Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

Numerical analysis of hydraulic fracture propagation in deep shale reservoir with different injection strategies

Deep shale reservoirs are characterized by elevated breakdown pressures,diminished fracture complexity,and reduced modified volumes compared to medium and shallow reservoirs.Therefore,it is urgent to investigate particular injection strategies that can optimize breakdown pressure and fracturing efficiency to address the increasing demands for deep shale reservoir stimulation.In this study,the efficiency of various stimulation strategies,including multi-cluster simultaneous fracturing,modified alternating fracturing,alternating shut-in fracturing,and cyclic alternating fracturing,was evaluated.Subsequently,the sensitivity of factors such as the cycle index,shut-in time,cluster spacing,and horizontal permeability was investigated.Additionally,the flow distribution effect within the wellbore was discussed.The results indicate that relative to multi-cluster simultaneous fracturing,modified alternating fracturing exhibits reduced susceptibility to the stress shadow effect,which results in earlier breakdown,extended hydraulic fracture lengths,and more consistent propagation despite an increase in breakdown pressure.The alternating shut-in fracturing benefits the increase of fracture length,which is closely related to the shut-in time.Furthermore,cyclic alternating fracturing markedly lowers breakdown pressure and contributes to uniform fracture propagation,in which the cycle count plays an important role.Modified alternating fracturing demonstrates insensitivity to variations in cluster spacing,whereas horizontal permeability is a critical factor affecting fracture length.The wellbore effect restrains the accumulation of pressure and flow near the perforation,delaying the initiation of hydraulic fractures.The simulation results can provide valuable numerical insights for optimizing injection strategies for deep shale hydraulic fracturing.

Flexible Fixture Design for the Top and End Surface Processing of NP2_NP4 Cylinder Heads

This paper focuses on the design of fixtures for NP2 and NP4 cylinder heads on a horizontal machining center of flexible machining automatic lines.It began with an analysis of the diagrams of part processing and working procedure which formed the basis for the design of the processing technology scheme,a selection of suitable machine tools,and the setting of processing parameters.Fixtures tailored to the chosen machine tools were then designed to meet the processing requirements.Additional aspects of the project included the design of part drawings,calculation of working time quota,design of auxiliary guides,support clamping,and hydraulic circuits,all aimed at fulfilling practical production requirements.

Data processing and preliminary results of the Chang'e-3 VIS/NIR Imaging Spectrometer in-situ analysis

The Chang＇e-3 Visible and Near-infrared Imaging Spectrometer （VNIS） is one of the four payloads on the Yutu rover. After traversing the landing site during the first two lunar days, four different areas are detected, and Level 2A and 2B ra- diance data have been released to the scientific community. The released data have been processed by dark current subtraction, correction for the effect of temperature, radiometric calibration and geometric calibration. We emphasize approaches for re- flectance analysis and mineral identification for in-situ analysis with VNIS. Then the preliminary spectral and mineralogical results from the landing site are derived. After comparing spectral data from VNIS with data collected by the Ma instrument and samples of mare that were returned from the Apollo program, all the reflectance data have been found to have similar absorption features near 1000 nm except lunar sample 71061. In addition, there is also a weak absorption feature between 1750-2400nm on VNIS, but the slopes of VNIS and Ma reflectance at longer wavelengths are lower than data taken from samples of lunar mare. Spectral parameters such as Band Centers and Integrated Band Depth Ratios are used to analyze mineralogical features. The results show that detection points E and N205 are mixtures of high-Ca pyroxene and olivine, and the composition of olivineat point N205 is higher than that at point E, but the compositions of detection points S3 and N203 are mainly olivine-rich. Since there are no obvious absorption features near 1250 nm, plagioclase is not directly identified at the landing site.

Development of the Data Processing and Analysis System Framework for ICF Experiments

An idea is presented about the development of a data processing and analysis system for ICF experiments, which is based on an object oriented framework. The design and preliminary implementation of the data processing and analysis framework based on the ROOT system have been completed. Software for unfolding soft X-ray spectra has been developed to test the functions of this framework.

Data processing and error analysis for the CE-1 Lunar microwave radiometer

The microwave radiometer （MRM） onboard the Chang＇ E-1 （CE-I） lu- nar orbiter is a 4-frequency microwave radiometer, and it is mainly used to obtain the brightness temperature （TB） of the lunar surface, from which the thickness, temperature, dielectric constant and other related properties of the lunar regolith can be derived. The working mode of the CE-1 MRM, the ground calibration （including the official calibration coefficients）, as well as the acquisition and processing of the raw data are introduced. Our data analysis shows that TB increases with increasing frequency, decreases towards the lunar poles and is significantly affected by solar illumination. Our analysis also reveals that the main uncertainty in TB comes from ground calibration.

Development of a Web-Based GIS of Flood Zones in the Municipality of Ouagadougou in Burkina Faso

This document describes the creation of an informative Web GIS aimed at mitigating the impacts of flooding in the municipality of Ouagadougou, in Burkina Faso, a region that is highly sensitive to climate change. Burkina Faso, which is undergoing rapid urbanization, faces major natural threats, particularly flooding, as demonstrated by the severe floods of 2009 that caused loss of life, injury, structural damage and economic losses in Ouagadougou. The aim of this research is to develop a web map highlighting the municipality’s flood-prone areas, with a view to informing and raising awareness of flood risk reduction. Using the Leaflet JavaScript mapping library, the study uses HTML, CSS and JavaScript to implement web mapping technology. Data on Ouagadougou’s flood zones is generated by a multi-criteria analysis combining Saaty’s AHP method and GIS in QGIS, integrating seven (7) parameters including hydrography, altitude, slope, rainfall, soil types, land use and soil moisture index. QGIS processes and maps the themes, PostgreSQL with PostGIS serves as the DBMS and GeoServer functions as the map server. The Web GIS platform allows users to visualize the different flood risks, from very low to very high, or the high-risk areas specific to Ouagadougou. The AHP calculations classify the municipality into five flood vulnerability zones: very low (24.48%), low (27.93%), medium (23.01%), high (17.11%) and very high (7.47%). Effective risk management requires communication and awareness-raising. This online mapping application serves as a tool for communication, management and flood prevention in Ouagadougou, helping to mitigate flood-related natural disasters.

Safety analysis of wheel brake system based on STAMP/STPA and Monte Carlo simulation

The wheel brake system safety is a complex problem which refers to its technical state, operating environment, human factors, etc., in aircraft landing taxiing process. Usually, professors consider system safety with traditional probability techniques based on the linear chain of events. However, it could not comprehensively analyze system safety problems, especially in operating environment, interaction of subsystems, and human factors. Thus,we consider system safety as a control problem based on the system-theoretic accident model, the processes(STAMP) model and the system theoretic process analysis(STPA) technique to compensate the deficiency of traditional techniques. Meanwhile,system safety simulation is considered as system control simulation, and Monte Carlo methods are used which consider the range of uncertain parameters and operation deviation to quantitatively study system safety influence factors in control simulation. Firstly,we construct the STAMP model and STPA feedback control loop of the wheel brake system based on the system functional requirement. Then four unsafe control actions are identified, and causes of them are analyzed. Finally, we construct the Monte Carlo simulation model to analyze different scenarios under disturbance. The results provide a basis for choosing corresponding process model variables in constructing the context table and show that appropriate brake strategies could prevent hazards in aircraft landing taxiing.

Analysis of a Cold Wave Weather Process in Chengdu in March 2010

[Objective] The aim was to analyze one cold wave weather process in Chengdu in March in 2010.[Method] Based on the NCEP 1°×1° 6 h interval reanalysis data and daily observation data,using synoptic analysis and diagnosis methods,and combining with the cold wave forecast index in spring of Sichuan,a cold wave event covering the whole region between March 21 and 24,2010 was analyzed from the aspects of circulation background,influencing weather systems and weather causation.[Result] Results showed that the 500 high-altitude cold vortex,700-850 hPa low layer shear,and ground cold front were the main systems that influenced this cold wave;there was a ridge from Lake Balkhash across Lake Baikal at 500 hPa.The early stage of the process was controlled by the high pressure ridge and the temperature was increasing obviously.The daily mean temperature was high.The range of cold high pressure was large and the central intensity was 1 043.0 hPa;the cold air was strong and deep which was in accordance with the strong surface temperature reduction center.The strong north airstream of Lake Balkhash to Lake Baikal,ground cold high pressure center intensity changes,north and south ocean pressure and temperature differences,850 hPa temperature changes,cold advection movement route and intensity were considered as reference factors for the forecast of cold wave intensity.[Conclusion] The study provided theoretical basis for improving the forecast ability of cold wave weather.

Analysis of the Flow Field Characteristics Associated with the Dynamic Rock Breaking Process Induced by a Multi-Hole Combined External Rotary Bit

The characteristics of the flow field associated with a multi-hole combined external rotary bit have been studied by means of numerical simulation in the framework of an RNG k-εturbulence model,and compared with the results of dedicated rock breaking drilling experiments.The numerical results show that the nozzle velocity and dynamic pressure of the nozzle decrease with an increase in the jet distance,and the axial velocity of the nozzle decays regularly with an increase in the dimensionless jet distance.Moreover,the axial velocity related to the nozzle with inclination angle 20°and 30°can produce a higher hole depth,while the radial velocity of the nozzle with 60°inclination can enlarge the hole diameter.The outcomes of the CFD simulations are consistent with the actual dynamic rock breaking and pore forming process,which lends credence to the present results and indicates that they could be used as a reference for the future optimization of systems based on the multi-hole combined external rotary bit technology.

Analysis on the Heavy Snow Weather Process in Benxi Area

[Objective] The aim was to study the formation and development of a heavy snow in Benxi area. [Method] Based on conventional meteorological data, the formation and development of a heavy snow in Benxi area from December 4th to 5th in 2009 were analyzed from the aspects of weather situation evolution and physical quantity field feature. [Result] The heavy snow was caused by upper trough and North China cyclone. In this process, there was upper level divergence and lower level convergence over Benxi area, and it was warm at low attitude and cold at high attitude; southwest jet at low attitude transported water vapor from Bohai Sea to eastern Liaoning, which provided good water vapor condition for snow, but it didn’t reach heavy snow due to inadequate ascending force. The development of Ural Mountains high ridge played an important role in the snow process and the strengthened high ridge moving northward was beneficial to the southward movement of cold air and deepening of upper trough. Analysis on physical quantity field could provide reference for predicting beginning and ending time and strength of heavy snow. [Conclusion] The study could provide basis for the forecast of heavy snow.

Analysis of a Rare Continuous Rainy Process in Midsummer

[Objective] The research aimed to analyze a rare low temperature and rainy weather process which happened in Anhui Province from July 22 to August 14,2009.[Method] Based on the data of conventional observation,NCEP analysis field and automatic station,a rare low temperature and rainy weather process which occurred in Anhui Province from July 22 to August 14,2009 was analyzed.The formation reason of continuous rainy process in midsummer was discussed.The circulation characteristics and influence systems of continuous rainy process were revealed.On the base,the influences of configuration of circulation fields and difference of physical quantity fields at high and low layers on range and intensity of precipitation were analyzed.[Result] According to the circulation situation and influence system,the continuous rainy process could be divided into four stages:July 22-24,from July 27 to August 1,August 4-8 and August 9-14.Moreover,it was respectively affected by northeast low vortex,cold and warm air,high-level low trough,typhoon and periphery of subtropical high at four stages.The maintenance of big specific humidity zone provided sufficient water vapor condition for the continuous rainy weather.The rainstorm appeared in dense zone of specific humidity line,where the specific humidity >13 g/kg in the humidity front zone.A temperature trough maintained at 850 hPa.The cold air which continued to diffuse and go south was main reason of the abnormally low temperature during the continuous rainy period.Moreover,it provided ascending motion condition for precipitation maintenance.[Conclusion] The research provided references for actual forecast of continuous rainy weather.

Deep tissue near-infrared imaging for vascular network analysis

Subcutaneous vein network plays important roles to maintain microcirculation that is related to some diagnostic aspects.Despite developments of optical imaging technologies,still the difficulties about deep skin vascular imaging have been continued.On the other hand,since hemoglobin con-centration of human blood has key role in the veins imaging by optical manner,the used wavelength in vascular imaging,must be chosen considering absorption of hemoglobin.In this research,we constructed a near infrared(NIR)light source because of lower absorption of hemoglobin in this optical region.To obtain vascular image,reflectance geometry was used.Next,from recorded images,vascular network analysis,such as calculation of width of vascular of interest and complexity of selected region were implemented.By comparing with other modalities,we observed that proposed imaging system has great advantages including nonionized radiation,moderate penetration depth of 0.5-3 mm and diameter of 1 mm,cost-effective and algorit hmic simplicity for analysis.

Stress Analysis of the Subsea Dynamic Riser BaseProcess Piping

Thesubsea dynamic riser base （SDRB） is an important piece of equipment for the floating production platform mooring system.One end is connected to the rigid pipeline, carrying a rigid pipeline thermal expansion load and the other end is connected to a flexible riser, carrying the dynamic load of the flexible riser, so its function is a transition connection between the flexible riser and the rigid pipeline which fixes the flexible riser on the seabed. On the other hand. as a typical subsea product, the design will satisfythe requirements of the standards for subsea products. By studying the stress analysisphilosophy of the topside piping and subsea pipeline, a physical model and procedure for piping stress analysis of the SDRB have been established.The conditions of the adverse design load have been considered, and a combination of the static load from the rigid pipeline and the dynamic load flexibility has also been optimized. And a comparative analysis between the AMSE, DNV and API standards for piping stress with the checking rules has been done.Because theSDRB belongs to the subsea pipeline terminal product, the use of DNV standards to check its process piping stress is recommended. Finally, the process piping stress of the SDRB has been calculated, and the results show that the jacket pipe and the carrier pipe stress of the SDRB process piping satisfy the DNV standards as a whole.The bulkhead cannot be accurately simulated by the AutoPIPE software which uses the FEA software ANSYS inthe detailed analysis, but the checking results will still meet the requirements of the DNV standards.

An aligned mixture probabilistic principal component analysis for fault detection of multimode chemical processes

A novel approach named aligned mixture probabilistic principal component analysis(AMPPCA) is proposed in this study for fault detection of multimode chemical processes. In order to exploit within-mode correlations,the AMPPCA algorithm first estimates a statistical description for each operating mode by applying mixture probabilistic principal component analysis(MPPCA). As a comparison, the combined MPPCA is employed where monitoring results are softly integrated according to posterior probabilities of the test sample in each local model. For exploiting the cross-mode correlations, which may be useful but are inadvertently neglected due to separately held monitoring approaches, a global monitoring model is constructed by aligning all local models together. In this way, both within-mode and cross-mode correlations are preserved in this integrated space. Finally, the utility and feasibility of AMPPCA are demonstrated through a non-isothermal continuous stirred tank reactor and the TE benchmark process.

Analysis of the geomorphology surrounding the Chang'e-3 landing site

Chang＇e-3 （CE-3） landed on the Mare Imbrium basin in the east part of Sinus Iridum （19.51°W, 44.12°N）, which was China＇s first soft landing on the Moon and it started collecting data on the lunar surface environment. To better understand the environment of this region, this paper utilizes the available high-resolution topography data, image data and geological data to carry out a detailed analysis and research on the area surrounding the landing site （Sinus Iridum and 45 km×70 km of the landing area） as well as on the topography, landform, geology and lunar dust of the area surrounding the landing site. A general topographic analysis of the surrounding area is based on a digital elevation model and digital elevation model data acquired by Chang＇e-2 that have high resolution; the geology analysis is based on lunar geological data published by USGS; the study on topographic factors and distribution of craters and rocks in the surrounding area covering 4km^4km or even smaller is based on images from the CE-3 landing camera and images from the topographic camera; an analysis is done of the effect of the CE-3 engine plume on the lunar surface by comparing images before and after the landing using data from the landing camera. A comprehensive analysis of the results shows that the landing site and its surrounding area are identified as typical lunar mare with flat topography. They are suitable for maneuvers by the rover, and are rich in geological phenomena and scientific targets, making it an ideal site for exploration.

Analysis on "96. 8" Heavy Rainstorm Process in Handan

[ ObjEtive] The research aimed to analyze ＂96.8＂ heavy rainstorm process causing flood disaster in Handan. [ Method] Based on ac- tual situation data, satellite cloud data and NCEP reanalysis data in the first dekad of August in 1996, ＂96.8＂ heavy rainstorm process causing flood disaster in Handan was analyzed to understand occurrence reason of the flood disaster. [ Result] Two meso-scale convective cloud clusters which developed and went north in turn caused ＂96.8＂ heavy rainstorm in Handan. Typhoon and inverted trough were main weather systems induced flood disaster in Handan. In going north process of the low-level jet, due to blocking of the subtropical high, water vapor and energy accumulated in Handan, providing material basis for formation of the heavy rainstorm. Development and eastward movement of the short-wave trough at middle lati- tude and continuous invasion of the reflux weak cold air at the low layer were direct reason for triggering generation and development of the convec- tive cloud cluster, and further causing continuous rainstorm. Wet layer over the rainstorm zone was deep and thick. Meridional distribution of the wet zone was wider than latitudinal distribution. South China Sea and Bay of Bengal were water vapor sources for the rainstorm zone. In the whole rain- storm period, it was convergence at low layer and divergence at high layer in the rainstorm zone. It was positive vorticity at low layer and negative vorticity at high layer. Precipitation intensity changed as convergence and divergence. Rainstorm zone had strong ascending motion. As strengthe- ning and uplifting of the ascending motion strong center, strong precipitation also strengthened. Rainstorm center was near the biggest vertical ve- locity center. Strong precipitation changed as vertical ascending motion. [ Conclmion] The research provided scientific basis for disaster prevention and reduction and decision-making service.

Wavelet Analysis of Space Solar Telescope Images

The scientific satellite SST (Space Solar Telescope) is an important research project strongly supported by the Chinese Academy of Sciences. Every day, SST acquires 50 GB of data (after processing) but only 10GB can be transmitted to the ground because of limited time of satellite passage and limited channel volume. Therefore, the data must be compressed before transmission. Wavelets analysis is a new technique developed over the last 10 years, with great potential of application. We start with a brief introduction to the essential principles of wavelet analysis, and then describe the main idea of embedded zerotree wavelet coding, used for compressing the SST images. The results show that this coding is adequate for the job.

Comparative Proteomic Analysis of the Fiber Elongating Process in Cotton

A comparative proteomic analysis was performed to explore the mechanism of cell elongation in developing cotton fibers.The temporal changes of global proteomes at five representative

Analysis on a Severe Convective Weather Process in Summer in Beihai

[Objective] The research aimed to analyze a strong convective weather process in Beihai in summer. [Method] By using Micaps conventional data and the single station site information of Beihai, radar data, a strong convective weather process in Beihai City in August, 2010 was analyzed. [Result] 850 and 700 hPa cyclonic low-pressure circulation in the north of Vietnam and Beibu Gulf coast was favorable for the transportation of Bengal Bay southwest airflow, which provided the sufficient water vapor condition for the strong precipitation. The interaction of weak cold air and southeast warm wet airflow was the main cause of the strong rainfall process. The falling zone of strong precipitation related to the water vapor convergence. The maintenance of water vapor flux divergence field in southeast-northwest direction was favorable for the duration of strong precipitation in the south of Guangxi. Before the strong precipitation, the positive and negative vorticity in the high and low levels in Beihai station both abruptly strengthened, which was very favorable for generating the convection. The vertical velocity in the strong precipitation process turned from the positive value at the beginning into the negative value as the height variation. The turning had the indicated and early-warning roles on the generation of strong convective weather. [Conclusion] The research provided the theory basis for the strong convective weather forecast in Guangxi coast in summer.