CN209765332U - Two-dimensional stability evaluation test bed - Google Patents
Two-dimensional stability evaluation test bed Download PDFInfo
- Publication number
- CN209765332U CN209765332U CN201920346460.8U CN201920346460U CN209765332U CN 209765332 U CN209765332 U CN 209765332U CN 201920346460 U CN201920346460 U CN 201920346460U CN 209765332 U CN209765332 U CN 209765332U
- Authority
- CN
- China
- Prior art keywords
- steering engine
- acrylic
- double
- shaped
- steering wheel
- 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.)
- Expired - Fee Related
Links
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The utility model discloses a two-dimensional stability evaluation test bed, including the ya keli chassis, be fixed with the ya keli support on the ya keli chassis, STM32 singlechip, DC-DC step-down module and lithium cell, the yakeli support top is fixed with the camera, be fixed with first U-shaped steering wheel support in the middle of the yakeli chassis, first U-shaped steering wheel support is connected with first double-shaft steering wheel side below, first double-shaft steering wheel side top is connected with second U-shaped steering wheel support, be fixed with third U-shaped steering wheel support on the second U-shaped steering wheel support in an orthogonal manner, third U-shaped steering wheel support is connected with second double-shaft steering wheel side below, second double-shaft steering wheel side top is connected with fourth U-shaped steering wheel support, be fixed with the loading board on the fourth U-shaped steering wheel support, the rubber pad has been laid on the loading board; the utility model discloses built the algorithm stability evaluation test platform of two degrees of freedom, control is simple, stability is good, low cost, and the range of application is wide.
Description
Technical Field
The utility model belongs to the technical field of mechanical engineering and automation thereof, a two dimensional stability aassessment test platform is related to.
Background
The concept of a cloud control system is provided by the Xianyuan Qingzhang university of Beijing rationality, the cloud computing technology, the networking control theory and the concept of Internet of things are fused, and the increasing requirement of modern society on the control of highly complex intelligent systems is met; the traditional control system has limited computing capacity and low intelligence degree, and is difficult to meet the requirements of modern society on intelligent manufacturing; the cloud control system utilizes the cloud end to realize a large amount of complex calculation processes of local control, fully utilizes the strong data processing and calculation capabilities of the cloud end, and combines a networked control theory to realize the control of the cloud end to the local. In the whole process, data are collected locally through a sensor and transmitted to a cloud end through the internet, the cloud end concentrates the dominant resources to perform data processing and calculation, the calculation result is transmitted to a local execution mechanism through the internet, and the execution mechanism controls a local object according to the calculation result. At present, the cloud control theory is in the process of continuous development and improvement and is widely applied.
The theory of reinforcement learning is born at the end of the last century and is a process of strategy learning. In the basic assumption of reinforcement learning, the process that an agent selects a behavior at the moment according to the current state st is called a strategy; the current state and the current behavior can determine the state at the next moment, and the process is called state transition and is a Markov process; after the agent finishes executing the behavior at each moment, the agent can obtain the reward rt from the environment, and in addition, the agent can observe the state of the agent at each moment; the goal of agent selection behavior is to maximize the expectation of future rewards, and therefore it is necessary to learn the optimal strategy by trial and error, constantly updating its own strategy. The deep reinforcement learning combines the deep learning with the reinforcement learning, greatly enhances the capability and effect of the reinforcement learning to process decision problems, and achieves outstanding effects in a plurality of fields such as games and games, robot control, industrial intelligence, artificial intelligence, smart power grids, medical services, financial management and the like. At present, the deep reinforcement learning theory is continuously developed and perfected, and the main research directions are as follows: optimization of a strategy network, optimization of a cost function, research of a continuous control strategy, research of a discrete control strategy, layered reinforcement learning and the like.
However, the deep reinforcement learning theory for the prediction control is still less researched, and in general, the strategy network can only calculate the control quantity at the next moment according to the current state, and if the control quantity in a future period of time is to be calculated, the environment needs to be modeled, so that the problem is converted into the model prediction control problem, and the advantages and the characteristics of the reinforcement learning theory cannot be well combined.
In the cloud control system, the problems of time delay and packet loss occur in the data transmission process, and if local real-time control is to be realized, the ideas of predictive control and networked control need to be applied; the deep reinforcement learning algorithm for prediction is applied to the cloud control system, the calculation efficiency, stability and convergence of the algorithm are improved, and a solution is provided for the problems of time delay and packet loss in the cloud control system.
after the model is established and the algorithm is compiled, a debugging platform is required to be carried to carry out experimental verification on the algorithm so as to determine the reliability of the algorithm; the single degree of freedom test bed technology of the verification algorithm is mature, and the main structure comprises a connecting rod, a turntable and a stepping motor; one end of a connecting rod is hinged with the rack, the other end of the connecting rod is hinged with one end of a second vertically-arranged connecting rod, the other end of the connecting rod is hinged with a disc, and the center of the disc is fixedly connected with a stepping motor; the connecting rod is provided with a groove, and a ball body is placed on the groove; after the system is powered on, the stepping motor rotates to drive the disc to rotate, the disc drives the connecting rod to generate angular displacement, a ball on the connecting rod generates large displacement along the tangential direction, and after image acquisition and calculation iteration, the connecting rod finally generates periodic micro motion near a certain angle, the ball almost keeps static, the whole system tends to be stable, and therefore the effectiveness of the algorithm is verified; but the structure can only be used for the verification of a one-dimensional stability system and cannot be used as a test platform of a higher-order algorithm.
Evaluating a carried deep learning algorithm by evaluating the motion stability of a sphere, wherein the evaluation is specifically embodied in that the sphere for testing is placed on two rotational freedom planes, and the sphere generates displacement along the tangential direction of the planes along with the planes when the sphere moves on the planes; with continuous iteration of image collection and control sequence calculation, the movement of the sphere tends to be static finally, and the system reaches a stable state. Therefore, a two-dimensional stability evaluation test bed is designed, a stable test platform can be provided for related algorithms, and the method has long-term significance for algorithm development.
disclosure of Invention
The utility model provides a two-dimensional stability aassessment test bench has solved prior art and can not carry out the problem verified to the high order algorithm, the utility model discloses a high order algorithm provides stable aassessment platform, further verifies the reliability of high order algorithm, and the simple structure, the running cost of aassessment test bench are cheap, can be used for the stability aassessment of multiple algorithm.
The utility model adopts the technical scheme that the two-dimensional stability evaluation test bed comprises an acrylic chassis, an acrylic bracket, an STM32 single chip microcomputer, a DC-DC voltage reduction module and a lithium battery are fixed on the acrylic chassis, a camera is fixed at the top of the acrylic bracket, an acrylic baffle with a through hole is arranged around the lithium battery, and the acrylic baffle is connected with the acrylic chassis through L-shaped angle iron;
A first U-shaped steering engine support is fixed in the middle of the acrylic chassis, a concave area of the first U-shaped steering engine support is opened upwards, the inner side of the concave area of the first U-shaped steering engine support is connected with a fixing hole below the side of a first double-shaft steering engine, a metal steering wheel disc above the side of the first double-shaft steering engine is connected with the inner side of the concave area of a second U-shaped steering engine support, a third U-shaped steering engine support is orthogonally fixed on the second U-shaped steering engine support, the inner side of the concave area of the third U-shaped steering engine support is connected with a fixing hole below the side of the second double-shaft steering engine, the metal steering wheel disc above the side of the second double-shaft steering engine is connected with the inner side of the concave area of a fourth U-shaped steering engine support, a round bearing plate is fixed on the fourth U-shaped steering engine support, upward flanges are arranged around the bearing;
The output end of the lithium battery is connected with the input end of the DC-DC voltage reduction module, the output end of the DC-DC voltage reduction module is respectively connected with power lines of the first double-shaft steering engine and the second double-shaft steering engine, signal lines of the first double-shaft steering engine and the second double-shaft steering engine are respectively connected with an IO (input/output) interface of the STM32 single chip microcomputer, the power line of the STM32 single chip microcomputer is electrically connected with a computer host, the power output end of the STM32 single chip microcomputer is electrically connected with the camera, and the camera.
furthermore, the acrylic support is cuboid, the side face of the acrylic support is surrounded by 4 acrylic plates, the acrylic plates are connected through L-shaped angle iron, and the top face of the acrylic support is provided with the acrylic plate with a through hole.
The utility model has the advantages that: 1. the utility model builds a test bed with two degrees of freedom on the basis of the existing single-degree-of-freedom test bed, and can be used as a test platform for stability test of high-order algorithms; 2. the utility model discloses a steering wheel is as the driver, and control is simple and stability is strong for simple structure, the low cost of test bench, and the function is perfect, and application range is wide.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of the present invention.
Fig. 2 is a flow chart of the present invention.
In the figure, 1 camera, 2 acrylic bracket, 3 acrylic chassis, 4 STM32 singlechip, 5 DC-DC voltage reduction module, 6 lithium battery, 7 bearing plate, 8 rubber pad, 9 first U-shaped steering engine bracket, 10 second U-shaped steering engine bracket, 11 third U-shaped steering engine bracket, 12 fourth U-shaped steering engine bracket, 13 first double-shaft steering engine, 14 second double-shaft steering engine.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.
referring to the attached figure 1, the two-dimensional stability evaluation test bed comprises a rectangular acrylic chassis 3 with round corners at the periphery, the acrylic chassis 3, and an acrylic bracket 2, an STM32 single chip microcomputer 4, a DC-DC voltage reduction module 5 and a lithium battery 6 are respectively fixed on four corners of the acrylic chassis 3; the acrylic bracket 2 is cuboid, the side surface of the acrylic bracket 2 is surrounded by 4 acrylic plates, L-shaped angle iron is matched and fixed with the acrylic plates through bolts and nuts, the top surface of the acrylic bracket 2 is the acrylic plate with through holes, a camera 1 is fixed on the acrylic plate with the through holes, and the bottom of the acrylic bracket 2 is fixed with an acrylic chassis through the angle iron; the voltage of the lithium battery 6 is 7.4V, an acrylic baffle plate with a through hole is arranged around the lithium battery 6, the acrylic baffle plate is connected with the acrylic chassis through L-shaped angle iron, and the L-shaped angle iron is fixed with the acrylic baffle plate and the acrylic chassis 3 through bolts and nuts; a first U-shaped steering engine support 9 is fixed in the middle of the acrylic chassis 3, the inner side of a concave area of the first U-shaped steering engine support 9 is connected with a fixing hole below the side of a first double-shaft steering engine 13, a metal steering wheel above the side of the first double-shaft steering engine 13 is connected with the inner side of a concave area of a second U-shaped steering engine support 10, a third U-shaped steering engine support 11 is orthogonally fixed on the upper surface of the second U-shaped steering engine support 10, the inner side of the concave area of the third U-shaped steering engine support 11 is connected with a fixing hole below the side of a second double-shaft steering engine 14, the metal steering wheel above the side of the second double-shaft steering engine 14 is connected with the inner side of a concave area of a fourth U-shaped steering engine support 12, a circular bearing plate 7 is fixed on the upper surface of the fourth U-shaped steering engine support 12, upward flanges are arranged around the bearing plate 7, a rubber pad 8 is laid on the bearing plate 7, the.
The output end of a lithium battery 6 of the two-dimensional stability evaluation test bed is connected with the input end of a DC-DC voltage reduction module 5, the output end of the DC-DC voltage reduction module 5 is respectively connected with power lines of a first double-shaft steering engine 13 and a second double-shaft steering engine 14, and signal lines of the first double-shaft steering engine 13 and the second double-shaft steering engine 14 are respectively connected with an IO (input/output) interface of an STM32 single-chip microcomputer 4; the power input end of STM32 singlechip 4 is connected with the computer mainframe electricity, and the 5V power output end and the camera 1 electricity of STM32 singlechip 4 are connected, and camera 1 is connected with the computer mainframe electricity.
Referring to the attached drawing 2, when the stability of the high-order algorithm is evaluated by using the present invention, firstly, the ball for testing is placed on the bearing plate 7, the algorithm to be tested is burned on the STM32 single chip microcomputer 4, the present invention is powered on, so that the ball for testing moves on the bearing plate 7 according to the content of the algorithm to be tested, the camera 1 collects the motion state of the ball for testing and sends the motion state to the CPU cloud of the computer, the computer calculates the optimal control sequence through the high-order algorithm to be tested and sends the optimal control sequence to the STM32 single chip microcomputer 4, the STM32 single chip microcomputer 4 controls the first dual-axis steering engine 13 and the second dual-axis steering engine 14, the displacement conversion is performed according to the control sequence calculated in real time, the first dual-axis steering engine 13 and the second dual-axis steering engine 14 drive the bearing plate 7 to perform the corresponding displacement conversion, which causes the displacement of the, and transmitting the data to a computer host for storage as the input of the next round of control sequence calculation; after a certain number of iterations of high-order algorithm operation, if the first dual-axis steering engine 13 and the second dual-axis steering engine 14 move periodically in a small amplitude and the movement state of the ball body for testing tends to be stable, the reliability of the algorithm to be evaluated can be verified, otherwise, the algorithm needs to be adjusted and improved until the stability is achieved; the utility model discloses use first double axle steering wheel 13 and the double axle steering wheel 14 drive loading board 7 of second for control process is simple, and stability is strong, and test bench overall structure simple structure, with low costs can be used for multiple high order algorithm aassessment, and application range is wide.
It is to be noted that, in the present invention, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (2)
1. The two-dimensional stability evaluation test bed is characterized by comprising an acrylic chassis (3), wherein an acrylic support (2), an STM32 single chip microcomputer (4), a DC-DC voltage reduction module (5) and a lithium battery (6) are fixed on the acrylic chassis (3), a camera (1) is fixed at the top of the acrylic support (2), an acrylic baffle with through holes is arranged around the lithium battery (6), and the acrylic baffle is connected with the acrylic chassis (3) through L-shaped angle iron;
A first U-shaped steering engine bracket (9) is fixed in the middle of the acrylic chassis (3), a concave area of the first U-shaped steering engine bracket (9) is opened upwards, a fixing hole below the side of a first double-shaft steering engine (13) is connected with the inner side of the concave area of the first U-shaped steering engine bracket (9), a metal steering wheel above the side of the first double-shaft steering engine (13) is connected with the inner side of the concave area of a second U-shaped steering engine bracket (10), a third U-shaped steering engine bracket (11) is orthogonally fixed on the second U-shaped steering engine bracket (10), the inner side of the concave area of the third U-shaped steering engine bracket (11) is connected with the fixing hole below the side of a second double-shaft steering engine (14), the metal steering wheel above the side of the second double-shaft steering engine (14) is connected with the inner side of the concave area of a fourth U-shaped steering engine bracket (12), a round bearing plate (7) is fixed on the fourth U-shaped steering engine bracket (12, a rubber pad (8) is laid on the bearing plate (7), and the position of the camera (1) is higher than that of the bearing plate (7);
The output end of the lithium battery (6) is connected with the input end of the DC-DC voltage reduction module (5), the output end of the DC-DC voltage reduction module (5) is connected with power lines of a first double-shaft steering engine (13) and a second double-shaft steering engine (14) respectively, signal lines of the first double-shaft steering engine (13) and the second double-shaft steering engine (14) are connected with an IO interface of an STM32 single chip microcomputer (4) respectively, the power line of the STM32 single chip microcomputer (4) is electrically connected with a computer host, the power output end of the STM32 single chip microcomputer (4) is electrically connected with the camera (1), and the camera (1) is electrically connected with the computer host.
2. The two-dimensional stability evaluation test bed according to claim 1, wherein the acrylic bracket (2) is rectangular, the side surfaces of the acrylic bracket (2) are surrounded by 4 acrylic plates, the acrylic plates are connected through L-shaped angle iron, and the top surface of the acrylic bracket (2) is an acrylic plate with through holes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920346460.8U CN209765332U (en) | 2019-03-19 | 2019-03-19 | Two-dimensional stability evaluation test bed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920346460.8U CN209765332U (en) | 2019-03-19 | 2019-03-19 | Two-dimensional stability evaluation test bed |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN209765332U true CN209765332U (en) | 2019-12-10 |
Family
ID=68755213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920346460.8U Expired - Fee Related CN209765332U (en) | 2019-03-19 | 2019-03-19 | Two-dimensional stability evaluation test bed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN209765332U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379279A (en) * | 2021-06-23 | 2021-09-10 | 黑龙江大学 | Deep reinforcement learning short-term voltage stability evaluation method based on incomplete data |
-
2019
- 2019-03-19 CN CN201920346460.8U patent/CN209765332U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379279A (en) * | 2021-06-23 | 2021-09-10 | 黑龙江大学 | Deep reinforcement learning short-term voltage stability evaluation method based on incomplete data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Semeraro et al. | Digital twin application in energy storage: Trends and challenges | |
| Flores-Hernández et al. | Mechatronic design and implementation of a two axes sun tracking photovoltaic system driven by a robotic sensor | |
| Wei et al. | Staying-alive path planning with energy optimization for mobile robots | |
| Jiang et al. | Optimal design of 6-DOF vibration isolation platform based on transfer matrix method for multibody systems | |
| CN209765332U (en) | Two-dimensional stability evaluation test bed | |
| CN109977468B (en) | Verification system, method, equipment and control system of energy management strategy | |
| CN105790266A (en) | Microgrid parallel multi-target robust optimization scheduling integrated control method | |
| CN103729483A (en) | Device and method for simulating and predicting mountain torrent disasters | |
| CN115314343B (en) | Source-charge-storage resource aggregation control gateway device and load and output prediction method | |
| Cragg et al. | Application of mobile agents to robust teleoperation of internet robots in nuclear decommissioning | |
| Lü et al. | Energy economy optimization and comprehensive performance improvement for PEMFC/LIB hybrid system based on hierarchical optimization | |
| CN101025625A (en) | DSP based embedded intelligent controller | |
| Tang et al. | Optimum design for a new reconfigurable two-wheeled self-balancing robot based on virtual equivalent parallel mechanism | |
| CN110262218A (en) | Control method, device, equipment and the storage medium of machine fish | |
| Wan et al. | Dynamic performance optimization of a novel 8-SPU parallel walking mechanism | |
| CN115099522A (en) | Active and reactive carbon emission prediction method for special transformer user based on BP neural network | |
| Xiao et al. | SOC Estimation of Vanadium Redox Flow Batteries Based on the ISCSO-ELM Algorithm | |
| CN106972538A (en) | A kind of micro-capacitance sensor equivalent modeling method of feature based mode | |
| Araújo et al. | Control with adaptive Q-learning | |
| Tang et al. | Energy Management Strategy Based on Model Predictive Control‐Differential Evolution for Hybrid Energy Storage System in Electric Vehicles | |
| CN118399460B (en) | Management method, device, equipment and storage medium of distributed energy storage system | |
| CN115609581B (en) | Mobile robot control and edge calculation method and robot controller | |
| Hu et al. | IEEE access special section editorial: Battery energy storage and management systems | |
| CN113671958B (en) | Determination method and system of obstacle avoidance path of robot, electronic equipment and medium | |
| CN113675889B (en) | Multi-terminal direct-current micro-grid hydrogen production control method based on energy storage regulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191210 Termination date: 20200319 |