High-density high-power programmable direct-current electronic load
By using neural network models to predict states and control instructions in programmable DC electronic load devices, the problems of equipment operation complexity and difficulty in parameter adjustment are solved, and the stable operation and high density of the equipment under various load changes are achieved.
Patent Information
- Application Number
- CN202510040047.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-09
- Publication Date
- 2025-04-15
AI Technical Summary
Existing programmable DC electronic load devices require users to manually set parameters, resulting in increased operational complexity and it is difficult for users to accurately adjust equipment parameters, affecting their usage prospects.
The neural network model is used to predict the operating status of the load control terminal, generate corresponding control instructions, provide parameter adjustment suggestions for the load control terminal in advance, optimize the equipment effect, and design the equipment as portable to be suitable for a variety of scenarios.
Through the prediction of neural network model and the generation of control instructions, the stable operation of load control terminals when facing various load changes is optimized, and the high density and usage prospects of the equipment are improved.
Smart Images
Figure CN119827811A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of programmable direct current electronic loads, in particular to a high-density and high-power programmable direct current electronic load. Background Art
[0002] Programmable DC electronic load The principle of programmable DC electronic load is to control the conduction amount (duty cycle) of the internal power MOSFET or transistor. It is a device that consumes electrical energy by the dissipated power of the power tube. It can accurately detect the load voltage and accurately adjust the load current. At the same time, it can simulate load short circuit. The simulated load is inductive resistance and capacitance, and the capacitive load current rise time. High-density and high-power programmable DC electronic load is a test equipment specially designed to simulate actual load conditions and test the performance of electronic products. It has the characteristics of high density, high power and programmability. It tests and verifies the performance of electronic products by precisely controlling the output voltage and current. It is widely used in application scenarios with high requirements for voltage, current and power accuracy.
[0003] However, in the prior art, programmable DC electronic load devices usually require users to manually set various parameters, which may increase the complexity of operation. In particular, in some cases, users may need to understand more complex circuit principles to correctly set up the device, which makes it difficult for users to accurately adjust device parameters, affecting the use prospects of existing programmable DC electronic load devices. Therefore, the existing needs are not met, and we propose a high-density, high-power programmable DC electronic load. Summary of the invention
[0004] The purpose of the present invention is to provide a high-density, high-power programmable DC electronic load, and to predict the operating state of the load control terminal through a neural network model, so as to obtain the prediction result of the operating state; based on the prediction result, a corresponding control instruction is generated, so as to provide parameter adjustment suggestions for the load control terminal in advance, so as to better optimize and improve the effect of the load control terminal, so that the load control terminal can maintain stable operation when facing various load changes; secondly, by setting the load control terminal to be easy to carry, the appearance is small and exquisite, so that it can be suitable for various scenarios, thereby improving the high density and use prospects of the load control terminal, and solving the problems raised in the above-mentioned background technology.
[0005] To achieve the above object, the present invention provides the following technical solutions: High-density, high-power programmable DC electronic loads, including: The load control terminal is a portable programmable DC electronic load device used to apply different load conditions to simulate the actual working environment and evaluate the output capacity and stability of the power supply or battery under different loads; A data collection unit is used to collect historical status information of the load control terminal, the historical status information includes: load voltage, current and temperature parameters; and to clean and pre-process the collected historical status information to obtain a new data set; A model building unit, used to train and test a data set using a neural network model to obtain a neural network model capable of predicting the operating state of a load control terminal; The data acquisition unit is used to collect the real-time status information of the load control terminal, including load voltage, current and temperature parameters; and feed the real-time status information back to the central processor; The load prediction unit is used to predict the state information of the current load control terminal using the tested neural network model, and generate corresponding control instructions based on the prediction results, and then feed them back to the central processor; A central processing unit, which is used to receive the real-time status information of the load control terminal and the control instructions generated by the neural network model, adjust the operating status of the load control terminal based on the control instructions, and feed back the real-time status information and operating status of the load control terminal to the human-computer interaction terminal for visual display; The human-computer interaction terminal is used to visualize the real-time status information and current operating status of the load control terminal in the form of charts, as well as the prediction results and control instructions output by the neural network model.
[0006] Furthermore, the load control terminal includes: The input and output port module is composed of an input port and an output port and is arranged on a programmable DC electronic load device. The input port is used to receive the output signal of the power supply or battery under test, and the output port is used to apply the load to the power supply or battery.
[0007] Furthermore, the data collection unit includes: A cleaning processing module is used to clean the collected historical status information and remove invalid data; A denoising processing module is used to perform denoising on the collected historical status information; The data partitioning module is used to divide the new data set into a training set and a test set, and train and test the neural network model through the training set and the test set; Furthermore, the model building unit includes: The model building module is used to create a neural network model and set the hyperparameters of the neural network model; The model training module is used to train the neural network model through the training set, establish the feature layer of the neural network model, and then verify the performance of the neural network model through the test set.
[0008] Furthermore, the model building unit further includes: The model optimization module is used to adjust the allocation ratio of the training set and the test set and the parameters of the neural network model when the performance of the neural network model does not meet expectations, and then continue to train and test the neural network model; if the verification passes, the optimized neural network model is obtained.
[0009] Furthermore, the data acquisition unit includes: The hardware connection module is used to physically connect with the load control terminal through a sensor interface, such as an analog interface and a digital interface, continuously read the real-time status information of the load control terminal, and record the real-time status information in a buffer area inside the hardware connection module; The data transmission module is used to feed back the real-time status information in the cache area to the central processor for visual display and storage backup.
[0010] Furthermore, the load prediction unit includes: The load prediction module is used to predict the real-time status information using the optimized neural network model to obtain the prediction result of the current load control terminal operation status; The instruction generation module generates corresponding control instructions based on the prediction results and feeds them back to the central processing unit for execution.
[0011] Furthermore, the central processing unit includes: An instruction transceiver module is used to receive the control instruction fed back by the load prediction unit and execute the control instruction to remotely adjust the load condition of the load control terminal; The data storage module is used to receive the real-time status information of the load control terminal and store it in time series to form a load information library.
[0012] Furthermore, the data storage module includes: A data encryption module is used to encrypt the real-time status information in the load information library using a symmetric encryption method; The access restriction module is used to set the access rights of the load information library and limit the access objects of the load information library.
[0013] Furthermore, the human-computer interaction terminal includes: The data display terminal is used to visualize the changing trends of various parameter indicators in the load control terminal, as well as the prediction results and control instructions output by the neural network model in the form of charts.
[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention predicts the operating state of the load control terminal through a neural network model, thereby obtaining a prediction result of the operating state of the load control terminal; and generates corresponding control instructions based on the prediction result, thereby providing parameter adjustment suggestions for the load control terminal in advance, so as to better optimize and improve the effect of the load control terminal, so that the load control terminal can maintain stable operation when facing various load changes.
[0015] 2. The present invention configures the load control terminal to be portable, making it small and delicate in appearance so that it can be applied to various scenarios, thereby improving the high density and use prospects of the load control terminal. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a structural diagram of a high-density, high-power programmable DC electronic load of the present invention; Figure 2 This is a diagram showing the composition of each module in the high-density, high-power programmable DC electronic load of the present invention.
[0017] In the figure: 1. Portable programmable DC electronic load device. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] In order to solve the technical problem that in the prior art, programmable DC electronic load devices usually require users to manually set various parameters, which increases the complexity of operation; especially in some cases, users may need to understand more complex circuit principles to correctly set the device, which makes it difficult for users to accurately adjust the device parameters, affecting the use prospects of existing programmable DC electronic load devices, please refer to Figure 1-2 , this embodiment provides the following technical solutions: High-density, high-power programmable DC electronic loads, including: The load control terminal is a portable programmable DC electronic load device 1, which is suitable for use in special scenarios, such as the aerospace field, and scenarios with certain requirements on the size of the load control terminal, thereby broadening the scope of application of the load control terminal; specifically, the load control terminal is used to apply different load conditions to simulate the actual working environment, so as to evaluate the output capacity and stability of the power supply or battery under different loads; the load control terminal includes: The input / output port module, which consists of an input port and an output port, is arranged on the programmable DC electronic load device 1. The input port is used to receive the output signal of the power supply or battery under test, and the output port is used to apply the load to the power supply or battery. In the specific implementation, the user needs to select the correct connection method according to the specific situation, such as series connection or parallel connection method, to ensure normal communication and energy transfer between the power supply or battery and the load control terminal.
[0020] The data collection unit is used to collect historical status information of the load control terminal, and the historical status information includes: load voltage, current and temperature parameters; and the collected historical status information is cleaned and pre-processed to reduce noise to obtain a new data set; specifically, since the status information of the load control terminal is usually stored in a specific format in the memory inside the load control terminal; therefore, through the hardware interface, that is: the hardware connection module mentioned below, various historical status information can be automatically collected from various load control terminals, and the above-mentioned various information can be pre-processed to facilitate subsequent analysis and learning using a neural network model, thereby evaluating and optimizing the operating status of the load control terminal.
[0021] Data collection unit, including: The cleaning processing module is used to clean the collected historical status information and remove invalid data; for example, there may be some invalid data in the historical status information, such as abnormal values, duplicate values, etc., and this part of the data is cleared to ensure the accuracy and completeness of the historical status information.
[0022] The denoising processing module is used to perform denoising processing on the collected historical state information, such as using a Kalman filter to eliminate the noise in the historical state information, thereby reducing the interference of the noise; based on the above operation, a new data set is obtained, which has all the historical state information after cleaning and denoising processing, so as to serve as a training sample for the neural network model; The data partitioning module is used to divide the new data set into a training set and a test set, and train and test the neural network model through the training set and the test set; specifically, the data set is divided into a training set and a test set according to the 30%-70% method, such as 70% training set and 30% test set, and the neural network model is trained with the training set to determine the feature layer of the neural network model; the neural network model is then tested with the test set, and the test results are output to verify the predictive ability of the neural network model; secondly, in the process of training and testing, the cross-validation technology is used to balance the training errors of the training and test sets to ensure the generalization ability of the neural network model.
[0023] The model building unit is used to train and test the data set using the neural network model to obtain a neural network model that can predict the operating state of the load control terminal; the model building unit includes: The model building module is used to create a neural network model and set the hyperparameters of the neural network model. Specifically, by selecting commonly used hyperparameters, such as learning rate, batch size, and number of iterations. The learning rate determines how fast the neural network model learns. The batch size determines the step size for each weight update. A too large batch size will increase the training time, while a too small batch size will reduce the convergence speed of the neural network model. The number of iterations determines the number of rounds of neural network model training to ensure the predictive performance of the neural network model.
[0024] The model training module is used to train the neural network model through the training set, establish the feature layer of the neural network model, and then verify the performance of the neural network model through the test set to understand the generalization performance of the neural network model on unknown data. The evaluation indicators of the neural network model include: accuracy, recall rate, and F1 score, etc., to ensure that the neural network model achieves ideal prediction performance.
[0025] The model optimization module is used to adjust the allocation ratio of the training set and the test set and the parameters of the neural network model when the performance of the neural network model does not meet expectations, such as adding or deleting certain feature layers, adjusting the network topology, etc.; and then continue to train and test the neural network model to obtain better prediction results; if the verification is passed, the optimized neural network model is obtained; secondly, regularization technology can be added during the training of the neural network model to obtain better prediction results, so that after being deployed in the actual application scenario, the neural network model can effectively predict the status information of the load control terminal.
[0026] The data acquisition unit is used to collect the real-time status information of the load control terminal, including load voltage, current and temperature parameters; and feed the real-time status information back to the central processor; the data acquisition unit includes: The hardware connection module is used to physically connect with the load control terminal through a sensor interface, such as an analog interface and a digital interface, continuously read the real-time status information of the load control terminal, and record the real-time status information in a cache area inside the hardware connection module to ensure that no data is lost for subsequent processing and use; specifically, the hardware connection module can be physically connected with the load control terminal through an analog interface or a digital interface to read and record the real-time status information of the load control terminal; wherein the interface can be connected through USB, Ethernet, etc.; after obtaining the real-time status information of the load control terminal, the information will be recorded in the cache area inside the hardware connection module, and the structure of the information will be optimized in the form of a chart to facilitate processing and analysis by the central processing unit.
[0027] The data transmission module is used to feed back the real-time status information in the cache area to the central processing unit for visual display and storage backup; specifically, according to the actual application scenario, a suitable communication protocol is selected, such as TCP / IP, HTTP, MQTT, so as to support a large amount of data transmission and adapt to various network environments and load conditions, thereby realizing high-density and high-power functions; the data transmission module extracts the real-time status information in the cache area from the hardware connection module and transmits it through the corresponding communication protocol; when the central processing unit receives a data transmission request, it automatically parses the data and displays it visually on the human-computer interaction terminal.
[0028] The load prediction unit is used to predict the state information of the current load control terminal using the tested neural network model, and generate corresponding control instructions based on the prediction results, and then feed them back to the central processor; the load prediction unit includes: The load prediction module is used to use the optimized neural network model to predict the real-time status information and obtain the prediction result of the current load control terminal operation status; if the prediction result is not ideal, the structure or parameters of the neural network model are readjusted to better match the actual load situation; the above steps are repeated to continuously optimize the neural network model to improve its prediction accuracy.
[0029] The instruction generation module generates corresponding control instructions based on the prediction results and feeds them back to the central processing unit for execution; specifically, the control instructions generated according to the prediction results are sent to the central processing unit; the central processing unit is responsible for receiving the control instructions and converting them into actual actions. For example, if the prediction results show that the current setting value of the programmable DC electronic load is too high or too low, the corresponding instructions can be generated, that is, the current setting value is appropriately adjusted to achieve the expected load control effect; for example, if the prediction results show that the voltage setting value of the programmable DC electronic load is too high or too low, the corresponding instructions can be generated, that is, the voltage setting value is appropriately adjusted to achieve the expected load control effect; for example, if the prediction results show that the operating temperature of the programmable DC electronic load is too high or too low, the corresponding instructions can be generated, that is, the temperature setting value is appropriately adjusted to achieve the expected load control effect; in the specific implementation, including but not limited to the above instructions; based on this, the effect of the load control terminal can be better optimized and improved, so that the load control terminal can maintain stable operation when facing various load changes.
[0030] The central processor is used to receive the real-time status information of the load control terminal and the control instructions generated by the neural network model, adjust the operating status of the load control terminal based on the control instructions, and feed back the real-time status information and operating status of the load control terminal to the human-computer interaction terminal for visual display; the central processor includes: The instruction transceiver module is used to receive the control instruction fed back by the load prediction unit, and execute the control instruction to remotely adjust the load condition of the load control terminal; as mentioned above, if the prediction result shows that the current setting value of the programmable DC electronic load is too high or too low, a corresponding instruction can be generated, that is, appropriately adjust the current setting value to achieve the expected load control effect; the central processing unit can remotely control and adjust the current current value of the load control terminal based on the specific current value given in the control instruction, thereby adaptively adjusting the dynamics of the load control terminal to meet the precise control requirements under different load conditions.
[0031] The data storage module is used to receive the real-time status information of the load control terminal and store it in time series to form a load information library. The data storage module includes: The data encryption module is used to encrypt the real-time status information in the load information library using a symmetric encryption method; specifically, by analyzing the characteristics of the real-time status information, a message digest algorithm is used to extract the characteristics; the digest is encrypted using a symmetric encryption algorithm, and the original data and the encrypted digest are stored together in the load information library; when data needs to be queried, the digest in the load information library is first obtained, and then the same key and digest algorithm are used to decrypt it, so as to obtain the actual original data, thereby ensuring data security.
[0032] The access restriction module is used to set the access rights of the load information library and limit the access objects of the load information library. Specifically, the access objects of the load information library are selected according to the actual application scenario; and different access rights are assigned to different users according to the user role settings; each user role has a corresponding access level, such as: ordinary user, administrator, senior administrator, etc., and users can only perform corresponding operations under their assigned roles; when accessing the load information library, the user name / password is first verified, and only users who have passed the identity authentication can enter the access interface of the load information library; and during the user access process, the user's activities on the load information library are recorded, such as: click, add, modify, delete, etc.; when suspicious behavior is found, a security alarm is triggered and timely measures are taken; and every user operation is recorded, such as: success, failure, repeated attempts, etc., so that it can help trace responsibility when necessary, thereby ensuring the security and reliability of the load information library.
[0033] The human-computer interaction terminal is used to visualize the real-time status information and current operating status of the load control terminal in the form of charts, as well as the prediction results and control instructions output by the neural network model; the human-computer interaction terminal includes: The data display terminal is a user display screen that is used to visualize the changing trends of various parameter indicators in the load control terminal in the form of charts, such as current, voltage, and power, as well as whether it is operating normally and whether there are any faults, so that users can intuitively understand the working status of the load control terminal; in addition, the display in the form of charts can also facilitate users to compare the operating conditions in different time periods or under different load conditions, so that users can better analyze and judge the status of the load control terminal; and display the prediction results and control instructions output by the neural network model. The prediction results can help users predict the future operation of the load control terminal so that users can prepare in advance; control instructions allow users to directly operate the load control terminal, such as starting, stopping, changing the working mode, etc., to help users better control and manage the load control terminal.
[0034] The beneficial effects achieved by the above content are: the corresponding control instructions are generated through the prediction results output by the neural network model, so as to provide parameter adjustment suggestions for the load control terminal in advance, so as to better optimize and improve the effect of the load control terminal, so that the load control terminal can maintain stable operation when facing various load changes. Secondly, by setting the load control terminal to be portable, its appearance is small and exquisite, so that it can be suitable for various scenarios, thereby improving the high density and use prospects of the load control terminal.
[0035] Working principle: The historical status information of the load control terminal is used as a data set, and the neural network model is used to learn the content of the data set, so as to obtain a model that can predict the operating status of the load control terminal; the real-time operating status of the load control terminal is predicted based on the optimized neural network model, so as to obtain the predicted result of the operating status of the load control terminal; and the corresponding control instructions are generated based on the predicted results, so as to provide parameter adjustment suggestions for the load control terminal in advance to ensure the stable operation of the load control terminal.
[0036] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "including", "having" or any other variations thereof are intended to cover non-exclusive possessing, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0037] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. High-density, high-power programmable DC electronic load, characterized by: include: The load control terminal is a programmable DC electronic load device (1) used to apply different load conditions to simulate the actual working environment and evaluate the output capacity and stability of the power supply or battery under different loads; A data collection unit is used to collect historical status information of the load control terminal, the historical status information includes: load voltage, current and temperature parameters; and to clean and pre-process the collected historical status information to obtain a new data set; A model building unit, used to train and test a data set using a neural network model to obtain a neural network model capable of predicting the operating state of a load control terminal; A data acquisition unit is used to collect real-time status information of the load control terminal and feed the real-time status information back to the central processor; The load prediction unit is used to predict the state information of the current load control terminal using the tested neural network model, and generate corresponding control instructions based on the prediction results, and then feed them back to the central processor; A central processing unit, which is used to receive the real-time status information of the load control terminal and the control instructions generated by the neural network model, adjust the operating status of the load control terminal based on the control instructions, and feed back the real-time status information and operating status of the load control terminal to the human-computer interaction terminal for visual display; The human-computer interaction terminal is used to display the real-time status information and operating status of the load control terminal in the form of charts, as well as the prediction results and control instructions output by the neural network model.
2. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The load control terminal comprises: The input / output port module is composed of an input port and an output port, and is arranged on a programmable DC electronic load device (1), wherein the input port is used to receive an output signal of a power source or battery under test, and the output port is used to apply a load to the power source or battery.
3. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The data collection unit comprises: A cleaning processing module is used to clean the collected historical status information and remove invalid data; A denoising processing module is used to perform denoising on the collected historical status information; The data partitioning module is used to divide the new data set into training sets and test sets, and train and test the neural network model through the training sets and test sets.
4. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The model building unit comprises: The model building module is used to create a neural network model and set the hyperparameters of the neural network model; The model training module is used to train the neural network model through the training set, establish the feature layer of the neural network model, and then verify the performance of the neural network model through the test set.
5. The high-density, high-power programmable DC electronic load according to claim 4, characterized in that: The model building unit further includes: The model optimization module is used to adjust the allocation ratio of the training set and the test set and the parameters of the neural network model when the performance of the neural network model does not meet expectations, and then continue to train and test the neural network model; if the verification passes, the optimized neural network model is obtained.
6. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The data acquisition unit comprises: The hardware connection module is used to physically connect with the load control terminal through the sensor interface, read the real-time status information of the load control terminal, and then record the real-time status information in the buffer area inside the hardware connection module; The data transmission module is used to feed back the real-time status information in the cache area to the central processor for visual display and storage backup.
7. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The load prediction unit comprises: The load prediction module is used to predict the real-time status information using the optimized neural network model to obtain the prediction result of the current load control terminal operation status; The instruction generation module generates corresponding control instructions based on the prediction results and feeds them back to the central processing unit for execution.
8. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The central processing unit comprises: An instruction transceiver module is used to receive the control instruction fed back by the load prediction unit and execute the control instruction to remotely adjust the load condition of the load control terminal; The data storage module is used to receive the real-time status information of the load control terminal and store it in time series to form a load information library.
9. The high-density, high-power programmable DC electronic load according to claim 8, characterized in that: The data storage module comprises: A data encryption module is used to encrypt the real-time status information in the load information library using a symmetric encryption method; The access restriction module is used to set the access rights of the load information library and limit the access objects of the load information library.
10. The high-density, high-power programmable DC electronic load according to claim 1, characterized in that: The human-computer interaction terminal comprises: The data display terminal is used to visualize the changing trends of various parameter indicators in the load control terminal, as well as the prediction results and control instructions output by the neural network model in the form of charts.