CN114413439A - Self-learning-based central air conditioner operation expert database management method and system - Google Patents

Self-learning-based central air conditioner operation expert database management method and system Download PDF

Info

Publication number
CN114413439A
CN114413439A CN202111675520.9A CN202111675520A CN114413439A CN 114413439 A CN114413439 A CN 114413439A CN 202111675520 A CN202111675520 A CN 202111675520A CN 114413439 A CN114413439 A CN 114413439A
Authority
CN
China
Prior art keywords
central air
data
rule
application end
air conditioner
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111675520.9A
Other languages
Chinese (zh)
Inventor
戴吉平
李信洪
袁宜峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Das Intellitech Co Ltd
Original Assignee
Shenzhen Das Intellitech Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Das Intellitech Co Ltd filed Critical Shenzhen Das Intellitech Co Ltd
Priority to CN202111675520.9A priority Critical patent/CN114413439A/en
Publication of CN114413439A publication Critical patent/CN114413439A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/56—Remote control
    • F24F11/58—Remote control using Internet communication
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/88—Electrical aspects, e.g. circuits
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/89—Arrangement or mounting of control or safety devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F24F2110/12—Temperature of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F24F2110/22—Humidity of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00—Control inputs relating to users or occupants
    • F24F2120/10—Occupancy

Abstract

The invention relates to a self-learning-based expert database management method and system for central air conditioner operation, which comprises the steps of obtaining project application end data of a project application end and uploading the project application end data to a platform application end; the platform application side preprocesses and stores the project application side data, and uploads the stored data to the cloud server based on preset conditions; the cloud server self-learns based on the data uploaded by the platform application terminal, generates a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal; and the project application end acquires the operation rule of the central air conditioner from the platform application end, executes the operation rule according to the operation rule of the central air conditioner and outputs an execution result. The data storage of the invention is performed on the cloud platform, the execution is performed by the project application end, the cloud server is responsible for rule updating, the pressure of the cloud server can be reduced, the rule is updated by the cloud server and is issued and uniformly stored on the platform application end to form expert experience, and meanwhile, the project application end can be customized according to the rule, thereby greatly reducing the project application cost.

Description

Self-learning-based central air conditioner operation expert database management method and system
Technical Field
The invention relates to the technical field of central air conditioner operation management, in particular to a self-learning-based central air conditioner operation expert database management method and system.
Background
The central air-conditioning system of the building is a big household of building energy consumption, wherein a part of the important reason that the energy consumption is high is caused by poor operation management of the central air-conditioning system, namely, the central air-conditioning system cannot save energy from the operation management process due to low-efficiency operation and unreasonable operation control strategy caused by system equipment failure. The traditional central air-conditioning group control needs to be deployed on a project to control the operation of equipment to be executed strictly according to a set operation strategy, is designed according to specific project design requirements, has various actual characteristics of a central air-conditioning system and an energy supply object, and is one of the difficult problems which plague central air-conditioning system operation managers.
The ideal method is to provide a self-learning extensible central air-conditioning operation expert base, and the self-learning generation rules are realized based on the mining analysis of the project full life cycle operation data or industry historical data. In order to realize the self-learning expandable expert database, the artificial intelligence algorithm support of deep learning such as complex load prediction, operation strategy mining and the like is often needed, the calculation amount is very huge due to large data volume, the traditional local controller cannot meet the calculation requirement, most of central air-conditioning group control systems for control optimization cannot meet the requirement of operation energy conservation in the current practical application, and the energy-saving potential in the operation process cannot be further mined.
Traditional cold station develops into the cloud computing wisdom cold station through the development of many years, and is direct to be deployed on the project mostly, directly issues early warning trouble message and optimal control's parameter to the application apparatus end after calculating in real time based on cloud server, adopts this technical scheme mainly to have following several key problems, leads to early warning, optimal control result unsatisfactory, the condition that terminal equipment linkage is out of control and energy consumption increases even appears:
1) all the calculation is carried out on a cloud server, and the project is heavily dependent on the cloud server; algorithms such as early warning fault monitoring and optimal control are distributed in the cloud end, so that the task of the cloud server is increased, the load borne by the cloud server is large, the computing efficiency of the cloud server is reduced, and meanwhile, the application end is seriously dependent on the result executed by the cloud server.
2) The data are stored in the cloud server and a rule is generated, and the timeliness of the equipment is influenced by the network delay; the types and the quantity of the devices to be managed are large, the requirements of early warning type data, control type data and real-time data on transmission capacity are high, and the data are stored in the cloud server, so that the transmission bandwidth load is large, high network delay is caused, and efficient and stable operation of the devices is influenced.
3) The cloud server bears a calculation and execution tool, and expert experience cannot be accumulated; the control effect of the method depends on the calculation result of the cloud server, rule experience generated by calculation of the cloud server cannot be accumulated, and more is that an instruction is directly issued to be transmitted to an application terminal after calculation. On one hand, the computing pressure and the high energy consumption of communication on the cloud server are increased; on the other hand, the effective application value of the operation rule knowledge base cannot be realized, and a set of cloud server needs to be deployed for independent calculation for different projects, so that resource waste is caused; even a set of cloud servers are deployed to perform early warning diagnosis and real-time optimized calculation on the central air-conditioning system, and the total energy consumption is higher than that of a system without the cloud computing server.
Disclosure of Invention
The invention aims to solve the technical problem of providing a self-learning-based expert database management method and system for central air conditioner operation, aiming at the defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a self-learning-based expert database management method for operation of a central air conditioner is constructed, and comprises the following steps:
acquiring project application end data of a project application end, and uploading the project application end data to a platform application end so that the platform application end can store the project application end data; the project application data comprises: central air conditioning system environmental data, central air conditioning system operating data and central air conditioning system energy data;
the platform application end preprocesses and stores the project application end data, and uploads the stored data to a cloud server based on a preset condition;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal so that the platform application terminal can store the central air conditioner operation rule;
and the project application end acquires the central air-conditioning operation rule from the platform application end, executes the central air-conditioning operation rule according to the central air-conditioning operation rule and outputs an execution result.
In the self-learning based expert database management method for central air-conditioning operation, the project application end for the platform application end to store the project application end data comprises the following steps: a detection device;
the acquiring project application end data of a project application end and uploading the project application end data to a platform application end comprises:
the detection device is used for acquiring the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system, and sending the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system to the platform application end, so that the platform application end can store the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system.
In the self-learning based expert database management method for operation of a central air conditioner, the environmental data of the central air conditioning system comprises the following steps: indoor personnel number, outdoor temperature, outdoor humidity, solar radiation intensity, indoor temperature and indoor humidity;
the central air conditioning system operation data includes: the system comprises a chilled water inlet temperature, a chilled water outlet temperature, a cooling water inlet temperature, a cooling water outlet temperature, a chilled water flow, a cooling tower fan rotating speed, a cooling tower inlet air temperature, a cooling tower inlet air humidity, an air handling unit fan rotating speed, an air handling unit inlet air temperature and an air handling unit inlet air humidity;
the central air conditioning system energy data includes: the system refrigerating capacity, the refrigerating capacities of all refrigerating hosts, the real-time power of the system and the real-time power of all equipment of the system.
In the self-learning based expert database management method for operation of a central air conditioner, the platform application end comprises: the device comprises a data storage module and a first trigger judgment module;
the platform application end preprocesses and stores the project application end data, and uploads the stored data to the cloud server based on preset conditions, and the method comprises the following steps:
the data storage module receives the project application end data and preprocesses the project application end data to obtain preprocessed data;
classifying the preprocessed data according to project assets and equipment types and then storing the preprocessed data;
the first trigger judging module judges whether the data stored by the data storage module meets a sending trigger condition;
and if the sending triggering condition is met, sending the data meeting the sending triggering condition to the cloud server.
In the self-learning based expert database management method for central air-conditioning operation, the first triggering judgment module judging whether the data stored by the data storage module meets the sending triggering condition comprises the following steps:
the first trigger judgment module acquires the running state of the cloud server;
the first trigger judgment module judges whether the data stored in the data storage module meets the sending trigger condition or not according to the running state of the cloud server and the data uploading trigger condition.
In the self-learning based expert database management method for operation of a central air conditioner, the cloud server comprises: a self-learning module;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal, and the cloud server comprises the following steps:
the self-learning module triggers training and verifies self-learning according to the data uploaded by the platform application terminal to generate a central air conditioner operation rule model;
and generating the central air-conditioning operation rule based on the central air-conditioning operation rule model.
In the self-learning based expert database management method for operation of a central air conditioner, the platform application end comprises: a first rule storage module;
the first rule storage module is used for receiving and storing the central air conditioner operation rule issued by the cloud server.
In the self-learning based expert database management method for operation of a central air conditioner, the project application end comprises the following steps: the second rule storage module, the second trigger judgment module and the rule execution module;
the project application end obtains the central air-conditioning operation rule from the platform application end, and the executing and outputting the executing result according to the central air-conditioning operation rule comprises the following steps:
the second rule storage module selects a corresponding central air conditioner operation rule from the first rule storage module, and determines an execution trigger condition based on the selected central air conditioner operation rule and the project characteristics;
the second trigger judging module judges whether to execute the selected central air conditioner operation rule according to the execution trigger condition;
if yes, sending the selected central air conditioner operation rule to the rule execution module;
the rule execution module reads input parameters from the platform application terminal according to the received central air conditioner operation rule;
and the rule execution module executes according to the received central air conditioner operation rule and the input parameters and outputs an execution result.
In the self-learning based expert database management method for operation of a central air conditioner, the project application end further comprises: an application display module;
the method further comprises the following steps: and the application display module reads and displays the data stored by the data storage module in real time.
The invention also provides a self-learning based expert database management system for operation of the central air conditioner, which comprises the following steps: the system comprises a cloud server, a platform application end and a project application end;
the project application end uploads project application end data to the platform application end, acquires the central air conditioner operation rule from the platform application end, executes the central air conditioner operation rule and outputs an execution result; the project application data comprises: central air conditioning system environmental data, central air conditioning system operating data and central air conditioning system energy data;
the platform application end preprocesses and stores the project application end data, uploads the stored data to a cloud server based on preset conditions, and stores the central air conditioner operation rule issued by the cloud server;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and sends the central air conditioner operation rule to the platform application terminal.
The implementation of the self-learning-based expert database management method and the self-learning-based expert database management system for the operation of the central air conditioner has the following beneficial effects: acquiring project application end data of a project application end, and uploading the project application end data to a platform application end; the platform application side preprocesses and stores the project application side data, and uploads the stored data to the cloud server based on preset conditions; the cloud server self-learns based on the data uploaded by the platform application terminal, generates a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal; and the project application end acquires the operation rule of the central air conditioner from the platform application end, executes the operation rule according to the operation rule of the central air conditioner and outputs an execution result. The data storage of the invention is performed on the cloud platform by the project application end, the cloud server is responsible for rule updating, the pressure of the cloud server can be reduced, the dependence on the cloud server is reduced, the rule can be updated by the cloud server and uniformly stored on the platform application end to form expert experience, and meanwhile, the project application end can be customized according to the rule, thereby greatly reducing the project application cost.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic structural diagram of a self-learning-based expert database management system for operation of a central air conditioner according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a self-learning-based expert database management method for central air conditioner operation according to an embodiment of the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Referring to fig. 1, a schematic structural diagram of an alternative embodiment of the self-learning based expert database management system for central air-conditioning operation provided by the present invention is shown.
As shown in fig. 1, the self-learning based central air-conditioning operation expert database management system includes: cloud server 10, platform application 20, and project application 30.
The project application end 30 uploads the data of the project application end 30 to the platform application end 20, obtains the central air-conditioning operation rule from the platform application end 20, executes according to the central air-conditioning operation rule, and outputs an execution result.
The data of the project application 30 includes: the central air-conditioning system environment data, the central air-conditioning system operation data and the central air-conditioning system energy data.
Optionally, in the embodiment of the present invention, the central air conditioning system environment data includes but is not limited to: indoor personnel count, outdoor temperature, outdoor humidity, solar radiation intensity, indoor temperature, and indoor humidity.
The central air conditioning system operating data includes, but is not limited to: the system comprises a chilled water inlet temperature, a chilled water outlet temperature, a cooling water inlet temperature, a cooling water outlet temperature, a chilled water flow, a cooling tower fan speed, a cooling tower inlet air temperature, a cooling tower inlet air humidity, an air handling unit fan speed, an air handling unit inlet air temperature and an air handling unit inlet air humidity.
The central air conditioning system energy data includes but is not limited to: the system refrigerating capacity, the refrigerating capacities of all refrigerating hosts, the real-time power of the system and the real-time power of all equipment of the system.
The platform application terminal 20 preprocesses and stores the data of the project application terminal 30, uploads the stored data to the cloud server 10 based on a preset condition, and stores the operation rule of the central air conditioner issued by the cloud server 10.
The cloud server 10 triggers training and verification self-learning based on the data uploaded by the platform application terminal 20 to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal 20.
Specifically, in order to reduce the pressure of the cloud server and ensure the stable and efficient energy-saving operation of the central air conditioner, the invention deploys a complex model training and rule generating method with large calculation amount on the cloud server 10 and can self-learn the updated model and the generated rules, meanwhile, the generated rules are issued to the rule expert library of the platform application terminal 20, and the project application terminal 30 can autonomously configure the rule expert library of the platform to perform judgment and execution based on the selected rules.
In addition, the invention stores data and rules in the platform application terminal 20, which can reduce the storage pressure of the server and the project application terminal 30. Moreover, the cloud server 10 periodically self-learns the rule to be updated according to the sending trigger condition without performing a large amount of calculation, so that the calculation load of the cloud server 10 can be greatly reduced, and meanwhile, the electric energy consumed by calculation and communication can be saved.
Specifically, as shown in fig. 1, the project application 30 includes: detection device 35 and central air conditioning equipment.
Optionally, the central air-conditioning apparatus may include: air handling unit, frozen water pump, cooling water set, cooling tower fan etc..
Optionally, in the embodiment of the present invention, the detecting device 35 is configured to obtain data of the project application 30, and directly upload the data of the project application 30 to the platform application 20. That is, the number of indoor persons, the outdoor temperature, the outdoor humidity, the solar radiation intensity, the indoor temperature, the indoor humidity, the chilled water inlet temperature, the chilled water outlet temperature, the cooling water inlet temperature, the cooling water outlet temperature, the chilled water flow rate, the cooling tower fan rotation speed, the cooling tower inlet air temperature, the cooling tower inlet air humidity, the air handling unit fan rotation speed, the air handling unit inlet air temperature, the air handling unit inlet air humidity, the system refrigeration amount, the refrigeration amounts of all refrigeration hosts, the system real-time power, the real-time powers of all devices of the system, and the like can be obtained through the detection device 35.
Further, as shown in fig. 1, the project application 30 further includes: a second rule storage module 31, a second trigger judgment module 32 and a rule execution module 33.
Optionally, in this embodiment of the present invention, the second rule storage module 31 selects a corresponding central air-conditioning operation rule from the first rule storage module 23, and determines to execute the trigger condition based on the selected central air-conditioning operation rule and the item characteristic. The execution trigger condition may be a timing or event trigger.
Optionally, in this embodiment of the present invention, the second triggering and determining module 32 determines whether to execute the selected central air conditioner operation rule according to the execution triggering condition; if so, the selected central air-conditioning operation rule is sent to the rule execution module 33.
Optionally, in this embodiment of the present invention, the rule execution module 33 reads the input parameters from the platform application 20 according to the received central air-conditioning operation rule, executes according to the received central air-conditioning operation rule and the input parameters, and outputs an execution result.
Specifically, whether the selected rule is executed is judged according to the execution trigger condition, if the selected rule is executed, the corresponding rule is sent to the rule execution module 33, and after the rule execution module 33 receives the selected rule, the corresponding input parameter is acquired from the platform application terminal 20 according to the selected rule, the execution is performed based on the acquired input parameter and the received rule, and the corresponding execution result is output. The output execution result may include, but is not limited to: index calculation class data, control output class data/signals, text message class data, and the like. The output execution result may be directly written into the platform application 20, or may be directly issued to the execution controller 34 of the end device, or may be simultaneously written into the platform application 20 and issued to the execution controller 34 of the end device. For example, the data/signals for controlling the output class can be written into the platform application 20 and the execution controller 34 issued to the end device at the same time.
Further, in the embodiment of the present invention, as shown in fig. 1, the project application 30 further includes: the display module 36 is applied. The application display module 36 is connected to the platform application terminal 20, and is configured to read and display data stored in the platform application terminal 20 in real time.
Optionally, in the embodiment of the present invention, the application display module 36 may be used to store and display, but is not limited to: the system comprises a message center, an air conditioner index monitoring system, a real-time control monitoring system, a load prediction monitoring system, an early warning diagnosis event and the like.
As shown in fig. 1, in the embodiment of the present invention, the platform application 20 includes: a data storage module 21. The data storage module 21 is in data communication with the detection device 35, the rule execution module 33 and the application display module 36 of the project application end 30, and is configured to receive the data of the project application end 30 acquired by the detection device 35 and preprocess the data of the project application end 30 to acquire preprocessed data; and classifying the preprocessed data according to the project assets and the equipment types and then storing the preprocessed data.
Optionally, in this embodiment of the present invention, the preprocessing, performed by the data storage module 21, of the data of the project application terminal 30 may include: preprocessing the project application 30 data may include, but is not limited to, a missing value removal process, a duplicate value removal process, and the like.
Meanwhile, the data stored in the data storage module 21 can be read by the rule execution module 33 and the application display module 36.
As shown in fig. 1, in the embodiment of the present invention, the platform application end 20 further includes: a first trigger judgment module 22.
The first trigger judging module 22 is configured to judge whether the data stored in the data storage module 21 meets a sending trigger condition; if the sending trigger condition is satisfied, the data satisfying the sending trigger condition is sent to the cloud server 10.
Further, as shown in fig. 1, in the embodiment of the present invention, the platform application end 20 further includes: a first rule storage module 23. The first rule storage module 23 is configured to receive and store a central air conditioner operation rule issued by the cloud server 10.
Optionally, in this embodiment of the present invention, the first rule storage module 23 may store the central air conditioner operation rule issued by the cloud server 10. Optionally, in this embodiment of the present invention, the central air conditioner operation rule issued by the cloud server 10 may include, but is not limited to, a load prediction rule, a control optimization rule, and an early warning diagnosis rule formulated based on an operation policy. Wherein, the rules stored by the first rule storage module 23 are integrated into an expert experience base.
Optionally, in the embodiment of the present invention, as shown in fig. 1, the cloud server 10 includes: and the historical database 11, wherein the historical database 11 is used for receiving the data uploaded by the platform application terminal 20.
Optionally, in this embodiment of the present invention, as shown in fig. 1, the cloud server 10 further includes: a self-learning module 12. The self-learning module 12 triggers training and verifies self-learning according to the data uploaded by the platform application terminal 20 to generate a central air conditioner operation rule model; and generating a central air-conditioning operation rule based on the central air-conditioning operation rule model. Alternatively, in some other embodiments, the cloud server 10 may also directly analyze the data received by the historical database 11 to generate the central air-conditioning operation rule.
Optionally, in the embodiment of the present invention, the self-learning module 12 may include, but is not limited to, a load prediction learner, a control optimization learner, an operation rule learner, and other big data application learners, through which data may be trained and verified. When the self-learning is carried out, the corresponding learner can be selected for self-learning according to actually uploaded data.
For example, if the data uploaded by the data storage module 21 is load prediction, a load prediction learner is used to predict future cooling capacity based on historical data (such as outdoor temperature and cooling capacity). The load prediction model is generated, for example, by training and verifying using a time-series LSTM algorithm, and the operation rules are generated based on the generated load prediction model after the load prediction model is generated. Namely, the future cold quantity can be predicted by monitoring the outdoor temperature and the historical cold quantity based on the generated load prediction model. Wherein, the operation rule is as follows: and inputting outdoor temperature and historical cold quantity data, and outputting predicted cold quantity data.
Or, if the data uploaded by the data storage module 21 is subjected to control optimization, a control optimization learner may be used, and the control optimization learner obtains a power model, i.e., a rule model, of the equipment based on historical data (historical operating data and power data of the chiller, the refrigeration pump, the cooling pump, and the cooling tower equipment) and based on a power calculation expression least square regression. And generating an operation rule based on the rule model. Wherein, the operation rule is as follows: inputting the generated power model, selecting an optimization algorithm, inputting outdoor temperature and predicted cold quantity, calculating a sample point with the minimum total power of the cold station, and outputting the operation parameters of each device.
Or, if the data uploaded by the data storage module 21 is changed in operation, an operation rule learner may be used, the operation rule learner obtains a plurality of cluster clusters based on the calendar history power consumption curve of each device and the clustering algorithm, associates the cluster clusters based on the outdoor temperature and the time attribute to obtain a prediction model of the cluster clusters, i.e., a rule model, and generates an operation rule based on the generated rule model. Wherein, the operation rule is as follows: and obtaining an operation clustering cluster by the input outdoor temperature and time attributes (attributes such as week and month) and a cluster prediction model, and monitoring whether the energy consumption is abnormal or not based on the clustering cluster (namely the maximum value and the minimum value), namely early warning diagnosis.
Specifically, in the embodiment of the present invention, the cloud server 10 triggers the self-learning module 12 to generate the rule model by self-learning again according to the data uploaded by the first trigger determining module 22, and after generating the central air conditioner operation rule based on the rule model, the central air conditioner operation rule is issued to the first rule storage module 23 in the platform application terminal 20, so as to update the rule (i.e., the coverage original rule) stored in the first rule storage module 23.
Specifically, in the embodiment of the invention, the central air-conditioning system can be managed through the self-learning-based central air-conditioning operation expert library management system.
A specific management method can be referred to fig. 2.
Specifically, as shown in fig. 2, the self-learning-based expert database management method for central air conditioner operation includes the following steps:
step S201, acquiring the data of the project application 30, and uploading the data of the project application 30 to the platform application 20. The project application 30 data includes: the central air-conditioning system environment data, the central air-conditioning system operation data and the central air-conditioning system energy data.
In some embodiments, obtaining the data of the project application 30, and uploading the data of the project application 30 to the platform application 20 includes: the environment data of the central air-conditioning system, the operation data of the central air-conditioning system and the energy data of the central air-conditioning system are obtained by the detection device 35.
Optionally, in an embodiment of the present invention, the central air conditioning system environment data includes but is not limited to: indoor personnel count, outdoor temperature, outdoor humidity, solar radiation intensity, indoor temperature, and indoor humidity.
The central air conditioning system operating data includes, but is not limited to: the system comprises a chilled water inlet temperature, a chilled water outlet temperature, a cooling water inlet temperature, a cooling water outlet temperature, a chilled water flow, a cooling tower fan speed, a cooling tower inlet air temperature, a cooling tower inlet air humidity, an air handling unit fan speed, an air handling unit inlet air temperature and an air handling unit inlet air humidity.
The central air conditioning system energy data includes but is not limited to: the system refrigerating capacity, the refrigerating capacities of all refrigerating hosts, the real-time power of the system and the real-time power of all equipment of the system.
Step S202, the platform application 20 preprocesses and stores the data of the project application 30, and uploads the stored data to the cloud server 10 based on a preset condition.
In some embodiments, the platform application 20 pre-processes and stores the data of the project application 30, and uploading the stored data to the cloud server 10 based on the preset condition includes: the data storage module 21 receives the data of the project application end 30, and preprocesses the data of the project application end 30 to obtain preprocessed data; classifying the preprocessed data according to project assets and equipment types and then storing the preprocessed data; the first trigger judging module 22 judges whether the data stored in the data storage module 21 meets the sending trigger condition; if the sending trigger condition is satisfied, the data satisfying the sending trigger condition is sent to the cloud server 10.
In some embodiments, the determining, by the first trigger determining module 22, whether the data stored by the data storage module 21 satisfies the sending trigger condition includes: the first trigger judgment module 22 acquires the operation state of the cloud server 10; the first trigger judging module 22 judges whether the data stored in the data storage module 21 satisfies the sending trigger condition according to the operating state of the cloud server 10 and the data uploading trigger condition.
Specifically, the first trigger determining module 22 determines whether the sending trigger condition is satisfied according to the operating state of the cloud server 10 and the data uploading trigger condition, and if so, uploads data to the history database 11 in the cloud server 10 to trigger the cloud server 10 to update data and update self-learning based on the updated data. Optionally, in this embodiment of the present invention, the sending trigger condition is: the cloud server 10 is running and a trigger event (such as a platform event or a timing condition) is reached, that is, when the cloud server 10 is in a running state and the platform event or the timing condition is satisfied, data can be uploaded to the history database 11 of the cloud server 10.
After the sending trigger condition is met, the first trigger determining module 22 may upload data to the history database 11 of the cloud server 10 according to the data cycle. For example, the data of the last half year is acquired every 1 month, that is, the data of the last half year is uploaded to the history database 11 of the cloud server 10 every 1 month for self-learning.
Step S203, the cloud server 10 triggers training and verification self-learning based on the data uploaded by the platform application terminal 20 to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal 20.
In some embodiments, the triggering, training, verifying, and self-learning by the cloud server 10 based on the data uploaded by the platform application 20 to generate the central air conditioner operation rule and issue the central air conditioner operation rule to the platform application 20 includes: the self-learning module 12 triggers training and verifies self-learning according to the data uploaded by the platform application terminal 20 to generate a central air conditioner operation rule model; and generating a central air-conditioning operation rule based on the central air-conditioning operation rule model.
Specifically, the self-learning module 12 performs training and self-learning based on the data uploaded by the platform application terminal 20 to generate a rule model, and generates the central air conditioner operation rule based on the rule model, and issues the rule to the first rule storage module 23 in the platform application terminal 20, so as to continuously update the latest rule expert database, and the rule is stored by the first rule storage module 23.
Optionally, in the embodiment of the present invention, the self-learning module 12 may include, but is not limited to, a load prediction learner, a control optimization learner, an operation rule learner, and other big data application learners, through which data may be trained and verified. When the self-learning is carried out, the corresponding learner can be selected for self-learning according to actually uploaded data.
Optionally, in the embodiment of the present invention, the self-learning module 12 may include, but is not limited to, a load prediction learner, a control optimization learner, an operation rule learner, and other big data application learners, through which data may be trained and verified. When the self-learning is carried out, the corresponding learner can be selected for self-learning according to actually uploaded data.
For example, if the data uploaded by the data storage module 21 is load prediction, a load prediction learner is used to predict future cooling capacity based on historical data (such as outdoor temperature and cooling capacity). The load prediction model is generated, for example, by training and verifying using a time-series LSTM algorithm, and the operation rules are generated based on the generated load prediction model after the load prediction model is generated. Namely, the future cold quantity can be predicted by monitoring the outdoor temperature and the historical cold quantity based on the generated load prediction model. Wherein, the operation rule is as follows: and inputting outdoor temperature and historical cold quantity data, and outputting predicted cold quantity data.
Or, if the data uploaded by the data storage module 21 is subjected to control optimization, a control optimization learner may be used, and the control optimization learner obtains a power model, i.e., a rule model, of the equipment based on historical data (historical operating data and power data of the chiller, the refrigeration pump, the cooling pump, and the cooling tower equipment) and based on a power calculation expression least square regression. And generating an operation rule based on the rule model. Wherein, the operation rule is as follows: inputting the generated power model, selecting an optimization algorithm, inputting outdoor temperature and predicted cold quantity, calculating a sample point with the minimum total power of the cold station, and outputting the operation parameters of each device.
Or, if the data uploaded by the data storage module 21 is changed in operation, an operation rule learner may be used, the operation rule learner obtains a plurality of cluster clusters based on the calendar history power consumption curve of each device and the clustering algorithm, associates the cluster clusters based on the outdoor temperature and the time attribute to obtain a prediction model of the cluster clusters, i.e., a rule model, and generates an operation rule based on the generated rule model. Wherein, the operation rule is as follows: and obtaining an operation clustering cluster by the input outdoor temperature and time attributes (attributes such as week and month) and a cluster prediction model, and monitoring whether the energy consumption is abnormal or not based on the clustering cluster (namely the maximum value and the minimum value), namely early warning diagnosis.
Step S204, the project application 30 obtains the central air-conditioning operation rule from the platform application 20, executes the central air-conditioning operation rule according to the central air-conditioning operation rule, and outputs an execution result.
In some embodiments, the acquiring, by the project application 30, the central air-conditioning operation rule from the platform application 20, executing according to the central air-conditioning operation rule, and outputting the execution result includes: the second rule storage module 31 selects a corresponding central air-conditioning operation rule from the first rule storage module 23, and determines an execution trigger condition based on the selected central air-conditioning operation rule and the item characteristics; the second trigger judging module 32 judges whether to execute the selected central air-conditioning operation rule according to the execution trigger condition; if yes, sending the selected central air-conditioning operation rule to the rule execution module 33; the rule execution module 33 reads the input parameters from the platform application terminal 20 according to the received central air-conditioning operation rule; the rule executing module 33 executes according to the received central air-conditioning operation rule and the input parameter, and outputs an execution result.
The output execution result may include, but is not limited to: index calculation class data, control output class data/signals, text message class data, and the like. The output execution result may be directly written into the platform application 20, or may be directly issued to the execution controller 34 of the end device, or may be simultaneously written into the platform application 20 and issued to the execution controller 34 of the end device. For example, the data/signals for controlling the output class can be written into the platform application 20 and the execution controller 34 issued to the end device at the same time.
Further, in some embodiments, the self-learning based expert database management method for central air-conditioning operation further includes: the application display module 36 reads and displays the data stored in the data storage module 21 in real time.
The embodiment of the invention discloses a self-learning-based expert database management method and system for central air conditioner operation, which is implemented by triggering and driving a cloud server 10 to self-learn and update an expert database based on a platform application terminal 20 and configuring operation rules by a project application terminal 30. The self-learning module 12 in the cloud server 10 triggers self-learning based on platform events or timing trigger conditions and issues to the platform application 20 to update the expert database.
In addition, an expert library is provided by the platform application end 20 to integrate the experience of cloud computing and rapid precipitation of artificial experience for project application, so that the requirement of the existing project customization business rule is met, the work efficiency of the project is improved, the development cost is reduced, and meanwhile, the accumulated precipitation business experience can be presented to the user.
The expert database management method provided by the invention is not limited to the operation of a central air conditioner, is also suitable for the operation management fields of different systems such as intelligent building illumination, water supply and drainage, elevators and the like, and can be used for formulating the operation expert databases of different systems based on the method.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should be covered by the claims of the present invention.

Claims (10)

1. A self-learning based expert database management method for operation of a central air conditioner is characterized by comprising the following steps:
acquiring project application end data of a project application end, and uploading the project application end data to a platform application end so that the platform application end can store the project application end data; the project application data comprises: central air conditioning system environmental data, central air conditioning system operating data and central air conditioning system energy data;
the platform application end preprocesses and stores the project application end data, and uploads the stored data to a cloud server based on a preset condition;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal so that the platform application terminal can store the central air conditioner operation rule;
and the project application end acquires the central air-conditioning operation rule from the platform application end, executes the central air-conditioning operation rule according to the central air-conditioning operation rule and outputs an execution result.
2. The self-learning based expert database management method for central air-conditioning operation according to claim 1, wherein the project application end comprises: a detection device;
the acquiring project application end data of a project application end and uploading the project application end data to a platform application end so that the platform application end stores the project application end data comprises:
the detection device is used for acquiring the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system, and sending the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system to the platform application end, so that the platform application end can store the environment data of the central air conditioning system, the operation data of the central air conditioning system and the energy data of the central air conditioning system.
3. The self-learning based expert database management method for central air conditioning system operation according to claim 2, wherein the central air conditioning system environment data comprises: indoor personnel number, outdoor temperature, outdoor humidity, solar radiation intensity, indoor temperature and indoor humidity;
the central air conditioning system operation data includes: the system comprises a chilled water inlet temperature, a chilled water outlet temperature, a cooling water inlet temperature, a cooling water outlet temperature, a chilled water flow, a cooling tower fan rotating speed, a cooling tower inlet air temperature, a cooling tower inlet air humidity, an air handling unit fan rotating speed, an air handling unit inlet air temperature and an air handling unit inlet air humidity;
the central air conditioning system energy data includes: the system refrigerating capacity, the refrigerating capacities of all refrigerating hosts, the real-time power of the system and the real-time power of all equipment of the system.
4. The self-learning based expert database management method for central air conditioning operation according to claim 1, wherein the platform application side comprises: the device comprises a data storage module and a first trigger judgment module;
the platform application end preprocesses and stores the project application end data, and uploads the stored data to the cloud server based on preset conditions, and the method comprises the following steps:
the data storage module receives the project application end data and preprocesses the project application end data to obtain preprocessed data;
classifying the preprocessed data according to project assets and equipment types and then storing the preprocessed data;
the first trigger judging module judges whether the data stored by the data storage module meets a sending trigger condition;
and if the sending triggering condition is met, sending the data meeting the sending triggering condition to the cloud server.
5. The self-learning based expert database management method for central air conditioning operation according to claim 4, wherein the first triggering judgment module judging whether the data stored in the data storage module meets the sending triggering condition comprises:
the first trigger judgment module acquires the running state of the cloud server;
the first trigger judgment module judges whether the data stored in the data storage module meets the sending trigger condition or not according to the running state of the cloud server and the data uploading trigger condition.
6. The self-learning based central air conditioner operation expert database management method according to claim 1, wherein the cloud server comprises: a self-learning module;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and issues the central air conditioner operation rule to the platform application terminal, and the cloud server comprises the following steps:
the self-learning module triggers training and verifies self-learning according to the data uploaded by the platform application terminal to generate a central air conditioner operation rule model;
and generating the central air-conditioning operation rule based on the central air-conditioning operation rule model.
7. The self-learning based expert database management method for central air conditioning operation according to claim 1, wherein the platform application side comprises: a first rule storage module;
the first rule storage module is used for receiving and storing the central air conditioner operation rule issued by the cloud server.
8. The self-learning based expert database management method for central air conditioning operation according to claim 7, wherein the project application end comprises: the second rule storage module, the second trigger judgment module and the rule execution module;
the project application end obtains the central air-conditioning operation rule from the platform application end, and the executing and outputting the executing result according to the central air-conditioning operation rule comprises the following steps:
the second rule storage module selects a corresponding central air conditioner operation rule from the first rule storage module, and determines an execution trigger condition based on the selected central air conditioner operation rule and the project characteristics;
the second trigger judging module judges whether to execute the selected central air conditioner operation rule according to the execution trigger condition;
if yes, sending the selected central air conditioner operation rule to the rule execution module;
the rule execution module reads input parameters from the platform application terminal according to the received central air conditioner operation rule;
and the rule execution module executes according to the received central air conditioner operation rule and the input parameters and outputs an execution result.
9. The self-learning based expert database management method for central air conditioning operation according to claim 4, wherein the project application end further comprises: an application display module;
the method further comprises the following steps: and the application display module reads and displays the data stored by the data storage module in real time.
10. A self-learning based expert database management system for operation of a central air conditioner is characterized by comprising the following components: the system comprises a cloud server, a platform application end and a project application end;
the project application end uploads project application end data to the platform application end, acquires the central air conditioner operation rule from the platform application end, executes the central air conditioner operation rule and outputs an execution result; the project application data comprises: central air conditioning system environmental data, central air conditioning system operating data and central air conditioning system energy data;
the platform application end preprocesses and stores the project application end data, uploads the stored data to a cloud server based on preset conditions, and stores the central air conditioner operation rule issued by the cloud server;
the cloud server triggers training and verifies self-learning based on the data uploaded by the platform application terminal to generate a central air conditioner operation rule and sends the central air conditioner operation rule to the platform application terminal.
CN202111675520.9A 2021-12-31 2021-12-31 Self-learning-based central air conditioner operation expert database management method and system Pending CN114413439A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111675520.9A CN114413439A (en) 2021-12-31 2021-12-31 Self-learning-based central air conditioner operation expert database management method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111675520.9A CN114413439A (en) 2021-12-31 2021-12-31 Self-learning-based central air conditioner operation expert database management method and system

Publications (1)

Publication Number Publication Date
CN114413439A true CN114413439A (en) 2022-04-29

Family

ID=81272374

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111675520.9A Pending CN114413439A (en) 2021-12-31 2021-12-31 Self-learning-based central air conditioner operation expert database management method and system

Country Status (1)

Country Link
CN (1) CN114413439A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108139854A (en) * 2015-08-26 2018-06-08 谷歌有限责任公司 The integrated antenna systems of intelligent thermostat and associated component management
CN110440396A (en) * 2019-07-11 2019-11-12 雄安达实智慧科技有限公司 The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration
CN112628956A (en) * 2020-12-24 2021-04-09 华中科技大学 Water chilling unit load prediction control method and system based on edge cloud cooperative framework
US20210180819A1 (en) * 2019-05-20 2021-06-17 Honeywell International Inc. Cloud and edge integrated energy optimizer
CN113739371A (en) * 2021-08-31 2021-12-03 广州汇电云联互联网科技有限公司 Central air-conditioning system based on cloud cooperation and control method thereof
EP3919992A1 (en) * 2020-06-06 2021-12-08 Honeywell International Inc. Method and system for managing virtual controllers in a building management system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108139854A (en) * 2015-08-26 2018-06-08 谷歌有限责任公司 The integrated antenna systems of intelligent thermostat and associated component management
US20210180819A1 (en) * 2019-05-20 2021-06-17 Honeywell International Inc. Cloud and edge integrated energy optimizer
CN110440396A (en) * 2019-07-11 2019-11-12 雄安达实智慧科技有限公司 The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration
EP3919992A1 (en) * 2020-06-06 2021-12-08 Honeywell International Inc. Method and system for managing virtual controllers in a building management system
CN112628956A (en) * 2020-12-24 2021-04-09 华中科技大学 Water chilling unit load prediction control method and system based on edge cloud cooperative framework
CN113739371A (en) * 2021-08-31 2021-12-03 广州汇电云联互联网科技有限公司 Central air-conditioning system based on cloud cooperation and control method thereof

Similar Documents

Publication Publication Date Title
US11513480B2 (en) Method and device for automatically diagnosing and controlling apparatus in intelligent building
CN113835344B (en) Control optimization method of equipment, display platform, cloud server and storage medium
CN107330056B (en) Wind power plant SCADA system based on big data cloud computing platform and operation method thereof
US6996508B1 (en) System and method for remote retrofit identification of energy consumption systems and components
CN112346351B (en) Thing networking device integration intelligence centralized control system based on BIM
US11188039B2 (en) Building management system with dynamic energy prediction model updates
CN115796393B (en) Energy management optimization method, system and storage medium based on multi-energy interaction
CN104063766A (en) Building energy efficiency management system based on cloud computing and big data technology
CN114489307A (en) Energy efficiency optimization method and device for internet data center
CN117036104B (en) Intelligent electricity utilization method and system based on electric power Internet of things
US11762349B2 (en) Control system for building equipment with equipment model adaptation
CN111780384A (en) Central air-conditioning control system
CN114383299A (en) Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation
CN111191851B (en) Knowledge graph-based data center energy efficiency optimization method
CN109901442B (en) Non-invasive energy consumption detection method and system
CN114358555A (en) Rail transit wisdom energy management system
CN112728723A (en) Method for monitoring and analyzing operation energy efficiency of refrigeration machine room by intelligent group control system
CN105299846A (en) Machine room group control device and method based on overall relevance optimization
CN103216919A (en) Air conditioner system based on dynamic environmental control refrigerating efficiency and control method
WO2019227273A1 (en) Hierarchical concept based neural network model for data center power usage effectiveness prediction
CN113790516A (en) Global optimization energy-saving control method and system for central air-conditioning refrigeration station and electronic equipment
CN111339641A (en) Refrigeration system management method and device, cloud platform and storage medium
CN114413439A (en) Self-learning-based central air conditioner operation expert database management method and system
CN116089086A (en) Rail transit energy saving method, device, equipment and storage medium
CN115099479A (en) Control method, device and storage medium for energy consumption budget of building energy equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination