End-to-end deep learning model for underground utilities localization using GPR

Yang, Shengqiang; Wang, Jun; Li, Danqi; Wang, Xiangyu; Hu, Lei; Yuan, Y.; Kang, Yuanxin

doi:10.1016/j.autcon.2023.104776

Cited by 35 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future work, we plan to deploy this algorithm on real WSNs to address localization challenges in practical scenarios [41]. A few variables to consider in dragging out the life of organizations is using the increases of compromises like power, dormancy, and precision, combined with utilizing various layered structures [42]. The proposed work presents an end-to-end deep learning model incorporating a key point-regression mode.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimizing energy efficiency and enhancing localization accuracy in wireless sensor networks through genetic algorithms

2024

IJATEE

View full text Add to dashboard Cite

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Optimizing energy efficiency and enhancing localization accuracy in wireless sensor networks through genetic algorithms

2024

IJATEE

View full text Add to dashboard Cite

show abstract

“…Due to the highly non-linear relationship between the mechanical parameters of construction material and influential characteristics, recent scientific efforts advice employing machine learning like artificial neural network (ANN) 32 , gradient tree boosting algorithm 33 , support vector regression (SVR) 34 , and adaptive neuro-fuzzy inference system (ANFIS) 35 models for such purposes. These models are able to map and reproduce the intrinsic dependency of any output parameter on its corresponding inputs 36 – 38 . For example, Ghasemi and Naser 39 could successfully use two explainable artificial intelligence techniques called XGBoost and random forest to predict the compressive strength of 3D concrete mixtures.…”

Section: Introductionmentioning

confidence: 99%

Satin bowerbird optimizer-neural network for approximating the capacity of CFST columns under compression

Liu,

Liang

2024

Sci Rep

View full text Add to dashboard Cite

Concrete-filled steel tube columns (CFSTCs) are important elements in the construction sector and predictive analysis of their behavior is essential. Recent works have revealed the potential of metaheuristic-assisted approximators for this purpose. The main idea of this paper, therefore, is to introduce a novel integrative model for appraising the axial compression capacity (Pu) of CFSTCs. The proposed model represents an artificial neural network (ANN) supervised by satin bowerbird optimizer (SBO). In other words, this metaheuristic algorithm trains the ANN optimally to find the best contribution of input parameters to the Pu. In this sense, column length and the compressive strength of concrete, as well as the characteristics of the steel tube (i.e., diameter, thickness, yield stress, and ultimate stress), are considered input data. The prediction results are compared to five ANNs supervised by backtracking search algorithm (BSA), earthworm optimization algorithm (EWA), social spider algorithm (SOSA), salp swarm algorithm (SSA), and wind-driven optimization. Evaluating various accuracy indicators showed that the proposed model surpassed all of them in both learning and reproducing the Pu pattern. The obtained values of mean absolute percentage error of the SBO-ANN was 2.3082% versus 4.3821%, 17.4724%, 15.7898%, 4.2317%, and 3.6884% for the BSA-ANN, EWA-ANN, SOSA-ANN, SSA-ANN and WDA-ANN, respectively. The higher accuracy of the SBO-ANN against several hybrid models from earlier literature was also deduced. Moreover, the outcomes of principal component analysis on the dataset showed that the yield stress, diameter, and ultimate stress of the steel tube are the three most important factors in Pu prediction. A predictive formula is finally derived from the optimized SBO-ANN by extracting and organizing the weights and biases of the ANN. Owing to the accurate estimation shown by this model, the derived formula can reliably predict the Pu of concrete-filled steel tube columns.

show abstract

“…Deep learning-based methods cannot optimize parameters globally because of their box-fitting mode, which requires the separation of a task into region detection and hyperbola fitting problems. An end-to-end deep learning model based on a key pointregression mode is proposed and validated in this study [7]. This paper performed fatigue crack growth of the rib-to-deck (RTD) innovative double-sided welded joints of orthotropic steel decks (OSD) considering welding residual stress (WRS) [8].…”

Section: Introductionmentioning

confidence: 99%

Analysis and Real-Time Monitoring of the Influence of Wind Load on a High-Altitude Steel Connecting Bridge with Small Spacing

Wu,

Chen,

et al. 2024

Buildings

View full text Add to dashboard Cite

With the development of steel-structure construction technology in high-rise buildings, the design and construction of high-rise steel structures tend to be complicated. Based on the Zhuhai Tiejian Square project, the fluid-structure coupling calculation analysis and on-site monitoring are carried out in view of the wind load of the high-altitude steel-structure connecting bridge in the hoisting stage of the Zhuhai Tiejian Square project. The main structure of the project is four towers and five high-altitude, small-spacing steel structures connecting the four towers. The lifting process of the third zone is taken as the analysis object, and the hoisting idea of “low-altitude hoisting, overall lifting” is adopted. Because the span of the high-altitude steel-structure connecting bridge is small and the installation height is high, the influence of wind load on the hoisting process cannot be ignored. Therefore, the unidirectional fluid-structure coupling model of the high-altitude small-space steel-structure connecting bridge in the third zone was established by using CFD calculation software ANSYS Fluent 2022 R1, and the corresponding flow field and solid calculation results were obtained and analyzed. The analysis results show that the lifting structure still produces a certain deformation when the wind speed is 5 m/s or 10 m/s, and the calculation results show that the stress calculation results are still within the safe range of steel strength for the sensitivity of the lifting structure under wind load. With the increase of wind speed, the local maximum stress of the structure increases greatly, but the overall deformation remains stable, which indicates that the greatest challenge of hoisting steel structures under wind load may be the stability direction rather than the strength, so it is necessary to strictly monitor the displacement deformation of the structure during construction. Then, through the monitoring of the overall lifting process of the high-altitude, large-span, steel-connected structure of Zhuhai Tiejian Square from pre-lifting to formal lifting, real-time monitoring and data analysis show that the lifting process of the high-altitude steel bridge of Zhuhai Tiejian Square is safe and reliable, the force transformation of each component is reasonable, the lifting process is relatively stable, the external environment has little impact, and the expected monitoring effect has been achieved. The calculation simulation and on-site monitoring in this paper can provide theoretical and practical guidance for the construction safety under the influence of wind load in the construction process of high-altitude steel-structure hoisting, and provide an important reference value for similar projects.

show abstract

End-to-end deep learning model for underground utilities localization using GPR

Cited by 35 publications

References 36 publications

Optimizing energy efficiency and enhancing localization accuracy in wireless sensor networks through genetic algorithms

Optimizing energy efficiency and enhancing localization accuracy in wireless sensor networks through genetic algorithms

Satin bowerbird optimizer-neural network for approximating the capacity of CFST columns under compression

Analysis and Real-Time Monitoring of the Influence of Wind Load on a High-Altitude Steel Connecting Bridge with Small Spacing

Contact Info

Product

Resources

About