The scrap falling state in the shearing process of a Wide Heavy Plate Mill depends on manual monitoring and judgment. The steel plate can only move forward after the scrap falls, otherwise, the equipment will be damaged. An experienced operator can use the sound they hear to estimate the falling state. To automatically recognize sound events, a scheme of sound data acquisition processing and recognition for monitoring the scrap state of the shearing process is proposed in this paper. Firstly, a pickup is installed at the monitoring point of the crop shear to collect the sound. Afterward, the sound data is processed and finally fed into the model for recognition. Since many sound segments in the field are not related to key actions, an endpoint detection technique based on a short-term energy threshold and the variable window length strategy is applied in the data processing section to obtain the sound segments to be identified. The Log-Mel spectrogram feature of the sound segment is then extracted. After a data filling to ensure a uniform data shape, the feature map is fed into a lightweight deep convolution neural network called MobileNetV2 to quickly identify sound events. For the shearing process events, the model recognition accuracy can reach 95% of the F1 score in a realistic noise environment and we can identify the scrap falling 0.3s after the action starts. Finally, the model was applied to the UrbanSound8K dataset and achieved 95% recognition accuracy, validating the performance of the method. 

Sound-based Real-time Scrap Falling State Monitoring in the Shearing Process of Wide Heavy Plate Mill

The segmentation of abnormal regions is vital in smart manufacturing. The blurring sauce-packet leakage segmentation task (BSLST) is designed to distinguish the sauce packet and the leakage’s foreground and background at the pixel level. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby hindering the measurements of leakage area and impeding the automated sauce-packet production. To alleviate this issue, we propose the two-stage illumination-aware sauce-packet leakage segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose image enhancement to relieve the impact of uneven illumination, enhancing the texture details of the ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the multi-scale feature fusion module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by the MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by the adaptive weighting of spatial and channel dimensions. Furthermore, we generate a self-built dataset of sauce packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method.

ISLS: An Illumination-Aware Sauce-Packet Leakage Segmentation Method

The scrap falling state in the shearing process of a Wide Heavy Plate Mill depends on manual monitoring and judgment. The steel plate can only move forward after the scrap falls, otherwise, the equipment will be damaged. An experienced operator can use the sound they hear to estimate the falling state. To automatically recognize sound events, a scheme of sound data acquisition processing and recognition for monitoring the scrap state of the shearing process is proposed in this paper. Firstly, a pickup is installed at the monitoring point of the crop shear to collect the sound. Afterward, the sound data is processed and finally fed into the model for recognition. Since many sound segments in the field are not related to key actions, an endpoint detection technique based on a short-term energy threshold and the variable window length strategy is applied in the data processing section to obtain the sound segments to be identified. The Log-Mel spectrogram feature of the sound segment is then extracted. After a data filling to ensure a uniform data shape, the feature map is fed into a lightweight deep convolution neural network called MobileNetV2 to quickly identify sound events. For the shearing process events, the model recognition accuracy can reach 95% of the F1 score in a realistic noise environment and we can identify the scrap falling 0.3s after the action starts. Finally, the model was applied to the UrbanSound8K dataset and achieved 95% recognition accuracy, validating the performance of the method.

A Sound Event Recognition Method of Crop Shear Scrap Falling State Based on Log-Mel Spectrogram and MobileNetV2

Convolutional neural network (CNN) models are widely used for environmental sound classification (ESC). However, 2-D convolutions assume translation invariance along both time and frequency axes, while in practice the frequency dimension is not shift-invariant. Additionally, single-scale convolutions limit the receptive field, leading to incomplete feature representation. To address these issues, we introduce a parallel time-frequency multi-scale attention (PTFMSA) module that integrates local and global attention across multiple scales to improve dynamic convolution in order to overcome these problems. We also introduce the parallel branch structure to avoid mutual interference of information in case of extracting time and frequency domain features. Additionally, we utilize learnable parameters that can dynamically adjust the weights of different branches during network training. Building on this module, we develop PTFMSAN, a compact network that processes raw waveforms directly for ESC. To further strengthen learning, between-class (BC) training is applied. Experiments on the ESC-50 dataset show that PTFMSAN outperforms the baseline model, achieving a classification accuracy of 90%, competitive among CNN-based networks. We also performed ablation experiments to verify the effectiveness of each module. 

Parallel Time-Frequency Multi-Scale Attention with Dynamic Convolution for Environmental Sound Classification

Water leakage detection is of great significance to reduce economic losses and safety hazards in industrial sites. Aiming at the problem of water leakage detection caused by weak light condition and uneven light on turbine layer, this paper proposes a water leakage detection method based on weak light compensation for MaskRCNN turbine layer equipment. Firstly, due to the poor light of the turbine layer, the boundary of the seepage area photographed by the inspection robot is not clear, and the segmentation method is difficult to determine the target boundary. In this paper, low light enhancement algorithm is used to process the image of water seepage area taken by inspection robot to strengthen the boundary of water seepage image. Then, software Labelme was used to label the water seepage area of the enhanced inspection image and generate the configuration file corresponding to the inspection image. Thirdly, MaskRCNN instance segmentation network is introduced to train the image of the seepage area, and the network model of the detection task of the seepage area is generated. Finally, the test image is used to detect the water seepage area. After weak light enhancement, the trained MaskRCNN model is imported to obtain the detection result of the water seepage area. The experimental results show that the proposed method is effective and accurate, and it has a good application effect in detecting water dripping and leakage of turbine floor equipment by the wheel inspection machine in Qingyuan Energy Storage Power Generation Station.

Water leakage detection and its application of turbine floor equipment based on MaskRCNN

Based on the analysis of the research status and application of the underwater vehicle system at home and abroad, the simulation analysis of the proposed underwater vehicle model was carried out with the help of CFD fluid dynamics simulation software. During this process, after careful consideration of the resistance in the case of long-distance operation, the model simulated the fluid resistance, viscous resistance and horizontal thrust in the movement of underwater vehicle in water. In this way, the layout and design indicators of the engine are optimized, which would provide reference for the subsequent optimization of the underwater vehicle power system.

Research on the Optimization of Underwater Vehicle Dynamic System

With the increase of the service life of long-distance tunnels, cracks and corrosion are likely to occur, which will affect the safety of underwater buildings. At the same time, the flowing water and muddy water in the tunnel environment also bring difficulties to the efficient detection of underwater vehicles. Therefore, this paper proposes a solution of a long cable ROV underwater vehicle. By using automatic hook and cable disengaging device, AUV automatic return system, image enhancement technology, automatic control propulsion system, the image characteristics of muddy water can be efficiently identified, effective proceeding under the circumstance of flowing water can be realized, the problem of getting rid of cable winding and return can be effectively solved, and underwater building anomalies can be accurately and efficiently detected in long-distance tunnels such as water diversion tunnels and water conservancy pipelines of hydropower plants.

Research of the underwater vehicle technology in long-distance tunnels

As the frontier construction direction of Smart Power Plants, “Unmanned Monitoring” requires monitoring system to autonomously identify abnormal states of production equipment. So as to further improve the intelligence level of the power plant sound monitoring system, this paper proposes an abnormal sound perception scheme for power plant production equipment based on machine hearing technology. Firstly, the sound defect records and inspection records of the production equipment are investigated and analyzed. Besides, a sound monitoring evaluation system based on the failure risk and inspection experience is proposed. This paper analyzes the abnormal sound characteristics of power plant production equipment, and verifies the effectiveness of time spectrum as a feature learning. Finally, combined with its audio characteristics, the abnormal sound perception scheme is proposed taking the existing machine hearing technology as the main frame.

Power Plant Production Equipment Abnormal Sound Perception Method Research based on Machine Hearing

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Jifan Ouyang

Author Tools

Chat about Author

Papers

Water leakage detection and its application of turbine floor equipment based on MaskRCNN

Research on the Optimization of Underwater Vehicle Dynamic System

Research of the underwater vehicle technology in long-distance tunnels

Power Plant Production Equipment Abnormal Sound Perception Method Research based on Machine Hearing