CN102393882A - Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line - Google Patents

Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line Download PDF

Info

Publication number
CN102393882A
CN102393882A CN2011102807261A CN201110280726A CN102393882A CN 102393882 A CN102393882 A CN 102393882A CN 2011102807261 A CN2011102807261 A CN 2011102807261A CN 201110280726 A CN201110280726 A CN 201110280726A CN 102393882 A CN102393882 A CN 102393882A
Authority
CN
China
Prior art keywords
iaq
sensor
train
test
virtual 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.)
Granted
Application number
CN2011102807261A
Other languages
Chinese (zh)
Other versions
CN102393882B (en
Inventor
宋哲
周炯
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.)
Ji Zhong energy saving technology (Suzhou) Co., Ltd.
Original Assignee
Ji Zhong Energy Saving Technology (suzhou) 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 Ji Zhong Energy Saving Technology (suzhou) Co Ltd filed Critical Ji Zhong Energy Saving Technology (suzhou) Co Ltd
Priority to CN201110280726.1A priority Critical patent/CN102393882B/en
Publication of CN102393882A publication Critical patent/CN102393882A/en
Application granted granted Critical
Publication of CN102393882B publication Critical patent/CN102393882B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Testing Or Calibration Of Command Recording Devices (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a method for monitoring and diagnosing an indoor air quality (IAQ) sensor on line. In the invention, on the base of the virtual model of an IAQ sensor, the IAQ sensor is monitored and diagnosed on line through a control graph, wherein the control graph can monitor the mean difference and variance between an IAQ parameter value predicted by the virtual model of the IAQ sensor and an IAQ parameter value measured by the sensor. By the model, according to the invention, as the accurate, stable and reliable virtual model of the IAQ has the functions of monitoring the IAQ sensor on line, initiatively finding potential faults, timely maintaining and calibrating the sensor, the invention has the advantages that the cost is low, the initiative is good, and the pertinence is strong.

Description

The method of air mass sensor in on-line monitoring and the diagnosis room
Technical field
The present invention relates to the building energy saving field, particularly relate to the method for air mass sensor in a kind of on-line monitoring and the diagnosis room.
Background technology
Building energy saving is a relatively younger industry.Through nearly 20 years development, from simple replacing new equipment energy-conservation develop into utilize a large amount of IT and automatic control technology realize energy-conservation with improve indoor comfort degree, but 90% Chinese building energy saving company also rests on the level of exchange device more.Nearly 50% energy consumption of building is to be used in the HVAC system, is emphasis to the energy-conservation of HVAC system therefore.
Normal and the operation efficiently of HVAC system relies on output, especially the IAQ sensor (such as carbon dioxide, humidity and temperature sensor) of various sensors.In order to guarantee the operate as normal of these important sensor, existing technological means is regularly these sensors to be calibrated, and redundant sensor perhaps is installed, and guarantees the accuracy of metrical information.
Mainly there is following deficiency in these technological means: at first be that cost is higher, redundant sensor is installed must increase corresponding cost; Next is a passivity, and this periodic calibration must have certain time interval, causes equipment to be in the blind area like this, can only wait until that also follow-on check constantly just can know even break down; Blindness, periodic calibration is no problem no matter this sensor has, all to calibrate, be waste of manpower and material resources to a certain extent, should preferentially calibrate those Symptomatic sensors.
Summary of the invention
The technical matters that the present invention mainly solves provides the method for a kind of on-line monitoring and diagnosis IAQ sensor; Based on accurate, a stable and reliable IAQ sensor virtual model on-line monitoring IAQ sensor; Initiatively find potential fault, in time the function of maintenance and calibrating sensors.
For solving the problems of the technologies described above; The technical scheme that the present invention adopts is: the method for a kind of on-line monitoring with diagnosis IAQ sensor is provided; This method is based on an IAQ sensor virtual model and through a control chart IAQ sensor is carried out on-line monitoring and diagnosis, said control chart with the IAQ parameter value of the prediction of IAQ sensor virtual model and sensor measurement to the IAQ parameter value between mean difference and variance be able to monitoring.
In preferred embodiment of the present invention, the construction method of said control chart is:
A, from the HVAC system, choose remove exceptional value by N TrainThe training dataset that individual measured value is formed and according to the N of time sequencing TestThe test data set that individual consecutive numbers strong point is formed,
The method for expressing of training dataset is: y-TrainSet=[y (i), y ' is (i)], and i=1 ..., N Train.,
The method for expressing of test data set is: y-TestSet=[y (i), y ' is (i)], and i=1 ..., N Test.;
B, calculate training data and concentrate difference ε and mean difference μ thereof between each point TrainAnd standard deviation sigma TrainAnd test data is concentrated difference ε and mean difference μ thereof between each point TestAnd standard deviation sigma Test
C, work as μ TrainAnd σ TrainKnown, through calculating mean difference μ TrainControl limit and variances sigma 2 TrainControl limit detect abnormal conditions, the definition μ TrainThe higher extreme value of control limit be UCL 1, low extreme value is LCL 1, definition σ 2 TrainThe higher extreme value of control limit be UCL 2, low extreme value is LCL 2
In preferred embodiment of the present invention; The computing method of said difference ε are: ε=
Figure 225064DEST_PATH_IMAGE001
; Wherein y is the IAQ parameter value that sensor measurement arrives, and y ' is by IAQ sensor virtual model prediction IAQ parameter value.
In preferred embodiment of the present invention, μ TrainAccount form be: μ Train=
Figure 2011102807261100002DEST_PATH_IMAGE002
Figure 204521DEST_PATH_IMAGE003
;
σ TrainAccount form be: σ Train=
Figure 2011102807261100002DEST_PATH_IMAGE004
μ TestAccount form be: μ Test=
Figure 545110DEST_PATH_IMAGE005
Figure 2011102807261100002DEST_PATH_IMAGE006
;
σ TestAccount form be: σ Test=
Figure 2636DEST_PATH_IMAGE007
In preferred embodiment of the present invention, UCL 1Account form be: UCL 1=
Figure 2011102807261100002DEST_PATH_IMAGE008
LCL 1Account form be: LCL 1=
Figure 879325DEST_PATH_IMAGE009
UCL 2Account form be: UCL 2=
Figure 2011102807261100002DEST_PATH_IMAGE010
LCL 2Account form be: LCL 2=0;
Wherein, N TestBe meant the quantity of the concentrated data point of test data, η is the multiple of control limit;
Wherein
Figure 764105DEST_PATH_IMAGE011
The card side of expression right side α/2 quantiles distributes N Test-1 is meant the degree of freedom that card side distributes.
In preferred embodiment of the present invention, said μ TestBe higher than UCL 1Perhaps be lower than LCL 1, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error I.
In preferred embodiment of the present invention, said σ 2 TrainBe higher than UCL 2, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error II.
In preferred embodiment of the present invention, the method for building up of said IAQ sensor virtual model comprises:
A, collection data: at first regulate and collect multiple parameter set (HVAC) system from heat supply, heating ventilation and air-conditioning; Comprise temperature parameter collection, carbon dioxide level parameter set, relative humidity parameter set; Each parameter set is divided into two independent subclass, comprises training dataset, test data set;
B, set up model: the IAQ sensor virtual model of concentrating data to set up based on training data with multiple different pieces of information mining algorithm; IAQ sensor virtual model is the HVAC parameter generating prediction IAQ parameter value with other, comprises the IAQ sensor virtual model of predicted temperature, the IAQ sensor virtual model of prediction carbon dioxide level, the IAQ sensor virtual model of prediction relative humidity;
C, select the optimum data mining algorithm: the IAQ parameter value of prediction and sensor to the absolute value of IAQ parameter value difference be absolute error; Standard deviation through absolute error mean value and absolute error is weighed the prediction effect with the IAQ sensor virtual model of the foundation of different pieces of information mining algorithm, the best data mining algorithm of selection prediction effect;
D, validity check: the measurement data that the IAQ parameter value and the test data of prediction are concentrated compares, and according to the consistance between two data values, judges the validity of the IAQ sensor virtual model that the best data mining algorithm of prediction effect is set up.
In preferred embodiment of the present invention, said absolute error is defined as AE, and the computing method of said AE are: AE=|y '-y|;
Said absolute error mean value is defined as MAE, and the computing method of said MAE are: MAE= ;
The standard deviation of said absolute error is defined as Std, and the computing method of said Std are: Std=
Figure 594920DEST_PATH_IMAGE013
;
Wherein y ' is the IAQ parameter value of IAQ sensor virtual model prediction, and y is the IAQ parameter value that sensor measurement arrives, and N is the quantity of test data point.
In preferred embodiment of the present invention, said multiple different pieces of information mining algorithm comprises that multilayer perceptron (MLP) neural network (NN), RBF (RBF) neural network (NN), SVMs return (SVM), progressively recurrence (Pacereg).
The invention has the beneficial effects as follows: the method for on-line monitoring of the present invention and diagnosis IAQ sensor can have on-line monitoring IAQ sensor based on accurate, stable and reliable IAQ sensor virtual model; Initiatively find potential fault; The function of timely maintenance and calibrating sensors; Cost is low, and initiative is good, and is with strong points.
Embodiment
Set forth in detail in the face of preferred embodiment of the present invention down, thereby protection scope of the present invention is made more explicit defining so that advantage of the present invention and characteristic can be easier to it will be appreciated by those skilled in the art that.
The embodiment of the invention comprises:
The method of a kind of on-line monitoring and diagnosis IAQ sensor; This method is based on an IAQ sensor virtual model and through a control chart IAQ sensor is carried out on-line monitoring and diagnosis, said control chart with the IAQ parameter value of the prediction of IAQ sensor virtual model and sensor measurement to the IAQ parameter value between mean difference and variance be able to monitoring.
The construction method of said control chart is:
A, from the HVAC system, choose remove exceptional value by N TrainThe training dataset that individual measured value is formed and according to the N of time sequencing TestThe test data set that individual consecutive numbers strong point is formed,
The method for expressing of training dataset is: y-TrainSet=[y (i), y ' is (i)], and i=1 ..., N Train.,
The method for expressing of test data set is: y-TestSet=[y (i), y ' is (i)], and i=1 ..., N Test.;
B, calculate training data and concentrate difference ε and mean difference μ thereof between each point TrainAnd standard deviation sigma TrainAnd test data is concentrated difference ε and mean difference μ thereof between each point TestAnd standard deviation sigma Test
C, work as μ TrainAnd σ TrainKnown, through calculating mean difference μ TrainControl limit and variances sigma 2 TrainControl limit detect abnormal conditions, the definition μ TrainThe higher extreme value of control limit be UCL 1, low extreme value is LCL 1, definition σ 2 TrainThe higher extreme value of control limit be UCL 2, low extreme value is LCL 2
The computing method of said difference ε are: ε=
Figure 856137DEST_PATH_IMAGE001
; Wherein y is the IAQ parameter value that sensor measurement arrives, and y ' is by IAQ sensor virtual model prediction IAQ parameter value.
μ TrainAccount form be: μ Train=
Figure 525016DEST_PATH_IMAGE002
Figure 580696DEST_PATH_IMAGE003
;
σ TrainAccount form be: σ Train=
Figure 335026DEST_PATH_IMAGE004
μ TestAccount form be: μ Test=
Figure 134354DEST_PATH_IMAGE005
Figure 657740DEST_PATH_IMAGE006
;
σ TestAccount form be: σ Test=
Figure 648436DEST_PATH_IMAGE007
;
UCL 1Account form be: UCL 1=
Figure 890061DEST_PATH_IMAGE008
LCL 1Account form be: LCL 1=
Figure 227502DEST_PATH_IMAGE009
UCL 2Account form be: UCL 2=
LCL 2Account form be: LCL 2=0;
Wherein, N TestBe meant the quantity of the concentrated data point of test data, η is the multiple of control limit;
Wherein
Figure 268456DEST_PATH_IMAGE011
The card side of expression right side α/2 quantiles distributes N Test-1 is meant the degree of freedom that card side distributes.Parameter alpha needs to be reduced the susceptibility that control chart changes data by adjustment.The variance that LCL2 is set to the difference of 0 explanation test data is 0, so the IAQ parameter value of the measured value of IAQ and normal condition conforms to.
Said μ TestBe higher than UCL 1Perhaps be lower than LCL 1, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error I.
Said σ 2 TrainBe higher than UCL 2, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error II.The type of error I is the sensor error that the difference variance unusual because unusual difference mean value and type of error II are causes.
IAQ sensor virtual model quilt is as the physical I AQ sensor in the monitoring HVAC system and the object of reference of IAQ.The control chart method is used to monitor the poor of IAQ measured value of parameters and reference point, and the variance of difference.Confirm that the IAQ sensor error in the non-static HVAC program of structure can onlinely detect.
The method that a kind of data-driven is provided is surveyed in online IAQ sensor monitoring for the IAQ sensor error in the HVAC industry.A plurality of IAQ sensor models are monitored and are calibrated as virtual-sensor, even can replace the physical sensors installed in the HVAC system.Virtual-sensor estimated parameter value is replenished or replacement as physical sensors.The method that the present invention proposes is to be intended to keep good IAQ and energy-conservation HVAC Control and Optimization provides the foundation.
The method of on-line monitoring of the present invention and diagnosis IAQ sensor is with the model of application data mining algorithm exploitation IAQ sensor.The model that builds will be used to draw the online data chart and the virtual-sensor of IAQ.This also can be used for monitoring the performance of the IAQ sensor that is installed in the HVAC system.The IAQ sensor model is based on the historical data of the HVAC system in certain existing apparatus and sets up.
The method for building up of said IAQ sensor virtual model comprises:
A, collection data: at first regulate and collect multiple parameter set (HVAC) system from heat supply, heating ventilation and air-conditioning; Comprise other IAQ parameter sets such as temperature parameter collection, carbon dioxide level parameter set, relative humidity parameter set; Each parameter set is divided into two independent subclass; Comprise training dataset, test data set, training dataset is used to develop IAQ sensor virtual model, test data set then be used to check from the training data focusing study to the validity of model;
Collect between each parameter value in the said parameter set and be provided with the time interval, at a distance from sample of collection in a minute, and each parameter value all is the point data when measuring for the last time as every;
B, set up model: the IAQ sensor virtual model of concentrating data to set up based on training data with multiple different pieces of information mining algorithm; IAQ sensor virtual model is the HVAC parameter generating prediction IAQ parameter value with other, comprises the IAQ sensor virtual model of corresponding other IAQ parameter sets of prediction such as IAQ sensor virtual model of the IAQ sensor virtual model of predicted temperature, the IAQ sensor virtual model of predicting carbon dioxide level, prediction relative humidity;
IAQ parameter value and other various HVAC parameters concern more complicated, therefore in mathematical modeling, be difficult to model of cognition and come accurately to predict the IAQ parameter value as the input data with high-dimensional HVAC parameter.And data mining is the strong instrument that from mass data, refines knowledge.IAQ sensor virtual model has reflected potential funtcional relationship between IAQ parameter and other HVAC parameters;
C, select the optimum data mining algorithm: the IAQ parameter value of prediction and sensor to the absolute value of IAQ parameter value difference be absolute error; Standard deviation through absolute error mean value and absolute error is weighed the prediction effect with the IAQ sensor virtual model of the foundation of different pieces of information mining algorithm; Select the best data mining algorithm of prediction effect; The value of the standard deviation of absolute error mean value and absolute error is more little, explains that the prediction effect of IAQ sensor virtual model is good more;
D, validity check: the measurement data that the IAQ parameter value and the test data of prediction are concentrated compares; According to the consistance between two data values; Judge the validity of the IAQ sensor virtual model that the best data mining algorithm of prediction effect is set up, consistance height then validity is good.
Said absolute error is defined as AE, and the computing method of said AE are: AE=|y '-y|;
Said absolute error mean value is defined as MAE, and the computing method of said MAE are: MAE=
Figure 997378DEST_PATH_IMAGE012
;
The standard deviation of said absolute error is defined as Std, and the computing method of said Std are: Std=
Figure 76192DEST_PATH_IMAGE013
;
Wherein y ' is the IAQ parameter value of IAQ sensor virtual model prediction, and y is the IAQ parameter value that sensor measurement arrives, and N is the quantity of test data point.
Said multiple different pieces of information mining algorithm comprises that multilayer perceptron (MLP) neural network (NN), RBF (RBF) neural network (NN), SVMs return (SVM), progressively recurrence (Pacereg).Wherein MLP NN algorithm and RBF NN algorithm often are applied to non-linear regression and classification model construction, because they can obtain the complex relationship between parameter.SVM is the learning algorithm that directiveness is arranged, and is used for classification and recurrence, and it has constituted a linear discrimination function and has come to separate as far as possible widely case.For the ease of calculating, a high-dimensional linear optimization problem is converted into a double-deck convex quadratic programming problem in SVM returns.Progressively regression algorithm then adopts one group or all optimum or optimum under specific circumstances estimator.This is a kind of newer relatively method at higher dimensional space exploitation linear model.
On-line monitoring of the present invention and the method for diagnosis IAQ sensor can only be utilized the information redundancy of system, realize the function of virtual-sensor through software, set up accurately, stable and IAQ sensor virtual model reliably, and cost is low; Have on-line monitoring IAQ sensor based on IAQ sensor virtual model, initiatively find potential fault, the function of timely maintenance and calibrating sensors, initiative is good, and is with strong points.
The above is merely embodiments of the invention; Be not so limit claim of the present invention; Every equivalent structure or equivalent flow process conversion that utilizes description of the present invention to do; Or directly or indirectly be used in other relevant technical fields, all in like manner be included in the scope of patent protection of the present invention.

Claims (10)

1. the method for on-line monitoring and diagnosis IAQ (IAQ) sensor; It is characterized in that; Comprise based on an IAQ sensor virtual model and the IAQ sensor carried out on-line monitoring and diagnosis through a control chart, said control chart with the IAQ parameter value of the prediction of said IAQ sensor virtual model and sensor measurement to the IAQ parameter value between mean difference and variance be able to monitoring.
2. the method for on-line monitoring according to claim 1 and diagnosis IAQ sensor is characterized in that the construction method of said control chart is:
A, from the HVAC system, choose remove exceptional value by N TrainThe training dataset that individual measured value is formed and according to the N of time sequencing TestThe test data set that individual consecutive numbers strong point is formed,
The method for expressing of training dataset is: y-TrainSet=[y (i), y ' is (i)], and i=1 ..., N Train.,
The method for expressing of test data set is: y-TestSet=[y (i), y ' is (i)], and i=1 ..., N Test.;
B, calculate training data and concentrate difference ε and mean difference μ thereof between each point TrainAnd standard deviation sigma TrainAnd test data is concentrated difference ε and mean difference μ thereof between each point TestAnd standard deviation sigma Test
C, work as μ TrainAnd σ TrainKnown, through calculating mean difference μ TrainControl limit and variances sigma 2 TrainControl limit detect abnormal conditions, the definition μ TrainThe higher extreme value of control limit be UCL 1, low extreme value is LCL 1, definition σ 2 TrainThe higher extreme value of control limit be UCL 2, low extreme value is LCL 2
3. the method for on-line monitoring according to claim 2 and diagnosis IAQ sensor; It is characterized in that: the computing method of said difference ε are: ε= ; Wherein y is the IAQ parameter value that sensor measurement arrives, and y ' is by IAQ sensor virtual model prediction IAQ parameter value.
4. the method for on-line monitoring according to claim 2 and diagnosis IAQ sensor is characterized in that:
μ TrainAccount form be: μ Train=
Figure 655281DEST_PATH_IMAGE002
Figure 2011102807261100001DEST_PATH_IMAGE003
;
σ TrainAccount form be: σ Train=
μ TestAccount form be: μ Test=
Figure 2011102807261100001DEST_PATH_IMAGE005
Figure 79495DEST_PATH_IMAGE006
σ TestAccount form be: σ Test=
Figure 2011102807261100001DEST_PATH_IMAGE007
5. the method for on-line monitoring according to claim 2 and diagnosis IAQ sensor is characterized in that:
UCL 1Account form be: UCL 1=
Figure 80818DEST_PATH_IMAGE008
LCL 1Account form be: LCL 1=
Figure 2011102807261100001DEST_PATH_IMAGE009
UCL 2Account form be: UCL 2=
Figure 27914DEST_PATH_IMAGE010
LCL 2Account form be: LCL 2=0;
Wherein, N TestBe meant the quantity of the concentrated data point of test data, η is the multiple of control limit;
Wherein The card side of expression right side α/2 quantiles distributes N Test-1 is meant the degree of freedom that card side distributes.
6. the method for on-line monitoring according to claim 2 and diagnosis IAQ sensor is characterized in that said μ TestBe higher than UCL 1Perhaps be lower than LCL 1, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error I.
7. the method for on-line monitoring according to claim 2 and diagnosis IAQ sensor is characterized in that said σ 2 TrainBe higher than UCL 2, the IAQ parameter then is considered to wrong at the value y-TestSet of sampling time point, and this error definition is the type of error II.
8. the method for on-line monitoring according to claim 1 and diagnosis IAQ sensor, it is characterized in that: the method for building up of said IAQ sensor virtual model comprises:
A, collection data: at first regulate and collect multiple parameter set (HVAC) system from heat supply, heating ventilation and air-conditioning; Comprise temperature parameter collection, carbon dioxide level parameter set, relative humidity parameter set; Each parameter set is divided into two independent subclass, comprises training dataset, test data set;
B, set up model: the IAQ sensor virtual model of concentrating data to set up based on training data with multiple different pieces of information mining algorithm; IAQ sensor virtual model is the HVAC parameter generating prediction IAQ parameter value with other, comprises the IAQ sensor virtual model of predicted temperature, the IAQ sensor virtual model of prediction carbon dioxide level, the IAQ sensor virtual model of prediction relative humidity;
C, select the optimum data mining algorithm: the IAQ parameter value of prediction and sensor to the absolute value of IAQ parameter value difference be absolute error; Standard deviation through absolute error mean value and absolute error is weighed the prediction effect with the IAQ sensor virtual model of the foundation of different pieces of information mining algorithm, the best data mining algorithm of selection prediction effect;
D, validity check: the measurement data that the IAQ parameter value and the test data of prediction are concentrated compares, and according to the consistance between two data values, judges the validity of the IAQ sensor virtual model that the best data mining algorithm of prediction effect is set up.
9. the method for on-line monitoring according to claim 8 and diagnosis IAQ sensor, it is characterized in that: said absolute error is defined as AE, and the computing method of said AE are: AE=|y '-y|;
Said absolute error mean value is defined as MAE, and the computing method of said MAE are: MAE=
Figure 419581DEST_PATH_IMAGE012
;
The standard deviation of said absolute error is defined as Std, and the computing method of said Std are: Std=
Figure 2011102807261100001DEST_PATH_IMAGE013
;
Wherein y ' is the IAQ parameter value of IAQ sensor virtual model prediction, and y is the IAQ parameter value that sensor measurement arrives, and N is the quantity of test data point.
10. the method for on-line monitoring according to claim 8 and diagnosis IAQ sensor is characterized in that: said multiple different pieces of information mining algorithm comprises that multilayer perceptron (MLP) neural network (NN), RBF (RBF) neural network (NN), SVMs return (SVM), progressively recurrence (Pacereg).
CN201110280726.1A 2011-09-21 2011-09-21 Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line Active CN102393882B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110280726.1A CN102393882B (en) 2011-09-21 2011-09-21 Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110280726.1A CN102393882B (en) 2011-09-21 2011-09-21 Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line

Publications (2)

Publication Number Publication Date
CN102393882A true CN102393882A (en) 2012-03-28
CN102393882B CN102393882B (en) 2014-11-26

Family

ID=45861205

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110280726.1A Active CN102393882B (en) 2011-09-21 2011-09-21 Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line

Country Status (1)

Country Link
CN (1) CN102393882B (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103048427A (en) * 2012-12-25 2013-04-17 安科智慧城市技术（中国）有限公司 Indoor air quality assessment method, device and system
CN103615716A (en) * 2013-08-05 2014-03-05 浙江大学 System and method for circulating fluidized bed boiler exhaust gas temperature prediction
CN104503404A (en) * 2014-12-12 2015-04-08 广西瀚特信息产业股份有限公司 Indoor air quality automatic regulating system based on environmental perception
CN106908082A (en) * 2017-02-28 2017-06-30 百度在线网络技术（北京）有限公司 Method, apparatus and system for the gyroscope in calibrating terminal
CN107036652A (en) * 2017-04-12 2017-08-11 林波荣 The indoor environment monitoring system and method for a kind of combination architectural environment simulation
CN107606739A (en) * 2017-08-15 2018-01-19 清华大学 The fault detection method of heating ventilation air-conditioning system
CN108961661A (en) * 2018-07-24 2018-12-07 数海信息技术有限公司 Three-dimensional security protection intelligent alarm linked system
CN109844416A (en) * 2016-09-02 2019-06-04 皇家飞利浦有限公司 Airhandling equipment, sensor device and operating method
CN110906508A (en) * 2019-12-09 2020-03-24 珠海格力电器股份有限公司 Fault detection method and system for air conditioner sensor
US10747214B2 (en) 2014-10-10 2020-08-18 Carrier Corporation HVAC system including active sensor network calibration
US10760804B2 (en) 2017-11-21 2020-09-01 Emerson Climate Technologies, Inc. Humidifier control systems and methods
CN111886482A (en) * 2018-03-22 2020-11-03 赫尔辛基大学 Sensor calibration
CN112128950A (en) * 2020-11-24 2020-12-25 北京蒙帕信创科技有限公司 Machine room temperature and humidity prediction method and system based on multiple model comparisons
CN113544608A (en) * 2019-03-07 2021-10-22 西门子股份公司 Method and system for quality control in industrial production
US11226128B2 (en) 2018-04-20 2022-01-18 Emerson Climate Technologies, Inc. Indoor air quality and occupant monitoring systems and methods
US11371726B2 (en) 2018-04-20 2022-06-28 Emerson Climate Technologies, Inc. Particulate-matter-size-based fan control system
CN114881168A (en) * 2022-05-25 2022-08-09 北京市生态环境监测中心 Photoionization detector calibration method, photoionization detector calibration system, electronic device and storage medium
US11421901B2 (en) 2018-04-20 2022-08-23 Emerson Climate Technologies, Inc. Coordinated control of standalone and building indoor air quality devices and systems
US11486593B2 (en) 2018-04-20 2022-11-01 Emerson Climate Technologies, Inc. Systems and methods with variable mitigation thresholds
US11609004B2 (en) 2018-04-20 2023-03-21 Emerson Climate Technologies, Inc. Systems and methods with variable mitigation thresholds
US11994313B2 (en) 2018-04-20 2024-05-28 Copeland Lp Indoor air quality sensor calibration systems and methods
US12018852B2 (en) 2018-04-20 2024-06-25 Copeland Comfort Control Lp HVAC filter usage analysis system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1821779A (en) * 2006-03-20 2006-08-23 中山大学 Air quality monitoring and control system
CN101140450A (en) * 2006-09-08 2008-03-12 香港中文大学精密工程研究所 Energy conservation type heat comfortable controller and control method
CN101477375A (en) * 2009-01-05 2009-07-08 东南大学 Sensor data verification method based on matrix singular values association rules mining
CN101556168A (en) * 2008-04-11 2009-10-14 株式会社东芝 Equipment operating data monitoring device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1821779A (en) * 2006-03-20 2006-08-23 中山大学 Air quality monitoring and control system
CN101140450A (en) * 2006-09-08 2008-03-12 香港中文大学精密工程研究所 Energy conservation type heat comfortable controller and control method
CN101556168A (en) * 2008-04-11 2009-10-14 株式会社东芝 Equipment operating data monitoring device
CN101477375A (en) * 2009-01-05 2009-07-08 东南大学 Sensor data verification method based on matrix singular values association rules mining

Non-Patent Citations (13)

* Cited by examiner, † Cited by third party
Title
何芬等: "温室湿度环境的主成分分析人工神经网络建模研究", 《上海交通大学学报(农业科学版)》 *
叶瑞等: "基于LS-SVM残差控制图的失控信号诊断", 《中国制造业信息化》 *
孙静: "自相关过程的残差控制图", 《清华大学学报(自然科学版)》 *
崔吉叶: "模型预测控制***性能评价方法的研究", 《中国优秀硕士学位论文全文数据库(电子期刊)信息科技辑》 *
张公绪等: "统计过程控制与诊断", 《质量与可靠性》 *
戴朝华: "基于TCI和IAQ的空调只能控制研究", 《中国优秀硕士学位论文全文数据库(电子期刊)工程科技II辑》 *
李晗等: "基于数据驱动的故障诊断方法总数", 《基于数据驱动的故障诊断方法综述》 *
王江等: "在检测中利用历史数据只能捕捉异常数据", 《电脑知识与技术》 *
王海涛等: "真实建筑中变风量空调末端装置故障在线检测与诊断研究", 《建筑科学》 *
王瑞芳等: "基于统计过程控制的机器人***故障预测技术研究", 《机床与液压》 *
田海晶等: "自相关过程的多变量统计过程监控", 《上海交通大学学报》 *
蒋励: "室内空气中甲醛的4-氨基-3联氨-5巯基三氮杂茂分光光度测定法的质量控制", 《环境与健康杂志》 *
陈平等: "基于神经网络的控制图模式识别和参数估计", 《机械与电子》 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103048427B (en) * 2012-12-25 2014-06-25 安科智慧城市技术（中国）有限公司 Indoor air quality assessment method, device and system
CN103048427A (en) * 2012-12-25 2013-04-17 安科智慧城市技术（中国）有限公司 Indoor air quality assessment method, device and system
CN103615716A (en) * 2013-08-05 2014-03-05 浙江大学 System and method for circulating fluidized bed boiler exhaust gas temperature prediction
CN103615716B (en) * 2013-08-05 2015-08-19 浙江大学 CFBB exhaust gas temperature prognoses system and method
US10747214B2 (en) 2014-10-10 2020-08-18 Carrier Corporation HVAC system including active sensor network calibration
CN104503404A (en) * 2014-12-12 2015-04-08 广西瀚特信息产业股份有限公司 Indoor air quality automatic regulating system based on environmental perception
CN109844416A (en) * 2016-09-02 2019-06-04 皇家飞利浦有限公司 Airhandling equipment, sensor device and operating method
CN106908082A (en) * 2017-02-28 2017-06-30 百度在线网络技术（北京）有限公司 Method, apparatus and system for the gyroscope in calibrating terminal
CN107036652B (en) * 2017-04-12 2019-07-09 林波荣 A kind of indoor environment monitoring system and method for the simulation of combination architectural environment
CN107036652A (en) * 2017-04-12 2017-08-11 林波荣 The indoor environment monitoring system and method for a kind of combination architectural environment simulation
CN107606739A (en) * 2017-08-15 2018-01-19 清华大学 The fault detection method of heating ventilation air-conditioning system
CN107606739B (en) * 2017-08-15 2019-07-26 清华大学 The fault detection method of heating ventilation air-conditioning system
US10760804B2 (en) 2017-11-21 2020-09-01 Emerson Climate Technologies, Inc. Humidifier control systems and methods
US10760803B2 (en) 2017-11-21 2020-09-01 Emerson Climate Technologies, Inc. Humidifier control systems and methods
CN111886482A (en) * 2018-03-22 2020-11-03 赫尔辛基大学 Sensor calibration
US11421901B2 (en) 2018-04-20 2022-08-23 Emerson Climate Technologies, Inc. Coordinated control of standalone and building indoor air quality devices and systems
US11226128B2 (en) 2018-04-20 2022-01-18 Emerson Climate Technologies, Inc. Indoor air quality and occupant monitoring systems and methods
US11371726B2 (en) 2018-04-20 2022-06-28 Emerson Climate Technologies, Inc. Particulate-matter-size-based fan control system
US11486593B2 (en) 2018-04-20 2022-11-01 Emerson Climate Technologies, Inc. Systems and methods with variable mitigation thresholds
US11609004B2 (en) 2018-04-20 2023-03-21 Emerson Climate Technologies, Inc. Systems and methods with variable mitigation thresholds
US11994313B2 (en) 2018-04-20 2024-05-28 Copeland Lp Indoor air quality sensor calibration systems and methods
US12018852B2 (en) 2018-04-20 2024-06-25 Copeland Comfort Control Lp HVAC filter usage analysis system
CN108961661A (en) * 2018-07-24 2018-12-07 数海信息技术有限公司 Three-dimensional security protection intelligent alarm linked system
CN108961661B (en) * 2018-07-24 2020-08-07 数海信息技术有限公司 Three-dimensional security intelligent alarm linkage system
CN113544608A (en) * 2019-03-07 2021-10-22 西门子股份公司 Method and system for quality control in industrial production
CN110906508A (en) * 2019-12-09 2020-03-24 珠海格力电器股份有限公司 Fault detection method and system for air conditioner sensor
CN112128950A (en) * 2020-11-24 2020-12-25 北京蒙帕信创科技有限公司 Machine room temperature and humidity prediction method and system based on multiple model comparisons
CN114881168A (en) * 2022-05-25 2022-08-09 北京市生态环境监测中心 Photoionization detector calibration method, photoionization detector calibration system, electronic device and storage medium

Also Published As

Publication number Publication date
CN102393882B (en) 2014-11-26

Similar Documents

Publication Publication Date Title
CN102393882B (en) Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line
Grillone et al. A review of deterministic and data-driven methods to quantify energy efficiency savings and to predict retrofitting scenarios in buildings
Li et al. A sensor fault detection and diagnosis strategy for screw chiller system using support vector data description-based D-statistic and DV-contribution plots
Zhao et al. Optimal inspection and replacement policy based on experimental degradation data with covariates
Du et al. Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks
US20140278165A1 (en) Systems and methods for analyzing energy consumption model data
CN109213127A (en) A kind of HVAC system gradual failure diagnostic method based on deep learning
CN101863088B (en) Method for forecasting Mooney viscosity in rubber mixing process
US11971706B2 (en) Industrial plant monitoring
CN106249709B (en) Dynamic process quality control figure repairs co-design optimal control method with age is determined
CN106649919A (en) Method and system for predicting carbon content of fly ash in coal-fired power plant boiler
JP6813291B2 (en) Performance evaluation method for photovoltaic power generation
CN111161095B (en) Method for detecting abnormal consumption of building energy
US10417565B1 (en) System, method, and computer program for modeling and predicting energy consumption in a building
CN102411339A (en) Method for evaluating performance reliability of numerical control equipment
CN114169254A (en) Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model
Alexandersen et al. A stair-step probabilistic approach for automatic anomaly detection in building ventilation system operation
CN115943352A (en) System and method for predictive maintenance of HVAC equipment using machine learning
Zhang et al. Evaluate the impact of sensor accuracy on model performance in data-driven building fault detection and diagnostics using Monte Carlo simulation
CN117764422B (en) Intelligent energy-saving operation and maintenance management cloud platform
CN108470699B (en) intelligent control system of semiconductor manufacturing equipment and process
Liu et al. Fault diagnosis of subway indoor air quality based on local fisher discriminant analysis
Rosato et al. Experimental studies of air-handling units’ faulty operation for the development of data-driven fault detection and diagnosis tools: A systematic review
CN103472732A (en) Improved multivariate controller performance monitoring method based on Mahalanobis distance
CN116664099A (en) Unmanned mine car health management method based on nonparametric regression

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
ASS Succession or assignment of patent right

Owner name: CHANGZHOU JIZHONG ENERGY TECHNOLOGY CO., LTD.

Effective date: 20130319

C41 Transfer of patent application or patent right or utility model
COR Change of bibliographic data

Free format text: CORRECT: ADDRESS; FROM: 215028 SUZHOU, JIANGSU PROVINCE TO: 215123 SUZHOU, JIANGSU PROVINCE

TA01 Transfer of patent application right

Effective date of registration: 20130319

Address after: Xinghu street Suzhou Industrial Park in Jiangsu province 215123 No. 328 Creative Industry Park 22-403

Applicant after: Ji Zhong energy saving technology (Suzhou) Co., Ltd.

Applicant after: Changzhou Jizhong Energy Technology Co., Ltd.

Address before: Xinghu Street Industrial Park of Suzhou city in Jiangsu province 215028 No. 328 Creative Industry Park 22-403 unit

Applicant before: Ji Zhong energy saving technology (Suzhou) Co., Ltd.

C14 Grant of patent or utility model
GR01 Patent grant
ASS Succession or assignment of patent right

Free format text: FORMER OWNER: CHANGZHOU JIZHONG ENERGY TECHNOLOGY CO., LTD.

Effective date: 20150126

C41 Transfer of patent application or patent right or utility model
COR Change of bibliographic data

Free format text: CORRECT: ADDRESS; FROM: 215123 SUZHOU, JIANGSU PROVINCE TO: 215028 SUZHOU, JIANGSU PROVINCE

TR01 Transfer of patent right

Effective date of registration: 20150126

Address after: Xinghu Street Industrial Park of Suzhou city in Jiangsu province 215028 No. 328 Creative Industry Park 22-403 unit

Patentee after: Ji Zhong energy saving technology (Suzhou) Co., Ltd.

Address before: Xinghu street Suzhou Industrial Park in Jiangsu province 215123 No. 328 Creative Industry Park 22-403

Patentee before: Ji Zhong energy saving technology (Suzhou) Co., Ltd.

Patentee before: Changzhou Jizhong Energy Technology Co., Ltd.