Driving Force Analysis of Natural Wetland in Northeast Plain Based on SSA-XGBoost Model.

Globally, natural wetlands have suffered severe ecological degradation (vegetation, soil, and biotic community) due to multiple factors. Understanding the spatiotemporal dynamics and driving forces of natural wetlands is the key to natural wetlands' protection and regional restoration. In this study, we first investigated the spatiotemporal evolutionary trends and shifting characteristics of natural wetlands in the Northeast Plain of China from 1990 to 2020. A dataset of driving-force evaluation indicators was constructed with nine indirect (elevation, temperature, road network, etc.) and four direct influencing factors (dryland, paddy field, woodland, grassland). Finally, we built the driving force analysis model of natural wetlands changes to quantitatively refine the contribution of different driving factors for natural wetlands' dynamic change by introducing the sparrow search algorithm (SSA) and extreme gradient boosting algorithm (XGBoost). The results showed that the total area of natural wetlands in the Northeast Plain of China increased by 32% from 1990 to 2020, mainly showing a first decline and then an increasing trend. Combined with the results of transfer intensity, we found that the substantial turn-out phenomenon of natural wetlands occurred in 2000-2005 and was mainly concentrated in the central and eastern parts of the Northeast Plain, while the substantial turn-in phenomenon of 2005-2010 was mainly located in the northeast of the study area. Compared with a traditional regression model, the SSA-XGBoost model not only weakened the multicollinearity of each driver but also significantly improved the generalization ability and interpretability of the model. The coefficient of determination (R2) of the SSA-XGBoost model exceeded 0.6 in both the natural wetland decline and rise cycles, which could effectively quantify the contribution of each driving factor. From the results of the model calculations, agricultural activities consisting of dryland and paddy fields during the entire cycle of natural wetland change were the main driving factors, with relative contributions of 18.59% and 15.40%, respectively. Both meteorological (temperature, precipitation) and topographic factors (elevation, slope) had a driving role in the spatiotemporal variation of natural wetlands. The gross domestic product (GDP) had the lowest contribution to natural wetlands' variation. This study provides a new method of quantitative analysis based on machine learning theory for determining the causes of natural wetland changes; it can be applied to large spatial scale areas, which is essential for a rapid monitoring of natural wetlands' resources and an accurate decision-making on the ecological environment's security.

Dynamic Condition Adversarial Adaptation for Fault Diagnosis of Wind Turbine Gearbox.

While deep learning has found widespread utility in gearbox fault diagnosis, its direct application to wind turbine gearboxes encounters significant hurdles. Disparities in data distribution across a spectrum of operating conditions for wind turbines result in a marked decrease in diagnostic accuracy. In response, this study introduces a tailored dynamic conditional adversarial domain adaptation model for fault diagnosis in wind turbine gearboxes amidst cross-condition scenarios. The model adeptly adjusts the importance of aligning marginal and conditional distributions using distance metric factors. Information entropy parameters are also incorporated to assess individual sample transferability, prioritizing highly transferable samples during domain alignment. The amalgamation of these dynamic factors empowers the approach to maintain stability across varied data distributions. Comprehensive experiments on both gear and bearing data validate the method's efficacy in cross-condition fault diagnosis. Comparative outcomes demonstrate that, when contrasted with four advanced transfer learning techniques, the dynamic conditional adversarial domain adaptation model attains superior accuracy and stability in multi-transfer tasks, making it notably suitable for diagnosing wind turbine gearbox faults.

Investigation of the Effect of Debris Position on the Detection Stability of a Magnetic Plug Sensor Based on Alternating Current Bridge.

Magnetic plug-type abrasive particle sensors have a wide range of applications in oil detection, but there is little literature on the effect of abrasive particle position on detection accuracy. In this paper, an alternating current (AC) bridge-type abrasive particle detection sensor is designed, in which the sensing module utilizes permanent magnets to attract iron particles, and the induction coil is specially designed to detect the magnetic field fluctuation caused by iron particles. A corresponding model was also designed to evaluate the sensor's sensitivity at different locations. In this paper, the magnetic field distribution of the sensor was first analyzed using finite element analysis software to obtain the magnetic field strength at different positions. Then, the response sensitivity of the sensor to particles and the effect of different positions on the detection results are explored through experiments. The simulation and the experimental results show substantial signal difference signal at different sensor positions. The method outlined in this article can determine the optimal sensing range for subsequent magnetic plug-type abrasive particle detection sensors and subsequently improve their reliability.

Analysis of the Effect of Velocity on the Eddy Current Effect of Metal Particles of Different Materials in Inductive Bridges.

A method for analyzing the influence of velocity changes on metal signals of different materials in oil detection technology is proposed. The flow rate of metal contaminants in the oil will have a certain impact on the sensitivity of the output particle signal in terms of electromagnetic fields and circuits. The detection velocity is not only related to the sensitivity of the output particle signal, but also to the adaptability of high-speed and high-throughput in oil online monitoring. In this paper, based on a high-sensitivity inductive bridge, the eddy current effect of velocity in a time-harmonic magnetic field is theoretically analyzed and experimentally verified, the phenomenon of particle signal variation with velocity for different materials is analyzed and discussed, and finally the effect of velocity on the output signal of the processing circuit is also elaborated and experimentally verified. Experiments show that under the influence of the time-harmonic magnetic field, the increase of the velocity enhances the detection sensitivity of non-ferromagnetic metal particles and weakens the detection sensitivity of non-ferromagnetic particles. Under the influence of the processing circuit, different velocities will produce different signal gains, which will affect the stability of the signal at different velocities.

Research on High Sensitivity Oil Debris Detection Sensor Using High Magnetic Permeability Material and Coil Mutual Inductance.

Metallic contaminants (solid) are generated by friction pair, causing wear of equipment by enters the lubricating system. This poses a great potential threat to the normal operation of such machines. The timely analysis and detection of debris can lead to the avoidance of mechanical failures. Abnormal wear in machinery may produce debris exceeding 10 µm. The traditional inductance detection method has low sensitivity and cannot meet the actual detection requirements. To boost the sensitivity of the inductance sensor, the mutual inductance of coils and the strong magnetic conductivity of permalloy was utilized to design a high sensitivity inductance sensor for the detection of debris in lubricating oil. This design was able to detect 10-15 µm iron particles and 65-70 µm copper particles in the oil. The experimental results illustrate that low-frequency excitation is the best for detecting ferromagnetic particles, while high-frequency excitation has the best effect for detecting non-ferromagnetic particles. This paper demonstrates the significant advantages of coil mutual inductance, and strong magnetic conductivity of permalloy in improving the detection sensitivity of oil debris sensors. This will provide technical support for wear detection in mechanical equipment and fault diagnosis.

Design and Research of Inductive Oil Pollutant Detection Sensor Based on High Gradient Magnetic Field Structure.

An inductive oil pollutant detection sensor based on a high-gradient magnetic field structure is designed in this paper, which is mainly used for online detection and fault analysis of pollutants in hydraulic and lubricating oil systems. The innovation of the sensor is based on the inductance detection method. Permalloy is embedded in the sensing region of the sensor, so that the detection area generates a high gradient magnetic field to enhance the detection accuracy of the sensor. Compared with traditional inductive sensors, the sensor has a significant improvement in detection accuracy, and the addition of permalloy greatly improves the stability of the sensor's detection unit structure. The article theoretically analyzes the working principle of the sensor, optimizes the design parameters and structure of the sensor through simulation, determines the best permalloy parameters, and establishes an experimental system for verification. Experimental results show that when a piece of permalloy is added to the sensing unit, the signal-to-noise ratio (SNR) of iron particles is increased by more than 20%, and the signal-to-noise ratio of copper particles is increased by more than 70%. When two pieces of permalloy are added, the signal-to-noise ratio for iron particles is increased by more than 70%, and the SNR for copper particles is increased several times. This method raises the lower limit of detection for ferromagnetic metal particles to 20 µm, and the lower limit for detection of non-ferromagnetic metal particles to 80 µm, which is the higher detection accuracy of the planar coil sensors. This paper provides a new and faster online method for pollutant detection in oil, which is of great significance for diagnosing and monitoring the health of oil in mechanical systems.

Inductive Magnetic Nanoparticle Sensor based on Microfluidic Chip Oil Detection Technology.

The wear debris in hydraulic oil or lubricating oil has a wealth of equipment operating information, which is an important basis for large mechanical equipment detection and fault diagnosis. Based on traditional inductive oil detection technology, magnetic nanoparticles are exploited in this paper. A new inductive oil detection sensor is designed based on the characteristics of magnetic nanoparticles. The sensor improves detection sensitivity based on distinguishing between ferromagnetic and non-ferromagnetic wear debris. Magnetic nanoparticles increase the internal magnetic field strength of the solenoid coil and the stability of the internal magnetic field of the solenoid coil. During the experiment, the optimal position of the sensor microchannel was first determined, then the effect of the magnetic nanoparticles on the sensor's detection was confirmed, and finally the concentration ratio of the mixture was determined. The experimental results show that the inductive oil detection sensor made of magnetic nanoparticle material had a higher detection effect, and the signal-to-noise ratio (SNR) of 20-70 µm ferromagnetic particles was increased by 20%-25%. The detection signal-to-noise ratio (SNR) of 80-130 µm non-ferromagnetic particles was increased by 16%-20%. The application of magnetic nanoparticles is a new method in the field of oil detection, which is of great significance for fault diagnosis and the life prediction of hydraulic systems.

Design and Parameter Research of Time-Harmonic Magnetic Field Sensor Based on PDMS in Microfluidic Technology.

In order to improve the throughput and sensitivity of the inductive metal micro-abrasive particle detection sensor, this paper uses microfluidic detection technology to design a high-throughput abrasive particle detection sensor based on PDMS (Polydimethylsiloxane). Theoretical modeling analyzes the magnetization of metal abrasive particles in the coil's time-harmonic magnetic field, and uses COMSOL simulation to calculate the best performance parameters of the sensor. Through the experiment of the control variable method, the corresponding signal value is obtained and the signal-to-noise ratio (SNR) is calculated. The SNR value and error value are calculated, and the SNR is corrected. The detection limit of the sensor is determined to be 10 µm iron particles and 60 µm copper particles. The optimal design parameters of the 3-D solenoid coil and the frequency characteristics of the sensor are obtained. Finally, through high-throughput experiments and analysis, it was found that there was a reasonable error between the actual throughput and the theoretical throughput. The design ideas suggested in this article can not only improve the sample throughput, but also ensure the detection accuracy. This provides a new idea for the development of an inductive on-line detection method of abrasive particle technology.