scholarly journals Integrated Unfold-PCA Monitoring Application for Smart Buildings: An AHU Application Example

Energies ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 235
Author(s):  
Llorenç Burgas ◽  
Joan Colomer ◽  
Joaquim Melendez ◽  
Francisco Ignacio Gamero ◽  
Sergio Herraiz
Keyword(s):  
Latent Variables ◽  
Web Application ◽  
Control Charts ◽  
Principal Component ◽  
Operating Conditions ◽  
Smart Buildings ◽  
Air Handling Unit ◽  
Squared Prediction Error ◽  
Lecture Theatre ◽  
On Line

This paper presents a complete methodology, together with its implementation as a web application, for monitoring smart buildings. The approach uses unfold-Principal Component Analysis (unfold-PCA) as a batch projection method and two statistics, Hotelling’s T-squared (T2) and the squared prediction error (SPE), for alarm generation resulting in two simple control charts independently on the number of variables involved. The method consists of modelling the normal operating conditions of a building (entire building, room or subsystem) with latent variables described expressing the principal components. Thus, the method allows detecting faults and misbehaviour as a deviation of previously mentioned statistics from their statistical thresholds. Once a fault or misbehaviour is detected, the isolation of sensors that mostly contribute to such detection is proposed as a first step for diagnosis. The methodology has been implemented under a SaaS (software as a service) approach to be offered to multiple buildings as an on-line application for facility managers. The application is general enough to be used for monitoring complete buildings, or parts of them, using on-line data. A complete example of use for monitoring the performance of the air handling unit of a lecture theatre is presented as demonstrative example and results are discussed

On-line NIR monitoring during anaerobic treatment of municipal solid waste

2003 ◽  
Vol 48 (4) ◽  
pp. 9-13 ◽  
Author(s):  
M. Hansson ◽  
Å Nordberg ◽  
B. Mathisen
Keyword(s):  
Municipal Solid Waste ◽  
Solid Waste ◽  
Near Infrared ◽  
C:N Ratio ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Anaerobic Treatment ◽  
Operating Conditions ◽  
On Line ◽  
Process Disturbances

An anaerobic digester (8 l) was fed with the organic fraction of municipal solid waste and monitored intermittently for two years with on-line near-infrared (NIR) spectroscopy and traditional chemical parameters analysed off-line. The dynamics that occurred due to changes in substrate composition (changed C:N ratio) and changes in operating conditions (overloading) could be followed using principal component analysis of the obtained NIR-spectra. In addition, process disturbances such as failed stirring and increased foaming were readily detected by the NIR-spectra. Using PLS regression the propionate concentration could be predicted in the range 0.1-3.6 g/l, RMSEP 0.53 g/l with slope 0.74 and correlation coefficient 0.85. The response on changes in the digester fluid was reproducible and could be detected within 2.5 minutes, which can be considered as real-time monitoring.

Generic monitoring tools for water characteristics assessment

2003 ◽  
Vol 3 (1-2) ◽  
pp. 351-357
Author(s):  
S. Le Bonté ◽  
M.-N. Pons ◽  
O. Potier ◽  
S. Chanel ◽  
M. Baklouti
Keyword(s):  
Municipal Wastewater ◽  
Principal Component ◽  
Toxic Substances ◽  
Capacity Curves ◽  
Water Characteristics ◽  
Monitoring Tools ◽  
Visible Spectra ◽  
On Line ◽  
Mining Procedure

An adaptive principal component analysis applied to sets of data provided by global analytical methods (UV-visible spectra, buffer capacity curves, respirometric tests) is proposed as a generic procedure for on-line and fast characterization of wastewater. The data-mining procedure is able to deal with a large amount of information, takes into account the normal variations of wastewater composition related to human activity, and enables a rapid detection of abnormal situations such as the presence of toxic substances by comparison of the actual wastewater state with a continuously updated reference. The procedure has been validated on municipal wastewater.

Validation of On-line Respiration Meter and its Applications by Computer Simulation

1992 ◽  
Vol 26 (5-6) ◽  
pp. 1355-1363 ◽  
Author(s):  
C-W. Kim ◽  
H. Spanjers ◽  
A. Klapwijk
Keyword(s):  
Steady State ◽  
Activated Sludge ◽  
Respiration Rate ◽  
Oxygen Demand ◽  
Operating Conditions ◽  
Mass Balances ◽  
Short Term ◽  
Respiration Rates ◽  
On Line ◽  
Made In

An on-line respiration meter is presented to monitor three types of respiration rates of activated sludge and to calculate effluent and influent short term biochemical oxygen demand (BODst) in the continuous activated sludge process. This work is to verify if the calculated BODst is reliable and the assumptions made in the course of developing the proposed procedure were acceptable. A mathematical model and a dynamic simulation program are written for an activated sludge model plant along with the respiration meter based on mass balances of BODst and DO. The simulation results show that the three types of respiration rate reach steady state within 15 minutes under reasonable operating conditions. As long as the respiration rate reaches steady state the proposed procedure calculates the respiration rate that is equal to the simulated. Under constant and dynamic BODst loading, the proposed procedure is capable of calculating the effluent and influent BODst with reasonable accuracy.

scholarly journals Optimal Tuner Selection for Kalman Filter-Based Aircraft Engine Performance Estimation

2009 ◽  
Vol 132 (3) ◽  
Author(s):  
Donald L. Simon ◽  
Sanjay Garg
Keyword(s):  
Kalman Filter ◽  
Estimation Error ◽  
Engine Performance ◽  
Aircraft Engine ◽  
Operating Conditions ◽  
Performance Estimation ◽  
Experimental Simulation ◽  
Tuning Parameter ◽  
Estimation Accuracy ◽  
On Line

A linear point design methodology for minimizing the error in on-line Kalman filter-based aircraft engine performance estimation applications is presented. This technique specifically addresses the underdetermined estimation problem, where there are more unknown parameters than available sensor measurements. A systematic approach is applied to produce a model tuning parameter vector of appropriate dimension to enable estimation by a Kalman filter, while minimizing the estimation error in the parameters of interest. Tuning parameter selection is performed using a multivariable iterative search routine that seeks to minimize the theoretical mean-squared estimation error. This paper derives theoretical Kalman filter estimation error bias and variance values at steady-state operating conditions, and presents the tuner selection routine applied to minimize these values. Results from the application of the technique to an aircraft engine simulation are presented and compared with the conventional approach of tuner selection. Experimental simulation results are found to be in agreement with theoretical predictions. The new methodology is shown to yield a significant improvement in on-line engine performance estimation accuracy.

scholarly journals Investigating microcrystalline cellulose crystallinity using Raman spectroscopy

Cellulose ◽  
2021 ◽  
Author(s):  
Ana Luiza P. Queiroz ◽  
Brian M. Kerins ◽  
Jayprakash Yadav ◽  
Fatma Farag ◽  
Waleed Faisal ◽  
...  
Keyword(s):  
Raman Spectra ◽  
Microcrystalline Cellulose ◽  
Web Application ◽  
Principal Component ◽  
Raw Material ◽  
Least Squares Regression ◽  
Analysis Model ◽  
General Reference ◽  
Material Source ◽  
Univariate Model

AbstractMicrocrystalline cellulose (MCC) is a semi-crystalline material with inherent variable crystallinity due to raw material source and variable manufacturing conditions. MCC crystallinity variability can result in downstream process variability. The aim of this study was to develop models to determine MCC crystallinity index (%CI) from Raman spectra of 30 commercial batches using Raman probes with spot sizes of 100 µm (MR probe) and 6 mm (PhAT probe). A principal component analysis model separated Raman spectra of the same samples captured using the different probes. The %CI was determined using a previously reported univariate model based on the ratio of the peaks at 380 and 1096 cm−1. The univariate model was adjusted for each probe. The %CI was also predicted from spectral data from each probe using partial least squares regression models (where Raman spectra and univariate %CI were the dependent and independent variables, respectively). Both models showed adequate predictive power. For these models a general reference amorphous spectrum was proposed for each instrument. The development of the PLS model substantially reduced the analysis time as it eliminates the need for spectral deconvolution. A web application containing all the models was developed. Graphic abstract

scholarly journals Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2848 ◽  
Author(s):  
Leonel Rosas-Arias ◽  
Jose Portillo-Portillo ◽  
Aldo Hernandez-Suarez ◽  
Jesus Olivares-Mercado ◽  
Gabriel Sanchez-Perez ◽  
...  
Keyword(s):  
Principal Component ◽  
Subspace Learning ◽  
Transport Systems ◽  
Video Sequences ◽  
Projected Image ◽  
The Road ◽  
Illumination Changes ◽  
On Line ◽  
Incremental Learning Method ◽  
On Line Learning

The counting of vehicles plays an important role in measuring the behavior patterns of traffic flow in cities, as streets and avenues can get crowded easily. To address this problem, some Intelligent Transport Systems (ITSs) have been implemented in order to count vehicles with already established video surveillance infrastructure. With this in mind, in this paper, we present an on-line learning methodology for counting vehicles in video sequences based on Incremental Principal Component Analysis (Incremental PCA). This incremental learning method allows us to identify the maximum variability (i.e., motion detection) between a previous block of frames and the actual one by using only the first projected eigenvector. Once the projected image is obtained, we apply dynamic thresholding to perform image binarization. Then, a series of post-processing steps are applied to enhance the binary image containing the objects in motion. Finally, we count the number of vehicles by implementing a virtual detection line in each of the road lanes. These lines determine the instants where the vehicles pass completely through them. Results show that our proposed methodology is able to count vehicles with 96.6% accuracy at 26 frames per second on average—dealing with both camera jitter and sudden illumination changes caused by the environment and the camera auto exposure.

Effects of Medium and Substituents on Dissociationof 4,4'-Disubstituted Bis(benzenesulfon)imides

1996 ◽  
Vol 61 (8) ◽  
pp. 1205-1214 ◽  
Author(s):  
Miroslav Ludwig ◽  
Pavel Štverka
Keyword(s):  
Latent Variables ◽  
Dissociation Constants ◽  
Substituent Effects ◽  
Principal Component ◽  
H Nmr ◽  
Base Process ◽  
Elemental Analyses ◽  
Substituent Constants ◽  
Model Substances ◽  
Strong Acids

Ten 4,4'-disubstituted bis(arenesulfon)imides of the general formula XC6H4SO2NHSO2C6H4X have been synthesized and their structures confirmed by their 1H NMR spectra. Elemental analyses are presented for the compounds not yet described. The dissociation constants of these model substances have been measured potentiometrically in pyridine, dimethylformamide, methanol, ethanol, propylene carbonate, acetone, acetonitrile, 1,2-dichloroethane and tetramethylene sulfone. The pKHA values obtained have been correlated with three sets of the Hammett substituent constants and the results have been used to discuss the solvent and substituent effects on the dissociation of the compounds studied. Sulfonimides with electron-acceptor substituents behave as rather strong acids in some solvents (pyridine, dimethylformamide, methanol and ethanol), whereas normal substituent dependences are found in other solvents. The experimental data have also been interpreted with the help of the statistical methods based on latent variables. From the calculations it follows that only the first principal component, which correlates well with the substituent constant sets adopted, is statistically significant in describing the substituent effect on the acid-base process studied.

Reaction Monitoring in Explorative Organic Synthesis Using Fiber-Optical NIR Spectroscopy and Principal Component Analysis

1996 ◽  
Vol 50 (12) ◽  
pp. 1541-1544 ◽  
Author(s):  
Hans-René Bjørsvik
Keyword(s):  
Principal Component Analysis ◽  
Data Analysis ◽  
Latent Variables ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Component Analysis ◽  
Quantitative Information ◽  
Chemistry Laboratory ◽  
Reaction Profile

A method of combining spectroscopy and multivariate data analysis for obtaining quantitative information on how a reaction proceeds is presented. The method is an approach for the explorative synthetic organic laboratory rather than the analytical chemistry laboratory. The method implements near-infrared spectroscopy with an optical fiber transreflectance probe as instrumentation. The data analysis consists of decomposition of the spectral data, which are recorded during the course of a reaction by using principal component analysis to obtain latent variables, scores, and loading. From the scores and the corresponding reaction time, it is possible to obtain a reaction profile. This reaction profile can easily be recalculated to obtain the concentration profile over time. This calculation is based on only two quantitative measurements, which can be (1) measurement from the work-up of the reaction or (2) chromatographic analysis from two withdrawn samples during the reaction. The method is applied to the synthesis of 3-amino-propan-1,2-diol.

MarkUs: An Open-Source Web Application to Annotate Student Papers On-Line

2012 ◽  
Author(s):  
Morgan Magnin ◽  
Guillaume Moreau ◽  
Nelle Varoquaux ◽  
Benjamin Vialle ◽  
Karen Reid ◽  
...  
Keyword(s):  
Higher Education ◽  
Open Source ◽  
Web Application ◽  
Online System ◽  
Important Benefit ◽  
Special Cases ◽  
Assessment Time ◽  
On Line ◽  
Active Pedagogy ◽  
Further Development

A critical component of the learning process lies in the feedback that students receive on their work that validates their progress, identifies flaws in their thinking, and identifies skills that still need to be learned. Many higher-education institutions have developed an active pedagogy that gives students opportunities for different forms of assessment and feedback. This means that students have numerous lab exercises, assignments, and projects. Both instructors and students thus require effective tools to efficiently manage the submission, assessment, and individualized feedback of students’ work. The open-source web application MarkUs aims at meeting these needs: it facilitates the submission and assessment of students’ work. Students directly submit their work using MarkUs, rather than printing it, or sending it by email. The instructors or teaching assistants use MarkUs’s interface to view the students’ work, annotate it, and fill in a marking rubric. Students use the same interface to read the annotations and learn from the assessment. Managing the students’ submissions and the instructors assessments within a single online system, has led to several positive pedagogical outcomes: the number of late submissions has decreased, the assessment time has been drastically reduced, students can access their results and read the instructor’s feedback immediately after the grading process is completed. Using MarkUs has also significantly reduced the time that instructors spend collecting assignments, creating the marking schemes, passing them on to graders, handling special cases, and returning work to the students. In this paper, we introduce MarkUs’ features, and illustrate their benefits for higher education through our own teaching experiences and that of our colleagues. We also describe an important benefit of the fact that the tool itself is open-source. MarkUs has been developed entirely by students giving them a valuable learning opportunity as they work on a large software system that real users depend on. Virtuous circles indeed arise, with former users of MarkUs becoming developers and then supervisors of further development. We will conclude by drawing perspectives about forthcoming features and use, both technically and pedagogically.

Sign in / Sign up

Export Citation Format

Share Document