization. A good performance prediction model can be used for checking and feeding back the design effect of a control strategy and is also the basis for developing the control and optimization of a diesel engine system. Compared with a bench test, the method has the advantages that the diesel engine performance is obtained by using the prediction model in the research process, the research efficiency can be greatly improved, and the test period is shortened.
With the development of diesel engine electric control technology, the traditional mechanism modeling and polynomial modeling have difficulty in accurately predicting the performance of the diesel engine. The neural network is widely applied to the prediction, control and optimization research of the diesel engine by virtue of strong self-learning and self-adapting capabilities. However, most of the traditional neural networks adopt a gradient descent method, have the defects of low training speed, poor generalization capability, easy trapping in local optimal values, sensitivity to parameter setting and the like, and are difficult to adapt to the multi-variable and multi-system real-time control requirements of the diesel engine. The ELM has the advantages of high calculation speed, high prediction accuracy, easiness in parameter adjustment and the like, so that the selection of the ELM neural network for the performance prediction of the high-altitude diesel engine is a trend, but the traditional ELM randomly generates weights and thresholds of the hidden layer, so that the prediction stability is still to be improved, and the determination of the number of neurons of the hidden layer is lack of theoretical basis.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the existing research and provides an optimized extreme learning machine algorithm based on chaotic particle swarm with extreme disturbance, and the diesel engine performance prediction model has the characteristics of high prediction precision and high training speed by using the algorithm.
As conceived above, the technical scheme of the invention is as follows: a method for predicting the performance of an optimized extreme learning machine high-altitude diesel engine based on chaotic particle swarm with extreme disturbance is characterized by comprising the following steps of: the method comprises the following steps: firstly, acquiring high-altitude operation data of the diesel engine, wherein the high-altitude operation data comprises working condition parameters and performance parameters; optimizing the weight and the threshold of the extreme learning machine by using the algorithm of the chaotic particle swarm with extreme disturbance to obtain the optimal weight and threshold; a global optimal particle position; and thirdly, giving the optimal weight and the threshold value obtained in the second step to an ELM neural network, inputting the acquired data into an extreme learning machine, and training to establish an optimal diesel engine high-altitude ELM neural network performance prediction model.
Further, the method of the second step is to determine input and output parameters of the ELM neural network, set the number of neurons in the hidden layer, normalize the input parameters, generate an initial weight and a threshold value by the neural network, encode the initial weight and the threshold value into a population position, and then input an algorithm of a chaotic particle swarm with extreme value disturbance to optimize the initial weight and the threshold value, wherein the algorithm comprises the following steps:
determining algorithm operation parameters including learning factors, population scale, evolution times and chaotic optimization times;
step2, initializing a population, randomly generating weights and thresholds of N particles in an ELM neural network, and taking the weights and the thresholds as the position and the speed of a population initial particle to obtain an initial fitness value of the population initial particle, so as to obtain initial individual optimal and global optimal particles;
step3, updating the disturbance operator, and updating the speed and the position of the population particles according to the individual optimal particles and the global optimal particles;
step4, after the updating is finished, performing chaotic optimization on the generated global optimal particle position, firstly mapping the particle position to a definition domain [0, 1] of a Logistic equation, iteratively generating chaotic variables by using the Logistic equation, returning the variables to an original solution space through inverse mapping, calculating the fitness value of each feasible solution, and reserving the particle p with the minimum fitness value;
step5, randomly selecting one particle from the population to be replaced by p;
step6, judging whether the maximum iteration times are reached or the precision condition is met, if the maximum iteration times are met, outputting the optimal particle position and the optimal solution, and if the maximum iteration times are not met, turning to Step 3;
further, the working condition parameters comprise five operating working condition parameters of the engine, namely, rotating speed, load, atmospheric pressure, fuel injection quantity and fuel injection advance angle.
Further, the performance parameters include torque, power, specific fuel consumption, air-fuel ratio, boost pressure, and intake air flow rate.
Further, working condition parameters and performance parameters of the engine are acquired by using a high-altitude performance simulation test bed of the internal combustion engine or a plateau engine mobile test bed and an orthogonal test method.
Further, the diesel engine high-altitude operation data acquired in the step I needs to be subjected to data processing, namely, repeated data is removed and an incomplete data set is recorded.
Further, Step3 updates the disturbance operator, and the specific method for updating the population particle speed and position according to the individual optimal particle and the global optimal particle is as follows:
disturbance operator r according to equations 1 and 23And r4Updating, namely updating the position and the speed of the population particles according to a formula 3 and the fitness value:
v(t+1)＝ωv(t)+c1r1(r3pi(t)-x(t))+c2r2(r4pg(t)-x(t)) (3)
wherein iter is the current iteration number, iterMax is the maximum iteration number, rand, r1、r2Is [0, 1]]Number of particles uniformly distributed, v (t) being at time tVelocity, ω is the inertial weight, c1、c2As a learning factor, pi(t)、pg(t) individually optimal and globally optimal particles at time t, respectively.
Further, the specific method of Step4 is as follows: global optimum particle position pg＝(pg，1，pg，2，…，pg，n) It is mapped to the domain of Logistic equation [0, 1] according to equation 4]Generating chaos variable by iteration according to Logistic formula 5, and mapping the variable p in reverseg，i＝ai+(bi-ai)ziReturning to the original solution space, calculating the fitness value of each feasible solution, and reserving the particle p with the minimum fitness value:
Zn+1＝μzn(1-zn)，n＝0，1，2…(5)
wherein, biIs the maximum value of the input data, aiMu is the minimum value of the input data and is the control parameter.
Further, the data processing is to perform normalization operation on the input and output parameters by using a mapminmax function carried by MATLAB.
The invention has the following advantages:
1. compared with the traditional neural network prediction algorithm, the ELM neural network prediction algorithm has the characteristics of less training time and strong generalization capability, and is strong in robustness and easy to tune.
2. The invention adopts the chaotic particle swarm algorithm with extreme disturbance, introduces disturbance factors and chaotic optimization measures, improves the global search and the ability of jumping out local extreme points of the algorithm, and has faster convergence speed compared with the standard particle swarm algorithm and the genetic algorithm.
3. According to the method, the weight and the threshold of the extreme learning machine are optimized by adopting the chaotic particle swarm algorithm with the extreme disturbance, the prediction stability of the extreme learning machine is effectively improved, the optimal weight and the optimal threshold are given to the neural network of the extreme learning machine, the prediction precision of a high-altitude diesel engine prediction model is improved, and the high-altitude multi-target diesel engine optimization and multi-system control research can be met.
Drawings
FIG. 1 is a flow chart of a modeling method of an optimized extreme learning machine based on chaotic particle swarm with extreme disturbance according to the invention;
FIG. 2 is an ELM neural network model structure;
FIG. 3 is a comparison graph of prediction accuracy of five model algorithms of a CHPSO-ELM and a particle swarm optimization extreme learning machine PSO-ELM, a genetic algorithm optimization extreme learning machine GA-ELM, a BP neural network and a support vector machine SVM of the invention;
FIG. 4 is a comparison graph of algorithm iteration convergence rates of three model algorithms of the CHPSO-ELM and the particle swarm optimization extreme learning machine PSO-ELM and the genetic algorithm optimization extreme learning machine GA-ELM.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
Referring to fig. 1 and 2, the invention provides a method for predicting the performance of an optimized extreme learning machine high-altitude diesel engine based on chaotic particle swarm with extreme disturbance, which takes a certain type of six-cylinder diesel engine as a research object and comprises the following specific implementation steps:
1. the method comprises the steps of selecting five working condition operating parameters of the diesel engine, such as the rotating speed, the load, the atmospheric pressure, the fuel injection quantity and the fuel injection advance angle, and selecting six performance parameters of the torque, the power, the fuel consumption rate, the air-fuel ratio, the supercharging pressure and the air intake flow. The total number of experimental samples is 300, the samples cover the full-working-condition operation data of the diesel engine with the altitude of 0-5000m, 240 groups are randomly selected as experimental training samples, and 60 groups are selected as experimental detection samples.
2. And data processing, including removing repeated data and recording an incomplete data set, and performing normalization operation on input and output parameters by adopting a mapminmax function of an MATLAB self-carrying function.
3. Determining input and output parameters of the ELM neural network, wherein the structure of the ELM neural network is shown in figure 2, and according to the relevant knowledge of the ELM neural network, the input parameter is x ═ x1，x2，…xn]TThe output parameter is y ═ y1，y2，…，ym]TAn ELM neural network model containing l hidden layer neurons, which can be expressed as:
where l is the number of hidden layer neurons, g (x) is the hidden layer neuron activation function, ωiRepresents the connection weight of the ith neuron of the hidden layer and the input layer, and is represented as omegai＝[ωi1，ωi2，…，ωin]，bi＝bi1，bi2，…，bimThreshold, β, for the ith hidden layer nodei1The connection weight of the ith hidden layer neuron and the 1 st output layer neuron. Expression 1 is expressed in matrix form:
Hβ＝T
wherein H is the hidden layer output matrix
ELM network training is equivalent to the following optimization problem:
when g (x) is infinitely differentiable, ω and b can be randomly selected and kept constant during training, and the implicit and input layer connection weights β can be obtained by solving a least-squares solution for a given system, which is
Wherein H+Moore-Penrose generalized inverse of matrix H.
Because the weight and the threshold are randomly generated by the ELM neural network, the model prediction performance is unstable, and the chaotic particle swarm optimization algorithm with extreme value disturbance is introduced in the method, compared with the standard particle algorithm and the genetic algorithm, the overall search capability of the algorithm is more excellent, the algorithm is not easy to fall into a local extreme value, and the iteration speed is higher. The invention encodes the weight and the threshold of the ELM neural network into the position of an algorithm population, and carries out iterative update by utilizing the fitness value, and the algorithm optimization steps are as follows:
determining algorithm operation parameters including learning factors, population scale, evolution times and chaotic optimization times;
step2, initializing a population, randomly generating weights and thresholds of N particles in an ELM neural network, and taking the weights and the thresholds as the position and the speed of a population initial particle to obtain an initial fitness value of the population initial particle, so as to obtain the position and the speed of an initial individual optimal particle and a global optimal particle;
step3. Pair of perturbation operators r according to equations 1 and 23And r4Updating, namely updating the population position and the population speed of the individual optimal particles and the global optimal particles according to a formula 3 and fitness values:
v(t+1)＝ωv(t)+c1r1(r3pi(t)-x(t))+c2r2(r4pg(t)-x(t)) (3)
wherein iter is the current iteration number, iterMax is the maximum iteration number, rand, r1、r2Is [0, 1]]Uniformly distributed number, v (t) is the velocity of the particle at time t, ω is the inertia weight, c1、c2As a learning factor, pi(t)、pg(t) individually optimal and globally optimal particles at time t, respectively.
Step4. for the resulting global optimum particle position pg＝(pg，1，pg，2，…，pg，n) Performing chaos optimization, and mapping to the definition domain [0, 1] of Logistic equation according to formula 4]Generating chaos variable by iteration according to Logistic formula 5, and mapping the variable p in reverseg，i＝ai+(bi-ai)ziReturning to the original solution space, calculating the fitness value of each feasible solution, and reserving the particle p with the minimum fitness value:
Zn+1＝μzn(1-zn)，n＝0，1，2…(5)
wherein, biIs the maximum value of the input data, aiMu is the minimum value of the input data and is the control parameter.
Step5, randomly selecting one particle from the population to be replaced by p;
step6, if the maximum iteration times are reached or the precision condition is met, outputting the optimal particle position and the optimal solution, and if the condition is not met, turning to Step 3;
4. and (4) decoding the globally optimal particle position obtained by optimizing the optimization algorithm into a weight and a threshold value again, giving the weight and the threshold value to the ELM neural network, and establishing an optimal diesel engine high-altitude ELM neural network performance prediction model.
In order to verify that the performance of the high-altitude diesel engine performance prediction method based on the chaos particle swarm with extreme disturbance, which is provided by the invention, is more superior in the high-altitude performance prediction of the diesel engine, the experiment compares the method (CHPSO-ELM) with a particle swarm optimization extreme learning machine (PSO-ELM), a genetic algorithm optimization extreme learning machine (GA-ELM), a BP neural network and a Support Vector Machine (SVM), five models are independently operated for 50 times respectively, and the accuracy of the method for predicting the performance of the diesel engine is measured by adopting the percentage of the average absolute error. The prediction accuracy of the five algorithms is shown in fig. 3, and the iterative convergence rate of the three algorithms CHPSO, PSO and GA is shown in fig. 4.
The method adopts the dynamic optimization ELM optimal parameter based on the chaotic particle swarm with the extreme disturbance, optimizes to obtain the optimal weight and threshold, establishes the optimal high-altitude performance prediction model of the diesel engine, has higher training speed and higher prediction precision, and can meet the requirements of multi-target optimization and multi-system control research of the high-altitude diesel engine.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. A method for predicting the performance of an optimized extreme learning machine high-altitude diesel engine based on chaotic particle swarm with extreme disturbance is characterized by comprising the following steps of: the method comprises the following steps: firstly, acquiring high-altitude operation data of the diesel engine, wherein the high-altitude operation data comprises working condition parameters and performance parameters; optimizing the weight and the threshold of the extreme learning machine by using the algorithm of the chaotic particle swarm with extreme disturbance to obtain the optimal weight and threshold; a global optimal particle position; and thirdly, giving the optimal weight and the threshold value obtained in the second step to an ELM neural network, inputting the acquired data into an extreme learning machine, and training to establish an optimal diesel engine high-altitude ELM neural network performance prediction model.
2. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance, according to claim 1, is characterized in that: determining input and output parameters of an ELM neural network, setting the number of neurons in a hidden layer, normalizing the input parameters, generating an initial weight and a threshold value by the neural network, encoding the initial weight and the threshold value into a population position, and then inputting an algorithm of chaotic particle swarm with extreme value disturbance to optimize the initial weight and the threshold value, wherein the algorithm comprises the following steps:
determining algorithm operation parameters including learning factors, population scale, evolution times and chaotic optimization times;
step2, initializing a population, randomly generating weights and thresholds of N particles in an ELM neural network, and taking the weights and the thresholds as the position and the speed of a population initial particle to obtain an initial fitness value of the population initial particle, so as to obtain initial individual optimal and global optimal particles;
step3, updating the disturbance operator, and updating the speed and the position of the population particles according to the individual optimal particles and the global optimal particles;
step4, after the updating is finished, performing chaotic optimization on the generated global optimal particle position, firstly mapping the particle position to a definition domain [0, 1] of a Logistic equation, iteratively generating chaotic variables by using the Logistic equation, returning the variables to an original solution space through inverse mapping, calculating the fitness value of each feasible solution, and reserving the particle p with the minimum fitness value;
step5, randomly selecting one particle from the population to be replaced by p;
and Step6, judging whether the maximum iteration number is reached or the precision condition is met, outputting the optimal particle position and the optimal solution if the condition is met, and turning to Step3 if the condition is not met.
3. The method for predicting the performance of the high-altitude diesel engine based on the optimized extreme learning machine based on the chaos particle swarm with the extreme disturbance, as recited in claim 1, wherein the working condition parameters comprise five operating working condition parameters of the engine, namely rotating speed, load, atmospheric pressure, fuel injection quantity and fuel injection advance angle.
4. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance, according to claim 1, is characterized in that: the performance parameters include torque, power, specific fuel consumption, air-fuel ratio, boost pressure, and intake air flow rate.
5. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance according to claim 1, characterized in that a high-altitude performance simulation test bed of an internal combustion engine or a high-altitude engine moving test bed and an orthogonal test method are used for collecting working condition parameters and performance parameters of the engine.
6. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance according to claim 1, wherein the high-altitude operation data of the diesel engine obtained in the step (i) is subjected to data processing, namely, repeated data is removed and an incomplete data set is recorded.
7. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance, according to claim 2, is characterized in that: the Step3 updates the disturbance operator, and the specific method for updating the speed and the position of the population particle according to the individual optimal particle and the global optimal particle is as follows:
disturbance operator r according to equations 1 and 23And r4Updating, namely updating the position and the speed of the population particles according to a formula 3 and the fitness value:
v(t+1)＝ωv(t)+c1r1(r3pi(t)-x(t))+c2r2(r4pg(t)-x(t)) (3)
whereiniter is the current iteration number, iterMax is the maximum iteration number, rand, r1、r2Is [0, 1]]Uniformly distributed number, v (t) is the velocity of the particle at time t, ω is the inertia weight, c1、c2As a learning factor, pi(t)、pg(t) individually optimal and globally optimal particles at time t, respectively.
8. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance, according to claim 1, is characterized in that: the specific method of Step4 is as follows: global optimum particle position pg＝(pg，1，pg，2，…，pg，n) It is mapped to the domain of Logistic equation [0, 1] according to equation 4]Generating chaos variable by iteration according to Logistic formula 5, and mapping the variable p in reverseg，i＝ai+(bi-ai)ziReturning to the original solution space, calculating the fitness value of each feasible solution, and reserving the particle p with the minimum fitness value:
Zn+1＝μzn(1-zn)，n＝0，1，2…(5)
wherein, biIs the maximum value of the input data, aiMu is the minimum value of the input data and is the control parameter.
9. The method for predicting the performance of the high-altitude diesel engine of the optimized extreme learning machine based on the chaotic particle swarm with the extreme disturbance, according to claim 6, is characterized in that the data processing is to perform normalization operation on input and output parameters by adopting a mapminmax function carried by MATLAB.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010570940.XA CN111931413A (en) | 2020-06-22 | 2020-06-22 | Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010570940.XA CN111931413A (en) | 2020-06-22 | 2020-06-22 | Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931413A true CN111931413A (en) | 2020-11-13 |
Family
ID=73316433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010570940.XA Pending CN111931413A (en) | 2020-06-22 | 2020-06-22 | Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931413A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541526A (en) * | 2020-11-25 | 2021-03-23 | 重庆邮电大学 | Electronic nose gas concentration prediction method based on PSO-ABC-ELM |
| CN113076996A (en) * | 2021-03-31 | 2021-07-06 | 南京邮电大学 | Radiation source signal identification method for improved particle swarm extreme learning machine |
| CN113361189A (en) * | 2021-05-12 | 2021-09-07 | 电子科技大学 | Chip performance degradation trend prediction method based on multi-step robust prediction learning machine |
| CN113722980A (en) * | 2021-08-06 | 2021-11-30 | 中国海洋大学 | Ocean wave height prediction method, system, computer equipment, storage medium and terminal |
| CN113935124A (en) * | 2021-09-09 | 2022-01-14 | 西华大学 | Multi-target performance optimization method for biodiesel for diesel engine |
| CN114282636A (en) * | 2021-11-17 | 2022-04-05 | 珠海格力智能装备有限公司 | Robot control model establishing method and robot control method |
| CN114637212A (en) * | 2022-05-17 | 2022-06-17 | 浙江浩普智能科技有限公司 | Oxygen content prediction control method and system |
| CN118070132A (en) * | 2024-04-24 | 2024-05-24 | 沈阳顺义科技股份有限公司 | Fire control system fault diagnosis method based on KPCA-ISSA-SVM |
-
2020
- 2020-06-22 CN CN202010570940.XA patent/CN111931413A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541526A (en) * | 2020-11-25 | 2021-03-23 | 重庆邮电大学 | Electronic nose gas concentration prediction method based on PSO-ABC-ELM |
| CN113076996A (en) * | 2021-03-31 | 2021-07-06 | 南京邮电大学 | Radiation source signal identification method for improved particle swarm extreme learning machine |
| CN113076996B (en) * | 2021-03-31 | 2022-08-23 | 南京邮电大学 | Radiation source signal identification method for improved particle swarm extreme learning machine |
| CN113361189A (en) * | 2021-05-12 | 2021-09-07 | 电子科技大学 | Chip performance degradation trend prediction method based on multi-step robust prediction learning machine |
| CN113361189B (en) * | 2021-05-12 | 2022-04-19 | 电子科技大学 | Chip performance degradation trend prediction method based on multi-step robust prediction learning machine |
| CN113722980A (en) * | 2021-08-06 | 2021-11-30 | 中国海洋大学 | Ocean wave height prediction method, system, computer equipment, storage medium and terminal |
| CN113722980B (en) * | 2021-08-06 | 2024-09-17 | 中国海洋大学 | Ocean wave height prediction method, ocean wave height prediction system, computer equipment, storage medium and terminal |
| CN113935124A (en) * | 2021-09-09 | 2022-01-14 | 西华大学 | Multi-target performance optimization method for biodiesel for diesel engine |
| CN114282636A (en) * | 2021-11-17 | 2022-04-05 | 珠海格力智能装备有限公司 | Robot control model establishing method and robot control method |
| CN114637212A (en) * | 2022-05-17 | 2022-06-17 | 浙江浩普智能科技有限公司 | Oxygen content prediction control method and system |
| CN114637212B (en) * | 2022-05-17 | 2022-08-30 | 浙江浩普智能科技有限公司 | Oxygen content prediction control method and system |
| CN118070132A (en) * | 2024-04-24 | 2024-05-24 | 沈阳顺义科技股份有限公司 | Fire control system fault diagnosis method based on KPCA-ISSA-SVM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111931413A (en) | Method for predicting performance of high-altitude diesel engine of optimized extreme learning machine based on chaotic particle swarm with extreme disturbance | |
| CN111738512B (en) | Short-term power load prediction method based on CNN-IPSO-GRU hybrid model | |
| CN110504676B (en) | Power distribution network state estimation method based on APSO-BP | |
| CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
| CN110020712B (en) | Optimized particle swarm BP network prediction method and system based on clustering | |
| CN104239982A (en) | Method for predicting energy consumption of buildings during holidays and festivals on basis of time series and neural networks | |
| CN113298257A (en) | Method and device for creating a model of a technical system from measurements | |
| CN116542382A (en) | Sewage treatment dissolved oxygen concentration prediction method based on mixed optimization algorithm | |
| CN113656892A (en) | Performance and emission real-time simulation model construction method of marine dual-fuel engine | |
| CN116757057A (en) | Air quality prediction method based on PSO-GA-LSTM model | |
| CN110245390B (en) | Automobile engine oil consumption prediction method based on RS-BP neural network | |
| CN113657651A (en) | Diesel vehicle emission prediction method, medium and equipment based on deep migration learning | |
| CN111832839B (en) | Energy consumption prediction method based on sufficient incremental learning | |
| CN108896330B (en) | Fault diagnosis method for hydroelectric generating sets | |
| CN114934848B (en) | Fuzzy neural network modeling method for optimizing control of combustion performance of diesel engine | |
| CN113111588B (en) | NO of gas turbine X Emission concentration prediction method and device | |
| CN116822742A (en) | Power load prediction method based on dynamic decomposition-reconstruction integrated processing | |
| CN117007970A (en) | Lithium ion battery RUL prediction method based on mixed ISSA-LSTM | |
| CN116796624A (en) | Self-adaptive incremental battery RUL prediction method combining multi-source degradation characteristics | |
| CN116106751A (en) | Lithium ion battery state of charge estimation method based on Informar | |
| CN115796327A (en) | Wind power interval prediction method based on VMD (vertical vector decomposition) and IWOA-F-GRU (empirical mode decomposition) -based models | |
| CN115330091A (en) | Precision rolling process optimization method based on artificial neural network and genetic algorithm | |
| CN117592382B (en) | Dynamic response prediction method, system and medium for railway track bridge system | |
| CN114970719B (en) | Internet of things operation index prediction method based on improved SVR model | |
| CN114841472B (en) | GWO optimization Elman power load prediction method based on DNA hairpin variation |
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 |