Diagnostic control method for energy-saving operation of central air conditioning system

Abstract

The invention relates to the technical field of central air-conditioning control, and discloses a diagnosis control method for energy-saving operation of a central air-conditioning system, which comprises the following steps of: firstly, deploying an Internet of Things sensor array to collect multi-dimensional operation data; preprocessing the data, and removing abnormal values and the like; analyzing the credibility by using an evaluation model, and performing early warning and supplementary mining when the credibility does not reach the standard; diagnosing based on a preset diagnosis rule base, wherein the base comprises a threshold range and the like; and generating an energy-saving strategy according to a diagnosis result and executing through a closed-loop system. In addition, the method further comprises the characteristics of multi-dimensional synchronous acquisition, machine learning trend prediction, multi-target optimization model construction, automatic retriggering diagnosis, rule base self-updating, visual report generation and the like, so that energy-saving and efficient operation of the system is realized. The system has the advantages that energy efficiency optimization and energy-saving operation of the system are realized through multi-dimensional data acquisition, accurate diagnosis and intelligent control strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of central air-conditioning control, and specifically refers to a diagnostic control method for the energy-saving operation of a central air-conditioning system. Background Art

[0002] With the development of social economy and the improvement of building intelligence level, central air-conditioning systems are widely used in commercial buildings, public facilities and large industrial sites. However, the energy consumption of central air-conditioning systems is huge. According to statistics, its energy consumption accounts for 40%-60% of the total building energy consumption. The excessive energy consumption not only increases the operation cost, but also causes great pressure on the energy supply. Traditional central air-conditioning operation control methods mostly adopt fixed parameter setting and empirical control. For example, some systems only control the start and stop of the compressor based on fixed temperature thresholds, without considering the actual load dynamic changes, resulting in frequent start and stop of equipment or long-term low-load operation, causing energy waste. Some systems have simple frequency conversion adjustment functions, but lack a comprehensive evaluation of the energy efficiency of the entire system and cannot achieve the coordinated optimization of the chilled water system, cooling water system and terminal equipment.

[0003] Existing energy-saving diagnosis methods also have limitations. Some solutions rely on manual inspection and data analysis, with low efficiency and difficulty in capturing real-time changes; diagnostic models based on single parameters cannot comprehensively reflect the system operation status and are prone to misjudgment; the application of machine learning algorithms in energy-saving diagnosis often fails to play an effective role due to unstable data quality and poor model adaptability. For example, a commercial complex uses traditional diagnosis methods. Although it finds that the refrigeration efficiency has decreased, it fails to accurately locate the correlation between the cooling tower fan failure and the imbalance of chilled water flow, resulting in poor energy-saving renovation effects. Therefore, there is an urgent need for a diagnostic control method for the energy-saving operation of a central air-conditioning system that can monitor in real time, accurately diagnose and dynamically optimize, so as to improve the system energy efficiency and reduce the operation cost. Summary of the Invention

[0004] In order to solve the above various problems, the present invention proposes a diagnostic control method for the energy-saving operation of a central air-conditioning system, which realizes system energy efficiency optimization and energy-saving operation through multi-dimensional data collection, accurate diagnosis and intelligent control strategies.

[0005] To solve the above technical problems, the technical solution proposed by the present invention is: a diagnostic control method for the energy-saving operation of a central air-conditioning system, including the following steps:

[0006] Step 1: Deploy an Internet of Things sensor array at key nodes of the refrigeration host, water pump, cooling tower and terminal equipment of the central air-conditioning system to collect operation data of chilled water temperature, cooling water temperature, compressor operating frequency, fan speed and terminal equipment load parameters in real time;

[0007] Step 2: Preprocess the collected original operation data, including removing outliers, filling in missing data, and normalizing the data;

[0008] Step 3: Use the data quality assessment model to analyze the credibility of the preprocessed data. When the data quality does not meet the standard, trigger the sensor fault warning and data re-collection mechanism;

[0009] Step 4: Analyze and diagnose the qualified operation data based on a preset diagnosis rule library, where the diagnosis rule library includes the threshold range formed by historical energy-saving operation data, the equipment performance degradation model, and the system energy efficiency ratio evaluation standard;

[0010] Step 5: Generate an energy-saving control strategy according to the diagnosis result. The energy-saving control strategy includes adjusting the number of compressor starts and stops, optimizing the flow ratio of chilled water and cooling water, dynamically matching the air volume of terminal equipment, and executing the energy-saving control strategy through a closed-loop control system.

[0011] Preferably, in Step 1, a multi-dimensional synchronous data collection is realized by using an Internet of Things sensor array.

[0012] Preferably, in Step 4, a machine learning algorithm is used to predict the trend of operation data, and the machine learning algorithm is trained based on historical fault data and energy-saving optimization cases.

[0013] Preferably, in Step 5, a multi-objective optimization model including equipment priority, energy consumption cost, and user comfort is constructed, and the dynamic balance between energy saving and service quality is achieved through weight allocation.

[0014] Preferably, after the closed-loop control system executes the energy-saving control strategy, continuously monitor the system operation status. When the monitored data deviates from the preset energy-saving target range, automatically trigger the re-execution of the diagnosis process.

[0015] Preferably, the diagnosis rule library has a self-update function, and dynamically adjusts the threshold range and equipment performance model parameters by analyzing the long-term operation data of the system.

[0016] Preferably, during the execution of the energy-saving control strategy, a visual diagnosis report is generated synchronously, and the report includes the system energy efficiency change curve, energy-saving potential analysis, and equipment health assessment results.

[0017] The advantages of the present invention compared with the prior art are as follows:

[0018] Multi-dimensional data collection and preprocessing ensure data accuracy and provide a basis for accurate diagnosis;

[0019] Data quality assessment and re-collection mechanism improve the reliability of diagnosis;

[0020] Combine historical data with the diagnostic rule base of machine learning algorithms to achieve a comprehensive and accurate assessment of system operating status;

[0021] The energy-saving control strategy generated by the multi-objective optimization model balances energy saving and user comfort requirements;

[0022] Closed-loop control and automatic re-diagnosis mechanisms ensure continuous and efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the workflow of the present invention. DETAILED DESCRIPTION

[0024] The present invention is further described in detail below with reference to the accompanying drawings.

[0025] Example 1

[0026] A large commercial complex includes shopping malls, office buildings and hotels. The cooling capacity demand of the central air-conditioning system is complex and changes dynamically.

[0027] When implementing the method of the present invention, in step 1, high-precision temperature sensors and pressure sensors are installed at the inlet and outlet of the refrigeration host, flow sensors are set at the water pump, speed sensors are equipped at the cooling tower fan, and temperature, humidity and CO2 concentration sensors are deployed at the terminal air conditioning unit to build an Internet of Things sensor array. The sensor collects data in real time at intervals of 1 minute, such as the outlet water temperature of the refrigeration host chilled water, the return water temperature of the cooling water, the compressor current, the pump frequency, etc.

[0028] Step 2: Use the 3σ principle to remove outliers, use linear interpolation to fill missing data, and normalize different types of data to the [0,1] interval. For example, after normalization, the chilled water temperature data can be analyzed together with other parameters.

[0029] Step three: The data quality assessment model establishes a confidence interval based on the historical sensor data. When the fan speed data of a cooling tower exceeds the interval for three consecutive times, a fault warning is triggered and the backup sensor is started to collect additional data.

[0030] Step 4: The diagnostic rule base sets the normal range of the chilled water supply and return temperature difference to 4-6°C based on the historical energy-saving operation data of the complex. If the temperature difference is detected to be continuously lower than 3°C, combined with parameters such as the compressor operating frequency, it is diagnosed as insufficient chilled water flow.

[0031] Step 5: Generate an energy-saving control strategy: reduce the frequency of the chilled water pump by 10% and start a spare cooling tower fan. After execution through the closed-loop control system, the system energy efficiency ratio is improved by 12% and the daily power consumption is reduced by about 800 degrees.

[0032] Example 2

[0033] A certain electronic manufacturing industrial plant has high requirements for the control accuracy of temperature and humidity and needs to operate continuously for 24 hours.

[0034] Step 1: Install sensors at key parts of equipment such as the chiller, circulating water pump, and surface cooler in the plant's central air-conditioning system. In addition to conventional temperature and flow parameters, focus on collecting the temperature and humidity fluctuation data of the clean room and the equipment operation noise data.

[0035] Step 2: Use wavelet denoising method to preprocess the noise data to remove environmental interference signals; when the temperature and humidity data are missing, estimate and fill them according to the data of adjacent monitoring points and the equipment operation status.

[0036] Step 3: The data quality assessment model introduces the correlation analysis of equipment operation conditions. If the current data of the chiller is normal but the chilled water flow data is abnormal, it is determined that the flow sensor fails and triggers early warning and supplementary collection.

[0037] Step 4: The diagnostic rule library combines the production process characteristics of the plant and sets the temperature and humidity fluctuation thresholds of the clean room as ±0.5°C and ±5%RH. When it is detected that the humidity continuously exceeds the set upper limit and the fan speed of the surface cooler has reached the maximum value, it is diagnosed that the dehumidification capacity is insufficient.

[0038] Step 5: Generate a control strategy: start the auxiliary dehumidification equipment, and at the same time adjust the chilled water temperature to decrease by 0.3°C. After the closed-loop control is executed, on the premise of meeting the production process requirements, the system energy consumption is reduced by 9%, and the annual electricity cost savings are about 200,000 yuan.

[0039] Example 3

[0040] The building function zoning of a comprehensive hospital is complex, including operating rooms, wards, outpatient halls, etc., and has extremely high requirements for air quality and system stability.

[0041] Step 1: When deploying sensors in the central air-conditioning system, especially add PM2.5 and bacteria concentration sensors in the operating rooms, CO2 concentration sensors and equipment vibration sensors in the wards.

[0042] Step 2: Perform standardization conversion on special data such as bacteria concentration, and use spectrum analysis to preprocess the vibration data to extract characteristic values.

[0043] Step 3: The data quality assessment model sets a multiple verification mechanism. For example, when the temperature data in the operating room is too different from the temperature data in the adjacent area, automatically compare other environmental parameters and equipment operation status to judge the data reliability.

[0044] Step 4, the diagnostic rule base is set for the hospital scenario: the temperature in the operating room is maintained at 22 - 24 °C, and the CO2 concentration does not exceed 500 ppm. If it is detected that the CO2 concentration in a certain operating room exceeds the standard and the fresh air unit is operating normally, combined with parameters such as the opening degree of the return air valve, it is diagnosed that the air distribution is unreasonable.

[0045] Step 5, generate a control strategy: increase the fresh air volume of the fresh air unit by 15%, adjust the opening degree of the return air valve in the operating room, and at the same time optimize the air-conditioning load distribution in adjacent areas. After the closed-loop control is executed, the air quality compliance rate in the operating room is increased to 99.5%, and the overall energy consumption of the system is reduced by 7%, effectively ensuring the medical environment requirements and energy-saving goals.

[0046] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A diagnostic control method for energy-saving operation of a central air-conditioning system, characterized in that, It includes the following steps: Step 1: Deploy an Internet of Things sensor array at key nodes of the chiller, water pump, cooling tower, and terminal equipment in the central air-conditioning system to collect real-time operation data such as chilled water temperature, cooling water temperature, compressor operation frequency, fan speed, and terminal equipment load parameters; Step 2: Preprocess the collected original operation data, including removing outliers, filling in missing data, and data normalization; Step 3: Use a data quality assessment model to analyze the credibility of the preprocessed data. When the data quality does not meet the standard, trigger the sensor fault warning and data re-collection mechanism; Step 4: Analyze and diagnose the qualified operation data based on a preset diagnostic rule library. The diagnostic rule library includes threshold ranges formed by historical energy-saving operation data, equipment performance degradation models, and system energy efficiency ratio evaluation criteria; Step 5: Generate an energy-saving control strategy according to the diagnostic results. The energy-saving control strategy includes adjusting the start-stop quantity of compressors, optimizing the flow ratio of chilled water and cooling water, dynamically matching the air volume of terminal equipment, and executing the energy-saving control strategy through a closed-loop control system.

2. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, characterized in that: In Step 1, an Internet of Things sensor array is used to achieve multi-dimensional synchronous data collection.

3. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, wherein: In Step 4, machine learning algorithms are used to predict the trend of operation data. The machine learning algorithms are trained based on historical fault data and energy-saving optimization cases.

4. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, characterized in that: In Step 5, a multi-objective optimization model including equipment priority, energy consumption cost, and user comfort is constructed to achieve dynamic balance between energy saving and service quality through weight allocation.

5. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, characterized in that: After the closed-loop control system executes the energy-saving control strategy, continuously monitor the system operation status. When the monitored data deviates from the preset energy-saving target range, automatically trigger the re-execution of the diagnostic process.

6. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, characterized in that: The diagnostic rule library has a self-update function. By analyzing the long-term operation data of the system, dynamically adjust the threshold range and equipment performance model parameters.

7. The diagnostic control method for energy-saving operation of a central air-conditioning system according to claim 1, characterized in that: During the execution of the energy-saving control strategy, a visual diagnostic report is generated synchronously. The report includes the system energy efficiency change curve, energy-saving potential analysis, and equipment health assessment results.

Images