Automatic Early Warning Research Articles

In-situ visual monitoring for multi-scale defects detection in laser powder bed fusion

Laser powder bed fusion (PBF-LB) is a promising metal additive manufacturing technology. However, ensuring consistent quality remains a pressing challenge due to defects that arise during the PBF-LB process. These defects significantly impede subsequent molding procedures, emphasizing the urgent need for real-time monitoring technology to steer part production effectively. Present monitoring techniques are limited, typically addressing specific defect types or contour deformations individually and lacking a simple and effective method to achieve multi-scale defects detection for PBF-LB parts. This study aims to pioneer a method that can detect defects and part contour deformations during the PBF-LB process using only an industrial camera as the monitoring device. The proposed method consists of two key components: a semantic segmentation model based on deep transfer learning (SS-DTF model) and a contour deformation detection module. To begin with, an off-axis in-situ monitoring system is deployed with an industrial camera to capture powder bed images for each layer after laser scanning and powder spreading. This enables the production of datasets for post-scanning and post-spreading anomalies. The SS-DTF model is trained on the above two datasets respectively to achieve segmentation for multi-category defects. The contour deformation detection module provides automatic early warning by comparing the true contour of the part with the nominal contour layer-by-layer, using statistical process monitoring method. The proposed method is then used to monitor parts with various geometries under real processing conditions, aiming to clarify the potential correlation between monitoring outcomes and the parts’ multi-scale defects in PBF-LB. The results show that the proposed method provides a promising solution for in-situ monitoring of the PBF-LB process.

Automatic early warning of rockbursts from microseismic events by learning the feature-augmented point cloud representation

This study proposes an automatic early warning system for rockbursts in deeply buried tunnels using microseismic data. A novel machine learning model is introduced, which is the first to treats the microseismic event data as a high-dimensional point cloud. The model utilizes a fast approximated convolution (FAC) method to effectively and efficiently learn features from the raw event data with small model sizes. The model is trained and tested using microseismic data from the Hanjiang-To-Weihe water diversion project. Two competing models, a time series model and a traditional threshold model, are also constructed for comparison. Results show that the proposed model achieves reliable early warnings for 90.1% of rockbursts in the tunnel. This study presents a new and feasible rockburst prediction method that can be used independently or as a supplement to current assessment and management approaches for both tunnel boring machines (TBMs) and drilling- and blasting-excavated tunnels.

Development and application of two closed-loop systems for automatic early warning of thrombus based on AI

Development and application of two closed-loop systems for automatic early warning of thrombus based on AI

Automatic Early Warning System Design with Firefighter Synchronization Based on Internet of Things (IoT)

The fire department or DamKar is one of the important agencies which is highly needed by Indonesian people, especially when a fire occurs. However, DamKar is often judged to be late in arriving at the location because help comes to the fire when the fire has already take a set. One of the reasons why delay happens in DamKar is because the report is received late by the DamKar officer. One of the fire prevention measures is to take the preventive action or early prevention from indications of a fire. Automatic early detection is needed in an emergency and requires speed and accuracy in overcoming the problem. designs an early detection system for fires that directs to DamKar and warehouse owners. This system can detect and provide temperature information in real time. This system works if there is a drastic change in temperature and there is a puff as soon as detected by the sensor The information is in the form of a notification "Excessive CO gas detected" if the temperature is in the range of 25 °C and the gas content is 100 PPM, if the temperature exceeds 35°C and the gas content is 500 PPM there will be a notification "The warehouse temperature is too hot", then a danger notification " indicated fire above”. From the experimental results, it is found that the mesh communication system can work properly

Optimal design of FBG flexible sensor for high-precision monitoring of three-dimensional deformation of power transmission line tower foundation

During the operation of the power transmission line tower foundation, uneven settlement and horizontal sliding were formed due to the damage of the local environment or external force. It is the most direct and effective way to realize the transformation from “passive response” to “active prevention and control” by real-time and long-term monitoring of the tower foundation and providing automatic early warning. In this paper, based on FBG (fiber Bragg grating) sensing technology, a FBG flexible sensor with temperature self-compensation characteristic was developed, which can be used for real-time monitoring of three-dimensional deformation field of tower foundation. Based on the strain information measured by the sensor, a coordinate transformation fitting algorithm was applied to reconstruct the deformation field of the tower foundation. To improve the displacement sensing precision of the flexible sensor, the influence of the length of the cemented layer and the groove radius on the strain transfer coefficient was analyzed, and the orthogonal curvature obtained by the sensing point was corrected by cubic spline interpolation. In the displacement sensing experiment, the mean absolute errors along the x-axis direction after interpolation correction were 1.84 mm (Type 1), 1.52 mm (Type 2) and 1.96 mm (Type 3), respectively; the mean absolute errors along the y-axis direction were 1.64 mm (Type 1), 2.34 mm (Type 2) and 1.21 mm (Type 3), respectively. After interpolation correction, the maximum absolute error percentages of the measuring points along the x-axis were 9.62% (Type 1), 9.01% (Type2) and 10.23% (Type 3); the maximum absolute error percentages along the y-axis were 10.44% (Type 1), 9.53% (Type2) and 9.43% (Type 3). Therefore, the designed FBG flexible sensor can be competent for the task of monitoring the three-dimensional deformation field of the tower foundation, which has important significance and application promotion value.

Research on automatic early warning of UAV attitude abnormal state based on MEMS sensor

Research on automatic early warning of UAV attitude abnormal state based on MEMS sensor

Research on automatic early warning of UAV attitude abnormal state based on MEMS sensor

The Unmanned Aerial Vehicle's (UAV) attitude control is crucial to the success of the mission. On the basis of this, the paper suggests a paradigm for autonomous early warning of improper UAV attitude based on MEMS sensors. To obtain early warning of anomalous UAV attitude, the model solves UAV attitude using the quaternion approach and employs a fading Kalman filter to correct for MEMS gyroscope inaccuracy. The simulation test demonstrates that in the static state, the errors of the drone's pitch angle and roll angle are within 0.2°, and the heading angle error is about 0.5°. In the high manoeuvring state, the errors of the UAV's pitch angle and roll angle are all within 0.5°, and the mean value of the heading angle error is also controlled within 2°. The experiment achieves high-precision automated warning of aberrant attitude by filtering the fading Kalman filter to correct the random error of the UAV gyroscope. It also increases the precision with which human motion is measured. The suggested approach promotes the growth of the UAV sector.

Application of atmospheric dispersion modelling in finding optimal locations of early warning stations around a nuclear power plant

The paper investigates a practical problem of finding optimal locations of radiometric detectors for the automatic early warning measurements around nuclear facilities. The proposed methodology combines an analysis of the capabilities of different detectors with atmospheric dispersion modelling in the JRodos decision support system. It was found that the radioactive contamination after a small abnormal release might be impossible to detect for a less sensitive device (like a popular GM counter) further away than 5 km from the nuclear reactor. On the other hand, a more sensitive detector (like a 3” NaI scintillator) could be inappropriate for measurements within a shorter distance because the radiation field could be too high. This work was performed in the context of the planned first Polish nuclear power plant, but our approach and findings are general and apply to other facilities using a pressurised water reactor with electrical power of about 1 GW.

Method of forest fire automatic early warning and alarm system design

Forest is a huge green wealth bestowed by nature to mankind, but forest fire will cause great harm. Automatic forest fire early warning and alarm system can warn the high fire risk areas in the forest, or find and alarm the forest fire as early as possible, which is of great significance to reduce the loss of forest fire. This paper introduces a construction method of forest fire automatic early warning and alarm system, which provides knowledge and experience accumulation for the subsequent research and development of related systems.

Analysis of an Automatic Early Warning System Based on Fog Architecture

In the process of analysing and processing terminal sensor information, a large number of terminal sensors are needed to collect front-end information. These front-end data collection, analysis and processing require high real-time, and need the support of location aware mobile computing services. Traditional cloud computing architecture is not the best choice for service scenarios with high real-time requirements. The fog computing architecture is to extend cloud computing services to the edge of the sensor network, coupled with appropriate fitness algorithms, can effectively improve the information analysis and early warning response speed of the geological disaster information early warning system.

Research on safety risk early warning of tunnel construction based on BIM and RFID Technology

Due to the frequent occurrence of safety accidents in tunnel construction, it poses a great threat to property safety and the life safety of construction personnel. According to the classification of accident types, this paper standardizes the data of influential risk factors, delimits the boundary of dangerous areas, and proposes the specific steps of inputting field information into BIM database. The results show that the combination of BIM and RFID technology can monitor the conditions of the construction site in real time, and realize the automatic early warning of the dangerous sources in the tunnel construction.

A smartphone-based school syndromic surveillance system and its application in Hangzhou

Objective To establish and implement a smartphone-based school syndromic surveillance system, and to provide references for school communicable disease control and prevention. Methods A smartphone-based school syndromic surveillance system was constructed and applied. A list of seven symptoms including fever, cough, vomit, diarrhea, rash, red eye and parotid swelling was classified as targeted indicators. Spatio-temporal permutation scanning was applied to automatic early warning. Results A total of 1 973 school joined the syndromic surveillance system. System usage rate was 54.13%, no significant differences were found among different types of schools (χ 2 = 1.58, P =0.67), whereas significant differences were observed among counties (χ 2 = 726.78, P <0.01). Totally, 852 036 pieces of symptoms data were reported during September 2018 to March 2019, the primary symptoms included cough (35.17%) and fever (21.11%). Time trends in different symptoms varied with time, with fever and cough highest in January, vomit and diarrhea in November. Thirteen pieces of early warning were confirmed as school communicable diseases by field investigation, the average number of the infected students were four. Conclusion The smartphone-based school syndromic surveillance system is generally acceptable. Characteristic seasonal distributions of school communicable diseases are reflected accurately by surveillance system which plays an active role in prevention and control of school communicable diseases. 【摘要】 目的 建立并应用基于智能手机的学校症状监测系统, 为学校开展传染病防控工作提供参考。 方法 依托 网络技术, 建立以智能手机为信息收集端的杭州市学校症状监测系统, 以发热、咳嗽、呕吐、腹泻、皮疹、红眼、腮腺肿大作为 监测指标, 采用时空扫描方式对症状数据进行绝对数阈值自动预警。 结果 2018 年 9 月至 2019 年 3 月, 系统共注册 1 973 所学校, 系统使用率达 54.13%, 不同类型学校系统使用率差异无统计学意义 (χ 2 =1.58, P =0.67), 不同地区系统使用率差 异有统计学意义 (χ 2 = 726.78, P <0.01)。累计上报 7 类监测症状信息共 852 036 条, 以咳嗽 (35.17%)、发热 (21.11%) 症状 为主, 不同症状时间变化趋势略有不同, 发热与咳嗽髙峰为 1 月, 呕吐与腹泻的髙峰为 11 月。13 条自动预警信息经调査 确认为聚集性疫情, 平均发病 4 人。 结论 杭州市学校症状监测系统适用性广泛, 监测数据较好地反映了学校常见传染病 的季节特征, 在传染病疫情早期预警中发挥了哨兵作用。

Automatic early warning of tail biting in pigs: 3D cameras can detect lowered tail posture before an outbreak.

Tail biting is a major welfare and economic problem for indoor pig producers worldwide. Low tail posture is an early warning sign which could reduce tail biting unpredictability. Taking a precision livestock farming approach, we used Time-of-flight 3D cameras, processing data with machine vision algorithms, to automate the measurement of pig tail posture. Validation of the 3D algorithm found an accuracy of 73.9% at detecting low vs. not low tails (Sensitivity 88.4%, Specificity 66.8%). Twenty-three groups of 29 pigs per group were reared with intact (not docked) tails under typical commercial conditions over 8 batches. 15 groups had tail biting outbreaks, following which enrichment was added to pens and biters and/or victims were removed and treated. 3D data from outbreak groups showed the proportion of low tail detections increased pre-outbreak and declined post-outbreak. Pre-outbreak, the increase in low tails occurred at an increasing rate over time, and the proportion of low tails was higher one week pre-outbreak (-1) than 2 weeks pre-outbreak (-2). Within each batch, an outbreak and a non-outbreak control group were identified. Outbreak groups had more 3D low tail detections in weeks -1, +1 and +2 than their matched controls. Comparing 3D tail posture and tail injury scoring data, a greater proportion of low tails was associated with more injured pigs. Low tails might indicate more than just tail biting as tail posture varied between groups and over time and the proportion of low tails increased when pigs were moved to a new pen. Our findings demonstrate the potential for a 3D machine vision system to automate tail posture detection and provide early warning of tail biting on farm.

Automatic Early Warning for Vehicles Accidents Based on User Location

Automatic Early Warning for Vehicles Accidents Based on User Location

Design and implementation of a 3D visualization and early warning system for Radar data based on GIS

With the application of GIS spatial analysis method,a 3D visualization and early warning system is designed and developed for new generation Doppler meteorological Radar data based on the technology of ESRI ArcGIS Engine and Microsoft VB.net.This system has the main functions of automatic coordinate conversion,statistic and dynamic analysis,3D visualization,automatic early warning,emergent communication,and special charting associated with geographic information.3D visualization can provide weather forecasters with detailed terrain information.For the first time,the automatic early warning model is built for the application of Doppler meteorological Radar data,which is based on GIS spatial analysis.The results show that this system can provide a powerful support for refined short-time weather forecasting.

Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods

Diabetic nephropathy is damage to the kidney caused by diabetes mellitus. It is a common complication and a leading cause of death in people with diabetes. However, the decline in kidney function varies considerably between patients and the determinants of diabetic nephropathy have not been clearly identified. Therefore, it is very difficult to predict the onset of diabetic nephropathy accurately with simple statistical approaches such as t-test or chi(2)-test. To accurately predict the onset of diabetic nephropathy, we applied various machine learning techniques to irregular and unbalanced diabetes dataset, such as support vector machine (SVM) classification and feature selection methods. Visualization of the risk factors was another important objective to give physicians intuitive information on each patient's clinical pattern. We collected medical data from 292 patients with diabetes and performed preprocessing to extract 184 features from the irregular data. To predict the onset of diabetic nephropathy, we compared several classification methods such as logistic regression, SVM, and SVM with a cost sensitive learning method. We also applied several feature selection methods to remove redundant features and improve the classification performance. For risk factor analysis with SVM classifiers, we have developed a new visualization system which uses a nomogram approach. Linear SVM classifiers combined with wrapper or embedded feature selection methods showed the best results. Among the 184 features, the classifiers selected the same 39 features and gave 0.969 of the area under the curve by receiver operating characteristics analysis. The visualization tool was able to present the effect of each feature on the decision via graphical output. Our proposed method can predict the onset of diabetic nephropathy about 2-3 months before the actual diagnosis with high prediction performance from an irregular and unbalanced dataset, which statistical methods such as t-test and logistic regression could not achieve. Additionally, the visualization system provides physicians with intuitive information for risk factor analysis. Therefore, physicians can benefit from the automatic early warning of each patient and visualize risk factors, which facilitate planning of effective and proper treatment strategies.

AEWS: an integrated knowledge-based system with neural networks for reliability prediction

The ability of accurately predicting reliability for products is an invaluable asset for any manufacturing company. The United Technologies Carrier developed such a system based on Weibull distribution. However, predicting accurate reliability requires experienced person's special knowledge. Two expert systems were developed to capture such knowledge. The use of Weibull plots was critical in interpreting the results of failure rates. This interpretation process was imitated by employing multi-layer feed-forward neural networks. The expert systems and neural networks are integrated with the already existing Early Warning System (EWS) and databases. The resulting system, Automatic Early Warning System (AEWS), is currently deployed in United Technologies Carrier and has led to a significant boost in productivity by at least 8 times in terms of process time.