This study presents a case study of public buildings using a novel deep learning method to forecast indoor air temperature. The aim is to explore the potential of long short-term memory (LSTM) model ...in forecasting indoor temperature, and a novel LSTM model modified by error correction model is established. The performance of the two models is compared with popular prediction methods in the building field.
Results show that the proposed novel LSTM model has slight advantages in level indoor temperature prediction performance comparing with other common machine learning methods. However, it outperforms other models including original LSTM in terms of directional prediction accuracy, and accurately predicts the indoor temperature variation trend. This work is enlightening and may have a further reference to the feasibility study of indoor air temperature prediction model.
•We proposed a novel deep learning method for indoor temperature prediction.•Error correction model was used to revise the LSTM model.•The method was compared with three common used machine learning models.•The method showed outstanding effect on improving the performance of indoor temperature prediction.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Weather data errors affect energy management by influencing the accuracy of building energy predictions. This study presents a long short-term memory (LSTM) prediction model based on the "Energy ...Detective" dataset (Shanghai, China) and neighboring weather station data. The study analyzes the errors of different weather data sources (Detective and A) at the same latitude and longitude. Subsequently, it discusses the effects of weather errors from neighboring weather stations (Detective, A, B, C, and D) on energy forecasts for the next hour and day including the selection process for neighboring weather stations. Furthermore, it compares the forecast results for summer and autumn. The findings indicate a correlation between weather errors from neighboring weather stations and energy consumption. The median R-Square for predicting the next hour reached 0.95. The model's predictions for the next day exhibit a higher Prediction Interval Mean Width (139.0 in summer and 146.1 in autumn), indicating a greater uncertainty.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
In this paper, an analytical model is developed for a fully clamped rectangular laminated glass subjected to low-velocity impact which is capable of capturing large non-linear deformation and glass ...fracture. The mathematical framework of the analytical model is based on first-order shear deformation plate theory, which incorporates the effect of bending, membrane and transverse shear and uses damage mechanics to capture the glass fracture process. A series of experiments are performed for laminated glass with two different interlayer materials, viz. polyvinyl butyral (PVB) and SentryGlas® Plus (SGP). The predicted time-history of transverse central displacement, velocity and acceleration are found in satisfactory correlations with those from the experiments. Non-dimensional parameters which govern the maximum transverse displacement and first peak contact force in the laminated glass are proposed. The analytical model developed enables quick and reliable assessment during the preliminary safety glass design where full-scale FE analysis is often too time-consuming.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
With the development in information technologies, today's building energy consumption can be well monitored by the building energy management systems. However, in most real applications there is no ...clear definition of abnormal building energy consumption. To overcome this limitation, this work proposes a novel deep learning based unsupervised anomaly detection framework that includes recurrent neural networks and quantile regression. Moreover, this framework is able to produce a prediction interval to detect and evaluate abnormal building energy consumption. The framework has been applied to analyze the energy data collected from three different residential houses, and anomaly detection results are evaluated by the quantile regression range. The research results can provide promising solutions for building managers to detect abnormal energy performance, and is also valuable to assess the level of anomalies and spot opportunities in energy conservation.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The genetic resources among pigs in Anhui Province are diverse, but their value and potential have yet to be discovered. To illustrate the genetic diversity and population structure of the Anhui pigs ...population, we resequenced the genome of 150 pigs from six representative Anhui pigs populations and analyzed this data together with the sequencing data from 40 Asian wild boars and commercial pigs. Our results showed that Anhui pigs were divided into two distinct types based on ancestral descent: Wannan Spotted pig (WSP) and Wannan Black pig (WBP) origins from the same ancestor and the other four populations origins from another ancestor. We also identified several potential selective sweep regions associated with domestication characteristics among Anhui pigs, including reproduction-associated genes (CABS1, INSL6, MAP3K12, IGF1R, INSR, LIMK2, PATZ1, MAPK1), lipid- and meat-related genes (SNX19, MSTN, MC5R, PRKG1, CREBBP, ADCY9), and ear size genes (MSRB3 and SOX5). Therefore, these findings expand the catalogue and how these genetic differences among pigs and this newly generated data will be a valuable resource for future genetic studies and for improving genome-assisted breeding of pigs and other domesticated animals.
Over extended periods of natural and artificial selection, China has developed numerous exceptional pig breeds. Deciphering the germplasm characteristics of these breeds is crucial for their ...preservation and utilization. While many studies have employed single nucleotide polymorphism (SNP) analysis to investigate the local pig germplasm characteristics, copy number variation (CNV), another significant type of genetic variation, has been less explored in understanding pig resources. In this study, we examined the CNVs of 18 Wanbei pigs (WBP) using whole genome resequencing data with an average depth of 12.61. We identified a total of 8,783 CNVs (~30.07 Mb, 1.20% of the pig genome) in WBP, including 8,427 deletions and 356 duplications. Utilizing fixation index (Fst), we determined that 164 CNVs were within the top 1% of the Fst value and defined as under selection. Functional enrichment analyses of the genes associated with these selected CNVs revealed genes linked to reproduction (
,
,
,
), growth and development (
,
,
), and immunity (
,
). This study enhances our understanding of the genomic characteristics of the Wanbei pig and offers a theoretical foundation for the future breeding of this breed.
The solidification and corrosion behavior of the Ti/B added Zn-Al-Mg alloys were experimentally investigated by means of microstructure characterization and electrochemical test. The basic ...calculations were carried out to predict the characteristics of the Ti-added Zn-Al-Mg alloys. The Zn-Al-Mg ingots with minor doping of Ti/B were prepared and solidified under different cooling rate, including air cooling, water quenching and furnace cooling. The scanning electron microscopy (SEM) and the X-ray diffraction method (XRD) were used to determine the microstructures and phase types of the alloy samples. It could be discovered that trace TiAl
3
particles were dispersed in the Ti/B added alloy samples which provide the heterogeneous nucleation sites to refine the size of the dendrites and the eutectic microstructures. More fined microstructures with the addition of both Ti and B were obtained compared with those with the merely addition of Ti, and the water cooled alloys presented the finest microstructures due to the fastest cooling rate. It could also be noticed that with the increasing solidification rate, the percentage of the MgZn
2
phase turned out to be higher because of the Mg
2
Zn
11
↔MgZn
2
transition, which is in consistent with the results in the actual hot-dip galvanizing process. Electrochemical experiments in the previous work included methods the of the Tafel polarization test and the electrochemical impedance spectroscopy test (EIS). Results show that the quenched Zn-Al-Mg alloy with the addition of both Ti and B takes on best corrosion resistance. Consequently, the addition of certain amount of Ti/B elements and the appropriate elevation of the cooling rate will be the practicable approaches to optimize the microstructure and the corrosion resistance of the Zn-Al-Mg coatings in the actual galvanizing process.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
In predicting building energy (affected by seasons), there are issues like inefficient hyperparameter optimization and inaccurate predictions, it is unclear whether spatial and temporal attention ...improves performance. This study proposes a method based on Bayesian Optimization (BO), Spatial-Temporal Attention (STA), and Long Short-Term Memory (LSTM). Seven improved LSTM models (BO-LSTM, SA-LSTM, TA-LSTM, STA-LSTM, BO-SA-LSTM, BO-TA-LSTM, and BO-STA-LSTM) are compared with LSTM and the impacts of seasonal variations on BO-STA-LSTM are analysed using different sample types and time domain analysis. To further demonstrate the efficiency of the proposed method, comparisons with convolutional neural network (CNN) and temporal convolutional network (TCN) are performed, and followed by validation with new datasets. The findings indicate that adding STA and BO to LSTM enhances the average R2 of prediction performance by 0.0885. BO alone contributes 0.0717, while adding attention improves 0.0560. BO-STA-LSTM achieves higher prediction accuracy for similar test and training samples or a test sample size of 14,016, effectively capturing seasonal, trend, and peak energy patterns. Additionally, BO-STA-LSTM outperforms CNN and TCN, demonstrating superior prediction accuracy.
•Proposing a spatial-temporal enhanced LSTM method for Bayesian optimization.•Evaluate BO and STA on 20 buildings for short-term energy predictions.•Enhance BO-STA-LSTM prediction R2 averagely by 0.0885 (STA 0.0560, BO 0.0717).•Seasonal variation in data is an important influencing factor for LSTM prediction.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Human drivers conduct compensatory behaviour to counteract the increased risk while being distracted. This kind of compensation strategy should be learned for a safer and smart design of adaptive ...cruise control system (ACC). Hence, a simulator study was conducted, requiring performance visual, cognitive, and combined secondary tasks during a car following scenario. An increased time headway (THW) was found in all of the three distraction conditions, which confirmed that drivers compensated an extra THW to counteract the increased crash risk. Furthermore, crash probability models using binary logistic regression with random intercept were constructed where driver distraction and dynamic traffic situations were embodied as inputs. Results showed that crash risk increased with reduced THW, increased lead vehicle deceleration, and unopened brake light of the lead vehicle. Besides, visual‐related distractions increased crash risk, while pure cognitive distraction lowered crash risk in low THW (lower than 1.8 s) condition and increased crash risk in high THW (larger than 1.8 s) condition. Based on the authors' proposed models, theoretical compensation in THW to fully counteract the increased crash risk by distraction was derived, which could be used for the design of a human‐like ACC with automatic adjustment of THW setting considering driver distraction.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Copy number variation (CNV) is an important class of genetic variations widely associated with the porcine genome, but little is known about the characteristics of CNVs in foreign and indigenous pig ...breeds. We performed a genome-wide comparison of CNVs between Anhui indigenous pig (AHIP) and Western commercial pig (WECP) breeds based on data from the Porcine 80K SNP BeadChip. After analysis using the PennCNV software, we detected 3863 and 7546 CNVs in the AHIP and WECP populations, respectively. We obtained 225 (loss: 178, gain: 47) and 379 (loss: 293, gain: 86) copy number variation regions (CNVRs) randomly distributed across the autosomes of the AHIP and WECP populations, accounting for 10.90% and 22.57% of the porcine autosomal genome, respectively. Functional enrichment analysis of genes in the CNVRs identified genes related to immunity (
,
,
,
,
,
) and meat quality (
,
) in the WECP population; these genes were a loss event in the WECP population. This study provides important information on CNV differences between foreign and indigenous pig breeds, making it possible to provide a reference for future improvement of these breeds and their production performance.
PDF
