CN113432243A - Intelligent early warning method for running state of air conditioner cabinet - Google Patents
Intelligent early warning method for running state of air conditioner cabinet Download PDFInfo
- Publication number
- CN113432243A CN113432243A CN202110723723.4A CN202110723723A CN113432243A CN 113432243 A CN113432243 A CN 113432243A CN 202110723723 A CN202110723723 A CN 202110723723A CN 113432243 A CN113432243 A CN 113432243A
- Authority
- CN
- China
- Prior art keywords
- early warning
- air
- parameters
- air conditioning
- 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
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
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/32—Responding to malfunctions or emergencies
- F24F11/38—Failure diagnosis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an intelligent early warning method for the running state of an air conditioner cabinet, which is mainly characterized in that transverse and longitudinal comprehensive analysis is carried out by monitoring multiple parameters of the air conditioner cabinet in real time, so as to judge the working state of the air conditioner cabinet and carry out slight fault early warning. Specifically, the running state of the existing air conditioning system is monitored in real time through data collection and machine self-learning analysis and study, and subtle abnormity occurring in the running process of the air conditioner is studied and judged through big data analysis, early warning is realized before serious faults occur, and a processing scheme of an early warning part is provided according to a data analysis result, so that the production safety is prevented from being influenced, an operator is specifically informed in a voice interaction mode, voice guidance is provided for early warning processing, and the hidden fault danger can be accurately eliminated by a maintainer.
Description
Technical Field
The invention relates to the field of cigarette industry, in particular to an intelligent early warning method for the running state of an air conditioner cabinet.
Background
The air conditioning system in the cigarette field plays a vital role in cigarette production safety, and due to the fact that the whole system is large, fine faults of the air conditioning system are difficult to find at the first time, so that serious production accidents are found and processed, production is seriously affected, and the air conditioning system also has a threat to cigarette safety production.
The working state of the air conditioning system is good and bad, the working state of the air conditioning cabinet is mainly reflected, the working state of the air conditioning cabinet is monitored in real time, and the major faults of the air conditioning system can be effectively avoided and the safety production is influenced by timely finding and early warning of slight problems. However, at present, a more intelligent and reasonable solution is still lacking for fault monitoring of an air conditioning system in the field of cigarette industry.
Disclosure of Invention
In view of the above, the present invention aims to provide an intelligent early warning method for the operation state of an air conditioning cabinet, so as to make up for the deficiency of fault monitoring of the air conditioning system in the field of the existing cigarette industry.
The technical scheme adopted by the invention is as follows:
an intelligent early warning method for the running state of an air conditioner cabinet comprises the following steps:
collecting the running state parameters of the air conditioning unit related to the air conditioning cabinet in real time;
combining a preset transverse and longitudinal anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative mode;
calling a pre-constructed voice interaction database according to the abnormal analysis result, and outputting early warning interaction voice information; the early warning interactive voice information comprises abnormal position interactive information, abnormal time node interactive information and repair guidance interactive information.
In at least one possible implementation manner, the preset transverse anomaly analysis strategy includes: and transversely comparing the operating parameters of different air conditioning units at the same time node and under the same working state.
In at least one possible implementation manner, combining a preset transverse anomaly analysis strategy with big data and a machine learning technology, and optimizing and outputting an anomaly analysis result in an iterative manner includes:
collecting full-line running states and parameters of different air conditioning units in no less than 3 seasons in advance;
a first abnormity studying and judging model is constructed in advance according to the full-line running state and parameters;
and obtaining an anomaly analysis result based on the result of the transverse comparison and the first anomaly studying and judging model.
In at least one possible implementation manner, the preset longitudinal anomaly analysis strategy includes: and longitudinally comparing the current operating parameters of the same air conditioning unit with the historical operating parameters under the same working state.
In at least one possible implementation manner, combining a preset transverse anomaly analysis strategy with big data and a machine learning technology, and optimizing and outputting an anomaly analysis result in an iterative manner includes:
collecting full-line running states and parameters of the same air conditioning unit in a plurality of historical time periods in advance; wherein the plurality of historical time periods comprise a plurality of combinations of the following historical time nodes: one day, one week, one month, one quarter, one half year, three quarters, one year;
a plurality of corresponding second anomaly studying and judging models are constructed in advance according to the full-line running states and parameters of a plurality of historical time periods;
obtaining a plurality of abnormal analysis results based on the result of longitudinal comparison and the plurality of second abnormal studying and judging models;
and performing fusion analysis on the plurality of abnormal analysis results to determine a target abnormal analysis result.
In at least one possible implementation manner, the method further includes: and before the abnormal state related to the early warning interactive voice information is eliminated, the early warning interactive voice information is repeatedly output according to a preset time period.
In at least one possible implementation manner, the method further includes: and classifying and storing the output abnormal analysis result and the early warning interactive voice information each time, and enabling the stored information to participate in the iterative optimization process of big data and machine learning.
In at least one possible implementation manner, the acquiring, in real time, the operating state parameters of the air conditioning unit related to the air conditioning cabinet includes reading, from the air conditioning cabinet, various combinations of the following operating parameters: fresh air speed, air supply speed, air return speed, air temperature, rheumatism, air pressure, air-conditioning fan operation frequency, air-conditioning fan temperature, air-conditioning fan vibration intensity, humidification system working parameters, steam system working parameters and pressure difference between two ends of a filter and a surface cooler.
The invention has the main conception that the transverse and longitudinal comprehensive analysis is carried out by monitoring a plurality of parameters of the air-conditioning cabinet in real time, so as to judge the working state of the air-conditioning cabinet and carry out slight fault early warning. Specifically, the running state of the existing air conditioning system is monitored in real time through data collection and machine self-learning analysis and study, and subtle abnormity occurring in the running process of the air conditioner is studied and judged through big data analysis, early warning is realized before serious faults occur, and a processing scheme of an early warning part is provided according to a data analysis result, so that the production safety is prevented from being influenced, an operator is specifically informed in a voice interaction mode, voice guidance is provided for early warning processing, and the hidden fault danger can be accurately eliminated by a maintainer.
According to the invention, the working state and the abnormal state of the air conditioning system are automatically and intelligently researched and judged through big data and a machine learning technology, and the early warning accuracy of slight abnormality of the system is gradually improved in a self-learning manner.
The invention has perfect intelligent analysis and voice interaction functions, and can be widely applied to large-scale industrial air-conditioning systems and commercial central air-conditioning systems similar to the cigarette field.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of an intelligent early warning method for an operation state of an air conditioner cabinet according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
The invention provides an embodiment of an intelligent early warning method for the running state of an air conditioner cabinet, which can be specifically shown in figure 1 and comprises the following steps:
step S1, collecting the running state parameters of the air conditioning unit related to the air conditioning cabinet in real time;
step S2, combining a preset transverse and longitudinal anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative mode;
step S3, calling a pre-constructed voice interaction database according to the abnormal analysis result, and outputting early warning interaction voice information; the early warning interactive voice information comprises abnormal position interactive information, abnormal time node interactive information and repair guidance interactive information.
In practical operation, the real-time collection of the operation state parameters of the air conditioning unit related to the air conditioning cabinet may include reading various combinations of the following operation parameters from the air conditioning cabinet: fresh air speed, air supply speed, air return speed, air temperature, rheumatism, air pressure, air-conditioning fan operation frequency, air-conditioning fan temperature, air-conditioning fan vibration intensity, humidification system working parameters, steam system working parameters and pressure difference between two ends of a filter and a surface cooler.
The invention emphasizes the purpose of combining the operation parameters of the air-conditioning cabinet with machine learning and big data technology, and can effectively improve the early warning accuracy, for example, the early warning can be performed when the better early warning accuracy can reach 1% of the abnormal rate, and the horizontal and vertical analysis results and the big data analysis are comprehensively researched and judged, so that the abnormal point position can be more accurately positioned, and a targeted maintenance and repair scheme can be provided.
The voice interaction database provided by the invention can also be continuously optimized and enriched by utilizing machine learning and big data technology, for example, but not limited to, the grammar and pronunciation of different personnel can be recognized in a self-learning mode, and the recognition and analysis capability of the voice interaction instruction can be continuously improved.
The strategy of carrying out horizontal and vertical analysis and combining big data, machine learning technique with air conditioner cabinet data and carrying out optimization output can carry out accurate early warning and provide optimal processing scheme to air conditioning system's slight trouble to and when realizing accurate early warning, borrow by accessible pronunciation intelligence mutual, promote the treatment effeciency of maintenance.
Further, the preset transverse anomaly analysis strategy may include: and transversely comparing the operating parameters of different air conditioning units at the same time node and under the same working state.
Further, combining a preset transverse anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative manner may include: collecting full-line running states and parameters of different air conditioning units in no less than 3 seasons in advance; a first abnormity studying and judging model is constructed in advance according to the full-line running state and parameters; and obtaining an abnormal analysis result (transverse direction) based on the result of the transverse comparison and the first abnormal judging model.
Further, the preset longitudinal anomaly analysis strategy may include: and longitudinally comparing the current operating parameters of the same air conditioning unit with the historical operating parameters under the same working state.
Further, combining a preset transverse anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative manner may include: collecting full-line running states and parameters of the same air conditioning unit in a plurality of historical time periods in advance; wherein the plurality of historical time periods comprise a plurality of combinations of the following historical time nodes: one day, one week, one month, one quarter, one half year, three quarters, one year; a plurality of corresponding second anomaly studying and judging models are constructed in advance according to the full-line running states and parameters of a plurality of historical time periods; obtaining a plurality of abnormal analysis results based on the result of longitudinal comparison and the plurality of second abnormal studying and judging models; the several anomaly analysis results are subjected to fusion analysis (such as but not limited to weighted summation) to determine a target anomaly analysis result (longitudinal).
Further, the method may further include: and before the abnormal state related to the early warning interactive voice information is eliminated, the early warning interactive voice information is repeatedly output according to a preset time period.
Further, the method may further include: and classifying and storing the output abnormal analysis result and the early warning interactive voice information each time, and enabling the stored information to participate in the iterative optimization process of big data and machine learning.
In summary, the main idea of the present invention is to perform a comprehensive analysis in the horizontal and vertical directions by monitoring multiple parameters of the air-conditioning cabinet in real time, so as to determine the working state of the air-conditioning cabinet and perform a fine fault pre-warning. Specifically, the running state of the existing air conditioning system is monitored in real time through data collection and machine self-learning analysis and study, and subtle abnormity occurring in the running process of the air conditioner is studied and judged through big data analysis, early warning is realized before serious faults occur, and a processing scheme of an early warning part is provided according to a data analysis result, so that the production safety is prevented from being influenced, an operator is specifically informed in a voice interaction mode, voice guidance is provided for early warning processing, and the hidden fault danger can be accurately eliminated by a maintainer.
The structure, features and effects of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the above embodiments are merely preferred embodiments of the present invention, and it should be understood that technical features related to the above embodiments and preferred modes thereof can be reasonably combined and configured into various equivalent schemes by those skilled in the art without departing from and changing the design idea and technical effects of the present invention; therefore, the invention is not limited to the embodiments shown in the drawings, and all the modifications and equivalent embodiments that can be made according to the idea of the invention are within the scope of the invention as long as they are not beyond the spirit of the description and the drawings.
Claims (8)
1. An intelligent early warning method for the running state of an air conditioner cabinet is characterized by comprising the following steps:
collecting the running state parameters of the air conditioning unit related to the air conditioning cabinet in real time;
combining a preset transverse and longitudinal anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative mode;
calling a pre-constructed voice interaction database according to the abnormal analysis result, and outputting early warning interaction voice information; the early warning interactive voice information comprises abnormal position interactive information, abnormal time node interactive information and repair guidance interactive information.
2. The intelligent early warning method for the operation state of the air conditioner cabinet according to claim 1, wherein the preset transverse anomaly analysis strategy comprises the following steps: and transversely comparing the operating parameters of different air conditioning units at the same time node and under the same working state.
3. The intelligent early warning method for the operation state of the air conditioner cabinet according to claim 2, wherein the step of combining a preset transverse anomaly analysis strategy with big data and machine learning technology, and the step of optimizing and outputting an anomaly analysis result in an iterative manner comprises the following steps:
collecting full-line running states and parameters of different air conditioning units in no less than 3 seasons in advance;
a first abnormity studying and judging model is constructed in advance according to the full-line running state and parameters;
and obtaining an anomaly analysis result based on the result of the transverse comparison and the first anomaly studying and judging model.
4. The intelligent early warning method for the operation state of the air conditioner cabinet according to claim 1, wherein the preset longitudinal anomaly analysis strategy comprises the following steps: and longitudinally comparing the current operating parameters of the same air conditioning unit with the historical operating parameters under the same working state.
5. The intelligent early warning method for the operation state of the air conditioning cabinet according to claim 4,
combining a preset transverse anomaly analysis strategy with big data and machine learning technology, optimizing and outputting an anomaly analysis result in an iterative mode comprises the following steps:
collecting full-line running states and parameters of the same air conditioning unit in a plurality of historical time periods in advance; wherein the plurality of historical time periods comprise a plurality of combinations of the following historical time nodes: one day, one week, one month, one quarter, one half year, three quarters, one year;
a plurality of corresponding second anomaly studying and judging models are constructed in advance according to the full-line running states and parameters of a plurality of historical time periods;
obtaining a plurality of abnormal analysis results based on the result of longitudinal comparison and the plurality of second abnormal studying and judging models;
and performing fusion analysis on the plurality of abnormal analysis results to determine a target abnormal analysis result.
6. The intelligent early warning method for the operation state of the air conditioner cabinet as claimed in claim 1, wherein the method further comprises: and before the abnormal state related to the early warning interactive voice information is eliminated, the early warning interactive voice information is repeatedly output according to a preset time period.
7. The intelligent early warning method for the operation state of the air conditioner cabinet as claimed in claim 1, wherein the method further comprises: and classifying and storing the output abnormal analysis result and the early warning interactive voice information each time, and enabling the stored information to participate in the iterative optimization process of big data and machine learning.
8. The intelligent early warning method for the operation state of the air conditioning cabinet according to any one of claims 1 to 7, wherein the real-time collection of the operation state parameters of the air conditioning unit related to the air conditioning cabinet comprises reading various combinations of the following operation parameters from the air conditioning cabinet: fresh air speed, air supply speed, air return speed, air temperature, rheumatism, air pressure, air-conditioning fan operation frequency, air-conditioning fan temperature, air-conditioning fan vibration intensity, humidification system working parameters, steam system working parameters and pressure difference between two ends of a filter and a surface cooler.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110723723.4A CN113432243A (en) | 2021-06-29 | 2021-06-29 | Intelligent early warning method for running state of air conditioner cabinet |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110723723.4A CN113432243A (en) | 2021-06-29 | 2021-06-29 | Intelligent early warning method for running state of air conditioner cabinet |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113432243A true CN113432243A (en) | 2021-09-24 |
Family
ID=77757442
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110723723.4A Pending CN113432243A (en) | 2021-06-29 | 2021-06-29 | Intelligent early warning method for running state of air conditioner cabinet |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113432243A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114396705A (en) * | 2021-12-20 | 2022-04-26 | 珠海格力电器股份有限公司 | Air conditioner fault detection method and device, electronic equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104697128A (en) * | 2015-03-05 | 2015-06-10 | 美的集团股份有限公司 | Air conditioner and fault detection method thereof |
CN106547858A (en) * | 2016-10-21 | 2017-03-29 | 珠海格力电器股份有限公司 | A kind of air conditioning unit big data analysis method and air conditioning unit |
CN109598308A (en) * | 2018-12-12 | 2019-04-09 | 国网山东省电力公司临沂供电公司 | A kind of data processing platform (DPP) and method judging automatically equipment fault |
CN109974209A (en) * | 2019-04-01 | 2019-07-05 | 珠海格力电器股份有限公司 | The control method and device of air-conditioning |
CN111578444A (en) * | 2019-02-19 | 2020-08-25 | 珠海格力电器股份有限公司 | Air conditioner fault prediction method and device, storage medium and air conditioner |
JP2020165622A (en) * | 2019-03-29 | 2020-10-08 | 三機工業株式会社 | Prediction method for air conditioning load and air conditioning system |
-
2021
- 2021-06-29 CN CN202110723723.4A patent/CN113432243A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104697128A (en) * | 2015-03-05 | 2015-06-10 | 美的集团股份有限公司 | Air conditioner and fault detection method thereof |
CN106547858A (en) * | 2016-10-21 | 2017-03-29 | 珠海格力电器股份有限公司 | A kind of air conditioning unit big data analysis method and air conditioning unit |
CN109598308A (en) * | 2018-12-12 | 2019-04-09 | 国网山东省电力公司临沂供电公司 | A kind of data processing platform (DPP) and method judging automatically equipment fault |
CN111578444A (en) * | 2019-02-19 | 2020-08-25 | 珠海格力电器股份有限公司 | Air conditioner fault prediction method and device, storage medium and air conditioner |
JP2020165622A (en) * | 2019-03-29 | 2020-10-08 | 三機工業株式会社 | Prediction method for air conditioning load and air conditioning system |
CN109974209A (en) * | 2019-04-01 | 2019-07-05 | 珠海格力电器股份有限公司 | The control method and device of air-conditioning |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114396705A (en) * | 2021-12-20 | 2022-04-26 | 珠海格力电器股份有限公司 | Air conditioner fault detection method and device, electronic equipment and medium |
CN114396705B (en) * | 2021-12-20 | 2023-05-30 | 珠海格力电器股份有限公司 | Air conditioner fault detection method and device, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102175282B (en) | Method for diagnosing fault of centrifugal air compressor based on information fusion | |
CN109185917B (en) | Boiler combustion state online diagnosis method and system based on flame intensity signal | |
CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
CN112836941B (en) | Online health condition assessment method for high-pressure system of steam turbine of coal motor unit | |
CN113432243A (en) | Intelligent early warning method for running state of air conditioner cabinet | |
CN112561238A (en) | Pumped storage power station auxiliary equipment state health evaluation system and method | |
CN116660672B (en) | Power grid equipment fault diagnosis method and system based on big data | |
CN110333697A (en) | A kind of internet of things data acquisition analysis system applied to high-pressure wash machine people | |
CN115639217B (en) | Industrial control full detection method and system for cover plate piece of new energy power battery | |
Rosli et al. | Predictive maintenance of air booster compressor (ABC) motor failure using artificial neural network trained by particle swarm optimization | |
CN112906920A (en) | State monitoring and predictive maintenance method and device for intelligent automobile manufacturing equipment | |
CN111950822A (en) | Performance detection method and device for cooling system of traction transformer of vehicle, storage medium and terminal | |
CN115309119A (en) | Control method and system of workshop inspection robot, computer equipment and medium | |
US20230376024A1 (en) | Device and Method for Identifying Anomalies in an Industrial System for Implementing a Production Process | |
CN112733943B (en) | Heat pump fault diagnosis model migration method based on data mixed shearing technology | |
CN113538997A (en) | Equipment predictive maintenance learning system | |
CN113268051A (en) | TBOX testing system and method based on cloud platform | |
Windmann et al. | Evaluation of model-based condition monitoring systems in industrial application cases | |
CN117170304B (en) | PLC remote monitoring control method and system based on industrial Internet of things | |
CN105629938A (en) | Intelligent monitoring method for vulnerable part | |
CN213482933U (en) | Workpiece production equipment maintenance monitoring devices based on state | |
CN117589177B (en) | Autonomous navigation method based on industrial large model | |
CN116777086B (en) | Predictive maintenance method and system for intelligent steel structure production line based on multimode data | |
CN116776650B (en) | Running state control system of box-type substation | |
CN117114254B (en) | Power grid new energy abnormal data monitoring method and system |
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 |