CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction

Shan, Liqun; Liu, Yanchang; Tang, Min; Yang, Ming; Bai, Xueyuan

doi:10.1016/j.petrol.2021.108838

Cited by 73 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BiLSTM model fully considers the data information before and after the current displacement data during model training. At present, the BiLSTM model has been successfully applied in many prediction fields, including solar radiation hourly prediction [ 37 ], well log prediction [ 38 ] and tourism demand prediction [ 39 ]. Figure 2 shows the BiLSTM model structure adopted in this paper.…”

Section: Methodsmentioning

confidence: 99%

Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model

Lin

Sun

2022

IJERPH

View full text Add to dashboard Cite

In recent years, machine learning models facilitated notable performance improvement in landslide displacement prediction. However, most existing prediction models which ignore landslide data at each time can provide a different value and meaning. To analyze and predict landslide displacement better, we propose a dynamic landslide displacement prediction model based on time series analysis and a double-bidirectional long short term memory (Double-BiLSTM) model. First, the cumulative landslide displacement is decomposed into trend and periodic displacement components according to time series analysis via the exponentially weighted moving average (EWMA) method. We consider that trend displacement is mainly influenced by landslide factors, and we apply a BiLSTM model to predict landslide trend displacement. This paper analyzes the internal relationship between rainfall, reservoir level and landslide periodic displacement. We adopt the maximum information coefficient (MIC) method to calculate the correlation between influencing factors and periodic displacement. We employ the BiLSTM model for periodic displacement prediction. Finally, the model is validated against data pertaining to the Baishuihe landslide in the Three Gorges, China. The experimental results and evaluation indicators demonstrate that this method achieves a better prediction performance than the classical prediction methods, and landslide displacement can be effectively predicted.

show abstract

Section: Methodsmentioning

confidence: 99%

Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model

Lin

Sun

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 3, the BiLSTM can extract contextual information through both forward and backward LSTM layers. 41 The forward LSTM layer generates an output sequence while the backward LSTM layer exports ⃖⃖ ℎ 𝑡 . Finally, the BiLSTM layer generates an output vector which is called 𝑌 = [𝑦 1 , 𝑦 2 , 𝑦 3 , ⋅ ⋅ ⋅, 𝑦 𝑡 ],and each element is calculated as:…”

Section: Bi-directional Long-short Term Memorymentioning

confidence: 99%

“…At each moment, the input is supplied to both networks in opposite directions, while the output is determined jointly by the two unidirectional networks. As shown in Figure 3, the BiLSTM can extract contextual information through both forward and backward LSTM layers 41 …”

Section: Theoretical Foundationmentioning

confidence: 99%

A CNN‐BiLSTM‐Bootstrap integrated method for remaining useful life prediction of rolling bearings

Guo

Wang

et al. 2023

Quality & Reliability Eng

View full text Add to dashboard Cite

Rolling bearings, an essential fundamental component in machinery and equipment, have been widely used. Predicting the remaining useful life (RUL) of rolling bearings helps maintain the reliability of mechanical systems. Accurate prediction of RUL requires extracting deep features in complex non-linear vibration signals, the prediction results often vary widely. This paper proposes a RUL prediction method based on convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), and bootstrap method (CNN-BiLSTM-Bootstrap) to model the forecasting uncertainty. The first step is to extract the first prediction time (FPT) of the degradation phase of rolling bearings using an adaptive method for the 3𝜎 intervals of rolling bearing vibration signal kurtosis. The model extracts the spatio-temporal features through CNN and BiLSTM, and combines the bootstrap method to quantify the RUL prediction interval (PI) of rolling bearings. The comparison with existing models verified the effectiveness and generalization of the proposed model.

show abstract

“…Zhang et al (2021b) introduced the overall design of a new acoustic logging tool while drilling, tested the tool, and obtained qualified data. Shan et al (2021) coupled the hybrid neural network prediction logging curve, carried out practice and evaluation in the field, and achieved high prediction accuracy. Keramat and Duan (2021) developed a new technique for leak detection, called Matched-Field Processing.…”

Section: Introductionmentioning

confidence: 99%

Leakage simulation and acoustic characteristics based on acoustic logging by ultrasonic detection

Wan

Wang

et al. 2022

Adv. Geo-Energy Res.

View full text Add to dashboard Cite

The detection of casing leakage in oil and gas wells or water injection wells is an important element of wellbore integrity management. Ultrasonic technology is suitable to detect and identify the position of leakage in oil and gas well shafts, providing engineering guidance for subsequent treatment. In this paper, the finite element calculation model of casing leakage in oil and gas wells is established by using the computational fluid dynamics method, and the large eddy simulation model and Ffowcs Williams-Hawkings acoustic model are utilized to simulate the casing leakage condition. The acoustic pressure signals of each monitoring point on the inner axis of the pipeline are obtained, and the influences of the pipeline pressure difference, the leakage hole diameter and the pipeline fluid on the leakage acoustic field are analyzed. The simulation results indicate that the acoustic pressure level measured on the pipeline axis rises with the increase of pipeline pressure difference and leakage hole diameter. The size and variation rule of acoustic pressure level also vary with the type of pipeline fluid. Overall, the results obtained show that ultrasonic logging can accurately locate and detect tubing leakage, and they provide theoretical guidance for practical casing leakage detection, assisting with wellbore integrity management.

show abstract

CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction

Cited by 73 publications

References 26 publications

Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model

Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model

A CNN‐BiLSTM‐Bootstrap integrated method for remaining useful life prediction of rolling bearings

Leakage simulation and acoustic characteristics based on acoustic logging by ultrasonic detection

Contact Info

Product

Resources

About