Mode Output Research Articles

Gearbox Fault Diagnosis Based on MSCNN-LSTM-CBAM-SE.

Ensuring the safety of mechanical equipment, gearbox fault diagnosis is crucial for the stable operation of the whole system. However, existing diagnostic methods still have limitations, such as the analysis of single-scale features and insufficient recognition of global temporal dependencies. To address these issues, this article proposes a new method for gearbox fault diagnosis based on MSCNN-LSTM-CBAM-SE. The output of the CBAM-SE module is deeply integrated with the multi-scale features from MSCNN and the temporal features from LSTM, constructing a comprehensive feature representation that provides richer and more precise information for fault diagnosis. The effectiveness of this method has been validated with two sets of gearbox datasets and through ablation studies on this model. Experimental results show that the proposed model achieves excellent performance in terms of accuracy and F1 score, among other metrics. Finally, a comparison with other relevant fault diagnosis methods further verifies the advantages of the proposed model. This research offers a new solution for accurate fault diagnosis of gearboxes.

Low-light image enhancement based on cell vibration energy model and lightness difference

Low-light image enhancement algorithms play a crucial role in revealing details obscured by darkness in images and substantially improving overall image quality. However, existing methods often suffer from issues like color or lightness distortion and possess limited scalability. In response to these challenges, we introduce a novel low-light image enhancement algorithm leveraging a cell vibration energy model and lightness difference. Initially, a new low-light image enhancement framework is proposed, building upon a comprehensive understanding and analysis of the cell vibration energy model and its statistical properties. Subsequently, to achieve pixel-level multi-lightness difference adjustment and exert control over the lightness level of each pixel independently, a lightness difference adjustment strategy is introduced utilizing Weibull distribution and linear mapping. Furthermore, to expand the adaptive range of the algorithm, we consider the disparities between HSV space and RGB space. Two enhanced image output modes are designed, accompanied by a thorough analysis and deduction of the relevant image layer mapping formulas. Finally, to enhance the reliability of experimental results, certain image faults in the SICE database are rectified using the feature matching method. Experimental results showcase the superiority of the proposed algorithm over twelve state-of-the-art algorithms. The resource code of this article will be released at https://github.com/leixiaozhou/CDEGmethod.

Analysis of dust deposition law at the micro level and its impact on the annual performance of photovoltaic modules

Solar photovoltaic (PV) power generation is a promising clean energy technology, but dust affects its performance. This study, conducted in nine Chinese cities with varying climates and geographies, analyzed the physicochemical properties of dust and its deposition patterns at different inclination angles using microanalysis. Inclination angles were classified into three categories, and a dust density prediction (DDP) model was developed for each. The study also quantified the effect of different dust densities on PV module temperature in a controlled environment and created a PV module output power prediction (POPP) model to assess dust accumulation impacts on PV efficiency. It was found that dust insulation could increase PV module output power by 1.64 %–1.79 % at dust densities of 5–10 g/m2 and radiation levels of 400–800 W/m2. Combining the DDP and POPP models, a PV efficiency loss rate model was proposed to evaluate annual average PV efficiency and power generation losses at different tilting angles. Results showed an annual average PV efficiency loss of over 7 % at a 15° inclination angle and about 4.5 % at a 90° inclination angle. This study provides a framework for evaluating PV module mounting angles and cleaning intervals, optimizing solar energy systems for improved efficiency and returns.

Deep Learning–Assisted Parameter Monitoring and Optimization in Rotary-Percussive Drilling

Summary As an efficient method for hard rock fracturing, rotary-percussive drilling has been widely used in various scenarios, especially deep drilling. Drilling parameter monitoring and control are necessary to ensure stable and efficient underground drilling processes. However, this may be more difficult in deep, harsh conditions. In this paper, our goal is to establish models based on deep learning for drilling parameter monitoring and optimization. Combining impregnated diamond bits and granite rock samples, we conducted rotary-percussive rock drilling experiments using a rock drilling test rig. Real-time acoustic signals during rotary-percussive drilling were recorded, segmented, and transformed as spectra, which made up a drilling acoustic signal data set. Drilling parameters, including rotational speed (revolutions per minute, RPM), pump flow rate, pump pressure, weight on bit (WOB), torque, and rate of penetration (ROP), were logged in the meantime. Given the acoustic signal as input, we built 1D convolutional neural network (1D-CNN) models for drilling parameter prediction. The prediction results revealed the high efficiency and accuracy of 1D-CNN regression models based on deep learning in drilling condition monitoring. Batch normalization played an essential role in the regression model training processes. Given that these parameters have different units and dimensions, we compared models with different output modes to evaluate the multiparameter prediction performance of the 1D-CNN. Taking RPM, flow rate, pressure, and WOB as independent variables and torque and ROP as dependent variables, we developed a conditional variational autoencoder to realize optimization on drilling parameters based on expected drilling performance.

Prototype as query for few shot semantic segmentation

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and support targets, e.g., texture or appearance. This greatly challenges the generalization ability of methods for FSS, which requires to effectively exploit the dependency of the query image and the support examples. Most existing methods abstracted support features into prototype vectors and implemented the interaction with query features using cosine similarity or feature concatenation. However, this simple interaction may not capture spatial details in query features. To address this limitation, some methods utilized pixel-level support information by computing pixel-level correlations between paired query and support features implemented with the attention mechanism of Transformer. Nevertheless, these approaches suffer from heavy computation due to dot-product attention between all pixels of support and query features. In this paper, we propose a novel framework, termed ProtoFormer, built upon the Transformer architecture, to fully capture spatial details in query features. ProtoFormer treats the abstracted prototype of the target class in support features as the Query and the query features as Key and Value embeddings, which are input to the Transformer decoder. This approach enables better capture of spatial details and focuses on the semantic features of the target class in the query image. The output of the Transformer-based module can be interpreted as semantic-aware dynamic kernels that filter the segmentation mask from the enriched query features. Extensive experiments conducted on PASCAL-5i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$5^{i}$$\\end{document} and COCO-20i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$20^{i}$$\\end{document} datasets demonstrate that ProtoFormer significantly outperforms the state-of-the-art methods in FSS.

A portability self-powered sensor facilitates sensitive Cd2+ detection: Dual mechanism and three quantitative mode

As a common heavy metal contaminant, Cd2+ has adverse effects on food safety and consumer health. It is very important for human health to realize highly sensitive Cd2+ detection methods. The self-powered sensing system based on enzyme biofuel cells (EBFCs) does not need an external power supply, which can simplify the experimental equipment and has great application value in portable detection. Thus, the biosensor is innovatively integrated into the screen-printed electrode to construct a new type of portable sensor suitable for on-site and real-time Cd2+ detection. Hybridization chain reaction (HCR) combined with the Cd2+-dependent deoxyribose (DNAzyme) signal amplification strategy is used to enhance the detection sensitivity while specifically recognizing the Cd2+. Moreover, the self-powered sensor combines with smartphones to realize quantitative Cd2+ detection without other instruments and has the characteristic of Effectively improving the hazard detection technology is essential to ensure food safety. Portability, simplicity, and speed are suitable for real-time Cd2+ detection in the field. The dual mechanism and three quantitative modes combining colorimetric and two electrical signals output modes are adopted to realize the visualization and accurate detection. A series of research results confirm that this strategy is of great significance to strengthen the development of intelligent Cd2+ technology, expand the application of self-powered sensing technology, and improve the safety detection system.

FlexLogNet: A flexible deep learning-based well-log completion method of adaptively using what you have to predict what you are missing

Well logs are essential tools for understanding the characteristics of subsurface formations and exploring petroleum resources. However, well logs are often missing randomly due to cost constraints, instrument failures, or other factors. Many methods have been developed for completing missing well logs, but these methods are all based on fixed types of known well-log inputs to predict specific types of missing logs. This fixed input–output mode severely limits the application of these methods in actual data, where the known and missing well-log types are often varying. To address this problem, we propose a hybrid deep learning method with two heads of heterogeneous graph neural network (HGNN) and fully connected network (FCN) to achieve mutual prediction among multiple types of well logs. It can adaptively use all known well logs to predict any missing well logs, achieving a very flexible and practical well log completion function of using what you have to complete what you are missing. Specifically, the HGNN head infers the inter-relationships among multiple well logs to predict normalized logs that contain detailed information, which achieved by using multiple independent kernels to extracting and aggregating the features of the multiple logs. The FCN head estimates the global statistics of the predicted logs, including means and standard deviations, for de-normalizing the well logs estimated by the HGNN head. Both the HGNN and FCN heads are trained simultaneously by a hybrid loss function to ensure the consistency of their predictions. Furthermore, we present an adaptive training strategy that leverages all well logs, including those with missing segments. We demonstrate the capability of our model using four well logs: gamma ray (GR), bulk density (RHOB), neutron porosity (NPHI), and compressional waves sonic (DTC). Theoretically, the model trained on other logs can also predict each other. Our approach yields high Pearson correlation coefficients and small root mean square error on a dataset obtained from an offshore North Sea field near Norway, demonstrating the efficacy of our proposed technique.

Broad, Tunable and Stable Single-Frequency Erbium Fiber Compound-Ring Lasers Based on Parallel and Series Structures in L-Band Operation

In this demonstration, we present two erbium-doped fiber (EDF) lasers, with series and parallel three sub-ring configurations, respectively, to achieve tunable channel output and stable single longitudinal mode (SLM) operation in the L-band range. Here, the fiber ring cavity contains the L-band EDF as a gain medium. Based on the measured results of the two quad-ring structures of the EDF lasers, tunable output bandwidth for the two lasers can be obtained from 1558.0 to 1618.0 nm simultaneously. All the 3 dB linewidths measured for both fiber lasers are 312.5 Hz over the effective wavelength output range. Furthermore, the related optical signal-to-noise ratio (OSNR), output power, output stabilities of the central wavelength and power, and equal output power range of the two proposed EDF lasers are also examined and discussed.

An FPGA-Based signal acquisition system for 3D holographic azimuthal electromagnetic resistivity logging instruments

Abstract A signal acquisition system of a 3D holographic azimuthal electromagnetic resistivity logging instrument while drilling is designed based on the Field Programmable Gate Array (FPGA). The azimuth electromagnetic wave resistivity logging instrument is mainly composed of transmitting coils, receiving coils, and control circuits. The signal acquisition system mainly includes the receiving coil and corresponding signal acquisition and processing circuit. First of all, the whole structure of the electromagnetic wave resistivity instrument system while drilling is briefly introduced, and then each function module of the acquisition board is elaborated in detail, and the hardware realization of the signal acquisition module and the corresponding FPGA program design flow chart are given. The acquisition system makes full use of the structured design of the module and First input First output (FIFO) cache technology and can complete the functions of signal acquisition, data transmission, and control on the acquisition board in real-time by using Serial Communication Interface (SCI) information transmission interface. The simulation results show that the system can realize the function of data acquisition and processing well.

A Novel Modulation Method to Decouple Output Power and Suppress Current Zero-Crossing Distortion for Vienna Rectifiers in Bipolar Output Mode

A Novel Modulation Method to Decouple Output Power and Suppress Current Zero-Crossing Distortion for Vienna Rectifiers in Bipolar Output Mode

Realization of modularized corrector magnet power supply with N+1 redundancy for TPS facilities

This paper delves into implementing multi-module parallel current output using the existing TPS storage ring correction magnet power supply. We have devised a control interface card with N+1 redundancy to facilitate bipolar high-current parallel module output. To achieve this, we have employed various current feedback methods, including external DC Current Transducer (DCCT) and internal module current feedback signals. Following PI compensation, these feedback signals are amalgamated with reference current signals to compute compensation values for each module, which are subsequently disseminated to each Corrector Magnet Power Supply (CMPS) for modulation, thereby enabling closed-loop current control. A single CMPS module can deliver ± 48 V/± 10 A output, while up to eight CMPS modules can be interconnected, yielding a maximum output of ± 80 A. Through numerous experimental measurements, the long-term output current stability remains within 0.6 mA, or 7.5 ppm, with the output current spectrum predominantly maintained within 500 μA. Furthermore, the system boasts N+1 redundancy functionality and bipolar output current characteristics. These exemplary performance attributes underscore the criticality of our design for future applications of TPS magnet power supplies.

The Basal Ganglia Downstream Control of Action - An Evolutionarily Conserved Strategy.

The motor areas of the cortex and the basal ganglia both contribute to determining which motor actions will be recruited at any moment in time, and their functions are intertwined. Here, we review the basal ganglia mechanisms underlying the selection of behavior of the downstream control of motor centers in the midbrain and brainstem and show that the basic organization of the forebrain motor system is evolutionarily conserved throughout vertebrate phylogeny. The output level of the basal ganglia (e.g. substantia nigra pars reticulata) has GABAergic neurons that are spontaneously active at rest and inhibit a number of specific motor centers, each of which can be relieved from inhibition if the inhibitory output neurons themselves become inhibited. The motor areas of the cortex act partially via the dorsolateral striatum (putamen), which has specific modules for the forelimb, hindlimb, trunk, etc. Each module operates in turn through the two types of striatal projection neurons that control the output modules of the basal ganglia and thereby the downstream motor centers. The mechanisms for lateral inhibition in the striatum are reviewed as well as other striatal mechanisms contributing to action selection. The motor cortex also exerts a direct excitatory action on specific motor centers. An overview is given of the basal ganglia control exerted on the different midbrain/brainstem motor centers, and the efference copy information fed back via the thalamus to the striatum and cortex, which is of importance for the planning of future movements.

Dual-driven AND molecular logic gates for label-free and sensitive ratiometric fluorescence sensing and inhibitors screening

Due to the complexity of regulatory networks of disease-related biomarkers, developing simple, sensitive, and accurate methods has remained challenging for precise diagnosis. Herein, an “AND” logic gates DNA molecular machine (LGDM) was constructed, which was powered by the catalytic hairpin assembly (CHA). It was coupled with dual-emission CdTe quantum dots (QDs)-based cation exchange reaction (CER) for label-free, sensitive, and ratiometric fluorescence detection of APE1 and miRNA biomarkers. Benefiting from synergistic signal amplification strategies and a ratiometric fluorometric output mode, this LGDM enables accurate logic computing with robust and significant output signals from weak inputs. It offers improved sensitivity and selectivity even in cell extracts. Using dual-emission spectra CdTe QDs, with a ratiometric signal output mode, ensured good stability and effectively prevented false-positive signals from intrinsic biological interferences compared to the approach relying on a single signal output mode, which enabled the LGDM to achieve rapid, efficient, and accurate natural drug screening against APE1 inhibitors in vitro and cells. The developed method provides impetus to streamline research related to miRNA and APE1, offering significant promise for widespread application in drug development and clinical analysis.

MPPT Charge Controller using Fuzzy Logic for Battery Integrated with Solar Photovoltaic System

In comparison to other Renewable Energy (RE) resources, solar energy has become the most prominent and prospective source for generating electricity, substituting conventional sources. However, solar Photovoltaic (PV) energy production is dependent on solar irradiance and cell temperature. By implementing the Maximum Power Point Tracking (MPPT) algorithm, it is achievable to maximize the power from solar PV. In spite of this, there is still a slower convergence rate, a significant fluctuation around Maximum Power Point (MPP), and a drift issue caused by rapid irradiance variations in solar PV. In order to prevent oscillation and attain a steady state and continuous output of the PV module, a Fuzzy Logic (FL)-based MPPT has been designed in this work. With the buck converter as the DC-DC converter and the lead acid battery as the input, the Perturb & Observe (P&O) MPPT method is selected. The overall design will be developed using Matlab Simulink, and the efficiency of the FL-MPPT charge controller will be evaluated under constant and step irradiance. Additionally, the battery's State of Charge (SOC) will be monitored to prevent overcharging and discharge. In addition, the effectiveness of the controller will be evaluated with and without the MPPT method. On the basis of simulation results obtained from constant and step irradiance levels, the FL-MPPT charge controller with the P&O algorithm and the lead acid battery as the load was able to maintain maximum system efficiency while extending battery life. The FL-MPPT charge controller obtained about 96% efficiency for both irradiance profiles, whereas the system without the FL-MPPT algorithm only achieved 42% efficiency.

A Radiation-Pattern Reconfigurable Antenna Array for Vehicular Communications.

This paper presents a low-profile reconfigurable antenna array capable of five radiation-pattern modes for vehicular communication applications. The antenna array consists of four antenna elements, each containing four square patches. Exciting one of the square patches generates a broadside radiation. A square parasitic patch is added at the rear of the excited patch, and two square parasitic patches are placed at the front. By optimizing the design of these parasitic patches, including the treatment of center slotting and addition of shorting pins, the antenna element achieves an end-fire beam with a certain tilt angle. On this basis, a reconfigurable feeding network is designed with 1:1 and 1:4 output modes. By connecting the reconfigurable feeding network to the four antenna elements and altering the on/off states of the PIN diodes in the feeding network, a reconfigurable antenna with four end-fire beams and one omnidirectional beam in its radiation pattern is realized. Measurement results demonstrate an excellent impedance bandwidth, radiation pattern, and gain performance in all modes. The four end-fire and one omnidirectional radiation characteristics make it highly suitable for vehicular communication applications.

Flexible, Wearable Wireless-Charging Power System Incorporating Piezo-Ultrasonic Arrays and MXene-Based Solid-State Supercapacitors.

With the continuous development of wearable electronics, higher requirements are put forward for flexible, detachable, stable output, and long service life power modules. Given the limited capacity of energy storage devices, the integration of energy capture and storage is a viable approach. Here, we present a flexible, wearable, wireless-charging power system that integrates a piezoelectric ultrasonic array harvester (PUAH) with MXene-based solid-state supercapacitors (MSSSs) in a soft wristband format for sustainable applications. The MSSS as the energy storage module is developed by using Ti3C2Tx nanosheet-loaded inserted finger-like carbon cloth skeletons as electrodes and poly(vinyl alcohol)/H3PO4 gel as electrolytes, with high energy density (58.74 Wh kg-1) and long cycle life (99.37%, 10,000 cycles). A two-dimensional stretchable piezoelectric array as a wireless-charging module hybridizes high-performance 1-3 composite units with serpentine electrodes, which allows wireless power via ultrasonic waves, with a maximum power density of 1.56 W cm-2 and an output voltage of 20.75 V. The overall PUAH-MSSS wireless energy supply system is 2 mm thick and offers excellent energy conversion/storage performance, cyclic stability, and mechanical flexibility. The results of this project will lay the foundation for the development of next-generation wearable electronics.

Simulation on water photovoltaic heat exchange mechanism and influence on water quality, a case on the middle route of South-to-North Water Diversion project

Water photovoltaic (WPV) power stations have developed rapidly in recent years around the world. However, the thermal performance, power generation characteristics and the influence on water temperature and water quality of WPV power station need to be further studied. At present, there is no systematic and complete numerical method that can simulate the impact of solar panel on water environment. In this paper, a joint calculation method of WPV heat exchange model and 1-D hydrodynamic and water quality model is proposed. Taking Hebei section of the middle route of the South-to-North Water Diversion project as an example, the solar panel temperature, electrical efficiency, water temperature and water quality changes are analyzed. The results show that, compared with the static water condition, the solar panel temperature and air temperature below the panel decrease under flowing water condition. And the photoelectric efficiency is improved. After covering the WPV, the air temperature below the panel is significantly affected by the solar panel temperature. When moving from south to north along the middle route of the South-to-North Water Diversion project, the photoelectric conversion efficiency of WPV gradually increases, but module output power per square meter drops by 1.75 W/m2. The short-wave radiation flux reduction factor of WPV should be less than 20 % for ensuring the stability of water quality and the large discharge will weaken the short-wave radiation flux reduction influences on water quality.

Adaptive Signal Modulation Evolved by the Inherent Nonlinearity of Phase-Change Quantum-Dot String.

To simulate a topological neural network handling weak signals via stochastic resonance (SR), it is necessary to introduce an inherent nonlinearity into nanoscale devices. We use the self-assembly method to successfully fabricate a phase-change quantum-dot string (PCQDS) crossing Pd/Nb:AlNO/AlNO/Nb:AlNO/Pd multilayer. The inherent nonlinearity of phase change couples with electron tunneling so that PCQDS responds to a long signal sequence in a modulated output style, in which the pulse pattern evolves to that enveloped by two sets of periodic wave characterized by neural action potential. We establish an SR mode consisting of several two-state systems in which dissipative tunneling is coupled to environment. Size oscillations owing to NbO QDs adaptively adjust barriers and wells, such that tunneling can be periodically modulated by either asymmetric energy or local temperature. When the external periodic signals are applied, the system first follows the forcing frequency. Subsequently, certain PCQDs oscillate independently and consecutively to produce complicated frequency and amplitude modulations.

Subwavelength and broadband on-chip mode splitting with shifted junctions

We design and fabricate a sub-wavelength on-chip mode splitter based on the implementation of a shifted junction between a single-mode waveguide and a multimode waveguide. A proper choice of the device parameters enables to split the input beam into a combination of different guided modes of the multimode waveguide, minimizing radiation and reflection losses that amount to ∼ 0.4 dB in our experiments. Because the splitting mechanism does not rely on phase-matching, we achieve broadband operation that could exceed 200 nm bandwidth (<0.5 dB splitting variation). This approach ensures temporal and phase synchronization among the output modes, with applications spanning from the emergent multimode photonics platform to traditional single-mode photonics operations.

Long-Term Solar Power Generation Forecasting at Eastern West Large Scale Solar (LSS) Farm using Random Forest Regression (RFR) Method

Precise forecasting of power generation and demand is essential for effective resource allocation and energy trading in contemporary energy systems. Power forecasting accuracy has increased dramatically since Random Forest Regression (RFR) techniques were used. The study's primary objective is to forecast electricity generation in Malaysia's Eastern West region, with a concentration on solar energy. The research process entails gathering and examining pertinent factors, weather information, and historical power data. To evaluate the accuracy and predictive potential of RFR models, a specific power grid is used for training, validation, and testing. One of the anticipated results is the creation of an accurate model for power generation predictions, which will help to optimise energy operations and smoothly incorporate renewable sources. The paper examines the advantages, disadvantages, and best practices related to RFR-based power forecasting. The dataset, which spans the years 2019 to 2023, includes 30-minute interval records for the following variables: average output power, ambient temperature, PV module temperature, global horizontal irradiance, and wind speed. Using the RandomForestRegressor class from the scikit-learn library, the RFR model is implemented. In order to assess the model's overall fit, average deviation, and sensitivity to outliers, measures such as root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) are used on the test set. The temperature, irradiance, and AC power output of PV modules are found to be strongly correlated.