Prediction of brake pedal aperture for automatic wheel loader based on deep learning

Shi, Jing; Sun, Dongye; Hu, Minghui; Liu, Sheng; Kan, Yingzhe; Chen, Ruibo; Ma, Ke

doi:10.1016/j.autcon.2020.103313

Cited by 25 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensitivity of warpage prediction to the relationship between the two most important material properties (glass fiber and holding time) was analyzed. In 2020, Junren Shi [27] combined the driving data of experienced drivers in different driving environments with deep learning to build a deep long-termshort-term memory network to predict the aperture of the brake pedal under different braking types. The proposed anthropomorphic control method, which combines driving data with deep learning, can be used to predict the aperture value of the pedal of the loading mechanism in a complex driving environment.…”

Section: Literature Reviewmentioning

confidence: 99%

Using Sequence-Approximation Optimization and Radial-Basis-Function Network for Brake-Pedal Multi-Target Warping and Cooling

et al. 2022

View full text Add to dashboard Cite

This paper uses a multi-objective optimization method to optimize the injection-molding defects of automotive pedals. Compared with the traditional automotive pedal material, aluminum alloy, the polymer pedal containing glass fibers not only reduces the aluminum pedal by at least half, but also improves the strength and hardness of the fibers by adjusting the orientation of the fibers in all directions. Injection factors include: filling time, filling pressure, melt temperature, cooling time, injection time, etc. For the optimization process influencing factors, herein, we focus on warpage analyzed via flow simulation, and setting warpage parameters and cycle time as discussed by setting different cooling distributions, pressures and temperature schemes. The multi-objective optimization design was mainly used to describe the relationship between cycle time and warpage, and the Pareto boundary was used for cycle time and warpage to identify the deviation function and radial-basis-function network. We worked with a small DOE for building the surface to run SAO programming—which improved the accuracy of the response surface by adding sampling points—terminating the time when the warpage value met the solution requirements, to find out the global optimal solution of the warpage value under different cooling times. Finally, the results highlighted four influencing parameters that match the experimental image of the actual production.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Using Sequence-Approximation Optimization and Radial-Basis-Function Network for Brake-Pedal Multi-Target Warping and Cooling

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Other applications of deep learning methods were undertaken to enhance construction machines tracking and operation. Shi et al (2020) has proposed deep LSTM network to predict the brake pedal aperture for different braking types. Lee et al (2020) have proposed an automatic detecting technique for excessive carrying-load (DeTECLoad) uses a hybrid Convolutional Neural Network-Long Short-Term Memory to predict load-carrying weights and postures simultaneously.…”

Section: Health and Safety Using Deep Learningmentioning

confidence: 99%

The application of “deep learning” in construction site management: scientometric, thematic and critical analysis

Elghaish

Matarneh

Alhusban

2021

View full text Add to dashboard Cite

Purpose The digital construction transformation requires using emerging digital technology such as deep learning to automate implementing tasks. Therefore, this paper aims to evaluate the current state of using deep learning in the construction management tasks to enable researchers to determine the capabilities of current solutions, as well as finding research gaps to carry out more research to bridge revealed knowledge and practice gaps. Design/methodology/approach The scientometric analysis is conducted for 181 articles to assess the density of publications in different topics of deep learning-based construction management applications. After that, a thematic and gap analysis are conducted to analyze contributions and limitations of key published articles in each area of application. Findings The scientometric analysis indicates that there are four main applications of deep learning in construction management, namely, automating progress monitoring, automating safety warning for workers, managing construction equipment, integrating Internet of things with deep learning to automatically collect data from the site. The thematic and gap analysis refers to many successful cases of using deep learning in automating site management tasks; however, more validations are recommended to test developed solutions, as well as additional research is required to consider practitioners and workers perspectives to implement existing applications in their daily tasks. Practical implications This paper enables researchers to directly find the research gaps in the existing solutions and develop more workable applications to bridge revealed gaps. Accordingly, this will be reflected on speeding the digital construction transformation, which is a strategy over the world. Originality/value To the best of the authors’ knowledge, this paper is the first of its kind to adopt a structured technique to assess deep learning-based construction site management applications to enable researcher/practitioners to either adopting these applications in their projects or conducting further research to extend existing solutions and bridging revealed knowledge gaps.

show abstract

“…Promising solutions involve autonomous construction and improving the efficiency of non‐skilled operators. Several studies have addressed autonomous construction involving wheel loaders (Shi et al, 2020a, 2020b), bulldozer (Barakat & Sharma, 2019), cranes (Chakraborty & Meena, 2016; Koivumaki & Mattila, 2015), and excavators. In the previous study, the target tasks for excavator automation are free‐form trenching (Jud et al, 2019), rock pile excavation (Fukui et al, 2017), manipulation of large‐scale stones (Mascaro et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of excavation motion sequence for hydraulic excavators based on extraction of excavation style and phase

Sato

Tsunano

Sano

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

In recent times, research on highly efficient construction has gained increasing popularity. During construction with hydraulic excavators, the sequence of excavation motions significantly affects the duration and precision of the work; therefore, it should be as efficient as possible. Because automation is still difficult, the ability improvement support system of nonskilled operators is required. However, currently, there exists no effective method for evaluating or planning the excavation motion sequence. This study proposes a method for evaluating excavation motion sequences based on a pattern recognition technique. First, the data array of hydraulic excavator motions is divided into unit excavation motions, characterized using a clustering method. Second, the patterns are divided into excavation phases with similar excavation motion patterns. Finally, the excavation motion sequence is evaluated by calculating the transition frequency between excavation phases. The result shows that the proposed approach can classify the skill level of the operator with accuracy of 0.8. Therefore, the frequency of excavation phase transitions can be used as a useful indicator for evaluating excavation motion sequences.

show abstract

Prediction of brake pedal aperture for automatic wheel loader based on deep learning

Cited by 25 publications

References 31 publications

Using Sequence-Approximation Optimization and Radial-Basis-Function Network for Brake-Pedal Multi-Target Warping and Cooling

Using Sequence-Approximation Optimization and Radial-Basis-Function Network for Brake-Pedal Multi-Target Warping and Cooling

The application of “deep learning” in construction site management: scientometric, thematic and critical analysis

Evaluation of excavation motion sequence for hydraulic excavators based on extraction of excavation style and phase

Contact Info

Product

Resources

About