CN109086523B - Automatic generation method of power supply design experiment questions based on cognitive computation model - Google Patents
Automatic generation method of power supply design experiment questions based on cognitive computation model Download PDFInfo
- Publication number
- CN109086523B CN109086523B CN201810872683.8A CN201810872683A CN109086523B CN 109086523 B CN109086523 B CN 109086523B CN 201810872683 A CN201810872683 A CN 201810872683A CN 109086523 B CN109086523 B CN 109086523B
- Authority
- CN
- China
- Prior art keywords
- experiment
- electric energy
- computation model
- cognitive
- questions
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Instructional Devices (AREA)
Abstract
The invention discloses a method for automatically generating power supply design experiment questions based on a cognitive computation model, which comprises the following steps: constructing an integral framework of the cognitive computation model; analyzing each experiment in the PMLK-BUCK by taking the power management experiment suite as a research platform, and excavating a mutual constraint relation among the experiments; based on the constraint relation, specific data are obtained by utilizing WEBENCH simulation and are imported into an SPSS tool to construct a cognitive computation model; developing an intelligent system for automatically generating experimental questions; students select the electric energy conversion performance indexes needing to be researched in the intelligent system, and the system can automatically generate design experiment questions around the indexes. The students independently design an experiment platform according to the questions and finish the experiment on the platform, so that the students can completely master theoretical knowledge points and apply the theoretical knowledge points to actual operation in the process from the design experiment to the completion experiment, and then culture the students according to the standard of engineering certification in the true sense.
Description
Technical Field
The invention relates to a method for automatically generating power supply designability experiment questions based on a cognitive computation model.
Background
The Washington association (Washington association) is an international agreement aiming at establishing a standard according to which universities all over the world cultivate contemporary college students, and before the agreement, countries cultivate talents in their own ways, so that engineers in the countries cannot trust, communicate and cooperate with each other. To address this dilemma, the educational organization including the united states calls for the world to grow engineering talents to a uniform standard, from which the washington protocol arose. The protocol is generally recognized internationally due to the fact that a complete engineering education professional certification system is used, and the protocol is authoritative, professional and high in internationalization degree. In 2016, china formally became the member country of the protocol of Washington, meaning that the education level of China has reached the advanced international level and can use the international standard to cultivate talents. Therefore, each college and university in China applies for the protocol and hopes to cultivate engineers according to international standards and improve the cultivation quality of engineering technical talents. Meanwhile, the protocol of Washington is the basis and key for promoting international mutual recognition of Chinese engineering masters and forms, and has important significance for dealing with international competition and moving to the world in the technical field of Chinese engineering.
The function of the literature ' Zhangxian ' experimental teaching in the electrical engineering teaching [ J ]. Experimental technology and management, 2011,28 (08): 297-298+304 ' mentions that the experiment is an effective way for helping electrician students to master professional knowledge. In general, knowledge abstraction in a course is difficult to understand, but an experiment can materialize abstract contents, and students combine practice to deepen understanding of abstract knowledge points, so that related knowledge points are rapidly mastered and practical ability is developed. However, the traditional experiment teaching requires students to go to a laboratory to do the same experiment, and a ready-made experiment platform and an experiment instruction book are available. Students can easily complete the experiment only by performing the steps according to the experiment instruction. However, the effectiveness of the experimental mode is not large, and the true purpose of the experiment cannot be achieved fundamentally. Therefore, an automatic experiment generation system needs to be developed to automatically create design questions for students, and the students independently design an experiment platform according to the questions and complete experiments on the platform. Thus, students have fully mastered the theoretical knowledge points from the design experiment to the completion experiment.
By the end of 1950, joms, when studying language architecture, considered not only syntactic to be autonomous, but also the language itself as an autonomous modular system. However, since human cognition is limited, cognitive linguists consider languages to be not independent of other disciplines, and thus a theory of cognitive models arises. The cognitive process of human beings comes from the perception of the outside world, and as the number of times of contacting the same object increases, the brain begins to store the characteristics of the object, summarize and summarize the object, and finally morphize, conceptualize and classify the object.
The computer cognition model is a model established by simulating the cognition process of human brain to things, and is different from the cognition model in the human brain, the computer cognition model is a mathematical model which is a quadruple (L) 1 ,L 2 L, H), wherein L 1 And L 2 Are all complete lattices, L 1 The element of (A) is called an epitaxial element, L 2 Is called an connotation element, L is L 1 To L 2 H is L 2 To L 1 To (3) is performed. L: l is 1 →L 2 Satisfies the following conditions: l (0L) 1 )＝1L 2 ；L(1L 1 )＝0L 1 ；L(a1∪a2)＝L(a1)∩L(a2)，a1，a2∈L 1 (ii) a The mapping L is called as an extension connotation operator of the cognitive process, and a belongs to L 1 L (a) is a connotation of a. H: l is 2 →L 1 Satisfies the following conditions: h (0L) 2 )＝1L 1 ；H(1L 2 )＝0L 1 ；H(b1∨b2)＝H(b1)∧H(b2)，b1，b2∈L 2 (ii) a The mapping H is called an entailment operator of the cognitive process, and for b epsilon L 2 H (b) is called the extension of b. The two operators L and H satisfy: h × L (a) is not less than a; l × H (b) is more than or equal to b; therefore, in the cognitive model, two operators, L and H, describe the process of change of objects and attributes in cognition.
Disclosure of Invention
In order to solve the technical problem, the invention provides the automatic generation method of the power supply design experiment problem based on the cognitive computation model, which is wide in application range.
The technical scheme for solving the problems is as follows: a power supply design experiment subject automatic generation method based on a cognitive computation model comprises the following steps:
the method comprises the following steps: constructing an integral framework of the cognitive computation model;
step two: analyzing each experiment in the PMLK-BUCK by taking the power management experiment suite as a research platform, and excavating a mutual constraint relation among the experiments;
step three: based on the mutual constraint relation among the experiments, specific data are obtained through WEBENCH simulation;
step four: importing specific data obtained by simulation into an SPSS tool to construct a cognitive computation model;
step five: constructing an intelligent system for generating the experimental questions based on the cognitive computation model;
step six: the intelligent system for generating the experimental questions automatically generates the experimental questions according to the performance indexes of the electric energy conversion field selected by the students.
In the method for automatically generating the power supply design experiment questions based on the cognitive computation model, in the first step, the overall framework of the cognitive computation model comprises three independent layers, wherein the first layer is a problem and a scene, and the first layer comprises various problems in the field of electric energy conversion; the second layer is an information source, and the information source designates the information source; the third layer is a project significant feature, wherein the project significant feature comprises elements and constraint conditions, the elements refer to various electric energy parameters, and the constraint conditions are used for limiting in the automatic generation process of the theme so as to ensure the reliability of the generated experiment.
In the third step, the electric energy data obtained by simulation includes various index values under different electric energy parameters, the electric energy parameters include input voltage, load current, switching frequency, input capacitance, equivalent resistance of the input capacitance, output capacitance, and equivalent resistance of the output capacitance, and the indexes include efficiency, output voltage ripple, inductive current ripple, total loss, crossover frequency, phase margin, and low-frequency gain.
In the third step, the electric energy data obtained through simulation is imported into a tool SPSS to obtain a pearson correlation coefficient between each electric energy parameter and each index, wherein the larger the numerical value of the pearson correlation coefficient is, the stronger the correlation between the electric energy parameter and the index is.
The method for automatically generating the power supply design experiment questions based on the cognitive computation model comprises the following specific steps: the students select and research a certain index in the field of electric energy transformation on an input interface of an intelligent system for generating experimental questions by combining with actual teaching conditions; the intelligent experiment subject generation system inquires the association degree of the selected index and the electric energy parameters according to the cognitive calculation model, screens the electric energy parameters with the association degree larger than a threshold value, and randomly selects one of the screened electric energy parameters for generating a designed experiment subject.
The invention has the beneficial effects that: the method comprises the steps of firstly establishing a cognitive computation model, then developing an experiment subject generation intelligent system according to the cognitive computation model, enabling the experiment subject generation intelligent system to screen out electric energy parameters with large degree of relevance with indexes selected by each student, then randomly selecting one of the screened electric energy parameters to automatically generate the experiment subject, and enabling the student to independently design an experiment platform and finish the experiment on the platform according to the subject, so that the student must completely master relevant theoretical knowledge points and apply the theoretical knowledge points to actual design in the process from the design of the experiment to the completion of the experiment, and further culture the student according to the standard of engineering certification in the true sense.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a framework diagram of the cognitive computation model of the present invention.
FIG. 3 is a flowchart of the intelligent system for generating experimental questions.
FIG. 4 is an operation diagram of an input interface of the intelligent system for generating experimental subjects according to the present invention.
FIG. 5 is a schematic diagram of an output result of an intelligent system for generating experimental subjects according to the present invention.
FIG. 6 is a circuit diagram of an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the figures and examples.
As shown in fig. 1, a method for automatically generating a power supply design experimental topic based on a cognitive computation model includes the following steps:
the method comprises the following steps: and constructing an integral framework of the cognitive computation model.
The overall framework of the cognitive computation model comprises three independent layers, wherein the first layer is a problem and a scene, and comprises various indexes in the field of electric energy conversion; the second layer is an information source, the information source specifies the information source, the information source can be specific to a specific problem or can be a general problem, and therefore, the method is suitable for various types of problems; the third layer is a project salient feature, wherein the project salient feature comprises elements and constraint conditions, the elements refer to various electric energy parameters, and the constraint relation is used for limiting in the automatic generation process of the theme so as to ensure the reliability of the generated experiment.
Step two: and analyzing each experiment in the PMLK-BUCK by taking the power management experiment suite as a research platform, and excavating the mutual constraint relation among the experiments.
The method takes TI-PMLK (Power management experiment suite) as a research platform, and PMLK is a development platform designed by TI company inviting Stanford university and used for power electronic experiment teaching, and mainly serves university plans of TI company inviting Stanford university. The PMLK kit comprises three experimental boards, namely a BUCK circuit experimental board, a BOOST circuit experimental board and an LDO circuit experimental board. Each panel includes 6 proof experiments through which students can learn some basic concepts from the power supply such as ripple, efficiency and transient response. The kit can be used for students in the relevant professions of common electricity to know the basic knowledge of the power supply, and can also be used for teaching of professional courses such as switching power supply design. Each test plate is provided with an experimental instruction book, wherein the experimental principle, the steps, the result analysis and the like are described in detail. The experiment generation system developed by the subject can automatically generate innovative experiment subjects by utilizing the cognitive computation model on the basis of the original experiment. The educator requires students to complete innovative experiments, so that the students can deeply know the power supply from theory to practice. And then the students are cultivated according to the standard of engineering certification in the true sense.
In the third layer of the cognitive computation model, an experiment generation setting rule needs to be given, and the purpose is to ensure that the generated experiment is effective and reliable. According to the characteristic points of the complex engineering problem, namely, the association between the sub-problems and the conflict between the multiple factors, the rule is the so-called constraint relation. The PMLK is a typical complex engineering problem, each experiment in the PMLK-BUCK is fully analyzed, the mutual constraint relation among the experiments is excavated, a constraint relation table is summarized, and a cognitive rule is provided for a cognitive calculation model. The constraint relationship is shown in table 1, wherein 11 is the constraint relationship between experiment 1 and experiment 1, 12 is the constraint relationship between experiment 1 and experiment 2, 8230, and so on, 66 is the constraint relationship between experiment 6 and experiment 6.
TABLE 1
21, an input capacitor Cin and an output capacitor Cout have power loss; so Cin, cout has an effect on efficiency and ripple also has an effect on efficiency.
Load current, the change in switching frequency has an effect on the input current ripple, which is proportional to the load current and inversely proportional to the switching frequency.
The switching frequency is detrimental to the power components, so setting the switching frequency has an effect on efficiency.
13: the input voltage has an effect on the load transient response.
41: inductor core material and winding both having power loss P L ,W＝ESRLI 2 α PP ,C＝K 1 f x (K 2 Δi PP ) y This has an effect on efficiency.
14: the input voltage and the load current have influence on the inductive current ripple, and different magnetic core materials have different effect on the inductive current ripple under constant load current.
15: the magnitude of the input voltage, load current, has an effect on the current limiting function.
51: the current limiting function determines the maximum current that the buck regulator can provide and thus determines the minimum value of efficiency.
61: experiment 1 has no binding to experiment 6.
16: the input voltage influences the switching frequency to a large extent, and tolerances and uncertainties of the output capacitance ESR may result in the value of the switching frequency differing from the intended value.
32: setting the switching frequency has an effect on the inductor current ripple.
23: both the switching frequency and the output voltage have an effect on the load transient response.
42, under the constant load current, different magnetic core materials have different ripple effects on the output voltage. The same magnetic core material outputs the voltage embossing to the voltage stabilizer at different saturation degrees.
The input voltage and output voltage, the switching frequency and the load current can make the inductor LThe ripple of the internal current is different from the expected triangular waveform and therefore also affects the output capacitance C out The ripple of (3).
And 52, as the load current increases, the inductor tends to be in a deep saturation state, and the ripple of the inductor current increases. If the output capacitance value is not changed, the output voltage ripple is caused to increase.
25 input voltage V in The switching frequency fs and the inductance L may affect the average load current, the inductance current peak-to-peak value and thus the current limiting behavior. A larger output capacitance produces a lower output voltage ripple and may increase the current limit level. The sensitivity of its current limit to the output capacitance magnitude depends on the voltage loop gain crossover frequency.
62: experiment 6 has no constraint relation to experiment 2.
26: the equivalent resistance ESR of the output capacitor has an effect on the transient response of the hysteretic regulator.
43: the saturation of the inductance has an effect on the crossover frequency and also on the load transient response.
34: experiment 3 has no constraints on experiment 4.
53: core saturation of different types of inductances can have an effect on load transient response.
35: the switching frequency and the output capacitance affect the current limit of the buck regulator according to the type of the inductor. A higher switching frequency should increase the current limit level because the magnitude of the inductor current ripple will be smaller and then the control voltage level will be smaller for a given load current. A larger output capacitance results in a lower output voltage ripple, which may increase the current limit level.
36: the output capacitance characteristics have an influence on the output voltage direct current precision, the output voltage ripple, the switching frequency, the input voltage and the load current of the hysteresis voltage-reducing regulator.
63: the output capacitance has an effect on the load transient response.
And 54, the saturation degree of the inductor magnetic core has influence on the inductance equivalent value and the inductance power ripple.
Depending on the type of core material, the inductance may saturate at high currents as the current increases, whereas inductances of different core types decrease to different degrees when saturated, and thus the type of inductance affects the current limiting behavior.
The input and output voltage, switching frequency and load current may cause the ripple of the current in the inductor L to vary from the desired triangular waveform, affecting the output voltage ripple.
46 experiment 4 has no binding to experiment 6.
56 experiment 5 has no binding to experiment 6.
Experiment 6 has no binding to experiment 5.
Step three: and (4) obtaining electric energy data through simulation, and constructing a cognitive computation model by using a tool SPSS based on the electric energy data and the constraint relation obtained in the first step.
The electric energy data obtained by simulation comprises various index values under the condition of different electric energy parameters, wherein the electric energy parameters comprise input voltage, load current, switching frequency, input current, equivalent resistance of an input capacitor, an output capacitor and equivalent resistance of an output capacitor, and the indexes comprise efficiency, output voltage ripple, inductive current ripple, total loss, crossing frequency, phase margin and low-frequency gain.
The constraint relation between each experiment in the PMLK is only a macroscopic representation method, the constraint relation needs to be converted into a data form and serves an information source of a second layer of a cognitive computation model framework, the data of the information source in the second layer provides contents for automatic generation of topics, and the data in the current information source is obtained by WEBENCH simulation. The data in the information source is shown in table 2.
TABLE 2
And (4) sending the electric energy data obtained by simulation and the constraint relation obtained in the first step into SPSS software to obtain the Pearson correlation coefficient of each electric energy parameter and each index, as shown in table 3.
TABLE 3
The numbers in the table 3 are Pearson correlation coefficients, the Pearson correlation coefficients form a cognitive calculation model, the larger the numerical value of the Pearson correlation coefficients is, the stronger the correlation between the electric energy parameters and the indexes is, and the cognitive calculation model can provide theoretical basis for automatically generating experimental subjects for an intelligent experimental generation system in the next chapter.
Step four: and constructing an experiment subject generation intelligent system based on the cognitive computation model.
The intelligent system is designed for automatically generating experimental subjects and automatically generating projects. The method is a process for generating projects through a model by using a computer technology, and the process can be divided into three steps: 1. the item is identified with a cognitive computing model to generate content. 2. Structured content of the project is automatically generated. 3. The project is generated using a computer algorithm.
3.1 identifying topic Generation content with cognitive computing models
The cognitive computing model is used to generate test items. The cognitive computing model of automatic project generation highlights the knowledge, skill and power required to solve problems in a particular domain.
To identify content in a cognitive computing model, an intelligent system needs to describe the knowledge, content, and reasoning skills needed to create a problem-solving task. Knowledge and skills specified in the cognitive computing model are identified through an induction process by requiring the intelligent system to find a parent, then identify and describe information that can be used to create a new project, the parent being a high quality topic, and derive powerful topic analysis results from existing operational tests.
3.2 automatically generating structured content for an item
In this step, a project model is developed to specify where the content in the cognitive computing model is placed before new topics can be generated. A project model is a template that can perform specified operations on properties in newly generated items.
3.3 generating topics Using computer algorithms
Computer-based algorithms place specified cognitive computational model content into the developed project model, subject to specified constraints. Content assembly is performed using computer algorithms because it is a complex, constrained logic programming task, especially when large problems containing many information sources of different characteristics are specified in cognitive computing models. The cognitive computing model can be used as a general experimental topic generation system to execute the content assembly task. The experimental automatic generation system is a java-based program that assembles innovative topics using term models of all combinations of elements specified in the cognitive computing model.
Step five: the intelligent system for generating the experimental questions automatically generates the experimental questions according to indexes of the electric energy conversion field selected by students. The method comprises the following specific steps: the students select and research a certain index in the field of electric energy transformation on an input interface of an intelligent system for generating experimental questions by combining with actual teaching conditions; the intelligent experimental subject generation system queries the association degree of the selected index and the electric energy parameters according to the cognitive computation model, screens the electric energy parameters with the association degree larger than a threshold value, and randomly selects one of the screened electric energy parameters to generate a new experimental subject, wherein a specific flow chart is shown in fig. 3. For example, if a student wants to study the efficiency of a switching power supply, the student only needs to select the performance index of "efficiency" on the input interface, as shown in fig. 4. The system obtains the load current based on the cognitive calculation model query, outputs the equivalent resistance of the capacitor, and has the largest influence on the efficiency by the three factors of the switching frequency. At the moment, a random function in the system randomly selects one factor to generate the subject, and ensures that the subjects obtained by students are inconsistent, thereby avoiding the phenomenon of mutual plagiarism. The random generation of topics is shown in FIG. 5.
In order to verify the correctness of an experimental system, the article takes a theme generated by the system, namely 'analysis and optimization design of influence of load current on efficiency', a circuit is designed according to the theme, the generated theme is proved to be effective and reliable by performing simulation and physical test on the designed circuit, the TPS54160 is taken as a core controller, and the schematic diagram design of a peripheral circuit is shown in fig. 6. Wherein the MOSFETs are already integrated inside the TPS 54160.
Calculating theoretical efficiency: each element in the designed circuit has own power loss, and the specific calculation formula is as follows:
1) MOSFET conduction loss:
2) MOSFET switching losses:
P MOS,SW ＝V in I out f s t sw (2)
3) MOSFET gate drive loss:
P MOS,g ＝Q g V dr f s (3)
current induction:
IC current induced losses:
a diode D1:
conduction loss:
P diode with a high-voltage source ＝V f D'I out (5)
Inductance L1:
1) Winding loss:
2) Magnetic core loss:
capacitance loss:
1) Input capacitance C 1 Loss:
P Cin ＝ESRC in I 2 out D'D (8)
2) Output capacitor C 11 Loss:
and others:
IC biasing:
P IC ＝V in I μ (10)
defining:
t ON is the MOSFET on-time; f. of s ＝1/T s Is the switching frequency; d is the MOSFET duty cycle:
t ON /T s ＝V out /V in (11)
D'＝1-D (12)
R ds is MOSFET on-resistance; q g Is MOSFET gate charge; t is s Is the MOSFET switching period; t is a unit of ON Is the on-time of the MOSFET; t is sw Is the switching time of the MOSFET; f. of s Is the MOSFET switching frequency; v out Is the output voltage; I.C. A out To output a current; alpha (alpha) ("alpha") pp Is the inductance ripple factor; v f Is a diode forward voltage drop; l is an inductance value; Δ i pp Is an inductive current ripple; ESR (equivalent series resistance) L Is an inductance equivalent series resistance; ESRC in An input capacitor is equivalent to a series resistor; ESRC out An equivalent series resistance of the output capacitor; i is μ Is the controller quiescent current; v dr Is the MOSFET gate driver voltage; k 1 、K 2 X and y are constants, and the values are determined by the magnetic core material and size, the switching frequency and the temperature.
Inductance current ripple:
Δi pp ＝V out D'/(fs·L) (13)
inductance ripple factor:
α pp ＝1+(Δi pp /I out ) 2 /12 (14)
4.2 data results analysis
The efficiency data obtained by theoretical calculation, simulation and experiment are shown in table 4;
TABLE 4
Theoretical loss P Loss of power ＝P MOSP +P MOS，SW +P MOS，g +P SNS +P Diode with a high-voltage source +P L，W +P L，C +P Cin +P Cout +P IC Theoretical efficiency η theo ＝(V out I out -P Loss of power )/V in I in And the experimental efficiency is as follows: eta exp ＝V out I out /V in I in The simulation efficiency is directly given by the simulation tool.
Comparing theoretical efficiency eta at the same output current theo Efficiency of simulation eta sim And experimental efficiency η exp The data of the three parts shows that the theoretical efficiency and the simulation efficiency are almost the same, the theoretical efficiency and the simulation efficiency are the same in principle, but errors exist in simulation, and compared with the simulation, the experimental efficiency is lower than the simulation by about two percent, because the actual efficiency is calculated roughly, namely eta is exp ＝P out /P in . The PCB wiring impedance is ignored, the power loss exists in the equivalent impedance of the passive device, and the like, and the data analysis of the table 4 shows that the circuit designed based on the automatically generated questions is effective, so that the questions automatically generated based on the cognitive calculation model can be shown to be correct and effective.
Claims (5)
1. A method for automatically generating power supply design experiment questions based on a cognitive computation model comprises the following steps:
the method comprises the following steps: constructing an integral framework of the cognitive computation model;
step two: analyzing each experiment in the PMLK-BUCK by taking a power management experiment suite as a research platform, and excavating a mutual constraint relation among the experiments;
step three: based on the mutual constraint relationship among the experiments, specific data are obtained through WEBENCH simulation;
step four: importing the specific data obtained by simulation into an SPSS tool to construct a cognitive computation model;
step five: developing an experimental subject based on a cognitive computation model to generate an intelligent system;
step six: the intelligent system for generating the experimental questions automatically generates the experimental questions according to the performance indexes of the electric energy conversion field selected by the students.
2. The method for automatically generating the power supply designability experiment questions based on the cognitive computation model as claimed in claim 1, wherein in the first step, the overall framework of the cognitive computation model comprises three independent layers, wherein the first layer is a problem and a scene, and comprises various problems in the field of electric energy conversion; the second layer is an information source, and the information source designates the information source; the third layer is a project significant feature, wherein the project significant feature comprises elements and constraint conditions, the elements refer to various electric energy parameters, and the constraint conditions are used for limiting in the automatic generation process of the theme so as to ensure the reliability of the generated experiment.
3. The method according to claim 1, wherein in the third step, the electric energy data obtained by simulation includes index values under different electric energy parameters, the electric energy parameters include input voltage, load current, switching frequency, input capacitance, equivalent resistance of the input capacitance, output capacitance, and equivalent resistance of the output capacitance, and the indexes include efficiency, output voltage ripple, inductive current ripple, total loss, crossover frequency, phase margin, and low-frequency gain.
4. The method for automatically generating power supply design experimental questions based on the cognitive computation model as recited in claim 3, wherein in the fourth step, the simulated power data are introduced into a tool SPSS to obtain a pearson correlation coefficient between each power parameter and each index, and a larger value of the pearson correlation coefficient indicates a stronger correlation between the power parameter and the index.
5. The method for automatically generating power supply design experimental questions based on the cognitive computation model as claimed in claim 4, wherein the specific steps of the sixth step are as follows: combining with the actual teaching condition, the students select and research a certain index in the electric energy conversion field on the input interface of the intelligent system for generating experimental questions; the intelligent experiment subject generation system inquires the association degree of the selected index and the electric energy parameters according to the cognitive calculation model, screens the electric energy parameters with the association degree larger than a threshold value, and randomly selects one of the screened electric energy parameters for generating a designed experiment subject.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810872683.8A CN109086523B (en) | 2018-08-02 | 2018-08-02 | Automatic generation method of power supply design experiment questions based on cognitive computation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810872683.8A CN109086523B (en) | 2018-08-02 | 2018-08-02 | Automatic generation method of power supply design experiment questions based on cognitive computation model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109086523A CN109086523A (en) | 2018-12-25 |
| CN109086523B true CN109086523B (en) | 2022-11-11 |
Family
ID=64833755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810872683.8A Active CN109086523B (en) | 2018-08-02 | 2018-08-02 | Automatic generation method of power supply design experiment questions based on cognitive computation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086523B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674315B (en) * | 2019-09-27 | 2022-09-27 | 湘潭大学 | Auxiliary power supply debugging method based on knowledge graph technology |
| CN111477048A (en) * | 2020-05-16 | 2020-07-31 | 安徽商贸职业技术学院 | Online experiment teaching platform and teaching method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101615265A (en) * | 2009-08-11 | 2009-12-30 | 路军 | A kind of intelligent decision simulating experimental system based on multi-Agent technology |
| WO2015027079A1 (en) * | 2013-08-21 | 2015-02-26 | Quantum Applied Science And Research, Inc. | System and method for improving student learning by monitoring student cognitive state |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
-
2018
- 2018-08-02 CN CN201810872683.8A patent/CN109086523B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101615265A (en) * | 2009-08-11 | 2009-12-30 | 路军 | A kind of intelligent decision simulating experimental system based on multi-Agent technology |
| WO2015027079A1 (en) * | 2013-08-21 | 2015-02-26 | Quantum Applied Science And Research, Inc. | System and method for improving student learning by monitoring student cognitive state |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109086523A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ibrahim | Engineering simulation with MATLAB: improving teaching and learning effectiveness | |
| Grasso et al. | SapWin 4.0–a new simulation program for electrical engineering education using symbolic analysis | |
| Asadi et al. | Dynamics and control of DC-DC converters | |
| Yalcin et al. | A web‐based virtual power electronics laboratory | |
| Hassell et al. | Using Matlab's Simscape modeling environment as a simulation tool in power electronics and electrical machines courses | |
| CN109086523B (en) | Automatic generation method of power supply design experiment questions based on cognitive computation model | |
| Abramovitz | Teaching behavioral modeling and simulation techniques for power electronics courses | |
| Abramovitz | An approach to average modeling and simulation of switch-mode systems | |
| Fontana et al. | A new simulation program for analog circuits using symbolic analysis techniques | |
| Tan et al. | A comprehensive modeling, simulation and computational implementation of buck converter using MATLAB/Simulink | |
| Mustofokulov et al. | METHODS FOR DESIGNING ELECTRONIC DEVICE CIRCUITS IN THE» PROTEUS” PROGRAM | |
| Veerachary | Signal flow graph modelling of multi-state boost DC–DC converters | |
| Mladenović | Contemporary electronics with LTSpice and mathematica | |
| Dujic et al. | Teaching power electronics: How to achieve the desired learning outcomes? | |
| Altintas | A GUI-based education toolbox for power electronics converters using MATLAB/Simulink and SimPowerSystems | |
| Stanisavljevic et al. | A module for automatic assessment and verification of students' work in digital logic design | |
| Yamin et al. | A new developed educational approach to improve conventional teaching methodology of the power electronics laboratory | |
| Farhan et al. | High order and a-stable envelope following method for transient simulations of oscillatory circuits | |
| Patil et al. | An open-source simulation package for power electronics education | |
| Li et al. | Design verification and testing of power supply system by using virtual prototype | |
| Moharil et al. | CSIT: An Open Source and interactive GUI based tool for learning and analyzing Control Systems | |
| Huselstein et al. | Interactive simulations of power electronics converters | |
| Miaja et al. | A switching power supply design tool for educational purposes in power electronics | |
| Rihar et al. | Enhancing the student experience in pre‐and mid‐COVID‐19 pandemic period by upgrading the power electronics laboratory practice curriculum | |
| Iqbal et al. | Pspice in undergraduate and graduate electrical engineering courses |
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 |