Control strategy debugging system, method and device of central air conditioning system

Abstract

The invention relates to a control strategy debugging system, method and device of a central air conditioning system. The control strategy debugging system of the central air conditioning system comprises a virtual cold station and an AI intelligent control device. The virtual cold station is used for simulating operation of the real cold station to obtain real-time operation parameters; the AI intelligent control device is used for acquiring real-time operation parameters of the virtual cold station; predicting a target load of the virtual cold station based on the real-time operation parameters; performing dynamic parameter optimization based on the target load to obtain multiple groups of energy efficiency control strategies; and performing energy efficiency evaluation in the multiple groups of energy efficiency control strategies to obtain an optimal control strategy. According to the embodiment of the invention, actual debugging in an actual central air-conditioning system is not needed, all-working-condition energy-saving effect debugging and verification can be realized in a laboratory in a factory, the debugging efficiency is greatly improved, and the debugging period is shortened; operation experiment working conditions can be flexibly set, the energy-saving effect of different control strategy combinations is verified, the optimal control strategy is selected, and the operation energy efficiency of the central air-conditioning system is improved.

Description

Technical Field

[0001] The present application relates to the field of central air-conditioning systems, and in particular to a control strategy debugging system, method and device for a central air-conditioning system. Background Art

[0002] Central air conditioning systems usually account for 30%-50% of public building energy consumption, becoming the main battlefield for building energy conservation and carbon reduction. Improving the energy efficiency of air conditioning systems is an important way to reduce building energy consumption and carbon emissions. With the rapid development of artificial intelligence (AI) technology, its application in the field of HVAC is becoming more and more extensive. AI can accurately characterize the operating characteristics of equipment or systems based on massive operating data, and realize dynamic adjustment of system operating parameters to achieve energy-saving effects.

[0003] Central air conditioning systems are often large in scale and have different operating conditions. The actual building operation and commissioning time period is quite long, and it is difficult to obtain control and adjustment performance in different seasons and different operating conditions. Due to the actual situation, the air conditioning system cannot be adjusted arbitrarily, and it is difficult to obtain full operating condition control and adjustment performance. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a control strategy debugging system, method and device for a central air-conditioning system.

[0005] In a first aspect, the present application provides a control strategy debugging system for a central air conditioning system, including: a virtual cooling station and an AI intelligent control device;

[0006] The virtual cold station is used to simulate the operation of a real cold station to obtain real-time operating parameters;

[0007] The AI ​​intelligent control device is used to obtain real-time operating parameters of the virtual cooling station; predict the target load of the virtual cooling station based on the real-time operating parameters; perform dynamic parameter optimization based on the target load to obtain multiple sets of energy efficiency control strategies; perform energy efficiency evaluation among the multiple sets of energy efficiency control strategies to obtain the optimal control strategy.

[0008] Optionally, it also includes: a controller and a host computer;

[0009] The virtual cold station is further used to send the real-time operating parameters to the controller;

[0010] The controller is used to send the real-time operating parameters to the host computer;

[0011] The host computer is used to send the real-time operating parameters to the AI ​​intelligent control device.

[0012] Optionally, the host computer is further used to send optimization target parameters to the controller;

[0013] The controller is further used to send the optimization target parameter to the virtual cold station.

[0014] In a second aspect, the present application provides a control strategy debugging method for a central air conditioning system, comprising:

[0015] Obtain the real-time operating parameters of the virtual cold station;

[0016] predicting a target load of the virtual cooling station based on the real-time operating parameters;

[0017] Perform dynamic parameter optimization based on the target load to obtain multiple groups of energy efficiency control strategies;

[0018] Energy efficiency evaluation is performed among multiple groups of energy efficiency control strategies to obtain the optimal control strategy.

[0019] Optionally, predicting the target load of the virtual cooling station based on the real-time operating parameters includes:

[0020] The real-time operating parameters are input into a preset time series neural network prediction model so that the time series neural network prediction model outputs the target load of the virtual cooling station.

[0021] Optionally, dynamic parameter optimization is performed based on the target load to obtain multiple groups of energy efficiency control strategies, including:

[0022] Obtain multiple sets of target optimization parameters;

[0023] Obtain reliability control boundary conditions;

[0024] The target load, the target optimization parameters and the reliability control boundary conditions are sent to the virtual cooling station, so that the virtual cooling station simulates the operation of the real cooling station based on the target load and the reliability control boundary conditions according to each group of the target optimization parameters to obtain multiple groups of energy efficiency control strategies.

[0025] Optionally, energy efficiency evaluation is performed in multiple groups of energy efficiency control strategies to obtain an optimal control strategy, including:

[0026] Acquire a benchmark control strategy, perform energy efficiency evaluation on the benchmark control strategy, and obtain first energy efficiency evaluation data;

[0027] Performing energy efficiency evaluation on the optimal control strategy to obtain second energy efficiency evaluation data;

[0028] If the second energy efficiency evaluation data is better than the first energy efficiency evaluation data, determining the second energy efficiency evaluation data as the target control strategy of the group control system;

[0029] If the optimal control strategy is worse than the first energy efficiency evaluation data, the benchmark control strategy is determined as the target control strategy of the group control system.

[0030] In a third aspect, the present application provides a control strategy debugging device for a central air conditioning system, comprising:

[0031] A parameter acquisition module is used to obtain real-time operating parameters of the virtual cold station;

[0032] A load prediction module, configured to predict a target load of the virtual cooling station based on the real-time operating parameters;

[0033] A dynamic optimization module, used to perform dynamic parameter optimization based on the target load to obtain multiple groups of energy efficiency control strategies;

[0034] The energy efficiency evaluation module is used to evaluate the energy efficiency among multiple groups of energy efficiency control strategies and obtain the optimal control strategy.

[0035] Optionally, the load prediction module 12 includes:

[0036] The load prediction unit is used to input the real-time operating parameters into a preset time series neural network prediction model so that the time series neural network prediction model outputs the target load of the virtual cooling station.

[0037] Optionally, the dynamic optimization module 13 includes:

[0038] A first acquisition unit, used to acquire multiple sets of target optimization parameters;

[0039] A second acquisition unit is used to acquire reliability control boundary conditions;

[0040] The dynamic optimization unit is used to send the target load, the target optimization parameters and the reliability control boundary conditions to the virtual cooling station, so that the virtual cooling station simulates the operation of the real cooling station based on the target load and the reliability control boundary conditions according to each group of the target optimization parameters to obtain multiple groups of energy efficiency control strategies.

[0041] Optionally, the energy efficiency evaluation module 14 includes:

[0042] A third acquisition unit is used to acquire a benchmark control strategy, perform energy efficiency evaluation on the benchmark control strategy, and obtain first energy efficiency evaluation data;

[0043] An energy efficiency evaluation unit, used to perform energy efficiency evaluation on the optimal control strategy to obtain second energy efficiency evaluation data;

[0044] A first determining unit, configured to determine the second energy efficiency evaluation data as a target control strategy of a group control system if the second energy efficiency evaluation data is better than the first energy efficiency evaluation data;

[0045] The second determining unit is configured to determine the reference control strategy as the target control strategy of the group control system if the optimal control strategy is worse than the first energy efficiency evaluation data.

[0046] In a fourth aspect, the present application provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0047] Memory, used to store computer programs;

[0048] The processor is used to implement the control strategy debugging method of the central air-conditioning system described in any one of the second aspects when executing the program stored in the memory.

[0049] In a fifth aspect, the present application provides a computer-readable storage medium, on which is stored a program for a control strategy debugging method for a central air-conditioning system. When the program for the control strategy debugging method for a central air-conditioning system is executed by a processor, the steps of the control strategy debugging method for a central air-conditioning system described in any one of the second aspects are implemented.

[0050] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0051] The embodiment of the present application simulates the operation of a real cold station through a virtual cold station to obtain real-time operating parameters, predicts the target load of the virtual cold station based on the real-time operating parameters through an AI intelligent control device, performs dynamic parameter optimization based on the target load, and performs energy efficiency evaluation on the obtained multiple sets of energy efficiency control strategies to obtain the optimal control strategy. There is no need for actual debugging in the actual central air-conditioning system, and the energy-saving effect debugging and verification of all working conditions can be achieved in the factory laboratory, which greatly improves the debugging efficiency and shortens the debugging cycle. The operating experimental conditions can be flexibly set to verify the energy-saving effects of different control strategy combinations, select the optimal control strategy, and improve the operating energy efficiency of the central air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0053] In order to more clearly illustrate the embodiments of the present invention 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.

[0054] Figure 1A structural diagram of a control strategy debugging system for a central air-conditioning system provided in an embodiment of the present application;

[0055] Figure 2 A hardware structure diagram of a control strategy debugging system for a central air-conditioning system provided in an embodiment of the present application;

[0056] Figure 3 A flow chart of a control strategy debugging method for a central air-conditioning system provided in an embodiment of the present application;

[0057] Figure 4 A host computer display interface provided in an embodiment of the present application (mode 1: group control strategy adjustment);

[0058] Figure 5 The host computer display interface provided in the embodiment of the present application (mode 2: AI debugging);

[0059] Figure 6 A structural diagram of a control strategy debugging device for a central air conditioning system provided in an embodiment of the present application

[0060] Figure 7 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] 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.

[0062] Central air conditioning systems are often large in scale and have different operating conditions. The actual building operation debugging time period is quite long, and it is difficult to obtain control and adjustment performance in different seasons and different operating conditions. Due to the actual situation, the air conditioning system cannot be adjusted arbitrarily, and it is difficult to obtain full-condition control and adjustment performance. To this end, the embodiments of the present application provide a control strategy debugging system, method and device for a central air conditioning system.

[0063] The present application embodiment provides a control strategy debugging system for a central air conditioning system, which can be used as a debugging cabinet in practical applications, such as Figure 1 As shown, it includes: virtual cold station and AI intelligent control device;

[0064] Among them, the virtual cold station is not a real cold station, but it can simulate the operation of a real cold station. It can be used to carry out dynamic simulation and provide real-time feedback on the operation effect of the real cold station system. Real cold stations are widely used in computer rooms to provide cooling or heating for computer rooms, such as large shopping malls, office buildings, factories and other places that require a lot of cooling. Cold stations are usually located underground to avoid surface heat, but the machines will generate heat when they are running. When the weather is hot, the cold station supplies cooling to the building, and when it is cold, it supplies heating. The cold station uses the principles of cold and heat to achieve cooling and heating. The AI ​​intelligent control device has the functions of data storage, load forecasting, strategy optimization and effect evaluation.

[0065] The virtual cold station is used to simulate the operation of a real cold station to obtain real-time operating parameters;

[0066] The AI ​​intelligent control device is used to obtain real-time operating parameters of the virtual cooling station; predict the target load of the virtual cooling station based on the real-time operating parameters; perform dynamic parameter optimization based on the target load to obtain multiple sets of energy efficiency control strategies; perform energy efficiency evaluation among the multiple sets of energy efficiency control strategies to obtain the optimal control strategy.

[0067] The embodiment of the present application simulates the operation of a real cold station through a virtual cold station to obtain real-time operating parameters, predicts the target load of the virtual cold station based on the real-time operating parameters through an AI intelligent control device, performs dynamic parameter optimization based on the target load, and performs energy efficiency evaluation on the obtained multiple sets of energy efficiency control strategies to obtain the optimal control strategy. There is no need for actual debugging in the actual central air-conditioning system, and the energy-saving effect debugging and verification of all working conditions can be achieved in the factory laboratory, which greatly improves the debugging efficiency and shortens the debugging cycle. The operating experimental conditions can be flexibly set to verify the energy-saving effects of different control strategy combinations, select the optimal control strategy, and improve the operating energy efficiency of the central air-conditioning system.

[0068] In another embodiment of the present application, the control strategy debugging system of the central air-conditioning system further includes: a controller and a host computer; wherein the host computer has the functions of parameter setting and management, data monitoring, and control instruction issuance, and the controller has the functions of data collection and control instruction execution; in addition, the control strategy debugging system of the central air-conditioning system further includes: a building load module, which is used to provide building cooling load for virtual cooling station simulation;

[0069] The virtual cold station is further used to send the real-time operating parameters to the controller;

[0070] The controller is used to send the real-time operating parameters to the host computer;

[0071] The host computer is used to send the real-time operating parameters to the AI ​​intelligent control device.

[0072] In another embodiment of the present application, the host computer is further used to send optimization target parameters to the controller;

[0073] The controller is further used to send the optimization target parameter to the virtual cold station.

[0074] In practical applications, the physical structure of the control strategy debugging system of the central air-conditioning system is as follows Figure 2 As shown in the figure, during normal operation, 220V AC is converted into 24V DC via the circuit breaker, power controller, and power supply 1 to supply power to the control cabinet; if power supply 1 is abnormal, power supply 2 is enabled. It includes 5 modules, including AI intelligent control device, host computer, building load, virtual cold station, and controller. The modules are connected by wire by default, among which interfaces 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12 are RJ45 interfaces. If wired connection is not used, wireless connection methods such as 4G / 5G and WIFI can also be used. The communication protocol between modules is shown in Figure 1 .

[0075] On the basis of the above-mentioned embodiment, in another embodiment of the present application, a control strategy debugging method for a central air-conditioning system is also provided, which is applied to an AI intelligent control device, such as Figure 3 As shown, including:

[0076] Step S101, obtaining real-time operating parameters of the virtual cooling station;

[0077] Step S102, predicting the target load of the virtual cooling station based on the real-time operating parameters;

[0078] In this step, the real-time operating parameters can be input into a preset time series neural network prediction model so that the time series neural network prediction model outputs the target load of the virtual cooling station.

[0079] Step S103, performing dynamic parameter optimization based on the target load to obtain multiple sets of energy efficiency control strategies;

[0080] In this step, multiple groups of target optimization parameters can be obtained; reliability control boundary conditions can be obtained; the target load, the target optimization parameters and the reliability control boundary conditions are sent to the virtual cold station, so that the virtual cold station can simulate the operation of the real cold station based on the target load and the reliability control boundary conditions according to each group of the target optimization parameters to obtain multiple groups of energy efficiency control strategies.

[0081] Step S104: perform energy efficiency evaluation among multiple groups of energy efficiency control strategies to obtain an optimal control strategy.

[0082] In this step, a benchmark control strategy is obtained, and an energy efficiency evaluation is performed on the benchmark control strategy to obtain first energy efficiency evaluation data; an energy efficiency evaluation is performed on the optimal control strategy to obtain second energy efficiency evaluation data; if the second energy efficiency evaluation data is better than the first energy efficiency evaluation data, the second energy efficiency evaluation data is determined as the target control strategy of the group control system; if the optimal control strategy is worse than the first energy efficiency evaluation data, the benchmark control strategy is determined as the target control strategy of the group control system.

[0083] The embodiment of the present application simulates the operation of a real cooling station through a virtual cooling station to obtain real-time operating parameters, predicts the target load of the virtual cooling station based on the real-time operating parameters through an AI intelligent control device, performs dynamic parameter optimization based on the target load, and performs energy efficiency evaluation on the obtained multiple sets of energy efficiency control strategies to obtain the optimal control strategy. Without actual debugging in the actual central air-conditioning system, real-time operating parameters of different full working conditions can be obtained, and finally the optimal control strategy that can make the central air-conditioning system most energy efficient is obtained, thereby shortening the debugging cycle and improving debugging efficiency.

[0084] The central air-conditioning system AI intelligent control strategy debugging method and device proposed in the present invention can support two debugging modes: AI debugging and group control strategy, respectively realizing energy-saving algorithm verification and control parameter stability verification. The specific implementation methods are as follows:

[0085] When selecting mode 1: group control strategy debugging, the debugging setting interface is as follows Figure 4 , including functions such as cold station selection, building load, parameter setting, and visualization charts. At this time, the overall architecture includes building load module, virtual cold station, DDC / PLC controller, and host computer;

[0086] When selecting mode 2: AI debugging, the debugging setting interface is as follows Figure 5 , including functions such as cold station selection, building load, optimal setting, and visual charts. At this time, the overall architecture includes building load module, virtual cold station, DDC / PLC controller, host computer, and AI intelligent control device.

[0087] 1. AI debugging implementation method

[0088] Step 1: Cold Station Selection

[0089] This example takes the primary pump variable flow system as an example. Other central air conditioning system forms (including secondary pump (multi-stage pump) variable flow system, ice (water) storage system, multi-split system, etc.) are also within the protection scope. The system obtains the connection form of the cold station and the equipment model, quantity and other parameters to complete the cold station selection.

[0090] Step 2: Building Loads

[0091] Based on the project location, project type, building area, operating time and other parameters, the cooling load and dry-bulb temperature of the project are called through the cloud service interface; or the user manually enters the building load data, including date, cooling load, dry-bulb temperature, wet-bulb temperature, and supports common data formats such as txt, xls, and csv. After obtaining the building load, start the virtual cooling station.

[0092] Step 3: Optimizing parameters

[0093] The optimization target parameters are obtained, including the number of chillers, the number of cooling tower fans, the chilled water supply temperature, the chilled water supply and return temperature difference, the cooling water supply and return temperature difference, the approximation degree, etc. At the same time, the system obtains the limiting condition parameters, including the minimum load rate of the chiller load_min, the upper limit frequency of the water pump f_pump_max, the lower limit frequency of the water pump f_pump_min, the upper limit frequency of the cooling tower fan f_tower_max, the lower limit frequency of the cooling tower fan f_tower_min, and the optimization evaluation benchmark value I 临界 , cooling tower lower limit flow G_min, electricity price, carbon emission factor, etc. At the same time, the optimal control step length parameter is obtained, the unit is minute. If this item is not entered, the default is 10 minutes.

[0094] Step 4: Start debugging

[0095] After completing the settings of the first three steps, you can click Start Debugging.

[0096] After debugging begins, the DDC / PLC controller obtains the real-time operating parameters of the virtual cold station (the virtual cold station can be compared to the actual refrigeration room system. Similar to the actual refrigeration room, the operating parameters of the virtual cold station will also change during operation) through Modbus TCP / IP communication, and sends equipment start and stop commands, frequency setting values, valve opening and other control commands to the virtual cold station.

[0097] The host computer sends the optimal target parameter setting values, such as approach degree and cooling supply and return water temperature difference, to the DDC / PLC controller through Modbus TCP / IP communication. In addition, it is necessary to obtain the real-time operating parameters of the virtual cooling station from the DDC / PLC controller, such as frequency feedback, water temperature, load rate, meteorological parameters, etc. The operating parameters can be viewed through a visual chart interface.

[0098] The AI ​​intelligent control device includes four basic modules: database, load forecasting module, dynamic optimization module, and effect evaluation module (see Figure 5 ), read the real-time operating parameters of the cooling station and the data in step 3: optimizing parameters from the host computer.

[0099] 1) Real-time operating parameters are stored in the database for model training and predictive control;

[0100] 2) The load forecasting module obtains historical data from the database to complete load forecasting. Specifically, a time series neural network forecasting model is used, with the input parameters being date, cooling load, dry bulb temperature, and wet bulb temperature, and the output values being the predicted values of cooling load, dry / wet bulb temperature for the future "optimization control step length" duration (e.g., 10 min), which are used as the input for the dynamic optimization module.

[0101] 3) The dynamic optimization module, based on the checked values of the optimization objectives in Step 3: Optimization Settings (the optimization objectives include one or more of chiller unit number optimization, cooling tower fan unit number optimization, chilled water supply temperature optimization, chilled water supply and return temperature difference, cooling water supply and return temperature difference, approach temperature, etc.), traverses all combinations of different values of the optimization objective parameters, uses the reliable control boundary as the constraint condition, and predicts the energy efficiency, power consumption, and carbon emissions for all strategy combinations (the optimization objective parameters are called strategy combinations) that meet the constraint conditions for the future "optimization control step length" duration.

[0102] The reliable control boundary conditions are:

[0103] Condition 1: Strategies where the number of operating chillers cannot meet load_min < load < 100%.

[0104] Condition 2: The frequency of the chilled / cooling water pumps cannot exceed f_pump_max and cannot be less than f_pump_min.

[0105] Condition 3: The frequency of the cooling tower fans cannot exceed f_tower_max and cannot be less than f_tower_min.

[0106] Condition 4: The number of chiller units is equal to the number of chilled / cooling water pumps.

[0107] Condition 5: The number of cooling tower grade units cannot be less than the number of chiller units.

[0108] Condition 6: The cooling water flow rate / the number of cooling tower fans cannot be less than the cooling tower lower limit flow rate G_min.

[0109] All of the above conditions need to be met for the control strategy combination to meet the load constraint conditions.

[0110] 4) The effect evaluation module

[0111] In 3) the dynamic optimization module, the power consumption and energy efficiency of all strategy combinations that meet the constraint conditions will be obtained. Taking the optimization control of the cooling water supply and return temperature difference and the approach temperature as an example, the reference strategy A is the cooling water supply and return temperature difference and the approach temperature at the current moment, and the energy efficiency optimal strategy B is the strategy combination with the highest energy efficiency (i.e., the lowest power consumption) among all traversed combinations. The comprehensive evaluation model is as follows:

[0112] I = Q4 / Q B × f1 + CA / C B ×f2+E A / E B ×f3

[0113] f1, f2, f3: evaluation weight factors, f1+f2+f3=1

[0114] I: Optimization effect factor

[0115] C A , C B : The cost of running the future "optimal control step length" according to strategy A and strategy B;

[0116] E A 、E B : Carbon emissions from running the future "optimal control step length" according to Strategy A and Strategy B;

[0117] Q A , Q B : The power consumption of the future “optimal control step length” according to strategy A;

[0118] If I>I 临界 , then send strategy B to the group control, otherwise keep the original strategy of the group control unchanged, I 临界 The critical optimization effect is input by the user based on actual engineering requirements.

[0119] 2. Group Control Strategy Debugging Implementation Method

[0120] Step 1: Cold Plant Selection and Step 2: Building Load

[0121] Same as steps 1 and 2 of AI debugging implementation method.

[0122] Step 3: Group Control Strategy

[0123] The user can change the control parameter setting values ​​such as the chilled water supply temperature, chilled water supply and return temperature difference, cooling water supply and return temperature difference, approach degree, machine load rate, PID parameters, etc. on the host computer.

[0124] Step 4: Start debugging

[0125] After completing the settings of the first three steps, you can click Start Debugging.

[0126] This step is the same as step 4 of the AI ​​debugging implementation method, except that the group control strategy is input by the user on the host computer. The DDC / PLC controller obtains the real-time operating parameters of the virtual cold station and transmits them to the host computer visualization interface for display.

[0127] In another embodiment of the present application, a control strategy debugging device for a central air-conditioning system is also provided, which is applied to an AI intelligent control device, such as Figure 6 As shown, including:

[0128] The parameter acquisition module 11 is used to obtain the real-time operating parameters of the virtual cooling station;

[0129] A load prediction module 12, configured to predict a target load of the virtual cooling station based on the real-time operating parameters;

[0130] A dynamic optimization module 13, used to perform dynamic parameter optimization based on the target load to obtain multiple sets of energy efficiency control strategies;

[0131] The energy efficiency evaluation module 14 is used to perform energy efficiency evaluation among multiple groups of energy efficiency control strategies to obtain an optimal control strategy.

[0132] Optionally, the load prediction module 12 includes:

[0133] The load prediction unit is used to input the real-time operating parameters into a preset time series neural network prediction model so that the time series neural network prediction model outputs the target load of the virtual cooling station.

[0134] Optionally, the dynamic optimization module 13 includes:

[0135] A first acquisition unit, used to acquire multiple sets of target optimization parameters;

[0136] A second acquisition unit is used to acquire reliability control boundary conditions;

[0137] The dynamic optimization unit is used to send the target load, the target optimization parameters and the reliability control boundary conditions to the virtual cooling station, so that the virtual cooling station simulates the operation of the real cooling station based on the target load and the reliability control boundary conditions according to each group of the target optimization parameters to obtain multiple groups of energy efficiency control strategies.

[0138] Optionally, the energy efficiency evaluation module 14 includes:

[0139] A third acquisition unit is used to acquire a benchmark control strategy, perform energy efficiency evaluation on the benchmark control strategy, and obtain first energy efficiency evaluation data;

[0140] An energy efficiency evaluation unit, used to perform energy efficiency evaluation on the optimal control strategy to obtain second energy efficiency evaluation data;

[0141] A first determining unit, configured to determine the second energy efficiency evaluation data as a target control strategy of a group control system if the second energy efficiency evaluation data is better than the first energy efficiency evaluation data;

[0142] The second determining unit is configured to determine the reference control strategy as the target control strategy of the group control system if the optimal control strategy is worse than the first energy efficiency evaluation data.

[0143] In another embodiment of the present application, an electronic device is provided, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus;

[0144] Memory, used to store computer programs;

[0145] The processor is used to implement the control strategy debugging method of the central air-conditioning system described in any of the above method embodiments when executing the program stored in the memory.

[0146] In the electronic device provided by the embodiment of the present invention, the processor realizes the simulation of the operation of the real cold station through the virtual cold station by executing the program stored in the memory, obtains the real-time operation parameters, predicts the target load of the virtual cold station based on the real-time operation parameters through the AI ​​intelligent control device, performs dynamic parameter optimization based on the target load, and performs energy efficiency evaluation on the obtained multiple groups of energy efficiency control strategies to obtain the optimal control strategy. There is no need for actual debugging in the actual central air-conditioning system, and the energy-saving effect debugging and verification of all working conditions can be achieved in the factory laboratory, which greatly improves the debugging efficiency and shortens the debugging cycle; the operating experimental conditions can be flexibly set to verify the energy-saving effects of different control strategy combinations, select the optimal control strategy, and improve the operating energy efficiency of the central air-conditioning system.

[0147] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0148] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0149] The memory 1130 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0150] The above-mentioned processor 1110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0151] In another embodiment of the present application, a computer-readable storage medium is further provided, on which a program of a control strategy debugging method for a central air-conditioning system is stored. When the program of the control strategy debugging method for a central air-conditioning system is executed by a processor, the steps of the control strategy debugging method for a central air-conditioning system described in any of the aforementioned method embodiments are implemented.

[0152] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0153] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A control strategy debugging system for a central air conditioning system, characterized in that: include: Virtual cold station and AI intelligent control device; The virtual cold station is used to simulate the operation of a real cold station to obtain real-time operating parameters; The AI ​​intelligent control device is used to obtain real-time operating parameters of the virtual cooling station; and predict the target load of the virtual cooling station based on the real-time operating parameters; Dynamic parameter optimization is performed based on the target load to obtain multiple groups of energy efficiency control strategies; energy efficiency evaluation is performed among the multiple groups of energy efficiency control strategies to obtain the optimal control strategy.

2. The control strategy debugging system for the central air conditioning system according to claim 1 is characterized in that: Also includes: Controller and host computer; The virtual cold station is further used to send the real-time operating parameters to the controller; The controller is used to send the real-time operating parameters to the host computer; The host computer is used to send the real-time operating parameters to the AI ​​intelligent control device.

3. The control strategy debugging system for the central air conditioning system according to claim 2 is characterized in that: The host computer is also used to send optimization target parameters to the controller; The controller is further used to send the optimization target parameter to the virtual cold station.

4. A control strategy debugging method for a central air conditioning system, characterized in that: include: Obtain the real-time operating parameters of the virtual cold station; predicting a target load of the virtual cooling station based on the real-time operating parameters; Perform dynamic parameter optimization based on the target load to obtain multiple groups of energy efficiency control strategies; Energy efficiency evaluation is performed among multiple groups of energy efficiency control strategies to obtain the optimal control strategy.

5. The control strategy debugging method of the central air conditioning system according to claim 4, characterized in that: Predicting the target load of the virtual cooling plant based on the real-time operating parameters includes: The real-time operating parameters are input into a preset time series neural network prediction model so that the time series neural network prediction model outputs the target load of the virtual cooling station.

6. The control strategy debugging method of the central air conditioning system according to claim 4, characterized in that: Based on the target load, dynamic parameter optimization is performed to obtain multiple groups of energy efficiency control strategies, including: Obtain multiple sets of target optimization parameters; Obtain reliability control boundary conditions; The target load, the target optimization parameters and the reliability control boundary conditions are sent to the virtual cooling station, so that the virtual cooling station simulates the operation of the real cooling station based on the target load and the reliability control boundary conditions according to each group of the target optimization parameters to obtain multiple groups of energy efficiency control strategies.

7. The control strategy debugging method of the central air conditioning system according to claim 4, characterized in that: Energy efficiency evaluation is performed among multiple sets of energy efficiency control strategies to obtain the optimal control strategy, including: Acquire a benchmark control strategy, perform energy efficiency evaluation on the benchmark control strategy, and obtain first energy efficiency evaluation data; Performing energy efficiency evaluation on the optimal control strategy to obtain second energy efficiency evaluation data; If the second energy efficiency evaluation data is better than the first energy efficiency evaluation data, determining the second energy efficiency evaluation data as the target control strategy of the group control system; If the optimal control strategy is worse than the first energy efficiency evaluation data, the benchmark control strategy is determined as the target control strategy of the group control system.

8. A control strategy debugging device for a central air conditioning system, characterized in that: include: A parameter acquisition module is used to obtain real-time operating parameters of the virtual cold station; A load prediction module, configured to predict a target load of the virtual cooling station based on the real-time operating parameters; A dynamic optimization module, used to perform dynamic parameter optimization based on the target load to obtain multiple groups of energy efficiency control strategies; The energy efficiency evaluation module is used to evaluate the energy efficiency among multiple groups of energy efficiency control strategies and obtain the optimal control strategy.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the control strategy debugging method of the central air-conditioning system described in any one of claims 4 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program of a control strategy debugging method for a central air-conditioning system, and when the program of the control strategy debugging method for a central air-conditioning system is executed by a processor, the steps of the control strategy debugging method for a central air-conditioning system described in any one of claims 4-7 are implemented.

Images