Prosthesis implantation and fat transplantation are common breast reconstructionmethods.In general,prosthesis implantation alone does not achieve a realistic enough appearance,and fat transplantation alone is difficul...Prosthesis implantation and fat transplantation are common breast reconstructionmethods.In general,prosthesis implantation alone does not achieve a realistic enough appearance,and fat transplantation alone is difficult to achieve in the correct capacity.To date,no reports have focused on methods of combining fat with implanted prostheses for breast reconstruction.Using a newly designed bionic ink(i.e.,polyether F127 diacrylate(F127DA)&poly(ethylene glycol)diacrylate(PEGDA))and projection-based three-dimensional bioprinting(PBP),we report the development of a new method for printing porous prostheses.PEGDA was used to improve the printing precision of the prosthesis by increasing the gel point of F127DA and reducing the impact of external temperature.The compression modulus of the printed prosthesis was very close to that of prostheses currently used in clinical practice and to that of natural breasts.Finally,stromal vascular fraction gel(SVF-gel),a human fat extract,was injected into the pores of the synthesized prostheses to prepare a prosthesis mixed with adipose tissue.These were implanted subcutaneously in nude mice to observe their biological performance.After 14 and 28 days of observation,the prosthesis showed good biocompatibility,and adipose tissues grew well in and around the prosthesis.This result shows that a porous prosthesis containing pre-placed adipose tissues is a promising breast reconstruction material.展开更多
Mn co-precipitation method combined with Raman spectroscopy were used to detenmine trace heavy metals(copper,zinc,cadmium and lead)in water sample.Different concentrations of heavy metals including copper,zinc,cadmiun...Mn co-precipitation method combined with Raman spectroscopy were used to detenmine trace heavy metals(copper,zinc,cadmium and lead)in water sample.Different concentrations of heavy metals including copper,zinc,cadmiun and lead in water samples were separated and enriched by Mn^(2+)-phen SCN-ternary complex 0o-precipitation procedure.The Raman spectra of co-precipitation sediments were collected using confocal micro-Raman spectrometry.Different preprocessing treatments and regression calibration methods were compared.The best models using partial least squares regression(PLS)of copper,zinc,cadmium and lead were built with a correlation cofficient of prediction(R_(p))of 0.979,0.964,0.956 and 0972,respectively,and the root mean square error of prediction(RMSEP)of 6.587,9.046,9.998 and 7.751 pug/kg,respectively.The co-precipitation procedure combined with Raman spectroscopy method are feasible to detect the amount of heavy metals in water.展开更多
The potential of Confocal micro Raman spectroscopy in the quantitative analysis of pesticide(Chlorpyrifos,Omethoate)residues on orange surface is investigated in this work.Quantitative analysis models were established...The potential of Confocal micro Raman spectroscopy in the quantitative analysis of pesticide(Chlorpyrifos,Omethoate)residues on orange surface is investigated in this work.Quantitative analysis models were established by partial least squares(PLS)using different preprocessing methods(Smoothing,First derivative,MSC,Baseline)for pesticide residues.For pesticide resi-dues,the higher correlation coefficients(r)is 0.972 and 0.943,the root mean square error of prediction(RMSEP)is 2.05%and 2.36%,respectively.It is therefore clear that Confocal micro-Raman spectroscopy techniques enable rapid,nondestructive and reliable measurements,so Raman spectrometry appears to be a prormising tool for pesticide residues.展开更多
Variable selection is applied widely for visible-near infrared(Vis-NIR)spectroscopy analysis of internal quality in fruits.Different spectral variable selection methods were compared for online quantitative analysis o...Variable selection is applied widely for visible-near infrared(Vis-NIR)spectroscopy analysis of internal quality in fruits.Different spectral variable selection methods were compared for online quantitative analysis of soluble solids content(SSC)in navel oranges.Moving window partial least squares(MW-PLS),Monte Carlo uninformative variables elimination(MC-UVE)and wavelet transform(WT)combined with the MC-UVE method were used to select the spectral variables and develop the calibration models of online analysis of SSC in navel oranges.The performances of these methods were compared for modeling the Vis NIR data sets of navel orange samples.Results show that the WT-MC-UVE methods gave better calibration models with the higher correlation cofficient(r)of 0.89 and lower root mean square error of prediction(RMSEP)of 0.54 at 5 fruits per second.It concluded that Vis NIR spectroscopy coupled with WT-MC-UVE may be a fast and efective tool for online quantitative analysis of SSC in navel oranges.展开更多
Background and objectives Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats.Skin defects lead to the loquat being easily destroyed during transportation and stor...Background and objectives Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats.Skin defects lead to the loquat being easily destroyed during transportation and storage,which causes the risk of other loquats being infected,affecting the selling price.Materials and Methods In this paper,a method combining band radio image with an improved three-phase level set segmentation algorithm(ITPLSSM)is proposed to achieve high accuracy,rapid,and non-destructive detection of skin defects of loquats.Principal component analysis(PCA)was used to find the characteristic wavelength and PC images to distinguish four types of skin defects.The best band ratio image based on characteristic wavelength was determined.Results The band ratio image(Q782/944)based on PC2 image is the best segmented image.Based on pseudo-color image enhancement,morphological processing,and local clustering criteria,the band ratio image(Q782/944)has better contrast between defective and normal areas in loquat.Finally,the ITPLSSM was used to segment the processing band ratio image(Q782/944),with an accuracy of 95.28%.Conclusions The proposed ITPLSSM method is effective in distinguishing four types of skin defects.Meanwhile,it also effectively segments images with intensity inhomogeneities.展开更多
The temperature difference of fruit itself will affect its near infrared spectrum and the accuracy of its soluble solids content(SSC)prediction model.To eliminate the influence of apple temperature difference on the S...The temperature difference of fruit itself will affect its near infrared spectrum and the accuracy of its soluble solids content(SSC)prediction model.To eliminate the influence of apple temperature difference on the SSC model,a diffuse transmission dynamic online detection device was used to collect the spectral data of apples at different temperatures,and four methods were used to establish partial least squares correction models:global correction,orthogonal signal processing,generalized least squares weighting and external parameter orthogonal(EPO).The results show that the temperature has a strong influence on the diffuse transmission spectrum of apples.The 20ºC model can get a satisfactory prediction result when the temperature is constant,and there will be great errors when detecting samples at other temperatures.The effect of temperature must be corrected to establish a more general model.These methods all improve the accuracy of the model,with the EPO method giving the best results;the prediction set correlation coefficient is 0.947,the root mean square error of prediction is 0.489%,and the prediction bias is 0.009%.The research results are of great significance to the practical application of SSC prediction of fruits in sorting workshops or orchards.展开更多
An orchard-lifting platform is a type of mechanical equipment to assist growers in fruit picking,fruit tree pruning,flower thinning,and other operations.In its operational processes,the tilting stability directly affe...An orchard-lifting platform is a type of mechanical equipment to assist growers in fruit picking,fruit tree pruning,flower thinning,and other operations.In its operational processes,the tilting stability directly affects the operational safety and adaptability under complex terrain conditions,while critical tilting angle is an important criterion to evaluate the tilting stability.Based on the structure and the operating characteristics of the three degree of freedom(3-DOF)lifting platform for hilly orchards,the tilting stability was analyzed in different parked states,and the theoretical expressions of critical tilting angle were obtained;in the theoretical expressions,the influencing factors on tilting stability were determined as the parked positionβ1,the manned worktable rotary positionβ2,the lifting height h,and the load m.Based on the multi-body dynamics principle,the tilting stability simulation was carried out.The relative error of tilting angles was approximately 4.6%between simulation and tilting verification experiment,which indicated that the results of tilting stability simulation were reliable.Therefore,the multi-body dynamics simulation was used for further clarifying the influencing factors on tilting stability.A virtual orthogonal test was designed,and the results showed that critical tilting angle ranged from 20°to 44°when the factors were at different values,which indicated that the 3-DOF lifting platform for hilly orchards had a high tilting stability performance and could adapt to the operating conditions of hills with slope angles from 5°to 20°.The results of the range analysis and ANOVA showed that the influence intensity of factors on tilting stability wasβ1>h>m>β2;at the same time,β1,h,and m exerted significant effect on tilting stability.The tilting stability first decreased and then either increased or decreased with the increasing lifting height;it gradually decreased with the increasing load.It also showed that the position of the manned worktable along the slope down always had the lowest tilting stability.This research can provide a theoretical basis and reference for the analysis of tilting stability of the lifting machinery for hilly orchards.展开更多
As photocrosslinkable materials,methacryloyl-modified hydrogels are widely used as bioinks in tissue engineering.Existing printing methods to use these hydrogels,including changing the viscosity of the material or mix...As photocrosslinkable materials,methacryloyl-modified hydrogels are widely used as bioinks in tissue engineering.Existing printing methods to use these hydrogels,including changing the viscosity of the material or mixing them with other printing components,have been explored,but their application has been limited due to low printing quality or high cost.In addition,the complex operation of bulky equipment restricts the application of these existing printing methods.This study presents a lightweight stereolithography-based three-dimensional(3D)bioprinting system with a smart mechanical and structural design.The developed bioprinter dimensions were 300 mm×300 mm×200 mm and it can be placed on a benchtop.The equipment has a mini bioink chamber to store a small amount of bioink for each printing.We systematically investigated the point-by-point curing process in the 3D bioprinting method,which can print mixed cells accurately and have good biocompatibility.Here,we provide a compact,low-cost stereolithography bioprinting system with excellent biocompatibility for 3D bioprinting with methacryloyl-modified hydrogels.It can be potentially used for drug screening,studying pathological mechanisms,and constructing biological disease models.展开更多
In order to solve the problem of poor traveling stability and excessive pesticide application during plant protection operations in hilly orchards,a novel crawler-type multi-channel air-assisted sprayer that is partic...In order to solve the problem of poor traveling stability and excessive pesticide application during plant protection operations in hilly orchards,a novel crawler-type multi-channel air-assisted sprayer that is particularly appropriate for hilly orchards was designed in this study.Considering anti-rolling requirements and the orchard environment in hilly areas,this study selected limits for uphill and downhill rolling angles as well as the transverse rolling angle as the evaluation indexes for determining both the layout and parameter settings of the sprayer.According to freely submerged jets and the requirements in plant protection operation,a multi-channel air-assisted system was developed.The test results showed that the anti-rolling performance and the designed air-assisted system were adequate.At 2 m from the longitudinal center plane of the sprayer,the airflow exhibited wavy distribution patterns under different parameter combinations since the four streams of the airflow were not thoroughly intersected and mixed.At 3 m from the longitudinal center plane of the sprayer,the jet was ejected at great velocity but underwent rapid attenuation;the airflow velocity in most areas barely satisfied the requirements for plant protection operation.In addition,different air outlet layout schemes led to significant differences in the spatial distribution of the airflow field.Compared with a traditional air-assisted sprayer,using the developed multi-channel air-assisted sprayer enhanced the droplet coverage uniformity by 19.4%,and the mean droplet deposition in the front,middle,and rear of the canopy was enhanced by 32.9%,50.3%,and 78.1%,respectively,while reducing ground deposition and air drift by 26.8%.展开更多
Aiming at the problems of traditional centralized cloud computing which occupies large computing resources and creates high latency,this paper proposes a fault detection scheme for insulator self-explosion based on ed...Aiming at the problems of traditional centralized cloud computing which occupies large computing resources and creates high latency,this paper proposes a fault detection scheme for insulator self-explosion based on edge computing and DL(deep learning).In order to solve the high amount of computation brought by the deep neural network and meet the limited computing resources at the edge,a lightweight SSD(Single Shot MultiBox Detector)target recognition network is designed at the edge,which adopts the MobileNets network to replace VGG16 network in the original model to reduce redundant computing.In the cloud,three detection algorithms(Faster-RCNN,Retinanet,YOLOv3)with obvious differences in detection performance are selected to obtain the coordinates and confidence of the insulator self-explosion area,and then the self-explosion fault detection of the overhead transmission line is realized by a novel multimodel fusion algorithm.The experimental results show that the proposed scheme can effectively reduce the amount of uploaded data,and the average recognition accuracy of the cloud is 95.75%.In addition,it only increases the power consumption of edge devices by about 25.6W/h in their working state.Compared with the existing online monitoring technology of insulator selfexplosion at home and abroad,the proposed scheme has the advantages of low transmission delay,low communication cost and high diagnostic accuracy,which provides a new idea for online monitoring research of power internet of things equipment.展开更多
基金This work was supported by the National Key Research andDevelopment Program of China(No.2018YFA0703000)the National Natural Science Foundation of China(Nos.T2121004,52235007,and 82203602)+2 种基金Zhejiang Provincial Natural Science Foundation of China under Grant No.LQ22H160020 to JWThis work was also supported by Start-up Funding of Zhejiang Provincial People’s Hospital(No.ZRY2021A001 to JW)Basic Scientific Research Funds of Department of Education of Zhejiang Province(No.KYQN202109 to JW).
文摘Prosthesis implantation and fat transplantation are common breast reconstructionmethods.In general,prosthesis implantation alone does not achieve a realistic enough appearance,and fat transplantation alone is difficult to achieve in the correct capacity.To date,no reports have focused on methods of combining fat with implanted prostheses for breast reconstruction.Using a newly designed bionic ink(i.e.,polyether F127 diacrylate(F127DA)&poly(ethylene glycol)diacrylate(PEGDA))and projection-based three-dimensional bioprinting(PBP),we report the development of a new method for printing porous prostheses.PEGDA was used to improve the printing precision of the prosthesis by increasing the gel point of F127DA and reducing the impact of external temperature.The compression modulus of the printed prosthesis was very close to that of prostheses currently used in clinical practice and to that of natural breasts.Finally,stromal vascular fraction gel(SVF-gel),a human fat extract,was injected into the pores of the synthesized prostheses to prepare a prosthesis mixed with adipose tissue.These were implanted subcutaneously in nude mice to observe their biological performance.After 14 and 28 days of observation,the prosthesis showed good biocompatibility,and adipose tissues grew well in and around the prosthesis.This result shows that a porous prosthesis containing pre-placed adipose tissues is a promising breast reconstruction material.
基金The authors gratefully acknowledge the financial support provided by National Science and Tech-nology Support Program(31160250,61178036 and 21265006)Ganpo excellence project 555 Talent Plan of Jiangxi Province(2011-64)Center of Photoelectric Detection Technology Engineering of Jiangxi Province(2012-155).
文摘Mn co-precipitation method combined with Raman spectroscopy were used to detenmine trace heavy metals(copper,zinc,cadmium and lead)in water sample.Different concentrations of heavy metals including copper,zinc,cadmiun and lead in water samples were separated and enriched by Mn^(2+)-phen SCN-ternary complex 0o-precipitation procedure.The Raman spectra of co-precipitation sediments were collected using confocal micro-Raman spectrometry.Different preprocessing treatments and regression calibration methods were compared.The best models using partial least squares regression(PLS)of copper,zinc,cadmium and lead were built with a correlation cofficient of prediction(R_(p))of 0.979,0.964,0.956 and 0972,respectively,and the root mean square error of prediction(RMSEP)of 6.587,9.046,9.998 and 7.751 pug/kg,respectively.The co-precipitation procedure combined with Raman spectroscopy method are feasible to detect the amount of heavy metals in water.
基金supported by National Science and Technology Support Program of China (31160250,61178036)Ganpo excellence project 555 Talent Plan of Jiangxi Province (2011-64)Center of Photoelctric Detection Technology Engineering of Jiangxi Province (2012-155).
文摘The potential of Confocal micro Raman spectroscopy in the quantitative analysis of pesticide(Chlorpyrifos,Omethoate)residues on orange surface is investigated in this work.Quantitative analysis models were established by partial least squares(PLS)using different preprocessing methods(Smoothing,First derivative,MSC,Baseline)for pesticide residues.For pesticide resi-dues,the higher correlation coefficients(r)is 0.972 and 0.943,the root mean square error of prediction(RMSEP)is 2.05%and 2.36%,respectively.It is therefore clear that Confocal micro-Raman spectroscopy techniques enable rapid,nondestructive and reliable measurements,so Raman spectrometry appears to be a prormising tool for pesticide residues.
基金support provided by National Natural Science Foundation of China (60844007,61178036,21265006)National Science and Technology Support Plan (2008BAD96B04)+1 种基金Special Science and Technology Support Program for Foreign Science and Technology Cooperation Plan (2009BHB15200)Technological expertise and academic leaders training plan of Jiangxi Province (2009DD00700)。
文摘Variable selection is applied widely for visible-near infrared(Vis-NIR)spectroscopy analysis of internal quality in fruits.Different spectral variable selection methods were compared for online quantitative analysis of soluble solids content(SSC)in navel oranges.Moving window partial least squares(MW-PLS),Monte Carlo uninformative variables elimination(MC-UVE)and wavelet transform(WT)combined with the MC-UVE method were used to select the spectral variables and develop the calibration models of online analysis of SSC in navel oranges.The performances of these methods were compared for modeling the Vis NIR data sets of navel orange samples.Results show that the WT-MC-UVE methods gave better calibration models with the higher correlation cofficient(r)of 0.89 and lower root mean square error of prediction(RMSEP)of 0.54 at 5 fruits per second.It concluded that Vis NIR spectroscopy coupled with WT-MC-UVE may be a fast and efective tool for online quantitative analysis of SSC in navel oranges.
基金the financial support provided by the National Natural Science Foundation of China(No.12103019)National Science and Technology Award Backup Project Cultivation Plan(No.20192AEI91007),China。
文摘Background and objectives Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats.Skin defects lead to the loquat being easily destroyed during transportation and storage,which causes the risk of other loquats being infected,affecting the selling price.Materials and Methods In this paper,a method combining band radio image with an improved three-phase level set segmentation algorithm(ITPLSSM)is proposed to achieve high accuracy,rapid,and non-destructive detection of skin defects of loquats.Principal component analysis(PCA)was used to find the characteristic wavelength and PC images to distinguish four types of skin defects.The best band ratio image based on characteristic wavelength was determined.Results The band ratio image(Q782/944)based on PC2 image is the best segmented image.Based on pseudo-color image enhancement,morphological processing,and local clustering criteria,the band ratio image(Q782/944)has better contrast between defective and normal areas in loquat.Finally,the ITPLSSM was used to segment the processing band ratio image(Q782/944),with an accuracy of 95.28%.Conclusions The proposed ITPLSSM method is effective in distinguishing four types of skin defects.Meanwhile,it also effectively segments images with intensity inhomogeneities.
基金the National Natural Science Foundation of China(No.31760344)the Science and Technology Research Project of Education Department of Jiangxi Province(No.GJJ200615),China。
文摘The temperature difference of fruit itself will affect its near infrared spectrum and the accuracy of its soluble solids content(SSC)prediction model.To eliminate the influence of apple temperature difference on the SSC model,a diffuse transmission dynamic online detection device was used to collect the spectral data of apples at different temperatures,and four methods were used to establish partial least squares correction models:global correction,orthogonal signal processing,generalized least squares weighting and external parameter orthogonal(EPO).The results show that the temperature has a strong influence on the diffuse transmission spectrum of apples.The 20ºC model can get a satisfactory prediction result when the temperature is constant,and there will be great errors when detecting samples at other temperatures.The effect of temperature must be corrected to establish a more general model.These methods all improve the accuracy of the model,with the EPO method giving the best results;the prediction set correlation coefficient is 0.947,the root mean square error of prediction is 0.489%,and the prediction bias is 0.009%.The research results are of great significance to the practical application of SSC prediction of fruits in sorting workshops or orchards.
基金The research was financially supported by Co-Innovation Center of the Intelligent Management and Equipment for Orchard on the Hilly Land in south China(JX2014XCHJ02).
文摘An orchard-lifting platform is a type of mechanical equipment to assist growers in fruit picking,fruit tree pruning,flower thinning,and other operations.In its operational processes,the tilting stability directly affects the operational safety and adaptability under complex terrain conditions,while critical tilting angle is an important criterion to evaluate the tilting stability.Based on the structure and the operating characteristics of the three degree of freedom(3-DOF)lifting platform for hilly orchards,the tilting stability was analyzed in different parked states,and the theoretical expressions of critical tilting angle were obtained;in the theoretical expressions,the influencing factors on tilting stability were determined as the parked positionβ1,the manned worktable rotary positionβ2,the lifting height h,and the load m.Based on the multi-body dynamics principle,the tilting stability simulation was carried out.The relative error of tilting angles was approximately 4.6%between simulation and tilting verification experiment,which indicated that the results of tilting stability simulation were reliable.Therefore,the multi-body dynamics simulation was used for further clarifying the influencing factors on tilting stability.A virtual orthogonal test was designed,and the results showed that critical tilting angle ranged from 20°to 44°when the factors were at different values,which indicated that the 3-DOF lifting platform for hilly orchards had a high tilting stability performance and could adapt to the operating conditions of hills with slope angles from 5°to 20°.The results of the range analysis and ANOVA showed that the influence intensity of factors on tilting stability wasβ1>h>m>β2;at the same time,β1,h,and m exerted significant effect on tilting stability.The tilting stability first decreased and then either increased or decreased with the increasing lifting height;it gradually decreased with the increasing load.It also showed that the position of the manned worktable along the slope down always had the lowest tilting stability.This research can provide a theoretical basis and reference for the analysis of tilting stability of the lifting machinery for hilly orchards.
基金support of National 863 Program(SS2012AA101306)“the 12th Five-Year Plan”,Jiangxi Advantageous Science and Technology Innovation Team Construction Plan(20153BCB24002)+2 种基金Collaborative Innovation Center Project of Intelligent Management Technology and Equipment for Southern Mountain Orchards(G.J.G.Z.[2014]No.60)National Natural Science Foundation of China(2002017018,51805474)the China Postdoctoral Science Foundation(Grant No.2019T120509).
文摘As photocrosslinkable materials,methacryloyl-modified hydrogels are widely used as bioinks in tissue engineering.Existing printing methods to use these hydrogels,including changing the viscosity of the material or mixing them with other printing components,have been explored,but their application has been limited due to low printing quality or high cost.In addition,the complex operation of bulky equipment restricts the application of these existing printing methods.This study presents a lightweight stereolithography-based three-dimensional(3D)bioprinting system with a smart mechanical and structural design.The developed bioprinter dimensions were 300 mm×300 mm×200 mm and it can be placed on a benchtop.The equipment has a mini bioink chamber to store a small amount of bioink for each printing.We systematically investigated the point-by-point curing process in the 3D bioprinting method,which can print mixed cells accurately and have good biocompatibility.Here,we provide a compact,low-cost stereolithography bioprinting system with excellent biocompatibility for 3D bioprinting with methacryloyl-modified hydrogels.It can be potentially used for drug screening,studying pathological mechanisms,and constructing biological disease models.
基金This project was supported by the National Natural Science Foundation of China(Grant No.51805271)Jiangsu Agricultural Science and Technology Innovation Fund(CX181007)and Fundamental Research Funds for the Central Universities(KYYJ201805).
文摘In order to solve the problem of poor traveling stability and excessive pesticide application during plant protection operations in hilly orchards,a novel crawler-type multi-channel air-assisted sprayer that is particularly appropriate for hilly orchards was designed in this study.Considering anti-rolling requirements and the orchard environment in hilly areas,this study selected limits for uphill and downhill rolling angles as well as the transverse rolling angle as the evaluation indexes for determining both the layout and parameter settings of the sprayer.According to freely submerged jets and the requirements in plant protection operation,a multi-channel air-assisted system was developed.The test results showed that the anti-rolling performance and the designed air-assisted system were adequate.At 2 m from the longitudinal center plane of the sprayer,the airflow exhibited wavy distribution patterns under different parameter combinations since the four streams of the airflow were not thoroughly intersected and mixed.At 3 m from the longitudinal center plane of the sprayer,the jet was ejected at great velocity but underwent rapid attenuation;the airflow velocity in most areas barely satisfied the requirements for plant protection operation.In addition,different air outlet layout schemes led to significant differences in the spatial distribution of the airflow field.Compared with a traditional air-assisted sprayer,using the developed multi-channel air-assisted sprayer enhanced the droplet coverage uniformity by 19.4%,and the mean droplet deposition in the front,middle,and rear of the canopy was enhanced by 32.9%,50.3%,and 78.1%,respectively,while reducing ground deposition and air drift by 26.8%.
基金supported by the Natural Science Foundation of China(52167008)Outstanding Youth Fund Project of Jiangxi Natural Science Foundation(20202ACBL214021)+1 种基金Key Research and Development Plan of Jiangxi Province(20202BBGL73098)Science and Technology Project of Education Department of Jiangxi Province(GJJ210650)。
文摘Aiming at the problems of traditional centralized cloud computing which occupies large computing resources and creates high latency,this paper proposes a fault detection scheme for insulator self-explosion based on edge computing and DL(deep learning).In order to solve the high amount of computation brought by the deep neural network and meet the limited computing resources at the edge,a lightweight SSD(Single Shot MultiBox Detector)target recognition network is designed at the edge,which adopts the MobileNets network to replace VGG16 network in the original model to reduce redundant computing.In the cloud,three detection algorithms(Faster-RCNN,Retinanet,YOLOv3)with obvious differences in detection performance are selected to obtain the coordinates and confidence of the insulator self-explosion area,and then the self-explosion fault detection of the overhead transmission line is realized by a novel multimodel fusion algorithm.The experimental results show that the proposed scheme can effectively reduce the amount of uploaded data,and the average recognition accuracy of the cloud is 95.75%.In addition,it only increases the power consumption of edge devices by about 25.6W/h in their working state.Compared with the existing online monitoring technology of insulator selfexplosion at home and abroad,the proposed scheme has the advantages of low transmission delay,low communication cost and high diagnostic accuracy,which provides a new idea for online monitoring research of power internet of things equipment.