44results about How to "Reliable basis for decision-making" patented technology

The invention discloses an abnormal / fault positioning detection method based on a binomial tree model. The method comprises the steps of firstly, converting the physical layout of an industrial pipe network into the binomial tree structural model, and storing the detected data into corresponding nodes of a binomial tree; secondly, according to the character of the binomial tree and the relevance between information of the detection nodes, and utilizing the flow conservation property of the data flow of the industrial pipe network for achieving computation of the data flow of nodes of sensors not to be deployed; thirdly, according to the relation between the actual measuring value of the deployed sensors of the detection nodes of the industrial pipe network and the computation value, analyzing the operation condition of the industry, and judging the abnormal / fault types; finally, utilizing the structure characteristics of the binomial tree model for analyzing the abnormal / fault positions of the industrial pipe network and giving an alarm. According to the method, the design is simple, the cost is low, abnormal / fault detection by a traditional artificial tour gauging method is broken through, and the real-time detection on the working condition of the industrial pipe network in a real time mode under the limiting situations of the detection nodes is achieved.

The invention discloses a distribution network optimization accurate analysis method and system based on deep learning. The method comprises the steps: building a distribution network equipment standing book system, and recording the capacity and load information of a transformer substation, a distribution line and a branch line through the system; Establishing a distribution network topological structure model, determining a connection relationship between the distribution network devices according to the distribution network data recorded in the distribution network device standing book system, and displaying the topological relationship of the distribution network in real time; According to the distribution network topology data generated by the distribution network topology structure model, displaying load data of the line, carrying out trial calculation on branches and node attributes of the topology, evaluating an equipment operation state according to a deep learning model, analyzing a load transfer magnitude and a current limiting value of the line, and planning a transfer path and a transfer load magnitude; And predicting and analyzing the load by using the neural networkmodel. According to the technical scheme of the invention, the management of the equipment ledger, the planning of the transfer path and the prediction of the load can be realized on the whole.

The invention provides a method for controlling the priming of the priming circuit of an electronic detonator. The method comprises a priming control process of the priming circuit of the electronic detonator on one hand and a priming control process of the electronic detonator on the other hand. Firstly, the priming device carries out pre-firing control process to the electronic detonator, sendsa pre-firing instruction to a detonator in an accurate condition, and places a pre-firing finish marker on the detonator after receiving pre-firing response information sent back by the detonator. Then, when the external priming cancelling information is received, the priming device enters an priming cancelling condition, sends a safe discharging instruction to the detonator, and places a pre-firing un-finish marker on the detonator; when receives external continuing priming information, the priming device enters a continuing priming condition, and carries out priming instruction sending process, and the detonator enters firing process as soon as a correct priming instruction is received. The technical scheme realizes the control over the synchronicity of the priming processes of the priming circuit of the electronic detonator, thereby improving the accuracy of priming intervals controlled by the priming circuit.

The invention discloses a vehicle trajectory prediction method and system based on video vehicle passing data. The method comprises the following steps: collecting vehicle passing data, and extractingeffective field information in the vehicle passing data; constructing a basic road network; sorting the vehicle passing data according to the sampling time to form a total travel chain of each vehicle in the sampling time period; extracting two adjacent sample sequences in turn, calculating the travel time of the vehicle passing through two adjacent intersections according to the sample sequences, judging that the two adjacent intersections are travel chain segmentation points, and segmenting the total travel chain into a series of sub-travel chains according to the travel chain segmentationpoints; calculating the steering state probability of each vehicle at each intersection according to the sub-travel chain to obtain a steering probability matrix; determining that the intersection corresponding to the maximum steering probability in the steering probability matrix is the intersection to be reached by the vehicle driving trajectory prediction. The invention avoids the shortcomingsof relying on continuous positioning data, so as to realize the travel behavior characteristic analysis of any vehicle.

The invention provides a scheduling method of disposable consumption emergency materials. The method includes the steps that the variety and the number of the emergency materials to be transported, various emergency material supply stations and an emergency point are determined; alternative transport road segments of the emergency materials to be transported are determined; required driving time of the road segments is calculated; various probable roads from a certain emergency material supply point to the emergency point are determined; road connectivity of the various probable roads from the certain emergency material supply point to the emergency point is determined; a comprehensive benefit optimization function of the roads is built; a comprehensive benefit optimization function value of the various probable roads from the certain emergency material supply point to the emergency point is calculated, and when comprehensive benefit optimization function value is minimum, the corresponding road is the optimal transport road from the emergency material supply point to the emergency point; a scheduling scheme of the emergency materials is acquired, and transport scheduling is conducted. The method combining multi-road optimization selection with material allocation is adopted, and then transport and allocation of the emergency materials can be effectively scheduled at special moments.

The invention discloses an airport security management system and a management method thereof. The system comprises at least one laptop or a personal computer (PC) terminal, a data memory, a data processing server, at least one hand-held terminal, a gateway, a relay and an Ethernet; the data processing server is electrically connected with the laptop, the PC terminal and the data memory and is connected with the hand-held terminal through a wireless communication unit; a camera, an image acquisition module and a global positioning system (GPS) positioning module are arranged on the hand-held terminal; and the data processing server is also sequentially connected with the gateway, the relay and the Ethernet electrically, and is used for reading and processing the information in the data memory and displaying and storing the processed information in the data memory. The airport security management system and the management method thereof have the advantages of real-time information reporting, accurate geographic location positioning, artificial form filling error avoidance, information state real-time control, high automation degree, resource conservation and the like.

The invention discloses a gridding automatic monitoring system integrating augmented reality and geographic information. The gridding automatic monitoring system comprises rear-end intelligent software and front-end sensing equipment (an intelligent lamp post and the like). The rear-end intelligent software mainly refers to a gridding automatic monitoring system integrating geographic informationand augmented reality. The front-end sensing equipment (intelligent lamp poles) is installed in different areas of a park and used for video security, miniature meteorological stations, information publishing, broadcasting and the like, the front-end sensing equipment (intelligent lamp poles) sends all data information to the management server, and the management server provides a function of remotely calling data for a user side. The gridding automatic monitoring system integrating geographic information and augmented reality has the functions of multi-parameter fusion early warning, in-parkvehicle monitoring and on-site video transmission. The system can be used remotely through a public wide area network and can also be used through a local area network, and a powerful guarantee is provided for lack of a public network environment in an emergency occasion. The gridding automatic monitoring system integrating geographic information and augmented reality can be applied to industrialparks of petroleum, chemical engineering and the like; according to the functions of automatic patrol, electronic boundary, forbidden zone alarm, unattended operation and the like, potential safety hazards can be rapidly recognized and automatic early warning can be achieved under the unattended operation condition, and powerful information support is provided for safety management and emergency rescue.

The invention relates to a full-process electronic operating system for inspecting the quality and safety of an air traffic control system and the inspection method thereof. The system consists of a first PC terminal, a first Ethernet network, a first relay apparatus, a first gateway, a data processing server, a data memory, a second PC terminal, a second Ethernet network, a second relay apparatus, a third PC terminal or at least one first laptop, a third relay apparatus, a third gateway, a fourth PC terminal, a fourth Ethernet network, a fourth relay apparatus, a fourth gateway, a fifth PC terminal, a fifth Ethernet network and a fifth relay apparatus. The system and the method have the advantages that: a clear and highly visual human-human interactive interface with complete user interfaces is provided for various users, and the distributed collaboration and interaction environment and the quality and safety inspection process are transparent; the organization management, process management, communication & coordination and collection & notification of process information of the quality and safety inspection work of the air traffic control system can be carried out electronically, and the objective of real-time monitoring of the inspection process is achieved.

The invention discloses an emergency command management system for a mine. A command and dispatch center station arranged on the ground is connected with underground command branches distributed in the mine through optical fibers so that before an accident occurrence or a security exercise, the command and dispatch center station can indicate a safe path through underground broadcasting and an LED information screen according to the accident cases and corresponding safety evacuation emergency plans prepared and saved in a emergency plan library, timely commands the underground workers to withdraw from the site effectively, and provides a reliable decision-making basis for rescue and relief work according to system records after a disaster.

The invention is applicable to the technical field of fire protection distribution, and provides a fire protection area distribution method, a device and a terminal device. The method comprises the following steps: obtaining fire protection sensing data of the fire protection area; Pre-processing the fire sensing data to obtain the eigenvalue of the information layer; The eigenvalue of informationlayer is fused to get the result of data fusion of information layer in sub-fire area. The data fusion results of the information layer of the sub-fire area are fused in the feature layer, and the data fusion results of the feature layer of the sub-fire area are obtained. The decision-making level data fusion is carried out on the feature level data fusion results of the sub-fire area, and the fire detection results about the fire area are obtained. The invention can determine whether a fire occurs or not, judge the fire coverage area and the harm degree, improve the fire identification ability, the detection ability and the anti-interference ability, reduce the misjudgment probability, and provide the reliable decision basis for the fire emergency management personnel through the multi-level data fusion of the fire protection sensing data.

The invention discloses a climbing lane traffic safety benefit calculation method based on inclination value matching, and relates to a climbing lane traffic safety benefit calculation method based oninclination value matching. The method aims to solve the problem that when a traditional regression method is used for analyzing the safety benefit of the climbing lane, due to the existence of sample selectivity deviation, the net influence of the climbing lane on traffic safety cannot be accurately obtained. The method comprises the following steps: 1, collecting, processing and organizing data, and determining samples of a control group and a control group; 2, constructing a tendency value model, and predicting tendency values of all samples; 3, sample matching based on the inclination value; 4, checking the balance of the confusion variable, if the confusion variable passes the check, executing the next step, otherwise, returning to the step 2; and 5, calculating the traffic safety benefit of the climbing lane. The method is used in the field of road traffic safety, and is especially suitable for analyzing the influence of a certain specific factor on traffic safety.

The invention provides a method for determining an acting range of a biogas gas guiding well of a municipal solid waste landfill, comprising the following steps of: drilling a plurality of gas guiding wells in the municipal solid waste landfill along the same straight line; selecting the two gas guiding wells to be respectively used as a gas pumping well and a detection well; if the pressure of the detection well is positive pressure, determining that the acting range of the gas guiding wells is less than the distance between the two wells; if the pressure of the detection well is negative pressure, determining that the acting range of the gas guiding wells is more than the distance between the two wells; selecting different gas guiding wells to be combined to gradually and accurately determine the acting range interval of the gas guiding wells; and when the pressure of the detection well is zero or weak negative pressure and the oxygen concentration is more than zero, determining that the distance between the detection well and the gas pumping well is the acting range of the gas guiding wells. According to the method for determining the acting range of the biogas gas guiding well of the municipal solid waste landfill, the problems of the existing method that the engineering period is long and the quantity of the drilled wells is more are solved, and the aim of determining the acting well of the gas pumping well by an optimized scheme is achieved; and the method is convenient to operate and is safe and practical.

The invention discloses a node load prediction method considering source-load coordination, which comprises the following steps: acquiring node load historical data, including the actual output of renewable energy on the load bus bar and the actual load of the node; carrying out non-parametric estimation fitting on the renewable energy output curve, and reducing the theoretical output of renewableenergy under power limitation; reducing the theoretical load of the node under the condition of reducing load regulation; taking the theoretical load of nodes and the theoretical output of renewableenergy as input and the actual load of nodes as output, and training a neural network; obtaining a node total load prediction model based on source-load coordination; based on support vector machine (SVM) model, predicting the theoretical load of nodes and the theoretical output of renewable energy; inputting a prediction result to the node load prediction model, and obtaining the final node loadprediction value. The method can provide more reliable decision-making basis for future power system operation and dispatching.

The invention discloses a preliminary prospecting well optimum decision-making method and system. The preliminary prospecting well optimum decision-making method comprises the steps: calculating the success probability of a preliminary prospecting well; calculating the value of the preliminary prospecting well; and establishing a decision coordinate system, and judging whether the preliminary prospecting well is an optimal preliminary prospecting well or not according to the positions of the data points of the preliminary prospecting well success probability and the preliminary prospecting well value in the decision coordinate system. According to the preliminary prospecting well optimum decision-making method, on the basis of considering the success probability and the value of the preliminary prospecting well, the two-dimensional optimization model is utilized to carry out preliminary prospecting well optimization decision, and a reliable and rapid decision basis can be provided forthe preliminary prospecting well, so that the deployment quality of the preliminary prospecting well is improved, and the exploration investment is inclined to a region with good benefits.

The invention discloses an urban forest tree preferential planting area selection method and system. The method comprises the steps of obtaining an urban vector layer and dividing the urban vector layer into a plurality of area units; inputting unit population, road area and real forest crown coverage area data of each region to obtain unit population density, road density and real forest crown coverage vector data of each region; performing normalization processing and format conversion to obtain a normalization population density grid layer, a normalization road density grid layer and a normalization real forest tree crown coverage rate grid layer; calculating the priority of each grid unit to obtain a priority PI grid layer; performing priority level division, drawing a PI priority level distribution grid layer, and regarding the region unit with the higher priority level as a region where trees need to be preferentially planted. The method can visually and accurately reflect the demand degree of different regional spaces of a city for urban forest construction, and provides a reliable decision basis for preferential site selection of an urban space forest planting region.

The invention discloses a construction process of a special-shaped transparent aluminum veneer ceiling under a steel truss. The process comprises the following steps of firstly, joint checking of a drawing and secondary design; secondly, design scheme disclosure; thirdly, suspender and keel machining and mounting; and fourthly, aluminum veneer mounting construction. Due to the application, a one-time molding good rate of construction of the special-shaped transparent aluminum veneer ceiling under the steel truss can be improved, rigidity and safety stability of the ceiling are greatly improved, a large amount of ceiling maintenance and repair construction can be avoided, the ceiling decoration construction duration can be shortened, input of persons and materials can be reduced, and through diversification and visualization disclosure of the BIM technology, animation demonstration, VR and the like, the good condition is created for subsequent decoration and construction.

The invention relates to the technical field of big data algorithms, and provides an intelligent prediction method and system for the goods volume during holidays. The method comprises the following steps: firstly, according to the week number of a prediction day, inputting historical cargo quantity sequence data, associated with the prediction day, of a to-be-predicted transport line into a trained LSTM week regulation model to obtain an initial cargo quantity prediction value of the to-be-predicted transport line on the prediction day; obtaining a holiday coefficient vector according to theactual daily commodity quantity value and the predicted daily commodity quantity value of the last year, and selecting a holiday coefficient corresponding to the predicted day according to the day information corresponding to the predicted day; and finally, according to the holiday coefficient corresponding to the prediction day, correcting the goods quantity initial prediction value to obtain a goods quantity final prediction value of the to-be-predicted transportation line on the prediction day. Functional modules in the system are arranged corresponding to the method. According to the intelligent prediction method and system provided by the invention, the predicted goods amount during holidays and festivals is more accurate, and a reliable decision basis is provided for the developmentof logistics business.

The invention discloses a rainfall titration tester. The rainfall titration tester comprises a cabinet, a single-chip microcomputer is arranged in the cabinet, and the single-chip microcomputer is connected with a memory, a water injection metering unit, a display control unit and a power supply unit. The rainfall titration test method comprises following steps: apparatus calibration; and titration testing. By employing the above technical scheme, according to the tester and the test method, by employing the principle of constant-flow pumping by a charge pump, artificial errors and field calibration uncertainty caused and brought by difficult control of the water injection speed by artificial titration are eliminated, an error evaluation standard is normalized and unified, the acquisition accuracy of the rainfall is improved, more reliable decision bases can be provided for improvement of the prediction precision of flood early warning, and the blanks of field calibration and test tools for rainfall acquisition accuracy are filled in.

According to the digital smart service processing method and system applied to big data, the quantitative common evaluation between the first smart service interaction event and the second smart service interaction event is determined based on the disassembled first hierarchical key description information and second hierarchical key description information; because the disassembled key content can represent the local content and the stage content in the intelligent service interaction event, the theme type interaction event identified based on the quantitative generality evaluation can be accurately and effectively discriminated from the aspects of the local content and the stage content; therefore, the accuracy and the feature recognition degree of the recognized theme-type interaction event can be improved, it is ensured as much as possible that the theme-type interaction event can reflect more significant content information in the diversified interaction event set, and an accurate and reliable decision basis is provided for theme determination of the diversified interaction event set.

The invention discloses a node load prediction method considering source-load coordination, which comprises the following steps: acquiring node load historical data, including the actual output of renewable energy on the load bus bar and the actual load of the node; carrying out non-parametric estimation fitting on the renewable energy output curve, and reducing the theoretical output of renewableenergy under power limitation; reducing the theoretical load of the node under the condition of reducing load regulation; taking the theoretical load of nodes and the theoretical output of renewableenergy as input and the actual load of nodes as output, and training a neural network; obtaining a node total load prediction model based on source-load coordination; based on support vector machine (SVM) model, predicting the theoretical load of nodes and the theoretical output of renewable energy; inputting a prediction result to the node load prediction model, and obtaining the final node loadprediction value. The method can provide more reliable decision-making basis for future power system operation and dispatching.

The invention discloses an intelligent elderly care system based on a BIM technology and a construction method. The system comprises a BIM model management platform, and the BIM model management platform comprises a leader cockpit, building equipment management, intelligent inspection, data monitoring and system alarm. Through the implementation of the invention, three-dimensional information distribution and construction of nursing home buildings and equipment are realized on the management platform of the BIM model, multi-dimensional information acquisition and display are realized, and themanagement level of the nursing home is improved. According to the intelligent elderly care system and method based on the BIM technology, based on latest technical means such as big data, artificialintelligence and the Internet of Things, intelligent hardware equipment is used for assisting, safety and health data and service demand data of the elderly are collected in daily operation, storage,data mining and decision analysis are carried out on the data, refined management is achieved, the overall working efficiency is improved, and a real-time, accurate and reliable decision basis is provided for management and service. Intelligent management of the elderly care institution is realized.

The invention discloses a mobile-phone-data-based real-time detection method for an abnormal event of a highway. The method comprises: a real-vehicle experiment is carried out to determine a switching point position of a highway and the highway is divided into a plurality of sections; mobile phone access amounts of section base stations in an abnormal event state and a normal state are extracted respectively; according to the mobile phone access amounts in the normal state, a time sequence model is constructed and numbers of mobile phone getting access to base stations in an abnormal event state are predicted; an abnormal event occurrence threshold value is calculated; and on the basis of the time sequence model, a number of mobile phone access to a base station at a future time is predicted in real time and an abnormal event determination index is calculated, and the abnormal event determination index is compared with the abnormal event occurrence threshold value to determine whether an abnormal event occurs. With the method, an abnormal traffic event can be identified accurately and a reliable decision-making basis is provided for the management staff.

In the information processing method, system, and cloud platform based on artificial intelligence and big data provided by the embodiments of the present application, in view of the fact that the AI ​​thread for interest mining is the set thread obtained through centralized positioning of the AI ​​thread that includes more diverse thread configuration states The intelligent thread whose performance parameters meet the set requirements can ensure the compatibility between the target AI thread and the big data of user behavior compared to the interest mining with the help of a fuzzy selected AI thread, so as to avoid the target AI thread's The configuration constraints that user behavior big data is subject to when mining interest can ensure the integrity and accuracy of the obtained session interest mining situation, and the session interest mining situation includes interest topic tags or potential session interests, so it can be used for subsequent interest mining. Demand analysis and business push optimization provide a reliable basis for decision-making.

The invention provides a method for determining an acting range of a biogas gas guiding well of a municipal solid waste landfill, comprising the following steps of: drilling a plurality of gas guiding wells in the municipal solid waste landfill along the same straight line; selecting the two gas guiding wells to be respectively used as a gas pumping well and a detection well; if the pressure of the detection well is positive pressure, determining that the acting range of the gas guiding wells is less than the distance between the two wells; if the pressure of the detection well is negative pressure, determining that the acting range of the gas guiding wells is more than the distance between the two wells; selecting different gas guiding wells to be combined to gradually and accurately determine the acting range interval of the gas guiding wells; and when the pressure of the detection well is zero or weak negative pressure and the oxygen concentration is more than zero, determining that the distance between the detection well and the gas pumping well is the acting range of the gas guiding wells. According to the method for determining the acting range of the biogas gas guiding well of the municipal solid waste landfill, the problems of the existing method that the engineering period is long and the quantity of the drilled wells is more are solved, and the aim of determining the acting well of the gas pumping well by an optimized scheme is achieved; and the method is convenient to operate and is safe and practical.

The invention discloses a design and implementation method of an intelligent body temperature monitoring and early warning big data platform, and relates to the technical field of body temperature monitoring. The system comprises data acquisition equipment, a data analysis module and a data display and summarization module, wherein the data acquisition equipment is used for acquiring student identity information data and body temperature data in real time and transmitting the student identity information data and the body temperature data to the data analysis module, and the data analysis module is used for comprehensively analyzing the student identity information data and the body temperature data; and the data display and summarization module is used for displaying and summarizing the student identity information data and the body temperature data analyzed by the data analysis module. The temperature, iris and other data are collected through the infrared detection technology and the iris collection technology, the data is sent to the cloud platform, the data is stored and analyzed in real time by means of the cloud server and the body temperature big data analysis platform, thedata visualization is achieved, the data query is facilitated, and the real-time early warning is achieved.

The present invention is applicable to the technical field of fire monitoring, and provides a fire monitoring method, device and edge computing device, wherein the method includes: acquiring more than two sets of environmental monitoring data, and monitoring the environment according to the time series of the environmental monitoring data Preprocessing the data, obtaining the preprocessed environmental monitoring data, inputting the preprocessed environmental monitoring data into the pre-training machine learning model, obtaining the decision result output by the pre-training machine learning model, and sending The corresponding warning information is sent to the user terminal. The invention utilizes an edge computing device to run a machine learning model to perform data fusion on environmental monitoring data to calculate the fire hazard degree, and realizes real-time, objective, safe and reliable fire hazard assessment. At the same time, corresponding warning information is sent according to the state of the fire, thereby providing real and reliable decision-making basis for firefighting and rescue personnel, and improving the efficiency of firefighting and rescue operations.

The invention provides an evaluation method of usage status of reservoir flooding water. The evaluation method of the usage status of the reservoir flooding water includes: first, according to a permeability saturation curve of normalization of an oil reservoir, confirming a reservoir water-cut rising regularity description equation; secondly, according to an actual recovery percent of recoverable reserves at different stages of the oil reservoir, calculating corresponding theoretical water content by adopting the reservoir water-cut rising regularity description equation, and then according to a stage injection-production ratio of the oil reservoir, calculating theoretical stage water storage rate and stage water drive index deviation of the oil reservoir; thirdly, according to the stage injection-production ratio and actual water content of the oil reservoir, calculating actual stage water storage rate and stage water drive index deviation of the oil reservoir, and respectively drawing curves of the actual and theoretical stage water storage rate and the actual and theoretical stage water drive index deviation, which change along with time; finally, evaluating the usage status of the reservoir flooding water by comparing the theoretical curves with the actual curves. By using the evaluation method of the usage status of the reservoir flooding water, the usage status of the reservoir flooding water can be accurately evaluated, and a reliable decision basis is provided to development adjustment of the reservoir flooding water.

The invention discloses a wire bonding online monitoring method based on a digital twinning technology. The method comprises the steps of establishing and optimizing a simulation model of wire bonding, establishing a data model of wire bonding, and establishing a visual model of wire bonding. The digital twinborn model is formed by mutual coupling evolution of a simulation model, a data model and a visual model. According to the online monitoring method, real-time analogue simulation is carried out on the wire bonding process by establishing the digital twinborn model for wire bonding, the digital twinborn model can be used for receiving external environment parameters and operation parameters in real time, real-time simulation is carried out on the bonding process, and visual monitoring on the bonding process is realized in a virtual space; key material parameters, such as crystal phase distribution, dislocation, porosity, atomic diffusivity and the like, which influence the service life and reliability of the device are provided for operators, and are taken as reference bases for judgment and decision making, so that the product yield is improved, and the loss caused by the fact that material defects are not perceived in time is reduced.

The invention discloses a scene modeling method suitable for planning operation of an integrated energy system, and the method comprises the steps: firstly collecting photovoltaic output data, wind power output data, electric load data, gas load data, cold load data and thermal load data of a researched region, carrying out the per-unit processing of the obtained data, arranging the data according to time, and generating a scene data set; then, adopting an improved LHS method to carry out sampling and correlation control processing on the scene data set, and obtaining a sample matrix; and finally, clustering the sample matrix by adopting an improved K-means method to form a specific probability scene which retains the characteristics of the original scene. The method overcomes the defects that in the prior art, scene description is inaccurate, and it is difficult to completely adapt to future planning and operation, lays a foundation for subsequent system planning design, operation scheduling and the like, avoids the problem that reliable operation of the system is affected by installation mismatching caused by inaccurate traditional scene prediction methods, and effectively improves the design and operation economy of the comprehensive energy system.