Multi-layer control system and method for power electronic products

Abstract

The present invention provides a multi-layer control system and method for a power electronic product. The multi-layer control system includes at least a first-layer controller and a second-layer controller. The first-layer controller acquires a first state signal obtained by the power electronic product in response to sensor detection, transmits the first state signal to the second-layer controller, and receives a control reference signal fed back from the second-layer controller. The second-layer controller acquires a second state signal other than the first state signal of the power electronic product based on the first state signal and a model simulating the power electronic product, and generates a control reference signal based on the first state signal, the second state signal, and a control target of the power electronic product, and outputs the control reference signal to the first-layer controller. The multi-layer control system and method can expand the control function of the power electronic product by using controllers at different levels, thereby improving the control performance of the power electronic product.

Description

[Technical Field]

[0001] The present invention relates to the field of power electronic products, and more particularly to a multi-layer control system and method for power electronic products. [Background technology]

[0002] With the acceleration of electrification and automation, the demands on the functionality and performance of power electronics products are also increasing. Whether a power electronics product can achieve optimal functionality and performance is inextricably linked to its control. Typically, at the start of operation, there is a one-to-one correspondence between a power electronics product and a controller. Due to limitations in the controller's software and hardware, even if a power electronics product can achieve better functionality and performance on the hardware, the corresponding controller may lack the ability to provide the desired control parameters, preventing the power electronics product from performing optimally.

[0003] With the development of electronic products, a single product typically combines a power electronics product and its controller with additional controllers, and can even be connected to a cloud-based controller. Without considering (and increasing costs for) replacing the controller attached to the power electronics product, it is desirable to have an external controller assist the power electronics product's controller in providing desired control parameters.

[0004] This need is also very prevalent in the electric vehicle field. As the electric vehicle market penetration rate increases, electric vehicle technology is developing rapidly, and the requirements for finished vehicle components (power electronics products) are becoming increasingly higher, requiring more functions and better performance. Meanwhile, the electronic architecture and smart connected technology of finished vehicles are also developing rapidly, leading to the emergence of computing units with high computing power, such as domain controllers, area controllers, and computers, which can be used as external controllers.

[0005] In light of this, it is desirable to provide a multi-layer control system and method for power electronic products that allows power electronic products and their controllers to have richer functions and better performance without increasing component costs, and that has the potential for a very wide range of applications, such as in the electric vehicle market. Summary of the Invention [Problem to be solved by the invention]

[0006] A brief summary of one or more aspects is presented below to provide a basic understanding of these aspects. This summary is not a detailed overview of all contemplated aspects, and is not intended to identify key or critical elements of all aspects or to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form, as a prelude to the more detailed description that follows.

[0007] As described above, in order to solve the problem that in the prior art, the control device of the power electronic product cannot provide better control parameters without incurring additional costs, the present invention provides a multi-layer control system and method for the power electronic product. [Means for solving the problem]

[0008] According to one aspect of the present invention, a multi-layer control system for a power electronics product includes at least a first-layer controller and a second-layer controller, wherein the first-layer controller is configured to acquire a first state signal obtained in the power electronics product in response to sensor detection, transmit the first state signal to the second-layer controller, receive a control reference signal fed back from the second-layer controller, generate a control signal for the power electronics product based on the control reference signal, and output the control signal to the power electronics product. The second-layer controller is configured to acquire a second state signal other than the first state signal in the power electronics product based on the first state signal and a model that simulates the power electronics product, generate the control reference signal based on the first state signal, the second state signal, and a control target of the power electronics product, and output the control reference signal to the first-layer controller.

[0009] According to one aspect of the present invention, a multi-layer control system for a power electronics product can generate optimized control parameters by a controller (first-layer controller) that assists the power electronics product based on an external controller (second-layer controller) without adding additional hardware and without incurring additional costs, thereby improving the control of the power electronics product, enriching the functions of the power electronics product, and improving the performance of the power electronics product.

[0010] In one embodiment of the multi-layer control system, preferably, the system further includes a third-layer controller, wherein the third-layer controller is configured to identify and optimize model parameters of the model based on the historical first state signal and historical control signal fed back from the first-layer controller and the historical second state signal and historical control reference signal fed back from the second-layer controller, and output the model parameters to the second-layer controller, and the second-layer controller is further configured to update the model based on the received model parameters.

[0011] In one embodiment of the multi-layer control system, preferably, the third layer controller is further configured to, in response to a change in the model parameter exceeding a preset threshold, transmit the model parameter, the change in the model parameter having exceeded a preset threshold, to the first layer controller, and cause the first layer controller to diagnose a hardware state of the power electronics product based on the model parameter.

[0012] In one embodiment of the multi-layer control system, preferably, the model for simulating the power electronic product in the second-layer controller comprises a mechanism model and / or a big data model, wherein the mechanism model is a mathematical-physical model for simulating the power electronic product to obtain, as the second state signal, simulation state variables other than the first state signal of the power electronic product based on the first state signal, and the big data model represents a mapping relationship between the first state signal and / or the simulation state variables of the power electronic product and predicted state variables of the power electronic product, and outputs the predicted state variables as the second state signal according to the first state signal and / or the simulation state variables.

[0013] In one embodiment of the multi-layer control system, preferably, the third-layer controller is further configured to identify and optimize model parameters of the mathematical-physical model and / or the big data model, and output the model parameters to the second-layer controller.

[0014] In one embodiment of the multi-layer control system, preferably, in response to the model comprising the mechanism model and the big data model, the second-layer controller is configured to obtain the simulation state variables from the first state signal and the mechanism model, input the first state signal and the simulation state variables into the big data model, obtain the predicted state variables as the second state signal, and generate the control reference signal according to the second state signal output by the big data model.

[0015] In one embodiment of the multi-layer control system, preferably, the multi-layer control system is applied to a vehicle, the first layer controller is a power electronics product controller of the vehicle, the second layer controller is an on-board computing unit of the vehicle, and the third layer controller is a cloud controller that corresponds one-to-one with the vehicle.

[0016] In the above embodiment, the multi-layer control system is applied to the automotive field, and with the rapid development of the electronic and electrical architecture of the entire vehicle and smart connected technology, high-computing power computing units such as an on-board domain controller, an on-board area controller, and an on-board computer have appeared in the vehicle. These controllers of the entire vehicle can be used as external controllers of the on-board power electronics products, thereby enriching the functions of the power electronics products based on the electrical architecture of the entire vehicle already installed in the vehicle without increasing the costs of the entire vehicle and its components, improving the performance of the power electronics products and providing more revenue for the entire vehicle. In the above embodiment, resources other than the controller product (resources such as other on-board controllers, on-board computers, and cloud) can be used to optimize the performance (control accuracy, system power, system efficiency, robustness, etc.) of the controller product (the controller remains unchanged using chips), thereby realizing a cost-saving solution for high-performance controllers.

[0017] Another aspect of the present invention provides a multi-layer control method for a power electronics product, the multi-layer control method including: a first layer controller acquiring a first state signal of the power electronics product according to sensor detection; a second layer controller acquiring a second state signal of the power electronics product other than the first state signal based on the first state signal and a model that simulates the power electronics product; the second layer controller generating a control reference signal based on the first state signal, the second state signal, and a control target of the power electronics product; and the first layer controller generating a control signal of the power electronics product based on the control reference signal and outputting the control signal to the power electronics product.

[0018] In one embodiment of the multi-layer control method, preferably, the multi-layer control method further includes: a third layer controller identifying and optimizing model parameters of the model based on the historical first state signal and historical control signal fed back from the first layer controller and the historical second state signal and historical control reference signal fed back from the second layer controller; and causing the second layer controller to update the model based on the model parameters.

[0019] In one embodiment of the multi-layer control method, preferably, the multi-layer control method further includes: in response to a change in the model parameter exceeding a preset threshold, the third layer controller transmits the model parameter, the change in the model parameter having exceeded the preset threshold, to the first layer controller, and causes the first layer controller to diagnose a hardware state of the power electronics product based on the model parameter.

[0020] In one embodiment of the multi-layer control method, preferably, the model for simulating the power electronic product in the second-layer controller comprises a mechanism model and / or a big data model, wherein the mechanism model is a mathematical-physical model for simulating the power electronic product to obtain, based on the first state signal, simulation state variables of the power electronic product other than the first state signal as the second state signal, and the big data model represents a mapping relationship between the first state signal and / or the simulation state variables of the power electronic product and predicted state variables of the power electronic product, and outputs the predicted state variables as the second state signal according to the first state signal and / or the simulation state variables.

[0021] In one embodiment of the multi-layer control method, preferably, in response to the model comprising the mechanism model and the big data model, the second-layer controller obtaining the second state signal comprises obtaining the simulation state variable from the first state signal and the mechanism model, inputting the first state signal and the simulation state variable into the big data model, and obtaining the predicted state variable as the second state signal, and the second-layer controller generates a control reference signal on which the control reference signal is based as the second state signal output by the big data model.

[0022] Another aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, realizes the steps of the multi-layer control method for power electronic products described in any one of the above-mentioned embodiments. [Effects of the Invention]

[0023] The multi-layer control system and method for power electronic products according to the present invention can provide more abundant functions and superior performance to power electronics and its controllers based on existing external controllers without adding additional hardware costs. The present invention can be applied to the automotive field, and can optimize the functions and performance of on-board power electronics products and their controllers through the electronic and electrical architecture of the vehicle and smart connected technology, without increasing the hardware costs of the vehicle, thereby improving the performance of the vehicle and providing more revenue for the vehicle. [Brief explanation of the drawings]

[0024] The above-mentioned features and advantages of the present invention can be better understood from the detailed description of the embodiments of the present disclosure in conjunction with the following drawings, in which components are not necessarily drawn to scale and components with similar related properties or characteristics may be labeled with the same or similar drawing symbols.

[0025] [Figure 1] 1 shows a structural schematic diagram of a multi-layer control system for a power electronics product provided by an embodiment of the present invention; [Figure 2] 1 shows a structural schematic diagram of a preferred embodiment of a multi-layer control system for a power electronic product provided by an aspect of the present invention; [Figure 3] 1 shows a flow diagram of a multi-layer control method for a power electronic product provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0026] The present invention will now be described in detail with reference to the drawings and specific embodiments. It should be noted that the embodiments described below in connection with the drawings and specific embodiments are illustrative and should not be construed as limiting the scope of protection of the present invention.

[0027] The following description is provided to enable those skilled in the art to make, use, and incorporate the present invention into particular application contexts. Various modifications and uses in various applications will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to a broader range of embodiments. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0028] In the following detailed description, numerous specific details are set forth to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that practice of the present invention may not necessarily be limited to these specific details. That is, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the present invention.

[0029] The reader is directed to all documents and literature submitted contemporaneously with this specification and open to public inspection, and the contents of all such documents and literature are incorporated herein by reference. Unless otherwise directly stated, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by alternative features achieving the same, equivalent, or similar purpose. Thus, unless otherwise expressly stated, each disclosed feature is only one example of a set of equivalent or similar features.

[0030] It should be noted that, when used, the flags left, right, front, back, top, bottom, positive, negative, clockwise, and counterclockwise are used for convenience only and do not imply any specific fixed direction. In fact, they are used to reflect the relative position and / or orientation between parts of an object. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0031] When used, "further," "preferably," "even further," and "even more preferably" are simple introductory expressions for describing another embodiment based on the previous embodiment, and the content following "further," "preferably," "even further," or "even more preferably" is intended to constitute a complete embodiment in combination with the previous embodiment. A composition that can be arbitrarily combined between several "further," "preferably," "even further," or "even more preferably" settings following the same embodiment is also an embodiment.

[0032] As described above, in order to solve the problem that in the prior art, the control device of a power electronic product cannot provide better control parameters without incurring additional costs, the present invention provides a multi-layer control system and method for a power electronic product.

[0033] First, please refer to Figures 1 and 2 to deepen your understanding of the configuration of a multi-layer control system for a power electronics product according to one embodiment of the present invention.

[0034] As shown in FIG. 1, a multi-layer control system for a power electronics product according to one embodiment of the present invention includes at least a first-layer controller 100 and a second-layer controller 200, which are connected to each other via communication. The first-layer controller 100 is electrically connected and / or connected to a controlled object (i.e., a power electronics product, including but not limited to an electric shaft, a charger, a DC-DC module, etc.). The first-layer controller 100 can acquire a first state signal obtained by the controlled object in response to sensor detection and output the first state signal to the second-layer controller 200. The first state signal is an electrical signal obtained by sampling based on an actual physical sensor, including but not limited to temperature, voltage, current, etc. The first-layer controller 100 has general control and computing capabilities and is mainly used to execute software processes with high real-time performance, low computing power demands, and low data storage, and simple control algorithms. It can output a control signal for the controlled object, typically a PWM duty signal.

[0035] The second-layer controller 200 has medium real-time requirements, high computational power demands, and low data storage requirements and is primarily used to execute software processes for smart optimization algorithms. Based on the first state signal and a simulated power electronics product model, the second-layer controller 200 can obtain a second state signal other than the first state signal of the power electronics product. The second state signal refers to a system state variable that is difficult to obtain through observation or cannot be measured by a physical sensor, including, but not limited to, a variable that is difficult to characterize, such as the temperature inside the controlled object. The second-layer controller 200 can obtain these state variables that are difficult to obtain through observation or sensor measurement by simulating a model of the power electronics product. Based on the second state signal, the second-layer controller 200 can calculate a control reference value for the first-layer controller 100 according to a control target, assuming that a certain target is optimized, and output the control reference value to the first-layer controller 100.

[0036] In a preferred embodiment, the multi-layer control system further includes a third-layer controller 300. The third-layer controller 300 is connected via communication between the first-layer controller 100 and the second-layer controller 200. The third-layer controller 300 may receive the historical first state signal and historical control signal output from the first-layer controller 100 and the historical second state signal and historical control reference signal output from the second-layer controller 200. Based on these historical signals, the second-layer controller 300 identifies and optimizes model parameters of the model in the second-layer controller 200, allowing the second-layer controller 300 to update the model, thereby better simulating and determining the state quantities of the controlled product based on the model. The third-layer controller 300 has a slow real-time response, high computational demands, and stores large amounts of data. It is used to execute software processes for smart optimization algorithms and to optimize or adjust the model parameters related to the second-layer controller. This distributed multi-layer control architecture can enrich the functions of power electronic products and improve the performance of power electronic products.

[0037] When applied to a vehicle, the first tier controller 100 may be considered to be a power electronics on-board controller, the second tier controller 200 may be considered to be an on-board computing unit, and the third tier controller 300 may be considered to be a cloud controller corresponding to the vehicle.

[0038] A preferred multi-tier control system provided by one embodiment of the present invention can be further understood by referring to Figure 2. As shown in Figure 2, this embodiment includes a first tier controller 100, a second tier controller 200, and a third tier controller 300.

[0039] The first layer controller 100 is used to realize the most basic control function of the power electronics controller, the second layer controller 200 is used to realize optimization control for optimizing a certain target, and the third layer controller 300 is used to optimize or adjust model parameters related to the second layer of the multi-layer control system. Note that the third layer controller 300 is used to process large amounts of data, similar to a cloud controller, but is slightly different from current clouds in that the third layer controller 300 in the present invention is only targeted at a single power electronics product, i.e., each power electronics product has its own independent first, second, and third layers of the multi-layer control system.

[0040] In this preferred embodiment, the first layer controller 100 further includes internal sub-modules such as data sampling 110, control algorithm 120, drive generation 130, and part diagnosis 140. The second layer controller 200 further includes a smart algorithm 210, a mechanism model 220, and a data model 230. The third layer controller further includes data storage 310, an identification algorithm 320, parameter transmission 330, an identification model 340, and data diagnosis 350. Although the term "module" is used, in reality, there are no physical modules within the controller, and the functions of each "module" may be realized by different software.

[0041] However, the controlled object (i.e., power electronics product) needs to output data obtained by sensor sampling to data sampling 110, and the transmitted data includes relevant electrical signals sampled by the first layer of the multi-layer control system based on actual physical sensors, including temperature, voltage, current, etc. Meanwhile, the signal received by the controlled object is often the control signal output by the first layer of the multi-layer control system to the controlled object, which in the case of a power electronics product is generally a PWM duty signal.

[0042] 100->300 data transmission: The first layer of the multi-layer control system transmits software sampling signals, software control signals and control-related intermediate quantities to the third layer of the multi-layer control system.

[0043] 100->200 data transmission: The first layer of the multi-layer control system transmits software sampling signals, software control signals and control-related intermediate quantities to the second layer of the multi-layer control system.

[0044] 200->300 data transmission: Based on the model and the data of 100->200 data transmission, the second layer of the multi-layer control system can observe or estimate system state variables that cannot be measured by actual sensors, such as the temperature inside the controlled object and variables that are difficult to characterize, and then transmit the observed system state variables to the third layer of the multi-layer control system.

[0045] 300->200 data transmission: The third layer of the multi-layer control system records the 100->300 data transmission and 200->300 data transmission of the entire life cycle through data storage 310, and identifies model parameters to be used in the second layer of the multi-layer control system online through identification algorithm 320 and identification model 340 based on the long-time scale data (since the characteristics of power electronics products, which are physical devices, change over time, the model parameters in the second layer of the multi-layer control system also need to change), and sends the identified model parameters to the model related to the second layer of the multi-layer control system through parameter transmission 330, replacing the current model parameters.

[0046] 200->100 data transmission: The second layer of the multi-layer control system, based on the 100->200 data transmission, calculates the control reference value of the first layer of the multi-layer control system through the smart algorithm 210 based on the corresponding algorithm scheduling and model estimation and prediction, and on the premise of the optimality of a certain target, and transmits it to the control algorithm 120 of the first layer of the multi-layer control system. The control algorithm 120 can calculate the relevant control signal of the controlled object based on conventional control and calculation capabilities, and output it to the controlled object.

[0047] In one embodiment, when applied to a vehicle, these control signals must be converted into relevant drive signals via drive generation 130 .

[0048] 300->100 data transmission: The third layer of the multi-layer control system records the 100->300 data transmission and 200->300 data transmission of the entire life cycle, and determines whether the controlled object is normal or not through data diagnosis 350 and identification algorithm 320 based on the long-term scale data. For example, if some parameters or state variables have a large change trend under the same operating conditions, the relevant data will be sent to the first layer of the multi-layer control system, and relevant diagnosis and response will be made through component diagnosis 140.

[0049] Particularly for the second-tier controller 200, the smart algorithm 210 is used to realize smart scheduling algorithms for goal optimization, such as PSO particle swarm algorithm, simulation annealing algorithm, model prediction algorithm, etc.

[0050] The mechanism model 220 is a mathematical-physical model that can reproduce the controlled object and is used to estimate relevant system state variables that cannot be measured in the controlled object.

[0051] Data model 230: A data model trained offline (a big data model such as a neural network model). When trained offline on a large amount of data and then applied online, the desired results can be output by inputting various state variables and sampling values of the control target.

[0052] 210->220 Data Transmission and Call: The smart algorithm 210 transmits the information in the data sent from the first layer to the second layer to the mechanism model 220, and the mechanism model 220 observes or estimates the internal state variables of the controlled object (contents that are difficult to measure in reality). The smart algorithm 210 also sends a related call instruction to the mechanism model 220 and calls the mechanism model 220 to obtain the second state signal.

[0053] 220->230 Data transmission: Based on the input data, the mechanism model 220 observes or estimates system state variables that are difficult to measure with sensors, and transmits them to the data model 230.

[0054] 210->230 Data transmission and calling: The smart algorithm 210 sends the information sent from the first layer to the second layer to the data model 230, and further, the smart algorithm 210 sends a related calling instruction to the data model 230 and calls the data model 230 to obtain the second state signal. In one embodiment, according to the simultaneous inclusion of the mechanism model 220 and the data model 230, the mechanism model 220 may first be called to obtain the simulation state variable based on the first state signal, and then the data model 230 may be called to obtain the predicted state variable as the second state signal based on the first state signal and the simulation state variable.

[0055] 230->210 data transmission: Based on 210->220 data transmission and 220->230 data transmission, the data model 230 outputs relevant data information that is difficult or inaccurate to calculate by the mechanism model based on a pre-trained data model (e.g., a neural network model), and transmits it to the smart algorithm 210.

[0056] 220->210 data transmission: Based on 210->220 data transmission, the mechanism model 220 observes or estimates state variables (contents that are difficult to measure in reality) inside the controlled object based on a physical mathematical model, and transmits them to the data model smart algorithm 210.

[0057] The smart algorithm 210 calculates a control reference signal for the control algorithm 120 based on a smart scheduling algorithm in which a certain goal is optimized based on the first state signal sent by the data sample 140 and the second state signal obtained by the mechanism model 220 and / or the data model 230.

[0058] Please refer to the flowchart of the multi-layer control method for power electronic products provided in another aspect of the present invention shown in Figure 3 to further understand the specific implementation process of the multi-layer control system provided by the present invention.

[0059] As shown in Figure 3, upon starting, the second layer controller 200 obtains a control target, and when applied to the vehicle, this control target is sent from the VCU of the vehicle. By optimizing the control target through the smart algorithm 210, a control reference signal is generated and sent to the control algorithm of the first layer controller 100, and the control algorithm 120 calculates a control signal based on the first state signal obtained by data sampling, and then outputs it to the controlled object based on the drive generation.

[0060] On the other hand, in the process in which the smart algorithm 210 optimizes the control target, it is necessary to obtain a second state signal that cannot be obtained by observation or sensor sampling based on a model, and to use an identification algorithm based on a model (including a mechanism model and / or a big data model) to optimize the control target with the smart algorithm based on the first state signal and the second state signal.

[0061] Because power electronics products are physical devices, their performance parameters change after a certain period of use. Therefore, changes in the physical device parameters must be reflected in the model used to simulate the power electronics product. Therefore, the third-layer controller 300 must identify and optimize model parameters based on various historical data stored in data storage and transmitted by the first-layer controller and second-layer controller through an identification model and an identification algorithm. When model parameters need to be updated, the third-layer controller outputs the relevant updated model parameters to the identification algorithm in the second-layer controller, thereby completing the replacement and update of the model parameters.

[0062] On the other hand, because power electronics products are physical devices that actually exist, if data diagnosis reveals that the hardware performance of the physical device simulated by the third-layer controller has changed significantly, and if it is discovered that this will affect the normal use of the physical device, the parameters that have changed significantly must be fed back to the first-layer controller in a timely manner, and the hardware status of the power electronics product must be diagnosed based on the model parameters identified by the third-layer controller through component diagnosis by the first-layer controller.

[0063] The above describes a specific implementation of the multi-layer control system and method for power electronic products provided by the present invention. The present invention utilizes the high computing power characteristics of the second layer in a distributed multi-layer control architecture to provide relevant information such as control targets, limiting conditions, and control corrections to the first layer in the distributed multi-layer control architecture, thereby improving the performance of the overall control software. In a preferred embodiment with a third-layer controller, the large-scale data processing capabilities and intelligent algorithm iterative optimization capabilities of the third layer in the distributed multi-layer control architecture are utilized to provide relevant information for long-term monitoring and control to the first layer in the distributed multi-layer control architecture, and relevant information such as model parameter optimization and algorithm parameter optimization to the second layer in the distributed multi-layer control architecture, thereby improving the performance of the overall control software.

[0064] The present invention is particularly applicable to the automotive field, and the multi-layer architecture can correspond to the controller (first layer) of an on-board power electronics product and the on-board computer (second layer). The third layer controller can also correspond to the cloud. The present invention can indirectly achieve a cost reduction method for high-performance controllers by utilizing resources other than the controller of the power electronics product (resources such as other on-board controllers, on-board computers, and the cloud) to optimize the performance (control accuracy, system power, system efficiency, robustness, etc.) of the controller (the controller remains the same even when using a chip).

[0065] Current controllers for power electronics products are subject to cost constraints, and the controller MCU has difficulty applying smart algorithms and complex models, making it difficult to achieve performance optimization control.Based on the multi-layer control architecture proposed by this invention, performance optimization control of the controller can be achieved by utilizing resources other than the controller and transmitting data via external communication, without changing the controller hardware, i.e., the cost.

[0066] Specifically, current power electronics products need to improve their performance (e.g., efficiency) to meet higher industrial goals, but meeting these demands is currently difficult. One way to improve system performance using software is to operate the system in its best performance region (e.g., highest efficiency) through optimization control. To operate the system in its best performance region in real time, online optimization control is required using several smart algorithms, mechanism models, and data models. Here, the parameters of the mechanism model and data model are obtained offline, but degradation may occur in the control system over time. Therefore, model parameters must be identified online based on the controller's long-term information and replaced in the mechanism model or data model. Therefore, we define traditional PI closed-loop control as the first layer, optimization control as the second layer, and parameter identification optimization using models in optimization control as the third layer. Current controllers have the problem of using MCU resources, so they can only complete the first layer, and it is difficult to complete the second and third layers. The second layer must constantly set control reference values in the first layer and has certain requirements for communication time, so the second layer must be installed in the vehicle (in a controller that can support SOA services). The third layer does not have requirements for communication time, but requires large amounts of data storage, so it can be installed either in the vehicle or in the cloud.

[0067] According to the present invention, the functions of the power electronics product software can be enriched, the performance of the power electronics product software can be improved, the performance requirements of the power electronics product software control chip can be reduced, and the cost of the product can be reduced.

[0068] Another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, realizes the steps of the multi-layer control method for power electronic products described in any one of the above embodiments. For details, please refer to the above description and do not repeat the process here. It should be understood that the above-mentioned computer-readable storage medium may be in the form of a system, i.e., it may include multiple computer-readable storage sub-media (corresponding to multiple layers), and these multiple computer-readable storage media can jointly realize the steps of the above-mentioned multi-layer control method for power electronic products.

[0069] The various illustrative logic modules and circuits described in connection with the embodiments disclosed herein may be implemented or performed by a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as, for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0070] The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integrated into the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as separate components in a user terminal.

[0071] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted by a computer-readable medium as one or more instructions or code. Computer-readable media includes both computer storage media and communication media, including any medium that enables a computer program to be transferred from one place to another. A storage medium may be any available medium that can be accessed by a computer. For example, and not as a limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is also properly termed a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair cable, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, the coaxial cable, fiber optic cable, twisted pair cable, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, "disk" and "disc" include compressed disks (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs; while "disks" often reproduce data magnetically, "discs" reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0072] The above description is provided to enable any person skilled in the art to practice the various aspects described herein. However, it should be understood that the scope of protection of the present invention should be governed by the appended claims and should not be limited to the specific configurations and components of the above-described embodiments. Those skilled in the art can make various changes and modifications to each embodiment within the spirit and scope of the present invention, and these changes and modifications are also included in the scope of protection of the present invention. [Explanation of symbols]

[0073] 100 First-tier controller 110 Data Sampling 120 Control Algorithm 130 Drive Generation 140 Parts Diagnosis 200 Second-tier controller 210 Smart Algorithms 220 Mechanism Model 230 Data Model 300 Third-tier controller 310 Data Storage 320 Identification Algorithm 330 Parameter Transmission 340 Identification Model 350 Data Diagnosis

Claims

1. A multi-layer control system for a power electronics product, comprising: the multi-layer control system comprises at least a first-layer controller and a second-layer controller; The first layer controller acquires a first state signal obtained by the power electronics product in response to sensor detection, and transmits the first state signal to the second layer controller; and configured to receive a control reference signal fed back from the second layer controller, generate a control signal for the power electronics product based on the control reference signal, and output the control signal to the power electronics product; the second layer controller acquires a second state signal other than the first state signal in the power electronics product based on the first state signal and a model that simulates the power electronics product; and configured to generate the control reference signal based on the first state signal, the second state signal, and a control target of the power electronics product, and output the control reference signal to the first layer controller.

2. further comprising a third layer controller; the third layer controller is configured to identify and optimize model parameters of the model based on a historical first state signal and a historical control signal fed back from the first layer controller and a historical second state signal and a historical control reference signal fed back from the second layer controller, and output the model parameters to the second layer controller; The multi-tier control system of claim 1 , wherein the second-tier controller is further configured to update the model based on the received model parameters.

3. 3. The multi-layer control system according to claim 2, wherein the third layer controller is further configured to, in response to a change in the model parameter exceeding a preset threshold, transmit the model parameter whose change exceeds the preset threshold to the first layer controller, and cause the first layer controller to diagnose a hardware state of the power electronics product based on the model parameter.

4. The model for simulating the power electronics product in the second layer controller comprises a mechanism model and / or a big data model; the mechanism model is a mathematical / physical model that simulates the power electronics product to obtain, as the second state signal, a simulation state variable of the power electronics product other than the first state signal based on the first state signal; 3. The multi-layer control system according to claim 1, wherein the big data model represents a mapping relationship between a first state signal and / or the simulation state variable of the power electronics product and a predicted state variable of the power electronics product, and outputs the predicted state variable as the second state signal according to the first state signal and / or the simulation state variable.

5. 5. The multi-layer control system of claim 4, wherein the third-layer controller is further configured to identify and optimize model parameters of the mathematical-physical model and / or the big data model, and output the model parameters to the second-layer controller.

6. In response to the model comprising the mechanism model and the big data model, the second layer controller further: obtaining the simulation state variables from the first state signal and the mechanism model; inputting the first state signal and the simulation state variable into the big data model, and obtaining the predicted state variable as the second state signal; The multi-layer control system of claim 4, further comprising: a control reference signal generating unit configured to generate the control reference signal according to a second state signal output by the big data model.

7. 5. The multi-layer control system of claim 4, wherein the multi-layer control system is applied to a vehicle, the first layer controller is a power electronics product controller of the vehicle, the second layer controller is an on-board computing unit of the vehicle, and the third layer controller is a cloud controller that corresponds one-to-one with the vehicle.

8. The first layer controller obtains a first state signal of the power electronics product according to the sensor detection; a second layer controller obtains a second state signal other than the first state signal of the power electronics product based on the first state signal and a model that simulates the power electronics product; the second layer controller generates a control reference signal based on the first state signal, the second state signal, and a control target of the power electronics product; The first layer controller generates a control signal for the power electronics product based on the control reference signal and outputs the control signal to the power electronics product.

9. The third layer controller further identifies and optimizes model parameters of the model based on the historical first state signal and the historical control signal fed back from the first layer controller and the historical second state signal and the historical control reference signal fed back from the second layer controller; The multi-layer control method according to claim 8, further comprising: causing the second layer controller to update the model based on the model parameters.

10. 10. The multi-layer control method according to claim 9, wherein the third layer controller further transmits, to the first layer controller, the model parameters whose changes exceed the predetermined threshold in response to the change in the model parameters exceeding the predetermined threshold, and causes the first layer controller to diagnose a hardware state of the power electronics product based on the model parameters.

11. The model for simulating the power electronics product in the second layer controller comprises a mechanism model and / or a big data model; the mechanism model is a mathematical / physical model that simulates the power electronics product to obtain, as the second state signal, a simulation state variable of the power electronics product other than the first state signal based on the first state signal; The multi-layer control method according to claim 8 or 9, characterized in that the big data model represents a mapping relationship between a first state signal and / or the simulation state variable of the power electronics product and a predicted state variable of the power electronics product, and outputs the predicted state variable as the second state signal according to the first state signal and / or the simulation state variable.

12. The second layer controller acquiring the second state signal in response to the model comprising the mechanism model and the big data model further comprises: obtaining the simulation state variables from the first state signal and the mechanism model; inputting the first state signal and the simulation state variables into the big data model and obtaining the predicted state variables as the second state signal; The multi-layer control method according to claim 11 , wherein the second layer controller generates a control reference signal based on the control reference signal as a second state signal output by the big data model.

13. A computer-readable storage medium storing a computer program, A computer-readable storage medium, characterized in that, when the computer program is executed by a processor, it realizes the steps of the multilayer control method for power electronic products according to any one of claims 8 to 12.

Images