Intelligent Monitoring Method Research Articles

Intelligent Monitoring Model for Lost Circulation Based on Unsupervised Time Series Autoencoder

Lost circulation, a common risk during the drilling process, significantly impacts drilling safety and efficiency. The presence of data noise and temporal evolution characteristics pose significant challenges to the accurate monitoring of lost circulation. Traditional supervised intelligent monitoring methods rely on large amounts of labeled data, which often do not consider temporal fluctuations in data, leading to insufficient accuracy and transferability. To address these issues, this paper proposes an unsupervised time series autoencoder (BiLSTM-AE) intelligent monitoring model for lost circulation, aiming to overcome the limitations of supervised algorithms. The BiLSTM-AE model employs BiLSTM for both the encoder and decoder, enabling it to comprehensively capture the temporal features and dynamic changes in the data. It learns the patterns of normal data sequences, thereby automatically identifying anomalous risk data points that deviate from the normal patterns during testing. Results show that the proposed model can efficiently identify and monitor lost circulation risks, achieving an accuracy of 92.51%, a missed alarm rate of 6.87%, and a false alarm rate of 7.71% on the test set. Compared to other models, the BiLSTM-AE model has higher accuracy and better timeliness, which is of great significance for improving drilling efficiency and ensuring drilling safety.

Intelligent stability monitoring and improvement of grid‐connected converter under weighted average control

AbstractThis article presents an intelligent stability monitoring and improvement method for the grid‐connected converter system. The model of grid‐connected converter, based on the weighted average current feedback (WACF) and weighted average voltage feedforward (WAVF) control, is first established. Then, the time‐varying grid impedance and parameter perturbation of LCL‐filter are precisely identified by artificial neural network (ANN) module in real time. Furthermore, the control parameters are adaptively tuned by certain rules based on the predicted parameters to increase the high‐frequency stability margin of converter system. Simulation and experimental results are given to validate the proposed identification and parameter tuning method. The proposed method is able to monitor the real‐time operation state of the grid‐connected converter and improve the self‐adaptivity of the grid‐connected converter system against parameter perturbation.

A real-time intelligent monitoring method for indoor evacuee distribution based on deep learning and spatial division

Providing real-time and detailed indoor evacuee distribution information is of great significance for the on-site formulating and dynamic adjustment of indoor emergency evacuation strategies. However, due to limitations in hardware costs and privacy protection, existing video surveillance and other evacuee counting methods cannot achieve real-time and accurate monitoring of the number and distribution of evacuees in all indoor areas. To solve the problem, using video data from an indoor surveillance system as a data source, an intelligent monitoring method for indoor pedestrian real-time distribution based on deep learning and spatial division is proposed. Firstly, the whole indoor area is divided many subareas according to the layout of indoor space and the size of spatial units. Then, deep learning detection and tracking algorithms are used to detect and track evacuees to achieve the number of evacuees at the boundary of each subarea and their movement directions; Finally, the numbers of evacuees entering and leaving each subarea are counted to obtain the spatial distribution information of evacuees. The experimental results show that within an appropriate monitoring distance, the proposed method achieves an average F1 score of 91.85% for evacuee counting at the boundaries of each subarea, with a processing speed of 22 FPS. More comprehensive and accurate real-time monitoring of evacuee distribution in the entire indoor space can be achieved, including no covered areas of cameras. It not only helps to formulate on-site emergency evacuation in case of a fire, but also enhances the daily operation and management capabilities of buildings.

Approaches of Combining Machine Learning with NMR-Based Pore Structure Characterization for Reservoir Evaluation

Tight gas, a category of unconventional natural gas, relies on advanced intelligent monitoring methods for their extraction. Conventional logging for reservoir evaluation relies on logging data and the manual setting of evaluation criteria to classify reservoirs. However, the complexity and heterogeneity of tight reservoirs pose challenges in accurately identifying target layers by using traditional well-logging techniques. Machine learning may hold the key to solving this problem, as it enables computers to learn without being explicitly programmed and manually adding rules. Therefore, it is possible to make reservoir evaluations using machine learning methods. In this paper, the reservoir quality index (RQI) and porous geometric parameters obtained from the optimized inversion of the spherical–tubular model are adopted to evaluate the reservoir. Then, three different machine learning approaches, the random forest (RF) algorithm, support vector machine (SVM) algorithm, and extreme gradient boosting (XGB) algorithm, are utilized for reservoir classification. The selected dataset covers more than 7000 samples from five wells. The data from four wells are arranged as the training dataset, and the data of the remaining one well is designed as the testing dataset to calculate the prediction accuracies of different machine learning algorithms. Among them, accuracies of RF, SVM, and XGB are all higher than 90%, and XGB owns the highest result by reaching 97%. Machine learning based approaches can greatly assist reservoir prediction by implementing the well-logging data. The research highlights the application of reservoir classification with a higher prediction accuracy by combining machine learning algorithms with NMR-logging-based pore structure characterization, which can provide a guideline for sweet spot identification within the tight formation. This not only optimizes resource extraction but also aligns with the global shift towards clean and renewable energy sources, promoting sustainability and reducing the carbon footprint associated with conventional energy production. In summary, the fusion of machine learning and NMR-logging-based reservoir evaluation plays a crucial role in advancing both energy efficiency and the transition to cleaner energy sources.

ЦИФРОВЫЕ РЕШЕНИЯ В АГРОБИЗНЕСЕ: ФОРМИРОВАНИЕ МЕТОДОЛОГИИ МОНИТОРИНГА ЗЕРНОВОГО ПРОИЗВОДСТВА В УСЛОВИЯХ ТЕХНОЛОГИЧЕСКИХ ИННОВАЦИЙ

The active penetration of digital technologies into human economic activity objectively poses the task of forming an informational space and a new technological base across the entire economic space of society. The appearance of key sectors of the national economy is changing, with an increasing portion of business processes moving into the digital environment, thereby forming a barrier-free character of exchange and consumption relationships. Among the sectors of the domestic economy, the agricultural sector (AIC) has the highest rates of digital activity growth in recent years, with its indicator in 2023 amounting to 200% relative to the average level across the economy – 131% (compared with 2016), indicating the beginning of fundamental transformations within the mode of production. The leader of the AIC is the production of grain and its processing products, collectively accounting for more than a third of the total volume of the agri-food market, hence the processes of digital solutions penetration into grain production require close attention. The key business process of grain production is the monitoring of all its elements, ensuring the quality and timeliness of management decisions at each level of added value production. The spread of business models based on digital technologies requires a new methodology of platform solutions not only at the level of technological adaptation but also restructuring, modification of established ways of conducting agribusiness, and significant organizational changes. Systematization of digital solutions approaches shows that the use of artificial intelligence significantly accelerates the digital transformation of grain production; however, for a widespread transition to intelligent monitoring methods of grain production, a number of objective conditions must be met, among them: data handling, the ability to choose a computer vision model, creation of neural network architecture, organization of training for personnel capable of making decisions on digital platforms, and the formation of corresponding psychological-behavioral client content. The implementation of these conditions, based on ongoing institutional transformations, is capable of ensuring stable growth of grain production, reducing its energy intensity, and preparing personnel with digital economy competencies.

The study of hydraulic machinery condition monitoring based on anomaly detection and fault diagnosis

The existing intelligent monitoring methods are hard to apply directly to hydraulic machinery due to fault data collection difficulties and the uncertainty of fault occurrence. To monitor the hydraulic machinery effectively, we design a novel feature extraction method called TFF_VMD and propose a comprehensive framework based on support vector data description (SVDD) and support vector machine (SVM), dividing the monitoring task into anomaly detection and fault identification. A pump test bench is built for data collection and method validation. Meanwhile, one online bearing dataset is used to pre-train SVM. The proposed method achieves satisfying results on three datasets, getting the accuracy of anomaly detection at 0.891, 0.999, and 0.995, respectively, getting mean and standard deviation of fault diagnosis accuracy at 0.954 ± 0.05, 0.96 ± 0.04, and 0.98 ± 0.03. Results show that TFF_VMD is valuable for SVDD and SVM, and the proposed framework can preliminarily achieve early warning and diagnosis of mechanical and hydraulic faults.

An intelligent monitoring method of underground unmanned electric locomotive loading process based on deep learning method

An intelligent monitoring method of underground unmanned electric locomotive loading process based on deep learning method

Intelligent monitoring of the available lead (Pb) and cadmium (Cd) in soil samples based on half adder and half subtractor molecular logic gates

The available heavy metals in soil samples can cause the direct toxicity on ecosystems, plants, and human health. Traditional chemical extraction and recombinant bacterial methods for the available heavy metals assay often suffer from inaccuracy and poor specificity. In this work, we construct half adder and half subtractor molecular logic gates with molecular-level biocomputation capabilities for the intelligent sensing of the available lead (Pb) and cadmium (Cd). The available Pb and Cd can cleave DNAzyme sequences to release the trigger DNA, which can activate the hairpin probe assembly in the logic system. This multifunctional logic system can not only achieve the intelligent recognition of the available Pb and Cd according to the truth tables, but also can realize the simultaneous quantification with high sensitivity, with the detection limits of 2.8 pM and 25.6 pM, respectively. The logic biosensor is robust and has been applied to determination of the available Pb and Cd in soil samples with good accuracy and reliability. The relative error (Re) between the logic biosensor and the DTPA + ICP-MS method was from −8.1 % to 7.9 %. With the advantages of programmability, scalability, and multicomputing capacity, the molecular logic system can provide a simple, rapid, and smart method for intelligent monitoring of the available Pb and Cd in environmental samples.

A kick monitoring method for deepwater open-circuit drilling based on convolutional neural network

In the case of shallow drilling in deepwater without installation of riser and subsea BOP, open-circuit drilling is usually used. In the process of open-circuit drilling, drilling fluid is directly returned to the seabed. Therefore, observing the return of seabed drilling fluid through Remotely Operated Vehicle (ROV) has become one of the main methods for monitoring the kick in open-circuit drilling. However, the current ROV monitoring method only relies on the professional technical personnel to observe the video screen, which is difficult to identify the kick quickly and accurately in the early stage. In view of this problem, an intelligent kick monitoring method based on deep learning image recognition technology is proposed in this paper. By collecting the actual video image data shot by ROV and simulating the drilling fluid return morphology under different gas influx using Ansys Fluent software, a typical sample database is constructed. Then, the pretrained GoogLeNet neural network model is used for transfer learning, and the video images shot by ROV on site are used to test the trained model. The results show that this method can identify the kick more quickly and accurately, and the model has good robustness. Using this method can greatly reduce the economic losses in the process of deepwater open-circuit drilling, and provides technical support for safe and efficient drilling of deepwater open-circuit drilling.

基于AI视觉技术的水面蒸发量智能监测方法与设备应用研究

基于AI视觉技术的水面蒸发量智能监测方法与设备应用研究

Intelligent monitoring method for agricultural nonpoint source pollution based on remote sensing image changes

Intelligent monitoring method for agricultural nonpoint source pollution based on remote sensing image changes

Remote intelligent monitoring method of automobile driving safety based on Internet of Things technology

Remote intelligent monitoring method of automobile driving safety based on Internet of Things technology

Analysis of common diseases, monitoring, and maintenance of cable-stayed bridges

The tide of bridge building has passed. Nowadays, the monitoring and maintenance of bridges is very important for their safety, durability, and applicability, and it is the focus of the worlds attention and research. This paper analyzes the common diseases and maintenance strategies of common cable-stayed bridges and cable-stayed bridges in coastal areas. This paper includes system composition, sensor layout, sensor types, monitoring objects, structural health status evaluation, and daily maintenance, as well as Sutong Bridge, Changmen Grand Bridge, and Ganjiang Grand Bridge of Changgan Passenger Transport in Ganzhou and other concrete examples. The modules and functions of structural health status assessment and the application of the bridge health monitoring system, such as early warning and assessment in the daily monitoring of cable-stayed bridges, are introduced. And Changmen Grand Bridge, Ganjiang Grand Bridge of Changgan Passenger Transport in Ganzhou, and Sutong Bridge are compared and analyzed according to the arrangement of measuring points, monitoring objects, and corresponding sensors. Finally, this paper briefly discusses the basic methods of preventive maintenance, BIM, and other related intelligent monitoring methods.

The intelligent monitoring method of main distribution microgrid operation panorama considering the high percentage of new energy sources

In the context of new power system construction, the proportion of new energy generation connected to the power system is increasing year by year. However, due to the strong randomness and volatility of new energy generation, a large number of accesses may threaten the safety of power system operations. Therefore, it is one of the important aspects in the construction of new power systems to improve the grid operation monitoring technology. This paper proposes a panoramic intelligent monitoring method for the operation of the main distribution microgrid considering the high percentage of new energy sources, in order to protect the safe operation of the new power system.

Novel Ramanujan Digital Twin for Motor Periodic Fault Monitoring and Detection

The signal-processing and intelligent diagnostic and monitoring methods based on motor current signature analysis (MCSA) for induction motors (IM) usually depend on preset parameters. Moreover, many of them have difficulty in achieving ideal health monitoring effect with strong noise interference and switching working conditions. To overcome these limitations, a novel digital twin architecture called the Ramanujan digital twin (RDT) is composed. This architecture uses the Ramanujan periodic transform (RPT) as its computational core to detect the potential fault signatures in each monitoring frame. The quantity of interest from IM will be selected and calibrated based on the Bayesian-updated driven calibration mechanism to construct the phenomenal simulation signals with high fidelity to the potential fault signatures. These signals will provide guidance information. The effectiveness and robustness of the RDT are validated through experimental cases.

Dynamic Monitoring of Low-Yielding Gas Wells by Combining Ultrasonic Sensor and HGWO-SVR Algorithm

As gas wells enter the middle and late stages of production, they will become low-yielding gas wells due to fluid loading and insufficient formation pressure. For many years, there has been a lack of effective dynamic monitoring methods for low-yielding gas wells, and it is difficult to determine the production of each phase in each production layer, which makes further development face great uncertainty and a lack of basis for measurement adjustment. In order to solve this problem, this paper proposes an intelligent dynamic monitoring method suitable for low-yielding gas wells, which uses an ultrasonic Doppler logging instrument and machine learning algorithm as the core to obtain the output contribution of each production layer of the gas well. The intelligent dynamic monitoring method is based on the HGWO-SVR algorithm to predict the flow of each phase. The experimental data are selected for empirical analysis, and the effectiveness and accuracy of the method are verified. The research shows that this method has good application prospects and can provide strong technical support for gas reservoir production stability and development adjustment.

Identification of cladding layer offset using infrared temperature measurement and deep learning for WAAM

In the wire arc additive manufacturing (WAAM) procedure, the stability of the cladding layer’s formation directly impacts the final dimensional precision of the WAAM weldment. To achieve high-precision forming of the WAAM weldment, online monitoring of the cladding layer offset is essential. This article explores the monitoring technology for the cladding layer offset in the WAAM process and introduces a cladding layer offset monitoring technique using infrared temperature measurement and deep learning. First, a temperature field measurement system for the WAAM weldment is set up using an infrared thermal imager. Next, a region of interest (ROI) is selected on the weldment sidewall. The optimised histogram of oriented gradient (HOG) algorithm is then employed to extract the temperature distribution characteristics of the ROI. The separability of the temperature field on the weldment sidewall is analysed under various offset degrees of the cladding layer. Finally, using the temperature image of the ROI as input, a cladding layer offset recognition model is developed using a convolutional neural network (CNN). This study also evaluates the effect of the selected ROI position on the recognition precision of the model for the cladding layer offset. Experimental results indicate that the recognition accuracy of the model for cladding layer offset, as presented in this article, exceeds 99%. Moreover, the model demonstrates strong robustness, further enriching the intelligent monitoring methods for the WAAM process.

Dual-mode sensor for intelligent solution monitoring: Enhancing sensitivity and recognition accuracy through capacitive and triboelectric sensing

Monitoring solution parameters is of utmost importance in various industries and daily applications. However, the challenge lies in using a single sensor to effectively monitor different parameters in the solution. In this study, a dual-mode sensor is proposed, capable of monitoring multiple solution parameters combined with deep learning method. The fabrication process of the dual-mode sensor is simple, involving a substrate, interdigital electrodes, and a dielectric layer. The sensitivity of the dual-mode sensor is improved by increasing the dielectric constant of the dielectric layer and optimizing the design of the interdigital electrodes. Under the capacitive sensing mode, the sensor effectively identifies solution type by detecting capacitance changes due to the conductivity of the mixed solution. Under the triboelectric sensing mode, the sensor exhibits high sensitivity to solution concentration through the coupling of the capacitive enhancement effect and the triboelectric effect. An electric switch is incorporated into the design to control the signal acquisition of the dual-mode sensor. By combining the deep learning method with the dual-mode sensor, high recognition accuracies have been achieved for both solution type and concentration, with average accuracies exceeding 95%. Furthermore, the dual-mode sensor is not limited to monitoring liquid droplets; it can also be used for monitoring the types of liquids in bottles. In addition, an intelligent system is developed to visualize the intelligent monitoring process. This work not only contributes to a better understanding of the underlying mechanisms of planar capacitive sensors (PCS) and free-standing triboelectric nanogenerators (FS-TENG), but also presents a promising method for intelligent solution monitoring.

Research on artificial intelligence-based computer-assisted anesthesia intelligent monitoring and diagnostic methods in health care

Research on artificial intelligence-based computer-assisted anesthesia intelligent monitoring and diagnostic methods in health care

Intelligent Construction Monitoring Method for Large and Complex Steel Structures Based on Laser Point Cloud

Large and complex steel structures play a vital role in building construction. However, deviations between the design model and the actual construction state are inevitable, which seriously affects the quality and safety of building construction. In our study, an intelligent construction monitoring method for large and complex steel structures based on laser point cloud is proposed. Firstly, three-dimensional laser scanning technology is introduced to capture accurate and complete spatial information on steel structures. Then, considering the inconsistency of the coordinate system between the design model and the laser point cloud, the building information model (BIM) is converted into the point cloud model, and the datum unification of the two types of the point cloud is achieved by adopting a coarse-to-fine registration strategy. Finally, the spatial information of steel structures is extracted from the laser point cloud based on the as-designed model, and the distance deviation between the two models is analyzed to reflect the actual construction state. To demonstrate the applicability of the proposed method, the steel structures’ point cloud of the stadium and the high-speed railway station is captured by the terrestrial three-dimensional laser scanner. The experimental results demonstrate that the method can extract the deviation between the design model and the actual construction, to provide accurate data sources for the intelligent fine construction of steel structures.