A hybrid deep transfer learning strategy for thermal comfort prediction in buildings

Somu, Nivethitha; Sriram, Anirudh; Kowli, Anupama; Ramamritham, Krithi

doi:10.1016/j.buildenv.2021.108133

Cited by 69 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For parameter-based TL, the appropriate transfer of weights from the source to the target domain is critical for improving model performance. The lower (convolutional) layers in CNNs capture domain-specific information, and the deeper (dense) layers contribute to the effective learning required for data classification 37 , 38 . Since the source and target domain datasets vary concerning the environment and load conditions, we hypothesise that the CNN architecture can be adapted to these changes by retraining the weights in only the lower layers, while weights in the deeper layers weights can be transferred unmodified for effective fault classification.…”

Section: Resultsmentioning

confidence: 99%

“…Parameter-based TL allows the reuse of parameter weights to improve the accuracy when data distribution differs from the source domain to the target domain. Lower (convolutional) layers of CNNs capture more domain-specific information concealed within the image by convolving it with a kernel (or filter), while deeper (dense) layers are responsible for learning information that is relevant for making the decision 37 , 38 . In the TL framework presented in this work, the source classifier CNN was trained on the CWRU dataset, and the target classifier (TL-CNN) was then allowed to leverage this learned information of decision-making by transferring weights of certain layers in the CNN, and retraining the remaining layers with data from the target domain.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Asutkar

Tallur

2023

Sci Rep

View full text Add to dashboard Cite

Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches demand a large amount of labelled data to build reliable models. The performance of such lab-trained models degrades when deployed in practical use cases in the presence of distinct distribution target domain datasets. In this work, we present a novel deep transfer learning strategy that fine-tunes the trainable parameters of the lower (convolutional) layers with respect to the changing target domain datasets and transfers the parameters of the deeper (dense) layers from the source domain for efficient domain generalisation and fault classification. The performance of this strategy is evaluated by considering two different target domain datasets and studying the sensitivity of fine-tuning individual layers in the networks using time-frequency representations of the vibration signals (scalograms) as inputs. We observe that the proposed transfer learning strategy yields near-perfect accuracy, even for use cases where low-precision sensors are used for data collection and unlabelled run-to-failure data with a limited number of training samples.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Asutkar

Tallur

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Parameter-based TL allows the reuse of parameter weights to improve the accuracy when data distribution differs from the source domain to the target domain. Lower (convolutional) layers of CNNs capture more domain-specific information concealed within the image by convolving it with a kernel (or filter), while deeper (dense) layers are responsible for learning information that is relevant for making the decision 34,35 . In the TL framework presented in this work, the source classifier CNN was trained on the CWRU data set, and the target classifier (TL-CNN) was then allowed to leverage this learned information of decision-making by transferring weights of certain layers in the CNN, and retraining the remaining layers with data from the target domain.…”

Section: Transfer Learning For Machine Fault Diagnosismentioning

confidence: 99%

“…For parameter-based TL, the appropriate transfer of weights from the source to the target domain is critical for improving model performance. The lower (convolutional) layers in CNNs capture domain-specific information, and the deeper (dense) layers contribute to the effective learning required for data classification 34,35 . Since the source and target domain data sets vary concerning the environment and load conditions, we hypothesise that the CNN architecture can be adapted to these changes by retraining the weights in only the lower layers, while weights in the deeper layers weights can be transferred unmodified for effective fault classification.…”

Section: Impact Of Retraining Individual Tl-cnn Layers On Accuracymentioning

confidence: 99%

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Asutkar

Tallur

2022

Preprint

View full text Add to dashboard Cite

Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches require a large number of supervised and labelled samples to build reliable models. The performance of such lab-trained models when deployed in practical use cases largely depends on their domain generalisation capability towards distinct distribution target domain datasets. These challenges are addressed to some extent by conventional parameter-based transfer learning techniques that fine-tune deeper (dense) layer parameters of the pre-trained networks when lower (convolutional) layers can capture more domain-specific information concerning the changing target domain distribution. In this work, we present a novel deep transfer learning strategy that utilises fine-tuning the parameters of convolutional layers and transfer of knowledge in the dense layers from the source domain for efficient domain generalisation and fault classification. The performance of this strategy is evaluated with two different target domain data sets, by studying the sensitivity of fine-tuning individual layers in the networks using time-frequency representations of the vibration signals (scalograms) as inputs. We observe that this strategy yields near-perfect accuracy, even for use cases where low-precision sensors are used for data collection, and unlabelled run-to-failure data with a limited number of training samples.

show abstract

“…Cao et al [25] reviewed the research related to dynamic thermal comfort, aiming to explain the development, prospects, and necessity of dynamic thermal comfort research. Somu et al [26] used transfer learning and a comprehensive thermal comfort evaluation index to solve the lack of thermal comfort samples. Korkas et al [27] guaranteed the independence of microgrid with supervisory strategy to improve the thermal comfort when energy storage and renewable energy sources are used.…”

Section: Introductionmentioning

confidence: 99%

Development of a Coupled EnergyPlus-MATLAB Simulation Based on LSTM for Predictive Control of HVAC System

Cong

Hou

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

To avoid unnecessary energy waste due to the single temperature setpoints of the heating, ventilation, and air conditioning (HVAC) system during the seasonal variation period, this study proposed a long-short-term memory (LSTM) neural network to predict and control the temperature setpoint. The thermal comfort, cooling rate, and heating rate were predicted with outdoor environment parameters and occupant count. A large scale of operation data was collected from the EnergyPlus simulation, which was previously developed based on the characteristics of a real case study house. Different kinds of input characteristics were offered to test the stable use of LSTM and other artificial neural networks. This paper discusses the development of a Matlab EnergyPlus co-simulation to predict and control the temperature setpoints of a variable air volume system, especially the relationship between temperature setpoint and energy consumption. The simulation results indicate the advantages of the LSTM prediction of energy consumption and the potential for energy saving with predictive control.

show abstract

A hybrid deep transfer learning strategy for thermal comfort prediction in buildings

Cited by 69 publications

References 34 publications

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Development of a Coupled EnergyPlus-MATLAB Simulation Based on LSTM for Predictive Control of HVAC System

Contact Info

Product

Resources

About