Graphene Foam Chemical Sensor System Based on Principal Component Analysis and Backpropagation Neural Network

Hua, Hongling; Xie, Xiaohui; Sun, Jinjin; Gan, Qintao; Tang, Caiyan; Zhang, Zhen; Ding, Zhaoqiang; Yue, Weiwei

doi:10.1155/2018/2361571

Cited by 4 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays it is still a challenge to create a device with a specificity capable of distinguishing between similar chemicals. Progress with carbon nanostructures has been achieved, as shown before [125]. In this sense, we envision that the innumerous possibilities of functionalization is the most promising approach to reach specificity and this tailoring of properties is achievable with carbon-based nanostructures.…”

Section: Discussionmentioning

confidence: 79%

“…The resistance of unmodified 3D graphene structures was also used to detect other organic molecules, among which are chloroform, ether and acetone as demonstrated by H. Hua et al [125]. The graphene foam was also synthesized using a nickel scaffold as a template while the resistance curves for the various molecules were acquired and an algorithm was applied to discriminate the specific molecules with over 97% accuracy.…”

Section: D Carbon Nanostructures As Chemical and Electrochemical Senmentioning

confidence: 99%

“…The fabrication process of 3D graphene foam and the electrical resistance time domain detection system (CCS: constant current source; IA: instrument amplifier; MCU: micro control unit). Reprinted with permission from ref [125]…”

mentioning

confidence: 99%

See 2 more Smart Citations

Carbon Nanostructures as a Multi-Functional Platform for Sensing Applications

et al. 2018

View full text Add to dashboard Cite

The various forms of carbon nanostructures are providing extraordinary new opportunities that can revolutionize the way gas sensors, electrochemical sensors and biosensors are engineered. The great potential of carbon nanostructures as a sensing platform is exciting due to their unique electrical and chemical properties, highly scalable, biocompatible and particularly interesting due to the almost infinite possibility of functionalization with a wide variety of inorganic nanostructured materials and biomolecules. This opens a whole new pallet of specificity into sensors that can be extremely sensitive, durable and that can be incorporated into the ongoing new generation of wearable technology. Within this context, carbon-based nanostructures are amongst the most promising structures to be incorporated in a multi-functional platform for sensing. The present review discusses the various 1D, 2D and 3D carbon nanostructure forms incorporated into different sensor types as well as the novel functionalization approaches that allow such multi-functionality.

show abstract

Section: Discussionmentioning

confidence: 79%

Section: D Carbon Nanostructures As Chemical and Electrochemical Senmentioning

confidence: 99%

See 1 more Smart Citation

Carbon Nanostructures as a Multi-Functional Platform for Sensing Applications

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Because BP neural networks have the ability to realize arbitrary nonlinear mapping of input and output, a three-layer BP neural network can approximate any nonlinear function with any degree of precision [27]. Although the BP algorithm has shortcomings, such as slow convergence speed and ease of encountering local minima, it is still widely used in pattern recognition, function approximation, and data analysis [28,29]. Since network performance is expected and increasing the number of implied layers too much can lead to a complex model, this study uses only one implied layer to evaluate network performance.…”

Section: Bp Neural Networkmentioning

confidence: 99%

Prediction of Ultimate Bearing Capacity of Pile Foundation Based on Two Optimization Algorithm Models

Ren

Xian-bin

2023

Buildings

View full text Add to dashboard Cite

The determination of the bearing capacity of pile foundations is very important for their design. Due to the high uncertainty of various factors between the pile and the soil, many methods for predicting the ultimate bearing capacity of pile foundations focus on correlation with field tests. In recent years, artificial neural networks (ANN) have been successfully applied to various types of complex issues in geotechnical engineering, among which the back-propagation (BP) method is a relatively mature and widely used algorithm. However, it has inevitable shortcomings, resulting in large prediction errors and other issues. Based on this situation, this study was designed to accomplish two tasks: firstly, using the genetic algorithm (GA) and particle swarm optimization (PSO) to optimize the BP network. On this basis, the two optimization algorithms were improved to enhance the performance of the two optimization algorithms. Then, an adaptive genetic algorithm (AGA) and adaptive particle swarm optimization (APSO) were used to optimize a BP neural network to predict the ultimate bearing capacity of the pile foundation. Secondly, to test the performance of the two optimization models, the predicted results were compared and analyzed in relation to the traditional BP model and other network models of the same type in the literature based on the three most common statistical indicators. The models were evaluated using three common evaluation metrics, namely the coefficient of determination (R2), value account for (VAF), and the root mean square error (RMSE), and the evaluation metrics for the test set were obtained as AGA-BP (0.9772, 97.8348, 0.0436) and APSO-BP (0.9854, 98.4732, 0.0332). The results show that compared with the predicted results of the BP model and other models, the test set of the AGA-BP model and APSO-BP model achieved higher accuracy, and the APSO-BP model achieved higher accuracy and reliability, which provides a new method for the prediction of the ultimate bearing capacity of pile foundations.

show abstract

“…The algorithm commonly used for feature dimensionality reduction is principal component analysis [20][21], which is performed as follows:…”

Section: Feature Dimensionality Reductionmentioning

confidence: 99%

Partial Discharge Detection Technology for GIS Insulation Defects under Complex Electromagnetic Environment

Chentian,

Huruizhi,

Liuyuting

et al. 2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper first introduces the main types of GIS insulation defects and explores the discharge mechanism of GIS insulation. Then, the space of discharge features of GIS insulation defects in a complex electromagnetic environment is constructed, and the feature dimensionality reduction is carried out by using principal component analysis. Then, the support vector machine algorithm is explored and optimized with the immune algorithm to identify and detect the local features of insulation defects. Finally, the local discharge characteristics of GIS insulation defects are investigated through simulation experiments, and the discharge results are analyzed. The results show that the average peak-to-peak value is around 31mV and the power distribution band is 133~168MHZ for the spiky insulation defects, the average peak-to-peak value is around 19.8mV and the power distribution band is around 202MHZ for the metallic particles insulation, and the peak value of the air gap is less than 8mV and more than 48mV for some, and the power distribution band is 98MHZ~146MHZ. The localized discharge characteristics of the defects of the GIS insulation parts are identified and detected by the immune optimization of the support vector machine algorithm. The overall recognition rate of immunodeficient partial discharges of insulating parts is around 0.90. This study is able to detect the type of partial discharges in GIS insulating parts well.

show abstract

Graphene Foam Chemical Sensor System Based on Principal Component Analysis and Backpropagation Neural Network

Cited by 4 publications

References 35 publications

Carbon Nanostructures as a Multi-Functional Platform for Sensing Applications

Carbon Nanostructures as a Multi-Functional Platform for Sensing Applications

Prediction of Ultimate Bearing Capacity of Pile Foundation Based on Two Optimization Algorithm Models

Partial Discharge Detection Technology for GIS Insulation Defects under Complex Electromagnetic Environment

Contact Info

Product

Resources

About