CN110594954B - Air conditioner fault detection method and detection device - Google Patents
Air conditioner fault detection method and detection device Download PDFInfo
- Publication number
- CN110594954B CN110594954B CN201910748767.5A CN201910748767A CN110594954B CN 110594954 B CN110594954 B CN 110594954B CN 201910748767 A CN201910748767 A CN 201910748767A CN 110594954 B CN110594954 B CN 110594954B
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- operation parameters
- parameters
- random forest
- forest model
- 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.)
- Active
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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an air conditioner fault detection method and a detection device, wherein the detection method comprises the steps of receiving operating parameters of an air conditioner from the outside; collecting various operating parameters of an air conditioner; removing abnormal data points in each operating parameter; drawing a change curve of each operating parameter along with time; calculating the change rate of each operating parameter; calculating the operation predicted value of each operation parameter according to the received operation parameters; establishing a random forest model; and the random forest model judges whether a fault condition occurs or not and outputs a specific fault type. According to the method, the external operation parameters are received, the operation parameters of the air conditioner are collected, the operation parameters and the operation parameters are used as the basis, the change rate and the operation predicted value of the operation parameters are calculated, the data are input into the random forest model, the random forest model is used for outputting the possible specific fault conditions of the air conditioner at the current moment, and the method is high in detection accuracy and strong in real-time performance.
Description
Technical Field
The invention relates to the technical field of air conditioner detection, in particular to an air conditioner fault detection method and device.
Background
With the increasing improvement of the quality of life of people at present, every family is provided with a plurality of air conditioning equipment. With the continuous development of the current intelligent control technology, the existing air conditioning equipment is generally provided with numerous intelligent control operation functions, and the functions of voice control, voice parameter alarm, remote control, intelligent regulation and control of the frequency of the temperature and wind speed compressor and the like are common.
Although the existing air conditioning equipment is provided with various intelligent control functions, the air conditioning equipment is rarely provided with intelligent fault detection, as is well known, the air conditioning equipment is a large-scale equipment formed by assembling a control system, a compressor system, an evaporator, a condenser and the like, various abnormal conditions are inevitable to appear in each module in the air conditioning equipment during operation, and how to identify the abnormal conditions of the air conditioning equipment according to the operation parameters of the air conditioning equipment becomes a key point of the intelligent fault detection of the air conditioning equipment.
Patent document CN201310022660.5 discloses a method for detecting air conditioner faults, in which temperature parameters and operating power are simply collected and whether the temperature parameters and the operating power are within a predetermined range is used as a basis for determining whether the air conditioner has faults. The technical scheme is difficult to accurately detect the specific fault type of the air conditioner.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: provided are an air conditioner fault detection method and a detection device.
The solution of the invention for solving the technical problem is as follows:
an air conditioner fault detection method comprises the following steps:
step 100, receiving operating parameters of an external air conditioner;
200, collecting various operating parameters of the air conditioner;
step 300, removing abnormal data points in each operation parameter;
step 400, drawing a change curve of each operation parameter along with time;
step 500, calculating the change rate of each operation parameter;
step 600, calculating operation predicted values of various operation parameters according to the received operation parameters;
step 700, establishing a random forest model and completing the training operation of a random forest module;
and 800, inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, judging whether a fault condition occurs or not by the random forest model, and outputting specific fault types.
As a further improvement of the above technical solution, in step 100, the operating parameters of the air conditioner from the outside are received through one of an infrared communication mode, a bluetooth communication mode, a radio frequency communication mode, a WIFI communication mode and a key input mode.
As a further improvement of the above technical solution, in step 200, the operation parameters include a rotation speed of the compressor, a PWM signal frequency output by the frequency converter, an outlet air temperature, a temperature of the condenser, a temperature of the evaporator, an opening degree of the electronic expansion valve, and a pressure difference between the front and rear pipes of the electronic expansion valve.
As a further improvement of the above technical solution, in step 300, for each operating parameter, the following steps are respectively performed:
step 310, accumulating a plurality of data collected before the current time;
step 320, counting the number of the data of the operation parameters collected before the current moment, and calculating the average number of the operation parameters before the current moment;
step 330, setting an abnormal threshold value;
step 340, calculating a difference between the data of the operation parameters acquired at the current moment and the average number of the operation parameters before the current moment, if the difference is smaller than the abnormal threshold range, determining that the data of the operation parameters acquired at the current moment is normal data, and if the difference is larger than the abnormal threshold range, determining that the data of the operation parameters acquired at the current moment is abnormal data, and removing the data of the operation parameters acquired at the current moment.
As a further improvement of the above technical solution, in step 400, a least square method is used to complete the fitting operation of the variation curve of each operating parameter.
As a further improvement of the above technical solution, in step 600, according to the received operation parameters, the operation prediction values of the operation parameters are calculated by using a model based on the BP neural network.
The invention also discloses an air conditioner fault detection device, which comprises:
the input module is used for receiving the operating parameters of the air conditioner from the outside;
the sensor module is used for acquiring various operating parameters of the air conditioner;
the abnormal point removing module is used for removing abnormal data points in various operating parameters;
the curve drawing module is used for drawing a change curve of each operating parameter along with time;
the change rate calculation module is used for calculating the change rate of each operating parameter;
the prediction calculation module is used for calculating the operation prediction value of each operation parameter according to the received operation parameter;
the operation model module is used for establishing a random forest model and finishing the training operation of the random forest model;
and the judging module is used for inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, and the random forest model judges whether a fault condition occurs and outputs a specific fault type.
As a further improvement of the above technical solution, the input module receives the operating parameters of the air conditioner from the outside through one of an infrared communication mode, a bluetooth communication mode, a radio frequency communication mode, a WIFI communication mode and a key input mode.
As a further improvement of the above technical solution, the sensor module is used for respectively detecting the rotation speed of the compressor, the frequency of the PWM signal output by the frequency converter, the outlet air temperature, the temperature of the condenser, the temperature of the evaporator, the opening of the electronic expansion valve, and the pressure difference between the front and rear pipes of the electronic expansion valve.
The invention has the beneficial effects that: according to the method, the external operation parameters are received, the operation parameters of the air conditioner are collected, the operation parameters and the operation parameters are used as the basis, the change rate and the operation predicted value of the operation parameters are calculated, the data are input into the random forest model, the random forest model is used for outputting the possible specific fault conditions of the air conditioner at the current moment, and the method is high in detection accuracy and strong in real-time performance.
Drawings
In order to more clearly illustrate the technical solution in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is clear that the described figures are only some embodiments of the invention, not all embodiments, and that a person skilled in the art can also derive other designs and figures from them without inventive effort.
FIG. 1 is a schematic flow diagram of the process of the present invention.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the features and the effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all embodiments, and other embodiments obtained by those skilled in the art without inventive efforts based on the embodiments of the present application belong to the protection scope of the present application. In addition, all the connection relations mentioned herein do not mean that the components are directly connected, but mean that a better connection structure can be formed by adding or reducing connection accessories according to the specific implementation situation. All technical characteristics in the invention can be interactively combined on the premise of not conflicting with each other. Finally, it should be noted that the terms "center, upper, lower, left, right, vertical, horizontal, inner, outer" and the like as used herein refer to an orientation or positional relationship based on the drawings, which is only for convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application.
Referring to fig. 1, the present application discloses an air conditioner fault detection method, a first embodiment of which includes the steps of:
step 100, receiving operating parameters of an external air conditioner;
200, collecting various operating parameters of the air conditioner;
step 300, removing abnormal data points in each operation parameter;
step 400, drawing a change curve of each operation parameter along with time;
step 500, calculating the change rate of each operation parameter;
step 600, calculating operation predicted values of various operation parameters according to the received operation parameters;
step 700, establishing a random forest model and completing the training operation of a random forest module;
and 800, inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, judging whether a fault condition occurs or not by the random forest model, and outputting specific fault types.
Specifically, in this embodiment, by receiving external operation parameters and collecting operation parameters of the air conditioner, taking the operation parameters and the operation parameters as a basis, calculating a change rate and an operation predicted value of the operation parameters, inputting the above data into the random forest model, and outputting a possible specific fault condition of the air conditioner at the current time by using the random forest model, the detection accuracy is high, and the real-time performance is strong.
Further as a preferred implementation manner, in this embodiment, in step 100, the operation parameters of the air conditioner from the outside are received through one of an infrared communication manner, a bluetooth communication manner, a radio frequency communication manner, a WIFI communication manner, and a key input manner.
Further preferably, in this embodiment, the operation parameters in step 200 include a rotation speed of the compressor, a PWM signal frequency output by the frequency converter, an outlet air temperature, a temperature of the condenser, a temperature of the evaporator, an opening degree of the electronic expansion valve, and a pressure difference between the front and the rear of the electronic expansion valve. Specifically, the present embodiment specifically uses the rotation speed of the compressor, the PWM signal frequency output by the frequency converter, the air outlet temperature, the temperature of the condenser, the temperature of the evaporator, the opening of the electronic expansion valve, and the pressure difference between the front and rear pipes of the electronic expansion valve as the basis for determining the fault type of the air conditioner, so as to determine and analyze the fault type of the air conditioner by more than 90%, that is, the fault location, and facilitate the identification of the fault location of the air conditioner by the post-maintenance personnel.
Further as a preferred implementation manner, in step 300 of this embodiment, for each operating parameter, the following steps are respectively performed:
step 310, accumulating a plurality of data collected before the current time;
step 320, counting the number of the data of the operation parameters collected before the current moment, and calculating the average number of the operation parameters before the current moment;
step 330, setting an abnormal threshold value;
step 340, calculating a difference between the data of the operation parameters acquired at the current moment and the average number of the operation parameters before the current moment, if the difference is smaller than the abnormal threshold range, determining that the data of the operation parameters acquired at the current moment is normal data, and if the difference is larger than the abnormal threshold range, determining that the data of the operation parameters acquired at the current moment is abnormal data, and removing the data of the operation parameters acquired at the current moment.
Specifically, in this embodiment, the abnormal data in each operating parameter is removed for two purposes, the first purpose is to improve the accuracy of air conditioner fault detection for subsequent operations, clear the abnormal data to prevent the abnormal data from affecting the detection accuracy, and the second purpose is to reduce the calculation amount for subsequent operations.
Further, as a preferred embodiment, in step 400 of this embodiment, the least square method is used to complete the fitting operation of the change curve of each operation parameter, so as to effectively simplify the operation time of the fitting operation of the change curve, and further improve the real-time performance of air conditioner fault detection.
Further preferably, in step 600, the operation prediction values of the operation parameters are calculated by using the BP-based neural network model according to the received operation parameters.
The invention also discloses an air conditioner fault detection device, and the first embodiment comprises:
the input module is used for receiving the operating parameters of the air conditioner from the outside;
the sensor module is used for acquiring various operating parameters of the air conditioner;
the abnormal point removing module is used for removing abnormal data points in various operating parameters;
the curve drawing module is used for drawing a change curve of each operating parameter along with time;
the change rate calculation module is used for calculating the change rate of each operating parameter;
the prediction calculation module is used for calculating the operation prediction value of each operation parameter according to the received operation parameter;
the operation model module is used for establishing a random forest model and finishing the training operation of the random forest model;
and the judging module is used for inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, and the random forest model judges whether a fault condition occurs and outputs a specific fault type.
Further, as a preferred embodiment, in this embodiment, the input module receives the operation parameters of the air conditioner from the outside through one of an infrared communication mode, a bluetooth communication mode, a radio frequency communication mode, a WIFI communication mode, and a key input mode.
In a further preferred embodiment, in the present embodiment, the sensor module is configured to detect a rotation speed of the compressor, a PWM signal frequency output by the inverter, an outlet air temperature, a condenser temperature, an evaporator temperature, an opening degree of the electronic expansion valve, and a duct pressure difference between the front and the rear of the electronic expansion valve, respectively.
While the preferred embodiments of the present invention have been described in detail, it should be understood that the invention is not limited to those precise embodiments, and that various changes and modifications may be effected therein by one skilled in the art without departing from the scope or spirit of the invention as defined in the appended claims.
Claims (7)
1. The air conditioner fault detection method is characterized by comprising the following steps:
step 100, receiving operating parameters of an external air conditioner;
200, collecting various operating parameters of the air conditioner;
step 300, removing abnormal data points in each operation parameter;
step 400, drawing a change curve of each operation parameter along with time;
step 500, calculating the change rate of each operation parameter;
step 600, calculating operation predicted values of various operation parameters according to the received operation parameters;
step 700, establishing a random forest model and completing the training operation of a random forest module;
step 800, inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, and judging whether a fault condition occurs or not and outputting specific fault types by the random forest model;
in step 300, the following steps are respectively performed for each operating parameter:
step 310, accumulating a plurality of data collected before the current time;
step 320, counting the number of the data of the operation parameters collected before the current moment, and calculating the average number of the operation parameters before the current moment;
step 330, setting an abnormal threshold value;
step 340, calculating a difference value between the data of the operation parameters acquired at the current moment and the average number of the operation parameters before the current moment, if the difference value is smaller than an abnormal threshold range, judging that the data of the operation parameters acquired at the current moment is normal data, and if the difference value is larger than the abnormal threshold range, judging that the data of the operation parameters acquired at the current moment is abnormal data, and removing the data of the operation parameters acquired at the current moment;
in step 600, according to the received operation parameters, an operation prediction value of each operation parameter is calculated by using the BP-based neural network model.
2. An air conditioner fault detection method according to claim 1, characterized in that: in step 100, an operation parameter of the air conditioner from the outside is received through one of an infrared communication mode, a bluetooth communication mode, a radio frequency communication mode, a WIFI communication mode and a key input mode.
3. An air conditioner fault detection method according to claim 1, characterized in that: in step 200, the operation parameters include the rotation speed of the compressor, the frequency of the PWM signal output by the frequency converter, the outlet air temperature, the temperature of the condenser, the temperature of the evaporator, the opening of the electronic expansion valve, and the pressure difference between the front and rear pipes of the electronic expansion valve.
4. An air conditioner fault detection method according to claim 1, characterized in that: in step 400, a least square method is used to complete the fitting operation of the variation curve of each operation parameter.
5. An air conditioner fault detection device, comprising:
the input module is used for receiving the operating parameters of the air conditioner from the outside;
the sensor module is used for acquiring various operating parameters of the air conditioner;
the abnormal point removing module is used for removing abnormal data points in various operating parameters;
the curve drawing module is used for drawing a change curve of each operating parameter along with time;
the change rate calculation module is used for calculating the change rate of each operating parameter;
the prediction calculation module is used for calculating the operation prediction value of each operation parameter according to the received operation parameter;
the operation model module is used for establishing a random forest model and finishing the training operation of the random forest model;
and the judging module is used for inputting the operation parameters, the operation predicted values of the operation parameters and the change rates of the operation parameters into a random forest model, and the random forest model judges whether a fault condition occurs and outputs a specific fault type.
6. The air conditioner fault detection device of claim 5, wherein the input module receives the operating parameters of the air conditioner from the outside through one of an infrared communication mode, a Bluetooth communication mode, a radio frequency communication mode, a WIFI communication mode and a key input mode.
7. The air conditioner fault detection device of claim 5, wherein the sensor module is configured to detect a rotation speed of a compressor, a frequency of a PWM signal output by an inverter, an outlet air temperature, a condenser temperature, an evaporator temperature, an opening degree of an electronic expansion valve, and a duct pressure difference between the front and the rear of the electronic expansion valve, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748767.5A CN110594954B (en) | 2019-08-14 | 2019-08-14 | Air conditioner fault detection method and detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748767.5A CN110594954B (en) | 2019-08-14 | 2019-08-14 | Air conditioner fault detection method and detection device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110594954A CN110594954A (en) | 2019-12-20 |
| CN110594954B true CN110594954B (en) | 2021-04-27 |
Family
ID=68854178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910748767.5A Active CN110594954B (en) | 2019-08-14 | 2019-08-14 | Air conditioner fault detection method and detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110594954B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468709A (en) * | 2020-03-30 | 2021-10-01 | 广州展闰数域科技有限公司 | Method for intelligently monitoring state, adjusting air conditioner parameters and predicting air conditioner fault |
| CN111706499B (en) * | 2020-06-09 | 2022-03-01 | 成都数之联科技有限公司 | Predictive maintenance system and method for vacuum pump and automatic vacuum pump purchasing system |
| CN114738938B (en) * | 2022-03-04 | 2024-09-13 | 青岛海尔空调电子有限公司 | Multi-split air conditioning unit fault monitoring method, device and storage medium |
| CN114781762B (en) * | 2022-06-21 | 2022-09-23 | 四川观想科技股份有限公司 | Equipment fault prediction method based on life consumption |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4392604B2 (en) * | 2004-09-07 | 2010-01-06 | 清水建設株式会社 | Air conditioning load prediction method |
| CN102692066B (en) * | 2012-06-14 | 2014-11-26 | 四川长虹空调有限公司 | Fault diagnosis control system for variable-frequency air conditioner and control method of fault diagnosis control system |
| CN107575996A (en) * | 2017-09-14 | 2018-01-12 | 深圳达实智能股份有限公司 | Hospital's air conditioner in machine room unit self checking method and device |
| CN108592352B (en) * | 2018-05-09 | 2020-09-11 | 国家计算机网络与信息安全管理中心 | Method, device and system for predicting running state health degree of water-cooled air-conditioning system |
| CN109460873A (en) * | 2018-11-14 | 2019-03-12 | 北京未来科学城科技发展有限公司 | Air-conditioning system running optimizatin method and apparatus |
-
2019
- 2019-08-14 CN CN201910748767.5A patent/CN110594954B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110594954A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110594954B (en) | Air conditioner fault detection method and detection device | |
| US20060155514A1 (en) | Method of tracking the performance of an industrial appliance | |
| CN112882445B (en) | Intelligent monitoring and management system for 5G and block chain for intelligent manufacturing | |
| CN111209934B (en) | Fan fault pre-alarm method and system | |
| CN110895867A (en) | Tailing conveying pipeline dynamic alarm method based on pressure signals | |
| CN114801751A (en) | Automobile battery fault prediction system based on data analysis | |
| CN111245833B (en) | Vehicle intrusion detection method and device | |
| CN110173422A (en) | Vacuum pump Internet of Things on-line monitoring system, method and terminal device | |
| CN105848158A (en) | Pseudo base station judging method and device | |
| CN114580852A (en) | Water pump breakwater clearance real-time warning system based on industry big data | |
| CN106837768A (en) | A kind of air compressor efficiency on-line checking assessment system and method | |
| CN112380707A (en) | Method and device for evaluating cooling performance of EGR cooler and electronic equipment | |
| CN115664551A (en) | Safety monitoring and early warning system for radio frequency power amplifier | |
| CN116951328B (en) | Intelligent drainage pipeline operation monitoring system based on big data | |
| CN112212980B (en) | Human body temperature detection method capable of resisting external environment temperature interference | |
| CN113324776A (en) | Detection device and detection method for air conditioning unit | |
| CN113050522A (en) | Valve state detection method based on safety monitoring function Internet of things intelligent gas meter | |
| CN111775760B (en) | Intelligent management system for solar charging piles | |
| CN206096384U (en) | Breaker state monitoring system based on divide closing coils electric current | |
| CN114488994A (en) | Optimization method and device for improving vehicle fault diagnosis robustness | |
| CN112351071B (en) | Traditional chinese medicine production remote monitering system based on cloud calculates | |
| CN110596526A (en) | Distribution line fault detection positioning system and method based on zero sequence current | |
| CN114659562B (en) | Intelligent state early warning method for fixed fire water supply equipment | |
| CN113607305B (en) | Alarm method for monitoring power environment of cabinet | |
| CN118169719B (en) | Energy management and optimal control system of Beidou navigation vehicle-mounted terminal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |