Heating and ventilation heat supply dynamic control system

Abstract

The invention provides a heating ventilation heat supply dynamic control system, and relates to the technical field of heat supply system control, the heating ventilation heat supply dynamic control system comprises an equipment connection layer and a cloud processing layer, the equipment connection layer comprises a data acquisition module, a data transmission module and an instruction execution module, and the cloud processing layer comprises a data receiving module, an intelligent database and an instruction sending module. The intelligent database comprises a data storage unit, a data analysis unit and an instruction generation unit, the load state of the heating and ventilation equipment is obtained through a time sequence analysis algorithm in the data analysis unit, and optimized operation parameters are obtained through a self-adaptive genetic algorithm according to the load state; the method is based on a global optimization strategy, utilizes an intelligent algorithm, reduces manual intervention and avoids unnecessary energy waste, so that the overall energy utilization efficiency of the system is improved, energy consumption can be effectively reduced by reducing the output power or operation time of equipment when the load is relatively low, and quick response can be realized when the load is relatively high, so that the energy utilization efficiency of the system is improved. And stable operation of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of heating system control, and in particular to a heating and ventilation dynamic control system. Background Art

[0002] Heating, ventilation and air conditioning (HVAC) systems are essential core facilities in modern buildings. Their main function is to ensure the comfort and health of the indoor environment by regulating temperature, humidity and air quality. With the expansion of building scale and the increase in energy costs, the energy consumption of HVAC systems has become an important part of the total energy consumption of buildings, and the heating function in HVAC systems is one of its important components. It provides heat to the room by adjusting boilers, water pumps, valves and other equipment.

[0003] The heating system is an important part of ensuring indoor thermal comfort in modern buildings. Its main task is to transfer heat to each room through pipes or wind systems according to environmental conditions and user needs. With the continuous development of science and technology, people's living standards are also constantly improving, and at the same time, higher requirements are also put forward for the comfort of life. At present, most of the traditional HVAC heating control systems use manual control methods to control temperature, which will lead to the following situations:

[0004] (1) Traditional HVAC heating control usually adopts fixed operation logic and lacks dynamic response capability. Even if the load is reduced, the equipment still runs at a higher power, resulting in energy waste;

[0005] (2) Due to the use of manual control, the real-time response to the external environment (such as changes in outdoor temperature and humidity) is slow, resulting in unstable system operation under high load and excessive equipment operation under low load;

[0006] (3) Currently, traditional HVAC heating control is usually based on the independent adjustment of a single device rather than the coordinated adjustment of the entire system. As a result, some equipment may be overloaded or idle, which is not conducive to balancing the overall system performance and reducing energy efficiency. Therefore, the present invention proposes a HVAC heating dynamic control system to solve the problems existing in the prior art. Summary of the invention

[0007] In view of the above problems, the purpose of the present invention is to propose a dynamic control system for HVAC and heating, which has the function of dynamically monitoring the system load status, responding to changes in the external environment and indoor demand in real time, and optimizing the operating parameters of each device by introducing intelligent algorithms, thereby balancing the energy efficiency and comfort of the entire system, and can solve the problems existing in the prior art.

[0008] To achieve the purpose of the present invention, the present invention is implemented through the following technical solutions: a HVAC heating dynamic control system, including a device connection layer and a cloud processing layer, the device connection layer interacts with the cloud processing layer through a network connection, the device connection layer includes a data acquisition module for real-time acquisition of HVAC equipment operation target parameters, a data transmission module for data interaction with the device connection layer, and an instruction execution module for controlling the HVAC equipment according to instructions, the cloud processing layer includes a data receiving module for receiving transmitted data, an intelligent database for analyzing and processing data, and an instruction issuing module for issuing control instructions according to the analysis results, the intelligent database includes a data storage unit for storing data, a data analysis unit for data model analysis, and an instruction generation unit for generating control instructions, the data analysis unit obtains the load state of the HVAC equipment through a time series analysis algorithm, and then obtains the optimized operating parameters according to the load state using an adaptive genetic algorithm.

[0009] A further improvement is that the data acquisition module includes a sensor unit connected to the HVAC equipment and a data gateway unit for aggregating data, and the sensor unit is connected to the data transmission module via the data gateway unit.

[0010] A further improvement is that the sensor unit includes a temperature sensor for monitoring indoor and outdoor temperatures, a humidity sensor for monitoring ambient humidity, a pressure sensor for monitoring pipeline pressure, a flow meter for monitoring pipeline water flow, and an electric energy meter for monitoring equipment energy consumption.

[0011] Further improvement is: the specific steps of obtaining the load state of HVAC equipment through the time series analysis algorithm are:

[0012] S1: Obtain load-related time series data from HVAC equipment and then process it;

[0013] S2: Divide the processed data into training set and test set;

[0014] S3: Based on the LSTM deep learning model, the training set is used for training, and the test set is used for testing after training to obtain the trained analysis model;

[0015] S4: Input the real-time collected HVAC equipment data into the analysis model to obtain the load status of the HVAC equipment;

[0016] S5: Use the support vector machine algorithm to classify the load status of HVAC equipment into low load, medium load and high load.

[0017] Further improvement is: according to the load state, the adaptive genetic algorithm is used to obtain the optimized operating parameters. The specific steps are:

[0018] SS1: Setting optimization targets for different load states;

[0019] SS2: Initialize the adaptive genetic algorithm model;

[0020] SS3: Input the load state into the adaptive genetic algorithm model, and after iterative calculation, obtain the optimized operating parameters.

[0021] A further improvement is that the data acquisition module also includes a time stamp unit.

[0022] A further improvement is that the data transmission module includes a wireless network unit for wireless communication and a data encryption unit for ensuring data security.

[0023] A further improvement is that the data receiving module includes a data receiving unit for receiving data, a data buffer unit for temporarily storing data, and a format conversion unit for format unification.

[0024] A further improvement is that the instruction execution module includes a PLC controller unit for controlling the operating status of the equipment and a device interface unit for connecting with the HVAC equipment.

[0025] A further improvement is that the target parameters include temperature, humidity, pressure, water flow, energy consumption and current.

[0026] The beneficial effects of the present invention are as follows: the present invention realizes intelligent control of system operation by introducing intelligent algorithms, thereby solving the problems of response lag, low energy efficiency and excessive manual intervention existing in the prior art. Therefore, under the dynamic monitoring system load state, it can respond to changes in the external environment and indoor demand in real time, and according to such changes, optimize the equipment operation parameters through adaptive genetic algorithms, balance the system energy efficiency and comfort, and achieve the effect of saving system energy. Therefore, the HVAC heating dynamic control system provided by the present invention is based on a global optimization strategy and utilizes intelligent algorithms to reduce manual intervention and avoid unnecessary energy waste, thereby improving the overall energy utilization efficiency of the system. When the load is low, energy consumption can be effectively reduced by reducing the output power or operating time of the equipment, and when the load is high, it can respond quickly to ensure the stable operation of the system.

[0027] To this end, the present invention effectively avoids the energy waste problem in traditional technologies through intelligent algorithms and optimization strategies, while significantly improving the operating efficiency and responsiveness of the system. It can achieve energy-saving operation under different load conditions and meet the needs of modern buildings for efficient and intelligent HVAC systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the system structure provided by the present invention. DETAILED DESCRIPTION

[0029] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0030] The following embodiments involve an LSTM deep learning model, which is a special recurrent neural network that can effectively solve the gradient vanishing and gradient exploding problems of traditional RNN in long sequence data processing. Therefore, it is widely used in processing time series data, natural language processing (NLP) and other tasks.

[0031] With the continuous advancement of science and technology and the continuous improvement of people's requirements for quality of life, HVAC dynamic control technology is developing in the direction of intelligence, collaboration and high efficiency and energy saving. However, traditional HVAC dynamic control methods have obvious limitations. For example, they usually only control a single HVAC device independently, but lack the perspective of global optimization of the system. This method often fails to meet actual needs when facing complex operating scenarios, and even leads to energy waste.

[0032] In traditional HVAC heating control systems (heating systems), the traditional method is usually to simply increase the power of the water pump when the load increases to increase the flow rate to meet the heating demand. However, this control method ignores the coordinated adjustment of other system components (such as valve opening, fan speed, etc.). In this process, increasing the power by only a single device may far exceed the actual load demand, resulting in unnecessary energy consumption. At the same time, without combining environmental parameters and system load status, the adjustment process often lags behind demand changes and cannot achieve real-time response.

[0033] Therefore, the present invention is based on Figure 1 As shown, a dynamic control system for HVAC heating is provided. Through real-time monitoring and intelligent adjustment of system load, this technology can achieve multiple goals such as energy saving and consumption reduction, improvement of comfort and intelligence level, etc.

[0034] Specifically, the system includes a device connection layer and a cloud processing layer. The device connection layer interacts with the cloud processing layer through a network connection. Therefore, the system consists of a device connection layer and a cloud processing layer. The two layers realize data collection, transmission, processing and command issuance through network interaction. The overall process is data collection, data transmission, data processing, command generation and command execution, building an intelligent, efficient and energy-saving HVAC dynamic control system.

[0035] The equipment connection layer includes a data acquisition module for real-time collection of HVAC equipment operation target parameters: the data acquisition module includes a sensor unit connected to the HVAC equipment and a data gateway unit for summarizing data. The sensor unit is connected to the data transmission module through the data gateway unit. Further, the sensor unit includes a temperature sensor for monitoring indoor and outdoor temperatures, a humidity sensor for monitoring ambient humidity, a pressure sensor for monitoring pipeline pressure, a flow meter for monitoring pipeline water flow, and an electric energy meter for monitoring equipment energy consumption. Correspondingly, the target parameters include temperature, humidity, pressure, water flow, energy consumption, and current. The data gateway unit supports multiple communication protocols (such as Modbus, BACnet, KNX), which summarizes the data of the sensor unit and sends it to the data transmission module through a unified interface. Furthermore, the data acquisition module also includes a timestamp unit, which marks the collection time for each group of collected data to ensure the timeliness of the data during processing. At the same time, according to the collection time, a time series of data can be formed, and these data are naturally converted into historical data as time accumulates.

[0036] Data transmission module used for data interaction with the device connection layer: it transmits the collected data from the device connection layer to the cloud processing layer to ensure the stability and real-time performance of data transmission. At the same time, the data transmission module includes a wireless network unit for wireless communication and a data encryption unit for ensuring data security.

[0037] Instruction execution module for controlling HVAC equipment according to instructions: The instruction execution module includes a PLC controller unit for controlling the operating status of the equipment and an equipment interface unit for connecting with the HVAC equipment. In the HVAC equipment, it includes a water pump inverter to adjust the operating frequency of the water pump. It also includes a valve actuator to control the opening of the valve and adjust the flow. It also includes a fan speed regulator to control the speed of the fan. After the adjustment is executed, the system monitors the results of the execution in real time through the data acquisition module, thereby forming a closed-loop control.

[0038] The cloud processing layer includes a data receiving module for receiving transmitted data: the data receiving module includes a data receiving unit for receiving data and decrypting it, and is also provided with a data cache unit for temporarily storing data and a format conversion unit for format unification. The data cache unit temporarily stores the received data to avoid transmission delays affecting subsequent analysis, while the format conversion unit is used to convert the acquired data format into a standardized format for easy processing.

[0039] Intelligent database for analyzing and processing data: The intelligent database includes a data storage unit for storing data, a data analysis unit for data model analysis, and an instruction generation unit for generating control instructions, wherein the data storage unit is used to store real-time data and historical data (such as temperature, humidity, load curve, etc.), and the data analysis unit obtains the load state of the HVAC equipment through the time series analysis algorithm, and then uses the adaptive genetic algorithm to obtain the optimized operating parameters according to the load state. Furthermore, the specific steps for obtaining the load state of the HVAC equipment through the time series analysis algorithm are as follows:

[0040] S1: Obtain load-related time series data from HVAC equipment and then process it. Processing means cleaning the data, dealing with outliers, missing values, and duplicate values ​​in historical data, and then downsampling the data. For example, compressing minute-by-minute data into hourly data to improve analysis efficiency. After that, the data is standardized, such as unifying the temperature into degrees Celsius and the flow into cubic meters per hour. Finally, time alignment is performed to ensure that all historical data are aligned along a unified time axis so that multi-dimensional association and modeling can be performed during analysis.

[0041] S2: Divide the processed data into training set and test set with a ratio of 8:2;

[0042] S3: Based on the LSTM deep learning model, the training set is used for training. Specifically, the number of network layers, the number of neurons in each layer, the learning rate, etc. are set for the LSTM deep learning model. The training set data is input into the model for model fitting. After training, the test set is used for testing. The model parameters are adjusted according to the test results to finally obtain the trained analysis model.

[0043] S4: Input the real-time collected HVAC equipment data into the analysis model, such as ambient temperature, humidity, and equipment status, to obtain the load status of the HVAC equipment. Accordingly, the obtained data is used as new input to generate subsequent results, which can be used as prediction results, so the future load change trend can be obtained;

[0044] S5: Use the support vector machine algorithm to classify the load status of the HVAC equipment into low load, medium load and high load. Low load means the predicted load value is less than 30% of the system capacity, medium load is 30% to 70%, and high load is greater than 70% of the system capacity.

[0045] And an instruction issuing module for issuing control instructions according to the analysis results: According to the load state, the adaptive genetic algorithm is used to obtain the optimized operating parameters. The specific steps are as follows:

[0046] SS1: Set optimization targets for different load states, i.e., under low load state, reduce the equipment operating power or shut down some equipment, such as reducing the operating frequency of the water pump or reducing the number of running equipment; under medium load state, maintain the current state; under high load state, increase the equipment operating power, such as increasing the water pump frequency, fan speed, etc.;

[0047] SS2: Initialize the adaptive genetic algorithm model, that is, in this algorithm, initialize the population, each individual represents a set of operating parameters (such as pump frequency, valve opening, fan speed), and randomly generate several sets of initial parameters (satisfying the constraints);

[0048] SS3: The load state is input into the adaptive genetic algorithm model, and after iterative calculation, the optimized operating parameters are obtained. For example, under low load conditions, the pump frequency is reduced to 30Hz and the valve opening is 20%. Under high load conditions, the pump frequency is increased to 60Hz and the valve opening is 80%. That is, under low load conditions, energy consumption is significantly reduced by reducing equipment output power or shortening operating time. Under high load conditions, it responds quickly to load changes to ensure efficient operation of the equipment and avoid system instability caused by overload.

[0049] Accordingly, the instruction issuing module sends the obtained operating parameters to the instruction execution module for corresponding adjustments to form a complete closed-loop control. Furthermore, with the monitoring of real-time data, continuous monitoring and control can be carried out. As the data increases, the system can continuously optimize the corresponding control strategy and reduce the need for manual intervention.

[0050] This system is applied to various buildings such as office buildings, hotels, shopping malls, hospitals, etc. For example, in an office building, the operating status of water pumps, valves and fans can be dynamically adjusted according to the density of people and work needs in different areas. For example, during peak working hours (such as 9 am to 5 pm), the air conditioning or heating power can be increased according to the predicted density of people; and during non-peak hours (such as lunch break or after get off work), the operating power of the equipment can be reduced to save energy.

[0051] Therefore, the present invention combines intelligent monitoring and optimization algorithms to dynamically adjust the operating status of heating equipment to achieve efficient load response and energy efficiency management. The system can not only avoid the common energy waste problem in traditional heating systems, but also improve operational stability and indoor thermal comfort, providing an effective solution for the green and energy-saving development of modern buildings.

[0052] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the framework and scope of application of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A dynamic control system for heating and ventilation, characterized in that: It includes a device connection layer and a cloud processing layer. The device connection layer interacts with the cloud processing layer through a network connection. The device connection layer includes a data acquisition module for real-time acquisition of HVAC equipment operation target parameters, a data transmission module for data interaction with the device connection layer, and an instruction execution module for controlling the HVAC equipment according to instructions. The cloud processing layer includes a data receiving module for receiving transmitted data, an intelligent database for analyzing and processing data, and an instruction issuing module for issuing control instructions according to analysis results. The intelligent database includes a data storage unit for storing data, a data analysis unit for data model analysis, and an instruction generation unit for generating control instructions. The data analysis unit obtains the load state of the HVAC equipment through a time series analysis algorithm, and then uses an adaptive genetic algorithm to obtain optimized operating parameters based on the load state.

2. A dynamic heating and cooling control system according to claim 1, characterized in that: The data acquisition module includes a sensor unit connected to the HVAC equipment and a data gateway unit for summarizing data, and the sensor unit is connected to the data transmission module through the data gateway unit.

3. A dynamic heating and cooling control system according to claim 1, characterized in that: The sensor unit includes a temperature sensor for monitoring indoor and outdoor temperatures, a humidity sensor for monitoring ambient humidity, a pressure sensor for monitoring pipeline pressure, a flow meter for monitoring pipeline water flow, and an electric energy meter for monitoring equipment energy consumption.

4. A dynamic heating and cooling control system according to claim 1, characterized in that: The specific steps to obtain the load status of HVAC equipment through the time series analysis algorithm are as follows: S1: Obtain load-related time series data from HVAC equipment and then process it; S2: Divide the processed data into training set and test set; S3: Based on the LSTM deep learning model, the training set is used for training, and the test set is used for testing after training to obtain the trained analysis model; S4: Input the real-time collected HVAC equipment data into the analysis model to obtain the load status of the HVAC equipment; S5: Use the support vector machine algorithm to classify the load status of HVAC equipment into low load, medium load and high load.

5. A dynamic heating and cooling control system according to claim 1, characterized in that: According to the load state, the specific steps of using adaptive genetic algorithm to optimize the operating parameters are as follows: SS1: Setting optimization targets for different load states; SS2: Initialize the adaptive genetic algorithm model; SS3: Input the load state into the adaptive genetic algorithm model, and after iterative calculation, obtain the optimized operating parameters.

6. A dynamic heating and cooling control system according to claim 1, characterized in that: The data acquisition module also includes a time stamp unit.

7. A dynamic heating and cooling control system according to claim 1, characterized in that: The data transmission module includes a wireless network unit for wireless communication and a data encryption unit for ensuring data security.

8. A dynamic heating and cooling control system according to claim 1, characterized in that: The data receiving module includes a data receiving unit for receiving data, a data buffer unit for temporarily storing data, and a format conversion unit for format unification.

9. A dynamic heating and cooling control system according to claim 1, characterized in that: The instruction execution module includes a PLC controller unit for controlling the operating state of the equipment and a device interface unit for connecting with the HVAC equipment.

10. A dynamic heating and cooling control system according to claim 1, characterized in that: The target parameters include temperature, humidity, pressure, water flow, energy consumption and current.

Images