Hardware-in-the-loop simulation platform and test method for controller of multi-split air-conditioning system

Abstract

The invention provides a multi-split air-conditioning system controller hardware-in-the-loop simulation platform and a test method. The multi-split air-conditioning system controller hardware-in-the-loop simulation platform comprises a multi-split air-conditioning system real-time simulation system, an AI controller system, a monitoring management system and a CAN-USB conversion module. The monitoring management system is used for receiving a test mode input by a user and receiving a target model parameter input by the user; the multi-split air conditioning system real-time simulation system is used for simulating real operation information of the multi-split air conditioning system according to the target model parameters; the AI controller system is used for generating target control information according to the operation information and feeding back the target control information to the multi-split air conditioning system real-time simulation system; the monitoring management system is also used for generating a corresponding state sequence according to the multiple pieces of operation information and the target control information corresponding to each piece of operation information, and determining a first test result of the AI controller system according to the state sequence; and the CAN-USB conversion module is used for connecting the multi-split air conditioning system real-time simulation system, the AI controller system and the monitoring management system.

Description

Technical Field

[0001] The present application relates to the technical field of simulation systems, and in particular to a hardware-in-the-loop simulation platform and a testing method for a controller of a multi-split air-conditioning system. Background Art

[0002] With the increasing development of artificial intelligence and big data technology, smart air conditioners have become a reality. Smart air conditioners can predict environmental changes by learning user habits, thereby providing a control method that meets user comfort and energy-saving requirements. This part of the control function is complex, and the operation method is fundamentally different from the internal and external units of the air conditioner. Therefore, this type of function is decoupled from the internal and external unit controllers to become an independent AI controller. In practical applications, in order to ensure the output effect of the AI ​​controller, it needs to be tested. Traditional multi-split air conditioning system AI controller testing methods are mostly physical tests on real air conditioning units.

[0003] However, this method of testing the AI ​​controller of the air-conditioning system through physical testing can provide control effects in a real physical environment, but because the algorithm design may not be perfect, there is a risk of operational failure of the experimental unit. At the same time, frequent physical testing is not conducive to the debugging of software algorithms and functional logic, resulting in a long development cycle. Summary of the invention

[0004] The present application provides a hardware-in-the-loop simulation platform and testing method for a multi-split air-conditioning system controller to solve the problem of experimental unit operation failure in the prior art of testing the air-conditioning system AI controller through physical testing. At the same time, frequent physical testing is not conducive to the debugging of software algorithms and functional logic, resulting in a problem of too long development cycle.

[0005] In a first aspect, the present application provides a hardware-in-the-loop simulation platform for a multi-split air conditioning system controller, the platform comprising: a multi-split air conditioning system real-time simulation system, an AI controller system, a monitoring management system, and a CAN-USB conversion module;

[0006] The monitoring management system is used to receive a test mode input by a user, and, when the test mode is a whole machine test, receive a target model parameter input by a user;

[0007] The multi-split air conditioning system real-time simulation system is used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters;

[0008] The AI ​​controller system is used to generate target control information according to the operation information, and feed back the target control information to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interaction processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0009] The monitoring management system is further used to generate a corresponding state sequence according to the multiple operation information in the multiple interaction process and the target control information corresponding to each of the operation information, and determine a first test result of the AI ​​controller system according to the state sequence;

[0010] The CAN-USB conversion module is used to connect the multi-split air-conditioning system real-time simulation system, the AI ​​controller system and the monitoring management system to achieve two-way data transmission among the multi-split air-conditioning system real-time simulation system, the AI ​​controller system and the monitoring management system.

[0011] In a possible implementation manner, the monitoring management system is further used to generate a specified working condition and a corresponding number of test cases when the test mode is a case test;

[0012] The AI ​​controller system is used to generate corresponding actual control information according to the specified working condition and the corresponding number of test cases, and feed back the actual control information to the monitoring management system;

[0013] The monitoring and management system is further used to determine a second test result of the AI ​​controller system based on the actual control information and the preset expected control information.

[0014] In a possible implementation, the monitoring and management system is further used to determine that the second test result is passed when the actual control information is consistent with the preset expected control information, and to determine that the second test result is failed when the actual control information is inconsistent with the preset expected control information.

[0015] In a possible implementation, the multi-split air conditioning system real-time simulation system includes: a first power supply module, a first real-time processor module, a multi-split air conditioning system model and a first CAN communication module;

[0016] The multi-split air conditioning system model is used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters;

[0017] The first real-time processor module is used to run the multi-split air conditioning system model;

[0018] The first CAN communication module is used to connect the first real-time processor module and the CAN-USB conversion module to achieve communication between the first real-time processor module and the AI ​​controller system and the monitoring management system;

[0019] The first power supply module is used to supply power to the first real-time processor module and the first CAN communication module.

[0020] In a possible implementation, the multi-split air conditioning system model includes a multi-split air conditioning unit model, a plurality of multi-split air conditioning indoor unit terminal models, and a building environment simulation model;

[0021] The multi-split air conditioning system model is used to simulate the energy efficiency of the multi-split air conditioning system under different loads, different temperatures, different high and low pressures, and different humidity;

[0022] A plurality of said multi-split air conditioner indoor unit terminal models are used to simulate the load changes of the indoor units of said multi-split air conditioner system under different indoor temperatures, different outdoor temperatures, different humidity and different wind speeds;

[0023] The building environment simulation model is used to simulate the changes in indoor temperature, heating and cooling loads and indoor humidity content under different building environments.

[0024] In a possible implementation, the AI ​​controller system includes: a second power supply module, a second real-time processor module, a control strategy, and a second CAN communication module;

[0025] The control strategy is used to generate target control information according to the operation information, and feed back the target control information to the multi-split air conditioning system real-time simulation system;

[0026] The second real-time processor module is used to run the control strategy;

[0027] The second CAN communication module is used to connect the second real-time processor module and the CAN-USB conversion module to achieve communication between the second real-time processor module and the multi-connected air conditioning system real-time simulation system and the monitoring management system;

[0028] The second power supply module is used to supply power to the second real-time processor module and the second CAN communication module.

[0029] In one possible implementation, the monitoring and management system is also used to generate a corresponding test room indoor temperature curve and a test whole machine energy consumption curve according to the state sequence, obtain a reference room indoor temperature curve and a reference whole machine energy consumption curve, and determine the first test result according to the test room indoor temperature curve, the reference room indoor temperature curve, the test whole machine energy consumption curve and the reference whole machine energy consumption curve.

[0030] In a second aspect, the present application provides a testing method, comprising:

[0031] A test mode for receiving user input;

[0032] When the test mode is a whole machine test, receiving target model parameters input by a user;

[0033] Using a real-time simulation system of a multi-split air conditioning system to simulate real operating information of the multi-split air conditioning system according to the target model parameters;

[0034] Utilize the AI ​​controller system to generate target control information according to the operation information, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interactive processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0035] According to the multiple operation information in the multiple interaction processes and the target control information corresponding to each of the operation information, a corresponding state sequence is generated, and a first test result of the AI ​​controller system is determined according to the state sequence.

[0036] In a possible implementation, the method further includes:

[0037] When the test mode is a case test, generating a specified working condition and a corresponding number of test cases;

[0038] Using the AI ​​controller system to generate corresponding actual control information according to the specified working condition and the corresponding number of test cases;

[0039] A second test result of the AI ​​controller system is determined according to the actual control information and the preset expected control information.

[0040] In a third aspect, the present application provides a testing device, comprising:

[0041] A mode receiving module, used for receiving a test mode input by a user;

[0042] A parameter receiving module, used for receiving target model parameters input by a user when the test mode is a whole machine test;

[0043] A simulation module, used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters using the real-time simulation system of the multi-split air conditioning system;

[0044] A generation module, used to generate target control information according to the operation information by using the AI ​​controller system, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interaction processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0045] A determination module is used to generate a corresponding state sequence according to multiple operation information in the multiple interaction processes and target control information corresponding to each of the operation information, and determine a first test result of the AI ​​controller system according to the state sequence.

[0046] In a fourth aspect, the present application provides a device, comprising: a processor and a memory, wherein the processor is used to execute a test program stored in the memory to implement the test method described in any one of the second aspects.

[0047] In a fourth aspect, the present application provides a storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the test method described in any one of the second aspects.

[0048] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the platform provided by the embodiment of the present application includes: a real-time simulation system for a multi-split air-conditioning system, an AI controller system, a monitoring and management system, and a CAN-USB conversion module; the monitoring and management system is used to receive a test mode input by a user, and, when the test mode is a whole-machine test, receive a target model parameter input by a user; the real-time simulation system for the multi-split air-conditioning system is used to simulate the actual operation information of the multi-split air-conditioning system according to the target model parameters; the AI ​​controller system is used to generate target control information according to the operation information, and feed the target control information back to the real-time simulation system of the multi-split air-conditioning system, so that the multi-split air-conditioning system The system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing the multiple interaction processes between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller system; the monitoring and management system is also used to generate corresponding state sequences according to the multiple operation information in the multiple interaction processes and the target control information corresponding to each of the operation information, and determine the first test result of the AI ​​controller system according to the state sequence; the CAN-USB conversion module is used to connect the real-time simulation system of the multi-split air-conditioning system, the AI ​​controller system and the monitoring and management system to realize two-way data transmission between the real-time simulation system of the multi-split air-conditioning system, the AI ​​controller system and the monitoring and management system. In this way, the control algorithm effect of the AI ​​controller can be verified through the continuous interaction between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller, which facilitates the design and adjustment of logic, algorithms and other work by developers, avoids frequent physical tests in the design stage, thereby shortening the development cycle and reducing development costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0051] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0052] Figure 1A schematic diagram of the structure of a hardware-in-the-loop simulation platform for a multi-split air conditioning system controller provided in an embodiment of the present application;

[0053] Figure 2 A flow chart of an embodiment of a testing method provided in an embodiment of the present application;

[0054] Figure 3 A block diagram of an embodiment of a testing device provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0058] In order to solve the problem that there is a risk of experimental unit operation failure when testing the AI ​​controller of the air-conditioning system through physical testing in the prior art, and at the same time, frequent physical testing is not conducive to the debugging of software algorithms and functional logic, resulting in a long development cycle, the present application provides a hardware-in-the-loop simulation platform for a multi-split air-conditioning system controller, which can verify the control algorithm effect of the AI ​​controller through continuous interaction between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller, facilitate developers to design and adjust logic, algorithms, etc., avoid frequent physical testing in the design stage, thereby shortening the development cycle and reducing development costs.

[0059] Figure 1 A schematic diagram of the structure of a hardware-in-the-loop simulation platform for a multi-split air-conditioning system controller provided in an embodiment of the present application.

[0060] like Figure 1As shown, the platform includes: a real-time simulation system for a multi-split air-conditioning system, an AI controller system, a monitoring management system, and a CAN-USB conversion module; the monitoring management system is used to receive a test mode input by a user, and, when the test mode is a whole-machine test, receive a target model parameter input by a user; the real-time simulation system for a multi-split air-conditioning system is used to simulate the actual operation information of the multi-split air-conditioning system according to the target model parameters; the AI ​​controller system is used to generate target control information according to the operation information, and feed the target control information back to the real-time simulation system of the multi-split air-conditioning system, so that the real-time simulation system of the multi-split air-conditioning system can generate target control information according to the operation information, and feed the target control information back to the real-time simulation system of the multi-split air-conditioning system, so that the real-time simulation system of the multi-split air-conditioning system can generate target control information according to the target control information Continue to simulate new operating information, thereby realizing multiple interactive processes between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller system; the monitoring and management system is also used to generate corresponding state sequences according to the multiple operating information in the multiple interactive processes and the target control information corresponding to each of the operating information, and determine the first test result of the AI ​​controller system according to the state sequence; the CAN-USB conversion module is used to connect the real-time simulation system of the multi-split air-conditioning system, the AI ​​controller system and the monitoring and management system, to realize two-way data transmission among the real-time simulation system of the multi-split air-conditioning system, the AI ​​controller system and the monitoring and management system.

[0061] The target model parameters are used to configure the parameters of the multi-split air-conditioning system real-time simulation system so that the multi-split air-conditioning system real-time simulation system can perform simulation based on the multi-split air-conditioning system real-time simulation system.

[0062] The operation information refers to the real operation environment outside the multi-split air-conditioning system simulated by the real-time simulation system of the multi-split air-conditioning system.

[0063] The state sequence refers to the sequence consisting of the working states of the indoor and outdoor units and the building environment of the multi-split air-conditioning system at different time sequences.

[0064] like Figure 1 As shown, the monitoring and management system runs in a PC, and the system includes a parameter configuration module, a data display module, and a test analysis module. Among them, the parameter configuration module includes a multi-split air-conditioning system model configuration unit, a serial communication configuration unit, and a test case generation unit. The multi-split air-conditioning system model configuration unit is used to configure the multi-split air-conditioning system whole machine model, n multi-split air-conditioning indoor unit terminal heat transfer models, and building environment simulation models according to the model parameter information input by the user. The serial communication configuration unit is used to configure the PC serial port communication, including the baud rate, data bit width, check bit, and control flow configuration. The data display module is used to receive the operation information of the real-time simulation system of the multi-split air-conditioning system and the control information of the AI ​​controller system and display them in real time.

[0065] Through the platform provided by the embodiment of the present application, the control algorithm effect of the AI ​​controller can be verified through continuous interaction between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller, which facilitates developers to design and adjust logic, algorithms, etc., avoids frequent physical experiments in the design phase, thereby shortening the development cycle and reducing development costs.

[0066] In another embodiment, the multi-split air-conditioning system real-time simulation system includes: a first power supply module, a first real-time processor module, a multi-split air-conditioning system model and a first CAN communication module; the multi-split air-conditioning system model is used to simulate the real operation information of the multi-split air-conditioning system according to the target model parameters; the first real-time processor module is used to run the multi-split air-conditioning system model; the first CAN communication module is used to connect the first real-time processor module and the CAN-USB conversion module to realize communication between the first real-time processor module and the AI ​​controller system and the monitoring and management system; the first power supply module is used to power the first real-time processor module and the first CAN communication module.

[0067] Among them, the multi-split air-conditioning system model includes a multi-split air-conditioning unit model, multiple multi-split air-conditioning indoor unit terminal models, and a building environment simulation model; the multi-split air-conditioning unit model is used to simulate the energy efficiency of the whole machine of the multi-split air-conditioning system under different loads, different temperatures, different high and low pressures, and different humidity; multiple multi-split air-conditioning indoor unit terminal models are used to simulate the changes in the indoor unit load of the multi-split air-conditioning system under different indoor temperatures, different outdoor temperatures, different humidity, and different wind speeds; the building environment simulation model is used to simulate the changes in indoor temperature, cold and hot loads, and indoor humidity content under different building environments.

[0068] In the embodiment of the present application, the multi-split air conditioner unit model is a function of the whole unit energy efficiency with respect to high / low pressure, indoor unit capacity, outdoor temperature, indoor unit capacity, and indoor temperature. The multi-split air conditioner indoor unit terminal model is a function of the capacity of each indoor unit with respect to indoor humidity, indoor temperature, indoor fan speed, and high / low pressure. The building environment simulation model is a function of the room load with respect to indoor temperature, indoor humidity, and outdoor temperature. Accordingly, the parameters to be configured for all models (i.e., target model parameters) are the coefficients in front of the variables formed by linear or nonlinear combination of these function independent variables.

[0069] Through the solution of the embodiment of the present application, the real-time simulation system of the multi-split air-conditioning system can realize the simulation process through the multi-split air-conditioning unit model, multiple multi-split air-conditioning indoor unit terminal models, and the building environment simulation model, avoiding the AI ​​controller from frequently conducting physical tests during the design stage, thereby shortening the development cycle and reducing development costs.

[0070] In another embodiment, the AI ​​controller system includes: a second power supply module, a second real-time processor module, a control strategy and a second CAN communication module; the control strategy is used to generate target control information according to the operation information, and feed back the target control information to the multi-split air-conditioning system real-time simulation system; the second real-time processor module is used to run the control strategy; the second CAN communication module is used to connect the second real-time processor module and the CAN-USB conversion module to achieve communication between the second real-time processor module and the multi-split air-conditioning system real-time simulation system and the monitoring and management system; the second power supply module is used to power the second real-time processor module and the second CAN communication module.

[0071] Among them, the target control information refers to the instructions generated by the AI ​​controller based on the simulated operation information, for example, the control instructions for the multi-connected indoor units (such as fan speed instructions) and the control instructions for the outdoor units (such as high / low voltage instructions).

[0072] Through this solution, the AI ​​controller can generate corresponding target control information based on the operating information simulated by the real-time simulation system of the multi-split air-conditioning system, thereby realizing the testing of the AI ​​controller.

[0073] In another embodiment, the monitoring and management system is also used to generate a corresponding test room indoor temperature curve and a test whole machine energy consumption curve according to the state sequence, obtain a reference room indoor temperature curve and a reference whole machine energy consumption curve, and determine the first test result according to the test room indoor temperature curve, the reference room indoor temperature curve, the test whole machine energy consumption curve and the reference whole machine energy consumption curve.

[0074] In this embodiment, the indoor temperature curve of the test room, the indoor temperature curve of the reference room, the energy consumption curve of the test whole machine and the energy consumption curve of the reference whole machine are displayed by the data display module, so that the staff can judge the corresponding test results according to these curves. Specifically, if the indoor temperature controlled by the AI ​​controller can be cooled to within the set temperature range, and the energy consumption of the whole machine is lower than that under the traditional control method, it means that the control effect of the AI ​​controller is better and the test is passed. Otherwise, it means that the effect of the AI ​​controller is worse and the test cannot be passed.

[0075] In the application, the data display module can also display system information in real time, such as the indoor temperature of each room, the capacity of the indoor unit, the speed of the indoor fan, the high / low pressure of the outdoor unit, the energy efficiency COP of the whole machine, the power saving, etc., so that the staff can fully understand the test situation.

[0076] For ease of understanding, the following is a unified description of the signal transmission process during the whole machine test:

[0077] In the multi-split air-conditioning system model configuration unit 3 in the monitoring and management system 1, parameter configuration is performed on the multi-split air-conditioning unit model 4, the n multi-split air-conditioning indoor unit terminal models 5, and the building environment simulation model 6 (the coefficients in front of the variables formed by linear or nonlinear combination of the model corresponding function independent variables), and the serial port communication configuration unit 7 is configured (such as baud rate, serial port number, data bits, check bits, control flow, etc.).

[0078] After the configuration is completed, the parameters of the three models of unit 3, unit 4 and unit 5 are organized into data frames in the form of CAN protocol messages and sent to the CAN bus 13 through the USB interface 11 and the CAN-USB conversion device 12. The real-time simulation system 14 of the multi-connected air conditioning system receives the signal through the CAN communication module 17 and interprets the frame content. Here, each frame content includes data and a check code. After receiving the frame content, the check code obtained by checking the data is compared with the received check code. If they are the same, it means that the reception is correct, otherwise it means that the data has changed during the transmission process, that is, the reception failed. If the reception is correct, a reception completion signal is sent to the CAN bus, otherwise a reception failure signal is sent.

[0079] After receiving, the received model parameters are converted into corresponding parameter values. As an example, the model parameter is a floating point data, that is, it needs 4 bytes to represent, and the CAN protocol can only be transmitted by bytes, that is, in the frame content, 4 consecutive bytes are a model parameter. For example, the value of a parameter is 16.2, and its hexadecimal representation is 40C19999. When CAN is transmitted, 40C19999 needs to be split into 4 bytes 40C1 99 99. At the receiving end, these 4 bytes need to be parsed into a floating point number, that is, 16.2.

[0080] These parameter values ​​are imported into the multi-split model respectively, and the models are all run on the real-time processor of the multi-split air conditioning system real-time simulation platform. After the model is run, the multi-split air conditioning system real-time simulation system sends the outdoor unit information (such as outdoor temperature, high / low pressure, etc.) and the indoor unit information (such as indoor temperature, indoor humidity, etc.) to the CAN bus. This information contains the information required by the AI ​​controller 21 (for example, the indoor temperature and relative humidity of each room at the current moment, the average indoor temperature at the previous moment, the total capacity of the indoor unit, and the outdoor temperature), as well as the information that the user wants to observe in the data display module 9 (for example, the indoor temperature of each room, the capacity of the indoor unit, the speed of the indoor fan, the high / low pressure of the outdoor unit, the energy efficiency COP of the whole machine, and the power saving).

[0081] After the AI ​​controller parses this information, it solves the optimal control command through control strategy 25. That is, after receiving the indoor temperature and relative humidity of each room at the current moment, the average indoor temperature at the previous moment, the total capacity of the indoor unit, and the outdoor temperature, the AI ​​controller calculates based on this information and outputs the control command (i.e., target control information) for the high / low pressure of the external unit and the wind speed of each indoor unit. Then, the control command is sent to the real-time simulation system of the multi-split air conditioning system via the CAN bus. Subsequently, the three models of the real-time simulation system of the multi-split air conditioning system adjust their working states according to the control command to form a closed loop.

[0082] By repeating the above process, we can obtain the control instruction sequences of the AI ​​controller with different time sequences and the state sequences of the indoor and outdoor units and the building environment on the multi-split air conditioning system. By analyzing these state sequences, we can comprehensively evaluate the control effect of the control strategy on the AI ​​controller and form a test conclusion.

[0083] In another embodiment, the monitoring and management system is further used to generate specified operating conditions and a corresponding number of test cases when the test mode is a use case test; the AI ​​controller system is used to generate corresponding actual control information according to the specified operating conditions and the corresponding number of test cases, and feed back the actual control information to the monitoring and management system; the monitoring and management system is further used to determine a second test result of the AI ​​controller system based on the actual control information and preset expected control information.

[0084] Specifically, the monitoring and management system is also used to determine that the second test result is passed when the actual control information is consistent with the preset expected control information, and to determine that the second test result is failed when the actual control information is inconsistent with the preset expected control information.

[0085] In the application, the information required by the AI ​​controller system includes the current indoor temperature and relative humidity of each room, the average indoor temperature at the previous moment, the total capacity of the indoor units, and the outdoor temperature. Correspondingly, the specified working condition is to specify these variables as a certain value, among which the specific value can be set by the user according to actual needs.

[0086] For example, generate 3 specified working conditions with a quantity of 1. This working condition is applicable to the situation where one outdoor unit drives two indoor units, as shown in the following table:

[0087]

[0088] In this embodiment, the test case generation unit can generate a single or multiple independent test cases, which are transmitted to the communication device in the form of a message to perform a test case test on the AI ​​controller. Here, the generated test cases are only received by the AI ​​controller, which runs the control strategy according to the information in the test cases and returns the control signal (i.e., the actual control information) to the monitoring and management system. The test analysis module in the monitoring and management system compares the actual control information fed back after the test cases are input into the AI ​​controller and the expected control information (i.e., the expected control information is calculated by the PC based on the information in the test cases), that is, compares the ideal control effect and the actual control effect to obtain the test conclusion. During this process, the real-time simulation system of the multi-split air conditioning system does not work, and only the monitoring and management system and the AI ​​controller system are on the CAN bus.

[0089] It should be noted that the control instructions returned by the AI ​​controller are obtained by optimizing the optimization algorithm of the control strategy according to the current internal and external machine information and environmental information. The ideal control effect refers to the optimization result obtained by running the algorithm in the AI ​​controller on the PC. Because the test case is to check whether the calculation of the AI ​​controller is correct, but its calculation accuracy is not as good as that of the PC. Therefore, by comparing whether the two calculation results are close, you can know whether the AI ​​controller calculation is correct. You can set the digit after the decimal point to be the same, and it can be considered that the calculation result of the AI ​​controller is correct under this test case.

[0090] Through this solution, users can flexibly set specified working conditions according to actual needs, thereby realizing use case testing of the AI ​​controller system. The testing process is simple, efficient, and has low operating costs.

[0091] For ease of understanding, the following is a unified description of the signal transmission process during the use case test:

[0092] In the multi-split air conditioning system model configuration unit 3 in the monitoring and management system 1, the serial communication configuration unit 7 is configured. Specifically, it can be configured through the Qt host computer programming language. The following are respectively configured as the serial port to COM5, the serial port baud rate to 9600bit, the data bit to 8bit, the stop bit to 1bit, and no parity bit.

[0093] QSerialPort->setPortName('COM5');

[0094] QSerialPort->setBaudRate(9600);

[0095] QSerialPort->setDataBits(QSerialPort::Data8);

[0096] QSerialPort->setStopBits(QSerialPort::OneStop);

[0097] QSerialPort->setParity(QSerialPort::NoParity).

[0098] In the test case generation unit, enter the user-specified working conditions, such as indoor temperature, outdoor temperature, indoor humidity, etc. If you want to generate multiple test cases, you can make a variable change in accordance with a specific rule, such as "linear increase in outdoor temperature". It should be noted that by entering the specified upper and lower limits and the number of tests to be generated, multiple test cases can be generated.

[0099] After these test cases are generated, they will be packaged into corresponding external machine information (such as the average indoor temperature at the last moment, the total capacity of the internal machine), internal machine information (such as the current indoor temperature, the current relative humidity), and environmental information (such as the current outdoor temperature), and sent to the CAN bus 13 through the USB interface 11 and the CAN-USB conversion device 12. At this time, the multi-split air conditioning system real-time simulation system does not work, and only the AI ​​controller receives these CAN signals. After the AI ​​controller parses these signals, it solves the optimal control instructions through the control strategy 25 and sends the instructions to the monitoring management system. The test analysis module 10 obtains the test conclusion of the corresponding test case by comparing the control instructions returned by the AI ​​controller with the ideal control effect.

[0100] Figure 2 The following is a flow chart of an embodiment of a test method provided in the present application. Figure 1 As shown, the method comprises the following steps:

[0101] Step 201, receiving a test mode input by a user;

[0102] Step 202: When the test mode is a whole machine test, receiving target model parameters input by a user;

[0103] Step 203, using the multi-split air conditioning system real-time simulation system to simulate the actual operation information of the multi-split air conditioning system according to the target model parameters;

[0104] Step 204: using the AI ​​controller system to generate target control information according to the operation information, and feeding back the target control information to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interaction processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0105] Step 205: Generate a corresponding state sequence according to the multiple operation information in the multiple interaction process and the target control information corresponding to each of the operation information, and determine a first test result of the AI ​​controller system according to the state sequence.

[0106] From the above description, it can be seen that this solution can verify the control algorithm effect of the AI ​​controller through the continuous interaction between the real-time simulation system of the multi-split air-conditioning system and the AI ​​controller, which is convenient for developers to design and adjust logic, algorithms, etc., and avoids frequent physical tests in the design stage, thereby shortening the development cycle and reducing development costs.

[0107] In another embodiment, the method may further include the following steps: when the test mode is a use case test, generating specified operating conditions and a corresponding number of test cases; using the AI ​​controller system to generate corresponding actual control information according to the specified operating conditions and the corresponding number of test cases; and determining a second test result of the AI ​​controller system according to the actual control information and preset expected control information.

[0108] Through the above solution, users can flexibly set the specified working conditions according to actual needs, thereby realizing the use case test of the AI ​​controller system. The testing process is simple, efficient and low in operating cost.

[0109] For ease of understanding, combined Figure 1 The platform structure explains the test method in detail:

[0110] 1) The user first selects the test method for the AI ​​controller, which is "whole machine operation test" or independent "use case test";

[0111] 2) If it is a "whole machine operation test", then the parameter configuration module 2 in the monitoring management system 1 in the PC is configured, that is, the multi-split air conditioning system model configuration unit 3 is configured;

[0112] 3) If it is a "use case test", the test case generation unit generates test cases with the specified working conditions and the corresponding number;

[0113] 4) Configure the serial communication configuration unit 7, select the baud rate, serial port, data bit, check bit, and control flow;

[0114] 5) The parameters configured in step 2) or the test cases generated in step 3) are sent to the CAN bus 13 via the CAN-USB module 12. The parameters configured in step 2) are only received by the multi-split air conditioning system real-time simulation system 14 via the CAN communication module 17, and the configuration completion information is returned to the monitoring management system 1. The test cases generated in step 3) are only received by the AI ​​controller 21. The AI ​​controller 21 runs the control strategy 25 according to the information in the test cases, and returns the control signal to the monitoring management system 1. The test analysis module 10 of the monitoring management system analyzes the results of the test cases. During this process, the multi-split air conditioning system real-time simulation system does not work, and only the monitoring management system and the AI ​​controller system are on the CAN bus.

[0115] 6) If it is a "whole machine operation test", after the model configuration is completed, the real-time simulation system of the multi-split air-conditioning system forms a closed-loop linkage with the AI ​​controller, and the display module 9 of the monitoring and management system displays the corresponding system information in real time.

[0116] Thus, the testing process of the AI ​​controller is realized.

[0117] Figure 3 This is a block diagram of an embodiment of a test device provided in an embodiment of the present application. Figure 3 As shown, the device comprises:

[0118] A mode receiving module 31 is used to receive a test mode input by a user;

[0119] A parameter receiving module 32, used for receiving target model parameters input by a user when the test mode is a whole machine test;

[0120] A simulation module 33, used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters using the real-time simulation system of the multi-split air conditioning system;

[0121] A generating module 34 is used to generate target control information according to the operating information by using the AI ​​controller system, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operating information according to the target control information, thereby realizing multiple interactive processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0122] The determination module 35 is used to generate a corresponding state sequence according to the multiple operation information in the multiple interaction process and the target control information corresponding to each of the operation information, and determine the first test result of the AI ​​controller system according to the state sequence.

[0123] like Figure 4As shown, an embodiment of the present application provides a device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0124] Memory 113, used for storing computer programs;

[0125] In one embodiment of the present application, the processor 111 is used to implement the test method provided by any one of the above method embodiments when executing the program stored in the memory 113, including:

[0126] When the test mode is a whole machine test, receiving target model parameters input by a user;

[0127] Using a real-time simulation system of a multi-split air conditioning system to simulate real operating information of the multi-split air conditioning system according to the target model parameters;

[0128] Utilize the AI ​​controller system to generate target control information according to the operation information, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interactive processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system;

[0129] According to the multiple operation information in the multiple interaction processes and the target control information corresponding to each of the operation information, a corresponding state sequence is generated, and a first test result of the AI ​​controller system is determined according to the state sequence.

[0130] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the test method provided in any of the aforementioned method embodiments are implemented.

[0131] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0133] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0134] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A hardware-in-the-loop simulation platform for a multi-connected air conditioning system controller, characterized in that: The platform includes: a real-time simulation system for a multi-split air conditioning system, an AI controller system, a monitoring management system, and a CAN-USB conversion module; The monitoring management system is used to receive a test mode input by a user, and, when the test mode is a whole machine test, receive a target model parameter input by a user; The multi-split air conditioning system real-time simulation system is used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters; The AI ​​controller system is used to generate target control information according to the operation information, and feed back the target control information to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interaction processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system; The monitoring management system is further used to generate a corresponding state sequence according to the multiple operation information in the multiple interaction process and the target control information corresponding to each of the operation information, and determine a first test result of the AI ​​controller system according to the state sequence; The CAN-USB conversion module is used to connect the multi-split air-conditioning system real-time simulation system, the AI ​​controller system and the monitoring management system to achieve two-way data transmission among the multi-split air-conditioning system real-time simulation system, the AI ​​controller system and the monitoring management system.

2. The platform according to claim 1, characterized in that The monitoring management system is further used to generate a specified working condition and a corresponding number of test cases when the test mode is a case test; The AI ​​controller system is used to generate corresponding actual control information according to the specified working condition and the corresponding number of test cases, and feed back the actual control information to the monitoring management system; The monitoring and management system is further used to determine a second test result of the AI ​​controller system based on the actual control information and the preset expected control information.

3. The platform according to claim 2, characterized in that: The monitoring and management system is also used to determine that the second test result is passed when the actual control information is consistent with the preset expected control information, and to determine that the second test result is failed when the actual control information is inconsistent with the preset expected control information.

4. The platform according to claim 1, characterized in that The multi-split air conditioning system real-time simulation system comprises: a first power supply module, a first real-time processor module, a multi-split air conditioning system model and a first CAN communication module; The multi-split air conditioning system model is used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters; The first real-time processor module is used to run the multi-split air conditioning system model; The first CAN communication module is used to connect the first real-time processor module and the CAN-USB conversion module to achieve communication between the first real-time processor module and the AI ​​controller system and the monitoring management system; The first power supply module is used to supply power to the first real-time processor module and the first CAN communication module.

5. The platform according to claim 4, characterized in that The multi-split air conditioning system model includes a multi-split air conditioning unit model, multiple multi-split air conditioning indoor unit terminal models, and a building environment simulation model; The multi-split air conditioning system model is used to simulate the energy efficiency of the multi-split air conditioning system under different loads, different temperatures, different high and low pressures, and different humidity; A plurality of said multi-split air conditioner indoor unit terminal models are used to simulate the load changes of the indoor units of said multi-split air conditioner system under different indoor temperatures, different outdoor temperatures, different humidity and different wind speeds; The building environment simulation model is used to simulate the changes in indoor temperature, heating and cooling loads and indoor humidity content under different building environments.

6. The platform according to claim 1, characterized in that: The AI ​​controller system includes: a second power supply module, a second real-time processor module, a control strategy and a second CAN communication module; The control strategy is used to generate target control information according to the operation information, and feed back the target control information to the multi-split air conditioning system real-time simulation system; The second real-time processor module is used to run the control strategy; The second CAN communication module is used to connect the second real-time processor module and the CAN-USB conversion module to achieve communication between the second real-time processor module and the multi-connected air conditioning system real-time simulation system and the monitoring management system; The second power supply module is used to supply power to the second real-time processor module and the second CAN communication module.

7. The platform according to claim 1, characterized in that The monitoring and management system is also used to generate a corresponding test room indoor temperature curve and a test whole machine energy consumption curve according to the state sequence, obtain a reference room indoor temperature curve and a reference whole machine energy consumption curve, and determine the first test result according to the test room indoor temperature curve, the reference room indoor temperature curve, the test whole machine energy consumption curve and the reference whole machine energy consumption curve.

8. A testing method, characterized in that: The method comprises: A test mode for receiving user input; When the test mode is a whole machine test, receiving target model parameters input by a user; Using a real-time simulation system of a multi-split air conditioning system to simulate real operating information of the multi-split air conditioning system according to the target model parameters; Utilize the AI ​​controller system to generate target control information according to the operation information, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interactive processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system; According to the multiple operation information in the multiple interaction processes and the target control information corresponding to each of the operation information, a corresponding state sequence is generated, and a first test result of the AI ​​controller system is determined according to the state sequence.

9. The method according to claim 8, characterized in that The method further comprises: When the test mode is a case test, generating a specified working condition and a corresponding number of test cases; Using the AI ​​controller system to generate corresponding actual control information according to the specified working condition and the corresponding number of test cases; A second test result of the AI ​​controller system is determined according to the actual control information and the preset expected control information.

10. A testing device, characterized in that: The device comprises: A mode receiving module, used for receiving a test mode input by a user; A parameter receiving module, used for receiving target model parameters input by a user when the test mode is a whole machine test; A simulation module, used to simulate the real operation information of the multi-split air conditioning system according to the target model parameters using the real-time simulation system of the multi-split air conditioning system; A generation module, used to generate target control information according to the operation information by using the AI ​​controller system, and feed the target control information back to the multi-split air conditioning system real-time simulation system, so that the multi-split air conditioning system real-time simulation system continues to simulate new operation information according to the target control information, thereby realizing multiple interaction processes between the multi-split air conditioning system real-time simulation system and the AI ​​controller system; A determination module is used to generate a corresponding state sequence according to multiple operation information in the multiple interaction processes and target control information corresponding to each of the operation information, and determine a first test result of the AI ​​controller system according to the state sequence.

Images