Electronic technology AI simulation experiment device based on real object and experiment method thereof

Abstract

The invention belongs to an electronic technology experiment system, and particularly relates to an electronic technology AI simulation experiment device and method based on a real object, and the device comprises an experiment board, an element storage box, an all-in-one machine, and a camera. The element storage box contains elements; the experiment board comprises a plurality of bread boards, and elements are installed on the bread boards to form an experiment circuit. The camera is used for shooting an area of the experiment table; an AI physical simulation experiment system is arranged in the all-in-one machine, and student identity recognition, circuit action sequence recognition establishment, element positioning and circuit connection recognition are achieved through a camera. The system can achieve the functions of precise student management, unmanned intelligent experiment guidance, power-free circuit simulation, experimental process data acquisition, assessment, physical component management and the like.

Description

Technical Field

[0001] The patent of this invention belongs to an electronic technology experimental system, and in particular relates to an electronic technology AI simulation experimental device based on a physical object and its experimental method. Background Art

[0002] Physical electronic technology experimental devices are widely used in electronic technology teaching, but their limitations and shortcomings are also very significant, mainly reflected in high costs, complex operation, difficult maintenance, and limited learning effects. First, the purchase and use costs of physical electronic technology experimental devices are high. The frequent use and wear of components in experiments leads to high maintenance and replacement costs. For schools and laboratories with limited funds, fully equipping physical experimental devices may be subject to budget constraints. Second, electronic technology experiments require students to have solid theoretical knowledge and practical operation skills. During the circuit connection, measurement, and debugging process, the slightest negligence may lead to experimental failure or damage components.

[0003] To reduce experimental costs, many schools have introduced virtual simulation experiments in electronic technology experiments. However, despite their many advantages, virtual simulation experiments also have certain disadvantages and limitations. Virtual simulation experiments lack the experience and contact with real physical phenomena, resulting in a less direct perception of experimental results than physical experiments. Secondly, virtual simulation experiments are insufficient in cultivating students' practical skills. Electronic technology is a highly hands-on subject, requiring students to master skills such as component characteristics, circuit connection techniques, and the use of instrumentation through repeated practice. Virtual simulation experiments lack comprehensive multi-sensory engagement and contextual experience. Therefore, in teaching practice, how to combine the advantages of virtual simulation and physical experiments and achieve optimal teaching results through their complementary effects, using simulation to enhance understanding of experimental phenomena while cultivating students' practical skills and engineering thinking through physical experiments, is a major topic in current experimental teaching. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems existing in the prior art and to propose an electronic technology AI simulation experiment device and an experimental method based on a physical object.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An electronic technology AI simulation experiment device based on physical objects, including an experiment board placed on a laboratory table, a component storage box, an all-in-one machine, and a camera;

[0007] Component storage box, including components;

[0008] Experimental board, which contains multiple breadboards, components are inserted into the breadboard to form experimental circuits;

[0009] A camera, used to capture the area of the lab table;

[0010] The all-in-one machine has a built-in AI physical simulation experiment system. The AI physical simulation experiment system includes a student management module, an experiment selection module, a physical component management module, an experiment circuit construction module, an experiment simulation unit module, an intelligent experiment guidance module, and an experiment process assessment module. It uses a camera to realize student identity recognition, circuit construction action sequence recognition and establishment, component positioning, and circuit connection recognition.

[0011] As a further preferred solution, the components include capacitors, resistors, diodes, transistors, integrated circuits, power supplies, connecting wires and various test terminals.

[0012] As a further preferred solution, the component storage box includes multiple inner compartments for placing different types of components, the interior of the inner compartments is white, and the outer circle of the inner compartments has partitions, which are black; each inner compartment is provided with a label for identification, and the label is used to display component information; one group of diagonals of the component storage box is respectively provided with a first infrared emitting tube and a first infrared receiving tube, and the other group of diagonals is respectively provided with a second infrared emitting tube and a second infrared receiving tube, as well as an indicator light. When the hand that takes the component blocks the infrared signal, the indicator light emits a light signal until the next time the component is taken.

[0013] As a further preferred solution, the experimental board contains multiple breadboards, which are easy to distinguish according to their uses and functions.

[0014] As a further preferred solution, the student management module uses cameras to identify students and manage the experimental content, experimental time, and experimental process assessment results;

[0015] The experiment selection module selects the experimental project, such as the experiment type, difficulty, goal, standard experimental circuit for verification, standard circuit electrical connection network table, standard simulation results, and standard circuit construction optimization action sequence;

[0016] The physical component management module manages the components in the component storage box and the component positioning set on the experimental board;

[0017] The experimental circuit construction module builds the physical circuit, realizes the management of the experimental circuit electrical connection network table and circuit construction action sequence; the module generates the circuit construction action sequence based on the hand movement determined by the component video tracking; and generates the experimental circuit electrical connection network table based on the position of the component on the experimental board;

[0018] The experimental simulation unit module converts the experimental circuit electrical connection network table into a simulation circuit and generates data such as specified test points and power supply current. It can also convert the generated experimental circuit electrical connection network table into the circuit electrical connection network table format of other circuit simulation software to obtain more authoritative simulation results by calling related circuit simulation software.

[0019] The intelligent experiment guidance module explains experimental principles, selects experimental components, and provides animated visual guidance for circuit connections. It uses standard experimental circuits to explain experimental principles and dynamically demonstrates the impact of changing component parameters on test point signals using the mouse. Based on the experimenter's actions in the experimental guidance, the module calculates the experimenter's experimental mastery and recommends relevant learning materials.

[0020] The experimental process assessment module calculates the assessment results and outputs the error set based on the circuit construction action sequence, the experimental circuit electrical connection network table, the alarm data and the circuit simulation data.

[0021] An experimental method for an electronic technology AI simulation experimental device based on a physical object includes the following steps:

[0022] Step 1: When the experimenter removes a component from the inner compartment of the component storage box, the camera uses the MLP-EMA attention mechanism algorithm based on YOLOv11 to track the removed component. The component parameters are determined based on the information collected from the component storage box and the current quantity management of the component storage box is updated; remove the component operation (Remove):

[0023]

[0024] Where: Remove(C target ) is to remove component C target Operation;

[0025] S' is the removed component C target The collection after

[0026] S is the removed component C target The previous collection;

[0027] GridMap(C target ) is the inner grid coordinate X where the calculation is located v , Y v ;

[0028] ifC target ∈S,GridMap(C target )=(X v ,Y v ), indicating component Ctarget Belongs to set S and is located in the inner compartment of the component storage box;

[0029] Update the current number of component storage boxes (Count'):

[0030] Count'(Type(C target ))=Count(Type(C target ))-1

[0031] Where: Count(Type(C target )) is C target The number of type components;

[0032] Step 2: After the component is removed, the video continues to track it until it leaves the experimenter's hand. If the component is placed on a breadboard, the Adaptive Weighted Rotated Detection (AWRD) and Adaptive Feature Enhancement (AFE) algorithms are used to accurately describe and detect the tilted object and record its position on the breadboard.

[0033] Experimental board adds C new Component and pin connection operation (Add):

[0034]

[0035]

[0036] Where: Indicates C new The pre-connection relationship between the pin and the network (NetID);

[0037] NetID is the collection of all electrical nets in the circuit (such as VCC, GND, Q1-2, DATA, etc.);

[0038] B is the component set on the experimental board;

[0039] B' adds C to the experimental board new The collection of components after the component;

[0040] Connections is the set of electrical connections of the circuit;

[0041] Connections add C to the circuit new The collection of electrical connections behind the component;

[0042] Step 3: If the component storage box is correctly placed, the number of component storage boxes will be updated; if it is placed in other locations, the system will alarm, prompting the experimenter to correct it and record the statistics;

[0043] Put the component back into component C i Storage box operation (Insert):

[0044]

[0045] Where: Insert(C i ,(x,y)) means C i Put the components back into the storage box;

[0046] S is the return element C i The previous collection;

[0047] S' is the element C that is put back i The collection after

[0048] GridMap is a collection of grid components in the component storage box;

[0049] GridMap∪{(x,y)→Ci} adds Ci to the GridMap collection;

[0050] Step 4: After the experimental circuit test is completed, when the circuit is disassembled, the AWRD algorithm is used to identify and track the disassembled components until they are placed back into the correct component storage box. If they are placed incorrectly, an alarm will be issued to prompt the experimenter to correct them and record the statistics. The physical component management module can accurately manage the number of components to prevent the loss of small components.

[0051] Beneficial Effects: The present invention enables precise student management, unmanned intelligent experiment guidance, power-free circuit simulation, experimental process data collection and assessment, and physical component management. Without actually connecting to a power source, signal source, or using related instruments, the device can identify the correctness of experimental circuit construction and simulate the voltage and current waveforms at each test point in the experimental circuit; establish an experimental error set; and after the experiment, the physical components are returned to the inner box for management, achieving precise physical component management and reducing component loss. The device enables full experimental process management and assessment, and has great application value and practical significance for the establishment of unmanned, open primary verification laboratories. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a schematic diagram of a simulation experimental device of the present invention;

[0053] Figure 2 A schematic diagram of an experimental board containing multiple breadboards;

[0054] Figure 3 Build a diagram for the actual experimental circuit;

[0055] Figure 4 This is a schematic diagram of the component storage box;

[0056] Figure 5 This is the circuit principle block diagram of the AI physical simulation experiment system;

[0057] Figure 6 This is a schematic diagram of the AI physical simulation experiment software system architecture;

[0058] Figure 7 A non-polar resistor element, wherein (a) is a side view of the non-polar resistor element, and (b) is a top view of the non-polar resistor element;

[0059] Figure 8 is a polarized capacitor element, wherein (a) is a side view of the polarized capacitor element, and (b) is a top view of the polarized capacitor element;

[0060] Figure 9 is a non-polar capacitor element, wherein (a) is a side view of the non-polar capacitor element, and (b) is a top view of the non-polar capacitor element;

[0061] Figure 10 is a diode element, wherein (a) is a side view of the diode element, and (b) is a top view of the diode element;

[0062] Figure 11 is a triode element, wherein (a) is a side view of the triode element, and (b) is a top view of the triode element;

[0063] Figure 12 is an integrated circuit element, wherein (a) is a side view of the integrated circuit, and (b) is a top view of the integrated circuit;

[0064] Figure 13 are terminal elements, where (a) is the positive pole of the power supply, (b) is the negative pole of the power supply, (c) is the signal source, and (d) is the test terminal;

[0065] Figure 14 It is a jumper component. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0067] The present invention is an electronic technology AI simulation experiment device based on a physical object, such as Figure 1 As shown, the experiment provides an experimental board 1-2 and a component storage box 1-3, which are placed on the experimental table 1-1. At the back of the experimental table 1-1, there is an all-in-one computer 1-4 with a display and a camera 1-5. The actual circuit is built on multiple breadboards 3, as shown in the figure. Figure 2Each physical component is mounted on the base of the PCB board, and polar components or ordered pins are marked to facilitate image recognition, such as Figure 3 All components are classified according to their parameters and placed in known component storage boxes 1-3, as shown in the figure below. Figure 4 shown.

[0068] The experimental board is the carrier of the physical circuit and is composed of multiple breadboards. Figure 2 As shown, the top rows S1 and S2 have their jacks connected internally; the bottom rows S3 and S4 have their jacks connected internally; the middle rows 1 through 60 have jacks, with the A, B, C, D, and E jacks in each row connected internally, and the F, G, H, I, and J jacks connected internally. The jacks are used to connect physical components.

[0069] Physical components such as Figure 7-14 As shown, the components required for the experiment are mounted on the PCB base for easy insertion and removal on the breadboard 3. The components required for the experiment include a non-polar resistor 2-1, a polar capacitor 2-2, a non-polar capacitor 2-3, a diode 2-4, a transistor 2-5, an integrated circuit 2-6, a terminal 2-7, and a jumper 2-8.

[0070] Figure 7 It is a non-polarity resistance element 2-1; Figure 8 The polarized capacitor element 2-2 has a positive electrode on one side and a negative electrode on the other side. Figure 9 It is a non-polar capacitor element 2-3; Figure 10 For diode element 2-4, the side with black mark is cathode and the other side is anode; Figure 11 For transistor components 2-5, the side with the black mark is pin 1, and the remaining pins are 2 and 3 respectively; Figure 12 For integrated circuit components 2-6, the left side with a black mark is pin 1, and the remaining pins are 2, 3, 4, etc. in counterclockwise order; Figure 13 Terminal elements 2-7 are divided into the positive power supply, negative power supply, signal source and test terminal as shown in the figure. Different black marks are printed on the top of them for image recognition to distinguish the positive power supply, negative power supply, signal source and test terminal; Figure 14 These are jumper components 2-8, used for circuit connection.

[0071] Take the construction of a triode single-stage amplifier physical experimental circuit as an example, Figure 3The circuit consists of an input signal source signal source1 (equivalent to the signal source in terminal element 2-7), an input coupling capacitor C1 (equivalent to the polarized capacitor element 2-2), a base pull-up bias resistor R1 (equivalent to the non-polarized resistor element 2-1), a base pull-down bias resistor R2 (equivalent to the non-polarized resistor element 2-1), a transistor Q1 (equivalent to transistor element 2-5), an emitter bias resistor R3 (equivalent to the non-polarized resistor element 2-1), an emitter bias resistor bypass capacitor C3 (equivalent to the polarized capacitor element 2-2), a collector bias resistor R4 (equivalent to the non-polarized resistor element 2-1), an output coupling capacitor C2 (equivalent to the polarized capacitor element 2-2), a signal test terminal signaltesting1 (equivalent to the test terminal in terminal element 2-7), a positive power supply VCC (equivalent to the positive power supply in terminal element 2-7), a negative power supply GND (equivalent to the negative power supply in terminal element 2-7), several wires (equivalent to jumper element 2-8), and a breadboard 3. Generate the circuit electrical connection network table file based on the physical experimental circuit image recognition:

[0072]

[0073] The components needed for the experiment are placed in the component storage box, such as Figure 4 As shown. 4-1 is the black partition of the storage box; 4-2 is the inner compartment of the storage box for storing physical components, with the interior color of the inner compartment being white to facilitate image recognition and segmentation; 4-3 is the inner compartment label, which displays the parameters of the component in the storage compartment. One set of diagonal pairs of component storage box 1-3 is respectively equipped with a first infrared emitting tube 4-6 and a first infrared receiving tube 4-4, while the other set of diagonal pairs is respectively equipped with a second infrared emitting tube 5-8 and a second infrared receiving tube 4-5, as well as an indicator light 4-7. The first infrared emitting tube 4-6 and the second infrared emitting tube 5-8 are controlled by the component storage box processing unit MCU to rapidly alternately transmit, covering the inner compartment of the component storage box. When a component is stored, the infrared signal of the inner compartment where the component is located is blocked. When detected by the MCU, the corresponding LED indicator is controlled to light up, and the LED indicators of the other inner compartments are turned off.

[0074] The component storage box is mainly used to determine the source of components, determine component parameters based on the source, and manage component usage statistics; it uses photoelectric sensors to sense the storage grid of the taken components, manage the entry and exit of components, and determine component parameters.

[0075] AI physical simulation experiment system circuit principle block diagram, such as Figure 5As shown in the figure, the component storage box processing unit manages components and identifies components for circuit construction. The AI physical simulation experiment system processing unit uses a camera to identify students, establish circuit construction action sequences, locate components, and identify circuit connections. Physical components are used to build experimental circuits, and image sequences are used to identify circuit connections. A network table of circuit electrical connections is generated, which is then imported into the circuit simulation module to test circuit test point parameters. The camera captures the circuit construction process and generates a circuit construction action sequence set, which is used by the experimental process assessment module to calculate the experimental score and explain experimental principles, select experimental components, and provide visual guidance for circuit connections.

[0076] Schematic diagram of the software architecture of the AI physical simulation experiment system. The AI physical simulation experiment system includes a student management module, an experiment selection module, a physical component management module, an experiment circuit construction module, an experiment simulation unit module, an intelligent experiment guidance module, and an experiment process assessment module. Figure 6 shown.

[0077] 1. The student management module uses cameras to identify students and manages experimental content, experimental time, and experimental process assessment results. The specific information is as follows:

[0078] Function: Identify students' identities through cameras and manage student information (such as student number, name, class, authority, experiment content, experiment time, experiment process assessment results, experiment progress, historical results, etc.).

[0079] Data interaction:

[0080] Provided to: experiment selection module (student permissions / progress), experiment process assessment module (recording results).

[0081] Received from: Experimental process assessment module (final score, experiment completion status).

[0082] 2. The experiment selection module manages the standard experimental circuits, standard circuit electrical connection network tables, standard simulation results, and standard circuit construction optimization action sequences for verification. The specific information is as follows:

[0083] Function: Students select experimental projects (such as experimental type, difficulty, objectives, standard experimental circuit for verification, standard circuit electrical connection network table, standard simulation results, and standard circuit construction optimization action sequence).

[0084] Data interaction:

[0085] Provided to: physical component management module (list of components required for the experiment), experimental circuit construction module (experimental template), intelligent experiment guidance module (experimental standard process).

[0086] Received from: Student Management Module (Optional Experiment on Student Authority Restriction).

[0087] 3. The physical component management module manages the components in the component storage box and the component positioning set on the experimental board. The specific information is as follows:

[0088] Function: Manage the physical component inventory (such as type, parameters, quantity, status) of the component inner box and the component positioning on the experimental board (the coordinates of the component on the experimental board).

[0089] Data interaction:

[0090] Provided to: experimental circuit construction module (component availability, parameters), experimental process assessment module (component usage record).

[0091] Received from: Experimental circuit construction module (component coordinate status updated on the experimental board).

[0092] The logic is implemented as follows:

[0093] (1) Formal description of component storage box

[0094] Definition: A component storage box is a container system with classification and positioning functions.

[0095] ① The component set is C={c1,c2,...,c n}, where each element c i The properties include:

[0096] ID(c i ): unique identifier;

[0097] Type(c i ): Type (such as resistor, capacitor, IC, etc.);

[0098] Position(c i ): coordinates or slot numbers in the storage box;

[0099] ·.

[0100] ②Storage box structure:

[0101] StorageBox=<S,GridMap,Capacity>

[0102] · A collection of components stored in a storage box;

[0103] GridMap:S→Z 2 : Mapping function, assigning components to two-dimensional grid coordinates;

[0104] ·Capacity=(TotalCapacity,Num)

[0105] TotalCapacity∈N + : Maximum number of components in the storage box

[0106] Count:Z 2 →N + : The current number of components in the storage box grid.

[0107] Example:

[0108] S={c1,c2,c3}

[0109] GridMap(c1),=(1,2)

[0110] Type(c1)=Resistor(10kΩ)

[0111] Capacity(c1)=(10,8).

[0112] (2) Formal description of the experimental board

[0113] Definition: A breadboard is a structured, planar system with electrical connections.

[0114] ① Let the set of installed components be B = {b1, b2, ..., bm}, and each component b j The properties include:

[0115] ID(b j ): unique identifier;

[0116] Type(b j ):type;

[0117] Position(b j ): Physical coordinates (or row and column numbers) on the board;

[0118] ·Pins(b j) :Pin collection {p j1 ,p j2 ,...,p jk}.

[0119] ②Experimental board structure

[0120] Board<B,Connections,Num>

[0121] The electrical connection relationship between pins.

[0122] ③Coordinates and connection rules

[0123] Coordinate system: Position(b j )=(x j ,y j )∈R 2 (discrete grid);

[0124] ·Connection constraint: If (p jk ,p lm )∈Connections, the two pins must meet the topological or electrical rules (co-line, co-network).

[0125] Example:

[0126] B={b1,b2},

[0127] Position(b1)=(10,5),

[0128] Type(b1)=Microcontroller(ATmega328),

[0129] Connections={(p 11 ,p 23 ),(p 12 ,p 24 )}.

[0130] (3) Operation process

[0131] ① When the experimenter takes out components from the component storage box, the camera uses the MLP-EMA attention mechanism algorithm based on YOLOv11 to track the removed components, and determines the component parameters and updates the current quantity management of the component storage box based on the information collected from the component storage box.

[0132] Removing components:

[0133]

[0134] Update the current quantity of component storage boxes:

[0135] Count'(Type(C target ))=Count(Type(C target ))-1.

[0136] ② After the component is removed, the video will continue to track the component until it leaves the experimenter's hand. If the component is placed on the experimental board, the Adaptive Weighted Rotated Detection (AWRD) and Adaptive Feature Enhancement (AFE) algorithms are used to accurately describe and detect the state of the tilted object and record its position on the experimental board.

[0137] Experimental board adds C new Component and pin connection operations:

[0138]

[0139] ③ If the component storage box is put back correctly, the number of component storage boxes will be updated; if it is placed in other locations, the system will alarm, prompting the experimenter to correct it and record the statistics.

[0140] Put the component back into component C i Storage box operation

[0141]

[0142] ④ After the experimental circuit test is completed, when the circuit is disassembled, the AWRD algorithm is used to identify and track the removed components until they are returned to the correct component storage box. If they are placed incorrectly, an alarm will be issued, prompting the experimenter to correct the problem and recording the statistics. The physical component management module can accurately manage the component quantity and prevent the loss of small components.

[0143] Fourth, the experimental circuit construction module implements real-time experimental circuit electrical connection network table and circuit construction action sequence management. The module generates the circuit construction action sequence based on the hand movements determined by component video tracking; and generates the experimental circuit electrical connection network table based on the position of the components on the experimental board. The specific information is as follows:

[0144] Function: Real-time recognition of students building physical circuits, enabling real-time management of the experimental circuit's electrical connection network table and circuit construction action sequence. The module generates the circuit construction action sequence based on hand movements determined by component video tracking; it also generates the experimental circuit's electrical connection network table based on the component's position on the experiment board, and uses the standard circuit electrical connection network table to assess circuit correctness.

[0145] Data interaction:

[0146] Provided to: experimental simulation unit module (circuit electrical connection network table), intelligent experiment guidance module (operation step record), experimental process assessment module (process assessment).

[0147] Received from: physical component management module (component parameters), experiment selection module (standard circuit electrical connection network table).

[0148] Automatically generate circuit electrical connection network name operation:

[0149]

[0150] 5. The experimental simulation unit converts the experimental circuit electrical connection network table into a simulation circuit, generating data such as specified test points and power supply current. Based on the generated experimental circuit electrical connection network table, the simulation circuit generates data such as specified test points and power supply current. The generated experimental circuit electrical connection network table can also be converted into the circuit electrical connection network table format of other circuit simulation software. By calling the relevant circuit simulation software, more authoritative simulation results can be obtained. The specific information is as follows:

[0151] Function: Convert the electrical connection network table of the experimental circuit into a simulation circuit, and generate the simulation circuit operation results (such as voltage, current, and waveform) of the specified test points; according to the generated electrical connection network table of the experimental circuit, convert it into a simulation circuit, generate data such as the specified test points and power supply current, and you can also convert the generated electrical connection network table of the experimental circuit into the circuit electrical connection network table format of other circuit simulation software, and get more authoritative simulation results by calling related circuit simulation software.

[0152] Data interaction:

[0153] Provided to: intelligent experiment guidance module (simulation abnormality feedback), experiment process assessment module (simulation result scoring).

[0154] Received from: Experimental circuit construction module (circuit electrical connection network table).

[0155] 6. The Intelligent Experiment Guidance Module provides animated visualization of experimental principles, experimental component selection, and circuit connection. This module uses standard experimental circuits to explain experimental principles and dynamically demonstrates the impact of changing component parameters on test point signals using the mouse. Based on the experimenter's actions in the experimental guidance, the module calculates the experimenter's experimental mastery and recommends relevant learning materials. Specific information is as follows:

[0156] Function: Real-time guidance and error prompts (such as step suggestions, error warnings).

[0157] Data interaction:

[0158] Provided to: students (operation suggestions), experimental process assessment module (record of prompt times).

[0159] Received from: Experiment selection module (standard process), Experiment simulation unit module (simulation exception), Experiment circuit construction module (operation steps).

[0160] 7. The experimental process assessment module calculates the assessment results and outputs the error set based on the circuit action sequence, the experimental circuit electrical connection network table, the alarm data and the circuit simulation data. The specific information is as follows:

[0161] Function: Record experimental process data and score (such as time, number of errors, and matching degree of simulation results).

[0162] Data interaction:

[0163] Provided to: student management module (final score, operation error set), intelligent experiment guidance module (grading rules).

[0164] Received from: All modules (data from all stages of the experiment).

[0165] The specific operation process of the present invention is:

[0166] 1. Students log in by face recognition;

[0167] 2. Students select experiments from the open experiment set;

[0168] 3. Build the experimental circuit according to the required experimental instructions;

[0169] 4. Take the component from the component storage box and determine the component parameters according to the component storage grid;

[0170] 5. Insert the components into the experimental board. According to the coordinates of the experimental board jacks, establish the component parameter and component positioning data set on the experimental board. At the same time, establish the circuit construction action sequence set. If the experimental circuit construction is not completed, go to 4. If it is completed, go to 6.

[0171] 6. After the experimental circuit is built, generate the circuit electrical connection network table based on the component parameters and component positioning data set on the experimental board;

[0172] 7. The circuit electrical connection network table is imported into the circuit simulation module to output the voltage and current waveforms of the test points;

[0173] 8. Conduct process assessment based on the circuit electrical connection network table, circuit action sequence set, and circuit simulation data, and add errors to the experimental error set;

[0174] 9. After the experiment is over, put the components on the experimental board back into the component storage box. According to the component parameters and the component positioning data set on the experimental board, the physical components are managed to return them to their original positions.

[0175] 10. During the experiment, you can enter the intelligent experiment guidance module for learning at any time.

[0176] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An electronic technology AI simulation experiment device based on physical objects, characterized by: It includes an experimental board (1-2) placed on an experimental table (1-1), a component storage box (1-3), an all-in-one machine (1-4), and a camera (1-5); Component storage box (1-3), containing components; An experimental board (1-2) includes a plurality of breadboards (3), and components are inserted into the breadboards (3) to form an experimental circuit; Camera (1-5), used to photograph the area of the laboratory table (1-1); The all-in-one machine (1-4) has a built-in AI physical simulation experiment system, which includes a student management module, an experiment selection module, a physical component management module, an experiment circuit construction module, an experiment simulation unit module, an intelligent experiment guidance module, and an experiment process assessment module; and realizes student identity recognition, circuit construction action sequence recognition and establishment, component positioning, and circuit connection recognition through cameras (1-5).

2. The electronic technology AI simulation experiment device based on physical objects according to claim 1 is characterized by: The components include capacitors, resistors, diodes, transistors, integrated circuits, power supplies, connecting wires and various test terminals.

3. The electronic technology AI simulation experiment device based on physical objects according to claim 1 is characterized by: The component storage box (1-3) comprises a plurality of inner compartments (4-2) for placing a plurality of types of components, wherein the inner compartments (4-2) are white in color, and the outer ring of the inner compartments (4-2) has a partition (4-1), and the partition (4-1) is black; each inner compartment (4-2) is provided with a label (4-3) for identification, and the label (4-3) is used to display component information; a first infrared emitting tube (4-6) and a first infrared receiving tube (4-4) are provided at one group of diagonal corners of the component storage box (1-3), and a second infrared emitting tube (5-8) and a second infrared receiving tube (4-5) are provided at another group of diagonal corners, as well as an indicator light (4-7); when the hand taking the component blocks the infrared signal, the indicator light (4-7) emits a light-on signal until the next component is taken.

4. The electronic technology AI simulation experiment device based on physical objects according to claim 1 is characterized by: The experimental board (1-2) includes multiple breadboards.

5. The electronic technology AI simulation experiment device based on physical objects according to claim 1 is characterized in that: The student management module manages student information by identifying students through a camera; experimental projects can be selected in the experiment selection module; the physical component management module is used to manage the physical component inventory in the component box and the component positioning set on the experimental board; the experimental circuit construction module recognizes students in real time when building physical circuits, generates an experimental circuit electrical connection network table based on the position of the components on the experimental board, and judges the correctness of the circuit; the experimental simulation unit module converts the experimental circuit electrical connection network table into a simulation circuit, and generates the simulation circuit operation results of the specified test point; the intelligent experiment guidance module provides real-time guidance and error prompts; the experimental process assessment module records the experimental process data and scores.

6. The experimental method of the electronic technology AI simulation experimental device based on a physical object according to claim 5, characterized in that: The following steps are involved: Step 1: When the experimenter takes out a component from the inner compartment of the component storage box, the camera uses the MLP-EMA attention mechanism algorithm based on YOLOv11 to track the removed component. The component parameters are determined based on the information collected from the component storage box and the current quantity management of the component storage box is updated; Remove component operation (Remove): Where: Remove(C target ) is to remove component C target Operation; S' is the removed component C target The collection after S is the removed component C target The previous collection; GridMap(C target ) is the inner grid coordinate X where the calculation is located v , Y v ; ifC target ∈S,GridMap(C target )=(X v ,Y v ), indicating component C target Belong to set S and are located in the inner grid of the component storage box (Count'); Update the current quantity of component storage boxes: Count’(Type(C target ))=Count(Type(C target ))-1 Where: Count(Type(C target )) is C target The number of type components; Step 2: After the component is removed, the video continues to track it until it leaves the experimenter's hand. If the component is placed on the experiment board, the adaptive weighted rotated object detection and adaptive feature enhancement module algorithms are used to accurately describe and detect the tilted object and record its position on the experiment board. Experimental board adds C new Component and pin connection operation (Add): Where: Indicates C new The pre-connection relationship between the pins and the network; NetID is the set of all electrical networks in the circuit; B is the component set on the experimental board; B' adds C to the experimental board new The collection of components after the component; Connections is the set of electrical connections of the circuit; Connections add C to the circuit new The collection of electrical connections behind the component; Step 3: If the component storage box is correctly placed, the number of component storage boxes will be updated; if it is placed in other locations, the system will alarm, prompting the experimenter to correct it and record the statistics; Put the component back into component C i Storage box operation (Insert): Where: Insert(C i ,(x,y)) means C i Put the components back into the storage box; S is the return element C i The previous collection; S' is the element C that is put back i The collection after GridMap is a collection of grid components in the component storage box; GridMap∪{(x,y)→Ci} adds Ci to the GridMap collection; Step 4: After the experimental circuit test is completed, when the circuit is disassembled, the Adaptive Weighted Rotated Detection algorithm is used to identify and track the disassembled components until they are placed back into the correct component storage box. If they are placed incorrectly, an alarm will be issued to prompt the experimenter to correct the problem and record the statistics. The physical component management module can accurately manage the number of components and prevent the loss of small components.

Images