Principal components null space analysis based non-intrusive load monitoring

Guzel, Tayyar; Ustunel, Eser

doi:10.1109/epec.2015.7379987

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CB classification is a supervised learning technique, which learns from known road lines to create its training information set. The algorithm is also called as PCNSA, which is a powerful tool to classify many objects in a test group [23–25]. In this paper, we use this method which was originally designed for classification problems, for road slope estimation.…”

Section: Cb Slope Estimationmentioning

confidence: 99%

“…Here, LFB method does not need the road lines and it estimates the road slope when the vehicle first experiences the change in road structure. As a third method, we call principal component null space analysis (PCNSA) as the covariance‐based (CB) method, which first constructs a covariance matrix between left and right road lines as in [23–25]. Then, principal component analysis (PCA) is used for dimension reduction of covariance matrix by suppressing noisy components and for finding the null space after dimension reduction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vision‐based road slope estimation methods using road lines or local features from instant images

Ustunel

Maşazade²

2019

IET Intelligent Transport Systems

Self Cite

View full text Add to dashboard Cite

Section: Cb Slope Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vision‐based road slope estimation methods using road lines or local features from instant images

Ustunel

Maşazade²

2019

IET Intelligent Transport Systems

Self Cite

View full text Add to dashboard Cite

“…However, a lot of electrical equipment has similar active and reactive characteristics and it is hard to identify when facing the equipment in variable speed drive state. In [13,14], steady-state current waveform and current harmonics are taken as the load signature, but there are error-prone problems for similar equipment. In [15], transient power or current during load switching are used as the load signature, which has high identification accuracy, but requires high data acquisition and requires a large amount of calculation.…”

Section: Introductionmentioning

confidence: 99%

Load Identification for the More Electric Aircraft Distribution System Based on Intelligent Algorithm

2022

View full text Add to dashboard Cite

Accurate identification of electrical load working status can provide information support to the remote electrical distribution system (EDS) of more electric aircraft (MEA), which could use it to realize redundant switching and protection. This paper presents a method to automatically identify the load status on the remote power distribution unit (RPDU) of MEA by using an intelligent algorithm. The experimental platform is built in an aircraft Electrical Power System (EPS) distribution large-scale test cabin. Four pieces of typical aviation equipment are installed in the test cabin and powered from RPDU. Voltage and current values under 15 working combinations on the RPDU are measured to extract the steady-state V-I trajectory. In total, 750 group samples were collected in the feature parameter database. A generalized regression neural network (GRNN) identification model was established, and the smoothing factor was calculated by using a conventional cross-validation method to train and reach an optimal value. However, the identification results are not ideal. In order to improve the accuracy, the parameter of GRNN was optimized by genetic algorithms. The proposed model shows great performance as accuracy of all 15 classifications reached 100%. The proposed model has advantages of flexible network structure, high fault tolerance, and robustness. It can realize global approximation optimization, avoid local optimization, effectively improve GRNN fitting accuracy, improve model generalization ability, and reduce model training calculation.

show abstract

“…Regardless of the electrical parameters chosen to create the load signatures, the recognition algorithm can operate using three different approaches: analyzing the transient characteristics (the period of time when the load is turned ON or OFF), the steady state characteristics or a combination of both [14]. Guzel and Ustunel [15], suggested that the use of both transient and steady states can increase the possibility of identifying which load type is turned "ON", since single state signature has its own limitation. Thus, this study considers both warm-up and standby states to determine the behavior of different electrical appliances at Ngarenanyuki secondary school.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Study of Electrical Appliances Consumption Using Panel Meter Data

Nyari¹,

Castro-Sitiriche²,

Park³

2017

JPEE

View full text Add to dashboard Cite

The present study uses power data from panel meter connected to the micro-grid to identify electrical energy consumption of the school appliances and their behavior in both warm-up, standby and active operation states. Before the conduction of experiments a load auditing of the school appliances was carried out by reading the rated power of each device (e.g. photocopy machine, printer, and fridge). The captures of this kind of information were essential as it provides a starting point to determine energy use of each appliance and hence simplify the process of identification. The electric parameters such as active power, reactive power and current were used to analyze the behavior of electrical appliances in all states. Experimental results show that, both active and reactive power were found to be high for old Canon photocopy machine as compared to new Canon photocopy machine. Another experiment reveals that printing one copy by using HP laser printer consumes about 700 W, while photocopying one copy with new Canon machine utilizes approximately 1100 W. This study concludes that new photocopy machine consumes more electric energy in warm-up state as compared to other states (standby and active operation states). Future work is to develop an algorithm for demand side management strategies which will enable efficient utilization of the electric energy from the micro-grid and hence bring the intended energy impact to the school.

show abstract

Principal components null space analysis based non-intrusive load monitoring

Cited by 8 publications

References 16 publications

Vision‐based road slope estimation methods using road lines or local features from instant images

Vision‐based road slope estimation methods using road lines or local features from instant images

Load Identification for the More Electric Aircraft Distribution System Based on Intelligent Algorithm

An Experimental Study of Electrical Appliances Consumption Using Panel Meter Data

Contact Info

Product

Resources

About