10results about How to "Realize discovery" patented technology

The invention discloses a method for counting drill rods of underground drilling rigs based on computer vision, comprising the following steps: S1, obtaining drill rod image data, and dividing the drill rod image data into two types of data; S2, performing image enhancement processing on the two types of data; S3, adding Gaussian white noise of different proportions to each cleaned image; S4, locking a sample image into a 416*416 image after being read in, and each image area passes through Darknet; S5, performing classification and regression tasks on the image candidate frame and the center point, width and height of the candidate frame, and modifying the output setting of the classification task to 1; S6, minimizing the loss function through training, and outputting a plurality of detection candidate frames through the monitoring network; S7, taking the inspection frame with the largest confidence in the inspection frame as the input frame, calculating the IOU of the overlapping inspection frames in turn, filtering when the calculated IOU value is greater than the set threshold, and repeating step S7; S8, tracking and calculating the monitored target by using image classification, Kalman filtering algorithm and Hungarian algorithm.

The invention relates to a thermal power plant integrated energy system operation and maintenance regulation and control method based on a BP neural network, and the method comprises the steps: collecting the real-time data and load demands of at least one device in a thermal power plant integrated energy system; according to the real-time data, generating at least one piece of prediction data of a target steam quantity, a target fuel quantity and a target electric load; comparing the at least one piece of prediction data with the real-time data; according to the fault information, the at least one piece of prediction data, the real-time data and the load demand, regulating and controlling the operation of the integrated energy system; and regulating and controlling the integrated energy system according to the load fluctuation condition, the real-time data and the at least one piece of prediction data so as to generate a regulation and control scheme of the integrated energy system. Therefore, the problems that the prior art does not consider the problems of power generation hour reduction, insufficient profitability and the like mainly faced by a power plant in combination with an integrated energy system, prediction is carried out only by using a neural network model, the prediction accuracy is insufficient, and design is not made from the angle of operation and maintenance of the power plant are solved.

The invention relates to a self-organizing testing method, device and system, a storage medium and a program product. Comprising the following steps: determining corresponding equipment detection strategies according to different equipment types; the equipment types comprise network equipment, standard equipment, non-standard equipment and equipment which cannot be automatically identified; according to an equipment detection strategy, automatically discovering equipment, and instantiating a corresponding hardware operation entity object; establishing an operation resource list according to the hardware operation entity object; performing tree description on all resources in the operation resource list to obtain an equipment resource description tree; different grpc services are established according to different device descriptions, and a device resource description tree and RPC operation interface descriptions of a corresponding resource operation interface tree are provided for a client; and grpc is used as an interaction mode between the equipment server and the client, and an RPC operation interface is provided for all resources. Therefore, the protocol docking complexity can be reduced, and the requirement for flexibility of non-standard integrated circuit board testing is met.

The present invention discloses a lost flying object search and rescue method and system applied to flying objects, the method comprising: obtaining emergency call SSB configuration information and emergency PC I information of the accessed NR cell; the emergency call SSB configuration information is set according to the remaining SSB of the NR cell; if the network of the NR cell loses synchronization, the emergency PC I information is sent at a specified location according to the emergency call SSB configuration information; when the emergency PC I information is received by other normal flying objects, the other normal flying objects are notified to report the search and rescue information corresponding to the emergency PC I information to the search and rescue system. The present invention allows the lost flying object to send the emergency PC I information in the idle SSB resource area, and then the normally working flying object transmits the emergency PC I information back to the system, so as to realize the discovery of the faulty flying object without adding or modifying the communication system architecture of the NR cell.

The present invention discloses a one-button intelligent safety control system for coal-injection powder making in iron smelting, including a monitoring acquisition module, a communication transmission module, a data preprocessing and analysis module, an early warning transmission module, an execution unit and a user visualization interface, and the present invention relates to the technical field of coal-injection powder making safety control. The one-button intelligent safety control system for coal-injection powder making in iron smelting, by receiving data and implementing classification processing operations, establishes a simulation analysis model related to powder making and powder injection, and predicts the risk of the powder making process based on the oxygen content curve formed during powder making according to the data, and predicts the risk of the coal powder storage process based on the coal injection amount and the rate of the powder making amount, thereby realizing a one-button intelligent powder making control operation, which not only effectively improves the efficiency of powder making, but also can predict safety risks in advance, improve the fault tolerance rate in operation, and also can realize the discovery and solution of fault problems, and realize safe and intelligent powder making control operation.

The present application relates to a kind of metabolic pathway extension network based on structural feature automatical establishment method, belong to bioinformatics and computational chemistry technical field.The purpose is to solve the problem of existing KEGG database incomplete, annotation lag of metabolite.Method includes: obtaining KEGG skeleton and modified group construction seed library;Through substructure matching and set difference calculation to determine the attribution of derivative;Iterative expansion forms structure association set;Combining stereochemistry rule and mass difference verification screening derivative;Merging KEGG reaction and extended relationship constructs network, and remove redundant path by graph theory method, finally output extended pathway network.The method greatly improves the annotation rate of metabolite pathway, supports in-depth functional analysis of metabolomics data.

The application relates to a method for discovering associated nodes of a springboard node. By analyzing the flow data of the springboard node in a botnet, nodes with highly similar behaviors are discovered from the nodes connected to the springboard node, thereby discovering multiple associated nodes belonging to the same botnet, positioning the C&C server node possibly at the upper level, and providing help for subsequent trace analysis, discovery and prevention of botnet threats. The application can extract important features representing the behaviors of network nodes through analysis of network flow data, input the features into a well-constructed program after pretreatment, complete the discovery of nodes with similar behaviors, and output the results. By drawing a flow curve of the communication between highly suspicious nodes and the springboard node and visually displaying the flow curve, the upper and lower control relationship of the suspicious IP pair is further verified, and the discovery of associated nodes of the same botnet and attack prevention are realized.

The invention discloses an iron-making coal injection one-key pulverizing intelligent safety control system, which comprises a monitoring acquisition module, a communication transmission module, a data preprocessing and analysis module, an early warning transmission module, an execution unit and a user visual interface, and relates to the technical field of coal injection pulverizing safety control. According to the one-key pulverizing intelligent safety control system for iron-making coal injection, by receiving data and realizing classified processing operation, a simulation analysis model related to pulverizing and powder injection is established, and the risk of the pulverizing process is predicted by forming an oxygen content curve during pulverizing according to the data; according to the coal injection amount and the pulverization amount rate, the risk of the pulverized coal storage process is predicted, so that one-button intelligent pulverization control operation is achieved, the pulverization efficiency is effectively improved, the safety risk can be predicted in advance, the error-tolerant rate in the operation is improved, meanwhile, fault problems can be found, solved and processed, and the safety of the pulverization process is improved. And safe and intelligent powder preparation control operation is realized.

The present application discloses a temperature curve splicing method and system for an ultra-long string of disc-shaped suspension porcelain insulators, belonging to the technical field of power transmission lines; the method comprises: obtaining a first infrared image and a second infrared image corresponding to a first target position and a second target position in an ultra-long string of disc-shaped suspension porcelain insulators; preprocessing the first infrared image and the second infrared image to obtain a first binary image and a second binary image corresponding thereto; obtaining a corresponding first temperature curve and a second temperature curve; optimizing the first temperature curve and the second temperature curve to obtain a corresponding first optimized temperature curve and a second optimized temperature curve; calculating a splicing point between the first optimized temperature curve and the second optimized temperature curve according to a window variance algorithm, so as to splice the first optimized temperature curve and the second optimized temperature curve according to the splicing point; finding the splicing point by using the window variance algorithm, so as to make the spliced ​​temperature curve more accurate.

The invention provides a local area network subnet vulnerability processing method, storage medium and system, and the method comprises the following steps: judging whether a hidden subnet exists in a local area network or not according to the feature difference of different protocols in network traffic; if the hidden subnet exists in the local area network, identifying the hidden subnet by adopting a flow analysis method; according to the identified network address information of the hidden subnet, implanting an agent program of a vulnerability scanner into the hidden subnet; the vulnerability scanner performs vulnerability scanning on assets in the hidden subnet according to the asset information to obtain vulnerability information existing in the hidden subnet; according to the vulnerability information, judging whether a vulnerability exists in the hidden subnet or not; and counting and classifying all vulnerabilities in the hidden subnet, and if the security risk level of the vulnerabilities meets a triggering condition, triggering a preset security policy, and processing the vulnerabilities existing in the hidden subnet. According to the method, the service continuity can be ensured, and meanwhile, comprehensive discovery, evaluation and security reinforcement of the hidden subnet can be realized.