scholarly journals Research on Defect Diagnosis Method of Reactor Acoustic Vibration Method Based on Deep Learning

2021 ◽  
Vol 243 ◽  
pp. 02005
Author(s):  
Peng-fei Jia ◽  
Shu-guo Gao ◽  
Xing-hui Zhang ◽  
Ling-ming Meng ◽  
Yang Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Evaluation Method ◽  
Vibration Signal ◽  
Acoustic Vibration ◽  
The State ◽  
Characteristic Parameters ◽  
Defect States ◽  
Defect Simulation ◽  
Function Relationship

Although the state evaluation method based on characteristic parameters and weight factors can extract the characteristic quantities in time domain and frequency domain according to the collected acoustic and vibration signals of reactors, it is necessary to analyze a large number of test data to establish the functional relationship between the characteristic quantities and the defect states, and to establish the function relationship between the characteristic quantities and the defect states, and to establish the function relationship between the characteristic quantities and the defect states The method can directly learn the data samples, and self-study the correlation rules of characteristic parameters and defects through the training of neural network. In this paper, the deep learning neural network model is constructed, and the data obtained from reactor defect simulation experiment and field measurement are used as samples to train the deep learning network. Through the training of neural network, the characteristics of acoustic vibration signal are automatically learned, and the characteristics are stored in the parameters of neural network. Finally, the state of reactor is realized by the classifier at the end of the network assessment

scholarly journals Classification of Chaotic Squeak And Rattle Vibrations By CNN Using Recurrence Pattern

2021 ◽  
Author(s):  
Jaehyeon Nam ◽  
Jaeyoung Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Lyapunov Exponent ◽  
Numerical Experiment ◽  
Vibration Signal ◽  
Single Mode ◽  
Recurrence Plot ◽  
Recurrence Pattern ◽  
Multi Mode

Abstract The chaotic squeak and rattle (S&R) vibrations in mechanical systems were classified by deep learning. The rattle, single-mode, and multi-mode squeak models were constructed to generate chaotic S&R signals. The repetition of nonlinear signals generated by them was visualized using an unthresholded recurrence plot and learned using a convolutional neural network (CNN). The results showed that even if the signal of the S&R model is chaos, it could be classified. The accuracy of the classification was verified by calculating the Lyapunov exponent of the vibration signal. The numerical experiment confirmed that the CNN classification using nonlinear vibration images as the proposed procedure has more than 90% accuracy. The chaotic status and each model can be classified into six classes.

scholarly journals Protein sequence design with a learned potential

2020 ◽  
Author(s):  
Namrata Anand-Achim ◽  
Raphael R. Eguchi ◽  
Alexander Derry ◽  
Russ B. Altman ◽  
Po-Ssu Huang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Amino Acid ◽  
Protein Design ◽  
Protein Sequence ◽  
State Of The Art ◽  
The State ◽  
Energy Functions ◽  
Sequence Design

AbstractThe primary challenge of fixed-backbone protein design is to find a distribution of sequences that fold to the backbone of interest. This task is central to nearly all protein engineering problems, as achieving a particular backbone conformation is often a prerequisite for hosting specific functions. In this study, we investigate the capability of a deep neural network to learn the requisite patterns needed to design sequences. The trained model serves as a potential function defined over the space of amino acid identities and rotamer states, conditioned on the local chemical environment at each residue. While most deep learning based methods for sequence design only produce amino acid sequences, our method generates full-atom structural models, which can be evaluated using established sequence quality metrics. Under these metrics we are able to produce realistic and variable designs with quality comparable to the state-of-the-art. Additionally, we experimentally test designs for a de novo TIM-barrel structure and find designs that fold, demonstrating the algorithm’s generalizability to novel structures. Overall, our results demonstrate that a deep learning model can match state-of-the-art energy functions for guiding protein design.SignificanceProtein design tasks typically depend on carefully modeled and parameterized heuristic energy functions. In this study, we propose a novel machine learning method for fixed-backbone protein sequence design, using a learned neural network potential to not only design the sequence of amino acids but also select their side-chain configurations, or rotamers. Factoring through a structural representation of the protein, the network generates designs on par with the state-of-the-art, despite having been entirely learned from data. These results indicate an exciting future for protein design driven by machine learning.

scholarly journals Research on Reactor Condition Evaluation Method Based on Acoustic Vibration Characteristic Parameters and Weight Factors

2021 ◽  
Vol 243 ◽  
pp. 02003
Author(s):  
Peng-fei Jia ◽  
Shu-guo Gao ◽  
Xing-hui Zhang ◽  
Ling-ming Meng ◽  
Li-hua Li ◽  
...  
Keyword(s):  
Evaluation Method ◽  
Detection Method ◽  
Power Level ◽  
Characteristic Parameter ◽  
Acoustic Vibration ◽  
Signal Spectrum ◽  
Characteristic Parameters ◽  
Term Operation ◽  
Vibration Detection ◽  
Distribution Rule

Compared with the traditional reactor abnormal state detection method, the acoustic vibration detection method combines the advantages of acoustic detection and vibration detection, which has the advantages of simple installation, strong portability and good signal integrity, and has a broad application prospect. In this paper, the characteristic parameters of reactor acoustic vibration, including sound pressure level, sound power level, acoustic signal spectrum, vibration amplitude, vibration acceleration value, vibration signal spectrum, harmonic proportion and frequency complexity, are obtained to analyze the range and distribution rule of each characteristic parameter under long-term operation condition of reactor, and the weight factor of each characteristic parameter is determined by analytic hierarchy process On the basis of fuzzy reasoning, the state evaluation model of reactor is established.

scholarly journals Physics-Aware Deep-Learning-Based Proxy Reservoir Simulation Model Equipped With State and Well Output Prediction

2021 ◽  
Vol 7 ◽  
Author(s):  
Emilio Jose Rocha Coutinho ◽  
Marcelo Dall’Aqua ◽  
Eduardo Gildin
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Simulation Model ◽  
Reservoir Simulation ◽  
The State ◽  
Data Driven ◽  
Training Procedure ◽  
State Variables ◽  
Input Output ◽  
Modeling Framework

Data-driven methods have been revolutionizing the way physicists and engineers handle complex and challenging problems even when the physics is not fully understood. However, these models very often lack interpretability. Physics-aware machine learning (ML) techniques have been used to endow proxy models with features closely related to the ones encountered in nature; examples span from material balance to conservation laws. In this study, we proposed a hybrid-based approach that incorporates physical constraints (physics-based) and yet is driven by input/output data (data-driven), leading to fast, reliable, and interpretable reservoir simulation models. To this end, we built on a recently developed deep learning–based reduced-order modeling framework by adding a new step related to information on the input–output behavior (e.g., well rates) of the reservoir and not only the states (e.g., pressure and saturation) matching. A deep-neural network (DNN) architecture is used to predict the state variables evolution after training an autoencoder coupled with a control system approach (Embed to Control—E2C) along with the addition of some physical components (loss functions) to the neural network training procedure. Here, we extend this idea by adding the simulation model output, for example, well bottom-hole pressure and well flow rates, as data to be used in the training procedure. Additionally, we introduce a new architecture to the E2C transition model by adding a new neural network component to handle the connections between state variables and model outputs. By doing this, it is possible to estimate the evolution in time of both the state and output variables simultaneously. Such a non-intrusive data-driven method does not need to have access to the reservoir simulation internal structure, so it can be easily applied to commercial reservoir simulators. The proposed method is applied to an oil–water model with heterogeneous permeability, including four injectors and five producer wells. We used 300 sampled well control sets to train the autoencoder and another set to validate the obtained autoencoder parameters. We show our proxy’s accuracy and robustness by running two different neural network architectures (propositions 2 and 3), and we compare our results with the original E2C framework developed for reservoir simulation.

scholarly journals Research on Video Quality Evaluation of Sparring Motion Based on BPNN Perception

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zhao Changbi ◽  
Wang Jinjuan ◽  
Ke Li
Keyword(s):  
Neural Network ◽  
Evaluation System ◽  
Quality Evaluation ◽  
Evaluation Method ◽  
Video Quality ◽  
Characteristic Parameters ◽  
Evaluation Algorithm ◽  
Video Quality Evaluation ◽  
Compression Damage

The quality of boxing video is affected by many factors. For example, it needs to be compressed and encoded before transmission. In the process of transmission, it will encounter network conditions such as packet loss and jitter, which will affect the video quality. Combined with the proposed nine characteristic parameters affecting video quality, this paper proposes an architecture of video quality evaluation system. Aiming at the compression damage and transmission damage of leisure sports video, a video quality evaluation algorithm based on BP neural network (BPNN) is proposed. A specific Wushu video quality evaluation algorithm system is implemented. The system takes the result of feature engineering of 9 feature parameters of boxing video as the input and the subjective quality score of video as the training output. The mapping relationship is established by BPNN algorithm, and the objective evaluation quality of boxing video is finally obtained. The results show that using the neural network analysis model, the characteristic parameters of compression damage and transmission damage used in this paper can get better evaluation results. Compared with the comparison algorithm, the accuracy of the video quality evaluation method proposed in this paper has been greatly improved. The subjective characteristics of users are evaluated quantitatively and added to the objective video quality evaluation model in this paper, so as to make the video evaluation more accurate and closer to users.

A hybrid GMDH neural network and logistic regression framework for state parameter-based liquefaction evaluation

2021 ◽  
Author(s):  
Wei Duan ◽  
Surya Sarat Chandra Congress ◽  
Guojun Cai ◽  
Songyu Liu ◽  
Xiaoqiang Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Logistic Regression ◽  
Relative Density ◽  
Evaluation Method ◽  
Ground Improvement ◽  
State Parameter ◽  
Mapping Function ◽  
Soil Liquefaction ◽  
The State ◽  
Group Method

The cyclic stress or liquefaction behavior of granular materials is strongly affected by the relative density and confining pressure of the soil. In this study, the state parameter accounting for both relative density and effective stress was used to evaluate soil liquefaction potential. Based on case histories along with the cone penetration test (CPT) database, models for calculating the state parameter using a group method of data handling (GMDH) neural network were developed and recommended according to their performance. The state parameter was then used to develop a state parameter-based probabilistic liquefaction evaluation method using a logistic regression model. From a conservative point of view, the boundary curve of 20% probability of liquefaction was suggested as a deterministic criterion for state parameter-based liquefaction evaluation. Subsequently, a mapping function relating the calculated factor of safety (FS) to the probability of liquefaction (PL) was proposed based on the compiled CPT database. Based on the developed PL–FS function, a new risk criterion associated with the state parameter-based design chart was proposed. Finally, a flowchart of state-based probabilistic liquefaction evaluation and quality control for ground-improvement projects was presented for the benefit of practitioners.

scholarly journals Classification of Chaotic Squeak and Rattle Vibrations by CNN Using Recurrence Pattern

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8054
Author(s):  
Jaehyeon Nam ◽  
Jaeyoung Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Lyapunov Exponent ◽  
Numerical Experiment ◽  
Vibration Signal ◽  
Single Mode ◽  
Recurrence Plot ◽  
Recurrence Pattern ◽  
Multi Mode

The chaotic squeak and rattle (S&R) vibrations in mechanical systems were classified by deep learning. The rattle, single-mode, and multi-mode squeak models were constructed to generate chaotic S&R signals. The repetition of nonlinear signals generated by them was visualized using an unthresholded recurrence plot and learned using a convolutional neural network (CNN). The results showed that even if the signal of the S&R model is chaos, it could be classified. The accuracy of the classification was verified by calculating the Lyapunov exponent of the vibration signal. The numerical experiment confirmed that the CNN classification using nonlinear vibration images as the proposed procedure has more than 90% accuracy. The chaotic status and each model can be classified into six classes.

Developing an Artificial Intelligence Project in your Radiology Department

2020 ◽  
Vol 2 ◽  
pp. 58-61 ◽  
Author(s):  
Syed Junaid ◽  
Asad Saeed ◽  
Zeili Yang ◽  
Thomas Micic ◽  
Rajesh Botchu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Health Care ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Radiology Department ◽  
Short Article ◽  
Computing Power ◽  
Road Map ◽  
Key Concepts

The advances in deep learning algorithms, exponential computing power, and availability of digital patient data like never before have led to the wave of interest and investment in artificial intelligence in health care. No radiology conference is complete without a substantial dedication to AI. Many radiology departments are keen to get involved but are unsure of where and how to begin. This short article provides a simple road map to aid departments to get involved with the technology, demystify key concepts, and pique an interest in the field. We have broken down the journey into seven steps; problem, team, data, kit, neural network, validation, and governance.

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Sign in / Sign up

Export Citation Format

Share Document