108results about How to "Strong subjectivity" patented technology

The invention provides a solar silicon wafer defect detecting system. The solar silicon wafer defect detecting system comprises a visual image acquisition system, an image processing system and a sorting system; the visual image acquisition system is used for automatically acquiring images of silicon wafers on an automatic silicon wafer production line; the image processing system is used for analyzing the acquired silicon wafer images, automatically identifying the silicon wafer images and sending identification signals to the sorting system; and the sorting system is used for executing the signals of the image processing system, sorting out defective silicon wafers and sorting the silicon wafers with the same defects into same sorting boxes to realize accurate sorting of the silicon wafers. The invention also provides a detecting method based on the solar silicon wafer defect detecting system disclosed by the invention; the silicon wafers can be conveyed rapidly and rapid defect detection of the silicon wafer images can be carried out; and a high-speed and high-precision visual detection requirement of the production line can be met.

The invention provides an X-ray film bone age prediction method and system based on deep learning. According to the invention, a bone age prediction result is finally formed through performing preprocessing on an X-ray image of a teenager, automatic segmentation of a hand bone area and bone age prediction. The method comprises a hand bone X-ray film preprocessing and sample data enhancement method, a hand bone X-ray film image block sampling method, a hand bone automatic segmentation algorithm and a transfer learning based hand bone X-ray film bone age assessment algorithm, and finally designsa hand bone X-ray film bone age prediction system taking Dicom data as input. Users only need to select a hand bone X-ray film with the bone age to be predicted, the segmentation and prediction process is completely automatic, and doctors are not required to perform region marking or selecting, and a powerful tool is provided for bone age assessment in scientific research and clinical practice.

The invention relates to an expressway overtaking behavior decision making method applied to an automatic drive vehicle. The method includes the following steps that S1, an overtaking intention model is established; S2, whether an overtaking intention is generated or not is judged; S3, if yes, S3 is executed, and if not, a lane keeping state continues to be kept; S3, whether overtaking conditions are met or not is judged, if yes, S4 is executed, and if not, the lane keeping state continues to be kept; S4, the vehicle gets into an overtaking sub-state. The overtaking intention is generated through an artificial neural network algorithm, and then judgment is carried out through safety, comfort and other conditions based on rules. The problems about whether it is necessary to carry out overtaking and whether overtaking succeeds or not are solved, the objective rules of the overtaking process are reflected, the subjective factors of the overtaking behavior are fully considered, and automatic drive shows the drive habits of human beings under the condition of guaranteeing overtaking safety, comfort and the like.

The invention discloses a geological survey method of a tunnel face based on a digital image. The geological survey method comprises the following steps of: A, confirming a target object and marking the tunnel face; B, photographing to the tunnel face by using a high-resolution digital camera to shoot a complete tunnel face region; C, calculating the proportion conversion coefficient of a real object and an image according to the distance of two marking points on the tunnel face and the pixel value of two points in the image; D, performing grey level transformation, color equalization, brightness / contrast adjustment, hue / saturation control and image filtering to logarithms; E, calculating all pixels in the digital image; F, calculating extended length of structural surface, total extension of unit area crack, linear fit of structural surface, viewing dip angle of structural surface and space structural surface parameter of structural surface by the binary image of the structural surface to obtain geological survey achievements of the tunnel face. The geologic sketch map of the tunnel face is obtained by the method, so that the geological sketch speed and the geological survey precision and accuracy are improved.

The invention belongs to the technical field of the quantitative statistical distribution analysis of characteristic chromatograms of microstructures and precipitated phases in metal materials, and relates to a full-view-field quantitative statistical distribution representation method of precipitated phase particles in a metal material. The method comprises the following steps of electrolytic corrosion of a metallic material sample, automatic collection of a characteristic chromatogram of a metallurgical structure, automatic splicing and fusion of the characteristic chromatograms of full-view-field metallurgical structures, automatic identification and segmentation of the precipitated phase particles and quantitative distribution representation of the large-range full-view-field precipitated phase particles. According to the full-view-field quantitative statistical distribution representation method, through establishing a mathematic model, the automatic splicing and fusion of the characteristic chromatograms of the full-view-field large-area metallurgical structures in a characteristic region and the automatic segmentation and identification of the precipitated phase particles are realized; the quantitative statistical distribution representation information of the full-view-field morphology, quantity, size, distribution and the like of plentiful precipitated phases in a larger range is quickly obtained, and the method has the features of being accurate and high-efficiency and large in quantitative distribution representation information quantity, and has much more statistical representativeness compared with conventional single-view-field quantitative image analysis.

The invention discloses an energy efficiency combination evaluation method of a machine tool product manufacture system. The method comprises the following steps: firstly, establishing a three-layer energy efficiency management evaluation index system of the comprehensive evaluation of machine tool product manufacture from an energy resource angle; then, establishing a mathematical model of the dynamic evaluation of the energy efficiency of the machine tool product manufacture; and finally, combining an analytic hierarchy process, a grey correlation method and a fuzzy comprehensive evaluation method to evaluate the manufacture energy efficiency by aiming at the mathematical model. On the basis of the statistical data of energy utilization and historical and current production data, the energy consumption of each hierarchy of the manufacture system is comprehensively considered mainly by aiming at the collection of a wireless sensor technology, a network technology and the like, qualitative analysis and quantitative analysis are effectively combined, subjectivity and uncertainty in an enterprise energy efficiency evaluation process are favorably avoided, and the systematicness and the reasonability of an evaluation result are effectively guaranteed.

A classification method and system for documents containing text sentences and images having meta-data. The classification method and system categorizes document sentences into subjective and non-subjective sentences and categorizes document images into descriptive and non-descriptive. The categorization is further used to calculate subjectivity and descriptive-images classification of a document. This classification system can be used by a web search engine to filter, sort or tag a set of document references based on user selection.

The invention provides a failure analysis method and device based on a power communication network. The method comprises the following steps: acquiring history data of failures to be analyzed in the power communication network, and acquiring a failure cause type set corresponding to generated failures, wherein each cause type comprises at least one cause factor; calculating cause probabilities corresponding to the cause factors in the cause types, acquiring weights corresponding to the cause factors according to the probabilities, and acquiring failure probabilities corresponding to the cause types according to the acquired weights corresponding to the cause factors; calculating the probabilities of the failures to be analyzed according to the failure probabilities corresponding to the cause types; and if the probabilities of the failures to be analyzed are greater than a first preset threshold, performing troubleshooting in sequence from large to small according to the failure probabilities corresponding to the cause types and the weights corresponding the cause factors in the cause types.

The invention discloses an automatic bone age identification system based on an improved residual network, and aims at solving the problem that an automatic deep learning processing means lacks in bone age detection via X ray photos domestically. The method comprises that data enhancement is carried out on a training sample, normalization is carried out, a bone age classification network based onthe improved residual error network is trained, 16 different slide windows are used during test, 16 classification results are predicted, and a classification of highest frequency is obtained.

The embodiment of the application discloses a method and a device for risk identification. The method comprises the following steps: monitoring and obtaining payment data corresponding to a current payment operation; obtaining historical payment data of a related account of the current payment operation; determining each payment dimension of the payment data and the historical payment data; determining a difference between the payment data and the historical payment data in each payment dimension, and performing risk identification on the current payment operation according to the difference.By the method, the deviation between the current payment operation and the original payment habit can be determined according to the difference between the payment data of the current payment operation and the historical payment data of the related account under different payment dimensions without relying on the black-and-white sample as the basis for risk identification.

The invention discloses a method for comprehensively evaluating a regional abrupt environmental pollution accident risk. The method comprises the following steps: building a multilayer evaluation index system for the regional environmental pollution accident risk; building a risk source dangerousness quantitative model, a receptor sensitivity quantitative model and a restoring force quantitative model by using an objective weighting method, and acquiring risk source dangerousness indexes, receptor sensitivity indexes and restoring force indexes of different study units in a study region; building an environmental risk receptor vulnerability evaluation concept model and a regional abrupt environmental pollution accident comprehensive risk evaluation concept model, and calculating an environmental risk receptor vulnerability index and a regional environmental pollution accident comprehensive risk index according to the concept models, the risk source dangerousness indexes, the receptor sensitivity indexes and the restoring force indexes; and hierarchically clustering comprehensive environmental risk profiles of evaluation units. Through adoption of the method, a scientific theoretical foundation is laid for regional environmental risk comprehensive management, industrial distribution adjustment and optimization, accident emergency and the like. The method has the advantages of high efficiency, low cost, high accuracy and the like.

The invention relates to a GA-BP neural network algorithm-based city ecological construction evaluation method and belongs to the field of smart city ecological construction. The method comprises thefollowing steps of constructing a city ecological evaluation index system; generating neural network training and test samples; determining a topological structure of a neural network; setting relatedparameters of neural network training; optimizing initial weight and threshold of the neural network by utilizing a genetic algorithm; and inputting the training and test samples for training and checking the GA-BP neural network to finally build a GA-BP neural network algorithm-based city ecological evaluation model. The method can realize a city ecological construction evaluation function and has relatively high scientificity, validity and practicality.

The invention discloses a lower limb movement ability evaluation method based on an improved convolutional neural network. The method comprises the following steps: obtaining gait video images and human skeleton joint position information in the gait process of a subject; generating depth data for the gait video image and carrying out binarization processing through a bilateral filtering method soas to obtain a gait contour image; calculating a knee joint angle by using a space vector method; extracting gait contour features of the gait contour image by using an improved convolutional neuralnetwork; connecting the gait contour features and knee joint angles in series, performing normalization, performing feature dimension reduction on the features by using a kernel principal component analysis method, establishing a lower limb athletic ability evaluation index, and performing lower limb athletic ability evaluation on the subject. According to the method, the video image features areautomatically extracted by using the improved convolutional neural network in which the space pyramid pooling layer and the COCOB optimization algorithm are added in the traditional convolutional neural network, so that the complexity is greatly reduced, and the evaluation accuracy is improved.

The invention provides an automatic measuring method and device for the volume change of a skeletal muscle. The device includes a data acquisition module, an image preprocessing module, a measurement module and a quantitative evaluation module, wherein the data acquisition module is combined with ultrasonic imaging equipment and collects a skeletal muscle cross-sectional ultrasound image, the image preprocessing module is used for reducing big speckle noise in the ultrasound image and enhancing the interest region contour of the image, the measurement module is used for extracting the interest region contour of the preprocessed ultrasound image, and the quantitative evaluation module is used for the quantitative analysis of the automatically extracted regional contour. The method and the device can automatically measure the volume change of the skeletal muscle, and have important clinical application value, for example, and a quantitative basis can be provided for the clinical diagnosis and rehabilitation evaluation of patients with sarcopenia.

The present invention relates to a method for evaluating a health index of a distribution transformer. The method comprises: (1) acquiring a characteristic quantity xi which represents a health status of the distribution transformer, wherein i belongs to [1, m], and m represents the number of the characteristic quantity; (2) establishing a health index evaluation model of the distribution transformer; and (3) determining a horizontal position evaluated value of the health index evaluation model and a weight coefficient estimated value beta i* corresponding to the characteristic quantity by adopting a least squares method; and (4) determining the reasonability of the health index evaluation model by adopting a Hosmer-Lemeshow goodness-of-fit index. The method provided by the present invention adopts a logistic regression analysis method to perform a fitting of the health index of an oil-immersed distribution transformer, can obtain an accurate health status evaluation result via a smaller key characteristic quantity, and can provide essential means and tool for advanced asset management.

The present invention provides a concrete dam silo surface vibrating task assignment method. The method comprises the following steps: collecting and sorting data for parameters involved in establishing a judgment rule and a simulation model; establishing a production judgment rule; establishing a decision function with an objective function to satisfy the shortest construction period, wherein thedecision function needs to satisfy the constraint condition; establishing a simulation model of the silo surface vibrating task assignment; and through the above steps, assigning silo surface vibrating tasks including mechanical construction main body and manual construction main body optimization. According to the method provided by the present invention, the configuration of the silo surface construction machinery and the vibrating workers can be guided, the vibrating machinery and the manual vibrating area can be reasonably divided, a favorable reference is provided for the mechanical andmanual configuration, the method is also a precondition for realizing the intelligent task assignment in the future, damage caused by the vibrating machinery to other construction components due to unreasonable task assignment is avoided, and the construction safety is improved.

The invention provides a detection and recognition device for sprayed codes on the cylindrical surfaces of copper rings. The detection and recognition device comprises an industrial display screen, a left conveying belt mechanism, a servo sliding table mechanism, a right conveying belt mechanism, an industrial computer, an article grasping clamping air cylinder, an image collecting mechanism, light source equipment, a rejected product receiving box, a qualified product receiving box, a removing mechanism and a rotating mechanism. According to the detection and recognition device for sprayed codes on the cylindrical surfaces of copper rings, the machine vision technology is adopted to detect and recognize sprayed code character information on the cylindrical surfaces of copper rings, and the defects of low precision, high subjectivity, low judgment efficiency, high missed detection rate and false detection rate and the like of traditional manual detection are overcome; the automation degree is high, and automatic recognition and automatic sorting of sprayed codes on the cylindrical surfaces of copper rings can be completed. The invention further provides a detection and recognition method for sprayed codes on the cylindrical surfaces of copper rings. By means of the detection and recognition method, irregular sprayed code information on the cylindrical surfaces of copper rings on a production line can be continuously and automatically collected and distinguished, and the detection and recognition method is especially suitable for handling recognition of fuzzy and irregularly-shaped characters on the cylindrical surfaces and is high in detection and recognition rate.

A cleaning device for a fan coil unit. The invention belongs to the field of fan coil cleaning. The purpose of the present invention is to provide a cleaning device for fan coils, which can automatically clean the fan coils and ensure the cleanliness of the air from the fan coils. The device of the present invention is composed of coil pipe, nozzle array pipe, nozzle, conveying pipeline, compressor, suction pipeline, water suction pipeline, water pump, detergent storage tank, controller, dirt detection device, motor, transmission mechanism, slider, guide Rod, valve one, valve two, brush rod, volute one, volute two, air outlet blade, air outlet blade adjustment device, groove and hair brush. The invention utilizes high-pressure air flow washing, brush contact wiping and cleaning, and detergent atomization and spraying technologies, and uses the electric signal loop of the controller to control and adjust the equipment, thereby realizing automatic cleaning of the fan coil unit and ensuring efficient dust removal and cleaning. Sterilize. The invention is suitable for the heating and cooling system of the terminal wind disk.

Autocorrelation coefficients for three dimensions defined by the horizontal direction, the vertical direction, and the time direction of evaluation target moving image data are acquired. A plurality of noise amounts are calculated by executing frequency analysis of the acquired autocorrelation coefficients for the three dimensions and multiplying each frequency analysis result by a visual response function representing the visual characteristic of a spatial frequency or a time frequency. The product of the plurality of calculated noise amounts is calculated as the moving image noise evaluation value of the evaluation target moving image data.

The invention discloses a transformer bushing evaluation method, which fuses a plurality of indexes reflecting the state of a transformer bushing, comprehensively and comprehensively reflects the state of the bushing based on a fuzzy theory and a neural network algorithm, and introduces a variable weight and the neural network algorithm on the basis of fuzzy comprehensive evaluation. According tothe fuzzy control method, the limitation of conventional weight and the subjectivity of artificially determining the membership function are overcome, and the self-updating and self-adaption of the membership function are realized through neural network training, so that the fuzzy control has certain self-learning capability, and the evaluation result is more reliable.

The invention discloses a grouping method in a wind power plant based on extreme gradient dynamic density clustering, and the method comprises the steps: selecting indexes of grouping in the wind power plant, and carrying out the abnormal value detection and truncation of corresponding index data in a certain time period; for the preprocessed grouping index data, carrying out dimension reduction selection on the grouping index data by adopting XGBoost; and carrying out cluster division on the selected index data on the basis of DBSCAN-DTW clustering. According to the method, the problem of partial missing of actual wind power plant data can be effectively solved, and the model accuracy is improved; and the method is used for processing the multi-dimensional time sequence characteristic operation data of the fan, so that accurate and effective division of the groups in the wind power plant can be obtained.

The invention discloses a method for calculating the misalignment rate of an electric meter. The method comprises the following steps: S1, acquiring related data in a transformer area on line througha metering monitoring instrument; S2, according to the condition of the related data, determining a reference value, that is, the electric quantity of the transformer area, as the reference value, andcalculating the misalignment rate of each electric meter by utilizing the law of conservation of energy; S3, after the misalignment rate of each electric meter is obtained through calculation, conducting secondary screening on the misalignment electric meters according to misalignment reasons, and independently marking the electric meters which cannot be solely solved through meter replacement. According to the invention, online monitoring of all intelligent electric meter data is more accurate, the misalignment rate of each electric meter in the transformer area is obtained based on calculation of the data model, electric meter state evaluation is carried out according to the misalignment rate, and accurate meter replacement is completed.

A method for synthetically evaluate that quality of saltwater goose and a quality evaluation model construct by using the method are disclosed. The invention relates to a novel food evaluation method,in particular to a cooked salt water goose quality comprehensive evaluation method and a quality evaluation model constructed by using the method. A comprehensive evaluation method of saltwater goosequality suitable for industrial processing and a quality evaluation model based on the method are provided. At first, that L* value affect the appearance and texture of the salted goose is selected,a* value, b* value, shear force value, and unsaturated fatty acid C18: 1, that content of the unsaturate fatty acid C18: 2 is taken as the main index of the principal component analysis, and the coloris an indispensable index in evaluating the quality of the ripe saline goose. The correlation coefficient between the evaluation method of the invention and the traditional sensory evaluation can reach 0.960, and the method has extremely significant correlation (P (0.01)), and the reliability and applicability are improve.

The invention relates to an auxiliary decision-making method and system for urban rail transit network operation emergencies. The method comprises the steps: building simulation models through a digital twinning technology, and combining a plurality of simulation models to build a digital twinning rail transit network; according to historical passenger flow data of the urban rail transit network, data simulation and prediction are carried out, and emergency situations under possible situations are analyzed; deducing driving and passenger flow trends in the simulation model according to an emergency situation, establishing communication between the urban rail transit system and the digital twin simulation system, and realizing real-time driving analysis and interaction of passenger flow data and analogue simulation data; and analyzing the harm degree and the development condition of the received emergencies, determining the early warning level, carrying out quantitative and qualitative evaluation on the effect after the implementation of the emergency treatment measures, and providing the simulation process and the result to the scheduling personnel of the network control center in the form of images and texts to assist the scheduling personnel to carry out strategy optimization.

The invention discloses an industrial equipment health state evaluation method. The method includes: performing importance weight grade evaluation of occurrence frequency, influence degree and undetectability on n fault modes by m members; acquiring evaluation results of each fault mode when the m members are influenced by each risk factor; acquiring evaluation results on importance of each risk factor by the m members; acquiring risk priority number so as to acquire an industrial equipment health state evaluation result. The equipment health state evaluation method based on the fault mode risk priority number is established, health state of industrial equipment can be evaluated in a relatively accurate and scientific manner, specific grades can be given, the problem of high subjectivity in equipment state evaluation in daily production can be solved, and evaluation accuracy is improved.

The invention relates to a subject learning development recommendation system and a subject learning development recommendation method based on data driving. The subject learning development recommendation system comprises a mobile terminal and a computer. The recommendation system is run in the computer, and comprises a data acquisition module, a recommendation algorithm module, a visualization output module, and a recommendation database. The data acquisition module is used for score data acquisition, evaluation data acquisition, and physiological appraisal data acquisition. The recommendation algorithm module is used for recommendation index calculation, recommendation index analysis, subject analysis, and learning classification, and is used to generate recommendations. The visualization display module comprises a visualization population subject relation graph, an individual subject state diagram, and a personalization subject recommendation result. The subject learning development recommendation system and the subject learning development recommendation method are suitable for planning and guiding of high school student school work learning, and by adopting the data of various types and sources, individual subject superior characteristics are identified to form a personalized subject learning guiding scheme, and then subjects of a senior high school entrance examination and a college entrance examination are selected reasonably, and scientific performance and accuracy of school work planning are improved.

The invention discloses an objective weather typing method based on numerical statistics. The objective weather typing method based on numerical statistics comprises the following steps of: (1) downloading long-time global weather re-analysis data, and selecting 850 hPa height layer specific weather elements specific to time every day as determining factors; (2) before the weather is subjected to parting by using a computer, performing standardized calculation of the meteorological grid point data; (3) integrating and monitoring physical and chemical parameters of a heavy-load airship, an unmanned aerial vehicle and an airborne atmosphere; (4) calculating and selecting typical weather types of representative days; (5) calculating standard deviation indexes of the typical weather types of representative days and a certain day, and classifying all the weather types into one typical weather type; and (6) repeating the objective weather classification step to classify the weather types of the next week. The objective weather typing method is high in universality, timeliness and objectivity, and objective typing of long-term weather types in the past and weather typing forecasting of a week in the future can be achieved rapidly and accurately.

The invention discloses a subzero temperature-gust quick semi-unfreezing process of frozen platy meat products. The subzero temperature-gust quick semi-unfreezing process comprises the following steps: loading the frozen platy meat products on unfreezing racks, placing the unfreezing racks in a subzero temperature unfreezing room with the room temperature being not higher than -6 DEG C, monitoring the center temperature and the surface temperature of the meat products by setting four frozen meat products as references, and enabling the center temperature of the frozen platy meat products to be -8+ / -1 DEG C by taking the center temperatures and the surface temperatures of the references as control nodes of a gust opening / closing procedure and at the air speed of (3-6)+ / -0.9m / s during opening, so that the state of internal / external balanced semi-unfreezing is achieved under the subzero temperature-gust unfreezing condition that the center / surface temperature difference is 0.5-1.5 DEG C. The subzero temperature-gust semi-unfreezing process has the positive effects that 1, the frozen platy meat products can quickly achieve the unfreezing state needed for quickly-frozen prepared foods; 2, the center / surface temperature difference after semi-unfreezing is less and the internal / external unfreezing degree is balanced; 3, the subzero temperature-gust quick semi-unfreezing process can be applied to quick unfreezing of large batches of frozen meat products; and 4, the energy consumption of semi-unfreezing is less and the production cost cannot be greatly increased.

The invention discloses an AHP-TOPSIS-based penetration testing tool comprehensive evaluation method. The method comprises the following steps: 1) using an analytic hierarchy process to establish an evaluation scheme with a target layer, a criterion layer and a scheme layer, using a pairwise comparison method to carry out value assignment on the criterion layer and the scheme layer to construct apairwise matrix, and constituting a pairwise judgment matrix; 2) calculating a weight vector, and carrying out consistency checking; 3) carrying out hierarchical total sorting, wherein respective weight values of the criterion layer and the scheme layer are obtained, and calculation of sorting of relative importance of each scheme in the scheme layer on the target layer is carried out; 4) obtaining a weighting-standardized matrix, wherein a degree of influence of each scheme of the scheme layer relative to a single criterion of the criterion layer is used to construct a pairwise matrix, and weighting is carried out according to weights, which are obtained by total sorting, to obtain the weighting-standardized matrix P; 5) calculating Euclidean distance by TOPSIS, wherein a TOPSIS method isutilized to find a positive ideal solution and a negative ideal solution of the weighting-standardized matrix P; and 6) constructing a final judgment weighting matrix. The method has the characteristics of simplicity, easy realization, high flexibility and a high reference value.