100results about How to "Timely forecast" patented technology

The invention discloses an engine fault prediction method. The method comprises the following steps that effective measurement data of a plurality of sensors of an engine are obtained; the effective measurement data are subjected to normalization processing; the effective measurement data obtained after normalization processing are sliced, and a plurality of slice samples are formed; the multiple slice samples are sent into a deep nerve network to be subjected to feature extraction, and after feature extraction, the slice samples are connected to a fully-connected network; and according to output of the fully-connected network, classification is conducted through a softmax classifier, and the left service life of the engine is determined. According to the provided engine fault prediction method, the process is small, operation is easy, and the engine fault prediction method can be widely applied to various engines of aircraft.

The invention provides an electric spindle condition monitoring and fault diagnosing system and a monitoring and diagnosing method thereof, which belong to the technical field of numerical control processing. The electric spindle condition monitoring and fault diagnosing system includes an electric spindle device, a signal conditioning and collecting device, a parameter setting module, an audio collecting device, a video monitoring device, a lower computer, an upper computer, and a client. The monitoring and diagnosing method includes the following steps: the fault value ranges of a current sensor, a voltage sensor and a vibration sensor are set through the parameter setting module; and the current sensor and the voltage sensor in the signal conditioning and collecting device respectively detect the current and voltage of the winding, the stator and the rotor in the electric spindle device, and the vibration sensor detects the speed signals of the spindle and the motor in the electric spindle device and the vibration signals of the bearings, the rotating shaft and the spindle casing. The problem that the existing electric spindle fault diagnosis system has a single diagnosis mode and cannot implement intelligent diagnosis is overcome. The reliability and accuracy of fault diagnosis are improved.

The invention discloses a wind driven generator part fault early warning method, which comprises the steps of: performing model training on a parallel echo state network group by calling data in a historical database, testing the accuracy of each echo state network model, and performing process statistical analysis on models satisfying the requirements so as to obtain a standard threshold of each characteristic parameter; after processing acquired different signals of all the parts of the wind driven generator, comparing each characteristic parameter in an information fusion module with a corresponding standard threshold, combining the comparison result with a corresponding weight value to give out early warning information, and adjusting the weight value of each characteristic parameter based on the practical condition of the on-site maintenance, wherein the monitored real-time data are based on the early-warning information and the on-site maintenance condition. According to the invention, health parameters of the parts of the wind driven generator are given after the monitoring results of the characteristic parameters are subjected to the fusion analysis, so that the accuracy and reliability of the early warning result are ensured.

The invention provides an urban gas pipe network safety monitoring and early warning method and system based on settlement monitoring, and the method comprises the steps: synthesizing urban land subsidence historical data and urban gas pipe network distribution and historical fault data, and employing a multi-factor judgment model and a GIS spatial analysis technology to carry out the division ofkey regions of gas pipe network settlement; selecting a key position of the key area as a settlement monitoring point, installing pipeline operation parameter acquisition equipment, constructing an urban gas pipe network settlement key area monitoring network, and acquiring pipeline operation parameters of each settlement monitoring point in real time; transmitting the pipeline operation parameters and the pipeline attribute parameters to a background server in real time through wireless communication; receiving, storing and preprocessing pipeline operation parameters and pipeline attribute parameters in real time through a background server, determining the current safety risk level of each settlement monitoring point pipeline based on the pipeline operation parameters and the pipeline attribute parameters by utilizing a pipeline settlement damage prediction model, and predicting and alarming pipeline faults.

The invention discloses a concrete crack detector with a reinforcing bar as an electrode. A reinforcing bar emission electrode and a reinforcing bar receiving electrode are embedded in concrete, wherein the emission electrode is connected with an emission circuit through an emission cable; a signal transmitted by the emission circuit is sent out from the concrete through the emission electrode; the receiving electrode is connected with a receiving circuit through a receiving cable; and the receiving circuit is used for amplifying and filtering a signal received by the receiving electrode. An output signal of the emission circuit is connected to a control and computation module through an emission communication control interface, and two-way communication control is performed between the control and computation module and the emission circuit. An output signal of the receiving circuit is connected to the control and computation module through a receiving communication control interface, and two-way communication control is performed between the control and computation module and the receiving circuit. As the reinforcing bar is used as the electrode, the original construction features and stress features of the concrete do not change, a construction process and a construction method have no need to change, and the electrode and the concrete structure have the same service life. The concrete crack detector with the reinforcing bar as the electrode has the advantages of simplicity in design, convenience for construction, low cost and long service life.

The invention discloses a cyanobacterial bloom predicting method based on a non-linear kinetic time-series model, which belongs to the water environment predicting field. The method comprises the following steps: using the blue algae growth rate as a time-varying parameter; creating a non-linear kinetic time-series model for the cyanobacteria growth with double nutrient salt cycling; using the combination of the numerical algorithm and the intelligent evolutionary algorithm, optimizing the constant parameters in the non-linear kinetic time-series model for the cyanobacteria growth; through setting the multivariate time-series model to realize the prediction of the time-varying parameter and the cyanobacteria biomass and through using the bifurcation theory and the central manifold theory to make a nonlinear kinetic analysis of the cyanobacteria growth time-varying system, obtaining the outbreak conditions for a cyanobacteria bloom so as to make an early warning of the bloom outbreak. The method proposed by the invention not only determines the conditions for a cyanobacteria bloom outbreak, but also improves the bloom prediction accuracy, providing an effective reference for an environmental protection department and governance decisions for water environment treatment.

The invention discloses a fault prediction method and a system for intelligent manufacturing equipment based on a neural network model, wherein, the method comprises the following steps: acquiring a running time-long parameter of the equipment, an average running load parameter in the running time and a daily average running time-long parameter in the running time; According to the running parameters of the equipment, the average running load parameter in the running time and the average running time parameter in the running time, the running data parameter set of the equipment is constructed.The parameters in the constructed equipment operation data parameter set are normalized to obtain the normalized equipment operation data parameter set; the normalized set of equipment running data is input into the trained neural network model to predict and analyze the equipment failure time, and the predicted results are outputted. In the embodiment of the invention, through the trained neuralnetwork model to predict the running data parameters of the equipment, the time when the equipment will fail can be predicted more accurately.

The invention relates to a lightening damage early-warning method and system for an electric transmission line. The method includes the following steps that first, weather, satellite, radar and lightening positioning system data are collected, and lightening early-warning parameters at some period in the future are obtained through a comprehensive lightening prediction algorithm; second, according to different lightening overvoltage formation mechanisms, shielding failure and back striking calculation models are selected respectively, calculation is performed through the lightening early-warning parameters and line characteristic parameters, and the lightening trip probability of the electric transmission line is predicted; third, the lightening trip probability of the line is evaluated, the lightening trip probability of each base electric transmission line pole tower is compared with a determined line trip risk early-warning threshold value, and different levels of early-warning signals are obtained. Through the lightening damage early-warning method and system for the electric transmission line, lightening damage to the electric transmission line can be early warned effectively and timely, and technological support is provided for lightening protection and disaster relief of the electric transmission line.

The invention provides a method and a device for predicting hard disk fault occurrence time and a storage medium, which are used for solving the problem that the hard disk fault occurrence time cannotbe predicted in related technologies. The method comprises the following steps: screening out hard disks with endangered faults from a plurality of hard disks according to acquired state data of thehard disks; Calculating the variable quantity and the discrete quantity of each piece of data in each piece of state data, collected in a first preset time period, of the hard disk with the endangeredfault, and obtaining a first prediction data set; And inputting the first prediction data set into the first training model to obtain the fault probability of each hard disk in a second preset time period in the future. The method and the device can predict the failure time of the hard disk.

The invention relates to a posture compensation method and a device based on image measurement and a tunnel settlement and deformation monitoring system, belonging to the technical field of tunnel engineering monitoring. A main device related to the method comprises an image sensor (image acquisition system), a microscope lens, a cross marker, a light source and the like. All parts of the device are arranged in a sealed space. The light source irradiates on the marker, the image sensor (image acquisition system) measures the cross marker suspended in the sealed space to determine the self angle position change of the image acquisition system. The method is used for compensating errors caused by self deflection of the measuring device in the tunnel deformation monitoring and improving the accuracy and the reliability of the monitoring system, and has the advantages that the principle is simple and practical, the application is convenient and the use requirement is met.

The invention discloses a method for automatically identifying and drawing a cold front in meteorology. The method comprises steps of carrying out cold cutting identification based on a low altitude wind field; carrying out detection and verification on a temperature difference or a dew point difference of two sides on a cold shearing belt; detecting groove lines of the near constant pressure field overhead the cold shearing belt; drawing a three-dimensional schematic diagram of the cold front and quantifying parameters; simplifying the wind vector field into a binary wind direction mark related to the cold shearing belt; carrying out conversion to marking an irrelevant region to be a three-valued image of 0; designing a cloud detection algorithm, a combined expansion, filtering and skeleton extraction algorithm, thereby achieving detection, positioning and shearing parameter extraction of the cold shearing belt; taking the cold shearing belt as the reference, verifying the dew point difference and the temperature difference in a local region and giving quantitative parameters; and finally, through the identification and matching of low pressure grooves, analyzing the frontal oblique angle. According to the invention, automatic detection is achieved; forecasting of weather disasters is facilitated; economical loss is reduced; and meanwhile, the formed quantitative description provides a certain foundation for objective training of a relation model of the cold front and the extreme weather.

The invention discloses a long wall coal mining roof pressure hydraulic support resistance change characteristic pre-warning method. A hydraulic support working resistance monitoring device, a pump station switch monitoring device and a hydraulic support resistance change index dynamic monitoring system are used for pre-warning; the hydraulic support working resistance monitoring device is used for recording and storing monitored working face hydraulic support working resistance and corresponding time in real time; the pump station switch monitoring device is used for recording and storing monitored working face hydraulic support injection pump pressure finishing time; the hydraulic support resistance change index dynamic monitoring system is used for processing and analyzing received data, marking a hydraulic support working resistance value corresponding to the working face hydraulic support injection pump pressure finishing time as hydraulic support setting load, and pre-warning about working face roof pressure according to the change of resistance change index values. Accurate and timely pre-warning about abnormal roof pressure can be realized, and normal periodic weighting length can be accurately determined in real time.

The invention relates to a delivery starting forecasting device based on uterine electromyography and a method for extracting characteristic parameter. The device comprises a uterine electromyography signal acquisition system, a uterine electromyography digital signal processing system, an image-text display device for processing result and a sound forecasting device; the uterine electromyography signal acquisition system is connected with the uterine electromyography digital signal processing system; and the uterine electromyography digital signal processing system is connected with the image-text display device and the sound forecasting device. The method for extracting characteristic parameter processes the uterine electromyography signal by using method of wavelet transform and artificial neural network, extracts characteristic parameter, judges and reads the processing result. Using the device and the method, the delivery starting time can be objectively and accurately forecasted, the risk of delivery can be effectively reduced, and the disease incidence and death rate of newborn baby can be decreased; meanwhile, the obstetrician can be helped to timely take effective measures for reducing occurrence rate of premature delivery and retarded birth so as to reduce the risk of delivery and defect rate of newborn baby.

The embodiment of the invention discloses a data processing method and device, intelligent equipment and a computer readable storage medium. The method comprises the following steps: obtaining description information and static attribute information of a target user, and taking the description information and the static attribute information as input of a data analysis model constructed by combining artificial intelligence and machine learning, obtaining an analysis result output by the data analysis model after the description information and the static attribute information are analyzed andprocessed, and outputting disease prompt information of the target user according to the analysis result. According to the embodiment of the invention, the hidden information with potential value in the existing medical record data is mined in combination with the artificial intelligence and the machine learning model, so that the illness information of the target user can be predicted based on the information and the description information of the target user, and a doctor-seeing reference is provided for the target user.

The invention discloses an intelligent and safe electricity utilization monitoring system fused with the Internet-of-Things technology. The system is characterized in that an equipment electricity utilization acquisition module sends acquired data to an Internet-of-Things transmission module; the Internet-of-Things transmission module transmits the received data to the monitoring analysis module; the power utilization monitoring analysis module is used for storing, analyzing and deciding the data acquired by the equipment power utilization acquisition module to obtain whether the operation condition of the to-be-monitored equipment is normal or not, carrying out power-off or shutdown processing on abnormal equipment, and carrying out early warning or prompting on abnormal data; according to the data acquired by the equipment electricity utilization acquisition module and the historical abnormal condition, the cause of the electrical fire is analyzed, the factor data of the electrical fire is tracked and statistically analyzed in real time, whether the electrical circuit and the to-be-monitored equipment have potential safety hazards is found, and the information of the potential safety hazards is sent to the user terminal. The system can discover abnormal electric equipment in time, predict and warn the potential safety hazard of electricity utilization, and reduce the occurrence of electricity utilization safety accidents of the equipment.

The invention discloses a forest fire meteorological warning method and system. The system comprises a meteorological station, a data receiving terminal, a forest fire meteorological index calculation module, a forest fire meteorological level calculation module, a forest fire warning information calculating and editing module, and a warning information transmitting module. The data receiving module receives information of the meteorological station and analyzes the information, the forest fire meteorological index calculation module calculates forest fire meteorological indexes of warning sub-areas and stores the indexes, the forest fire meteorological level calculation module further calculates forest fire meteorological levels, the forest fire warning information calculating and editing module calculates warning levels and edits warning information, and the warning information transmitting module transmits the warning information to terminal users.

A dormitory fire and safety system comprises a monitoring node, a transmission network module, a server, a monitoring terminal, a hydrant system module, an automatic nozzle system module, a power supply and distribution management module, a system self-inspection module, an alarming module and an evacuation assisting module, wherein the monitoring node is connected with the server through the transmission network module, the server is bidirectionally connected with the monitoring terminal, the hydrant system module, the automatic nozzle system module, the power supply and distribution management module, the system self-inspection module, the alarming module and the evacuation assisting module are respectively connected with the monitoring terminal, the automatic nozzle system module comprises a nozzle, a nozzle moving guide slot, an alarming valve, a signal valve and a microprocessor control unit, the nozzle, the alarming valve and the signal valve are arranged on the nozzle moving guide slot, and the microprocessor control unit controls the nozzle, the alarming valve and the signal valve.

Provides is a bridge structure health monitoring system based on the big data idea and a realization method of the system. The monitoring system comprises a bridge structure big data mining system, a bridge structure big data storing system, a bridge structure big data analyzing system and a bridge structure big data health monitoring system. The monitoring system is huge in the data amount, includes many data types, is rapid in data processing, and can evaluate and predict the bridge structure health state timely accurately, and also has the advantages of reasonable design, high adaptability, high reliability and convenient popularization and application.

The invention discloses a wireless sensor device and a method used for coal field fire zone parameter dynamic monitoring, and belongs to the field of wireless sensing system used for large-scale coal field fire zone monitoring. The wireless sensor device is composed of parameter acquisition and wireless transmission nodes, and terminal signal receiving stations in coal fields. The parameter acquisition and wireless transmission nodes are composed of a plurality of sensors, A / D converters successively connected after signal linear amplification, single chip microcomputers, infrared thermal imaging monitoring systems, and wireless transceiver modules; the terminal signal receiving stations are composed of the wireless transceiver modules, single chip microcomputers, and host computer servers; the wireless sensor device can be used for continuous monitoring on temperature, CO, and CO2 parameters of coal fields, and real-time transmission of the parameters to the signal receiving stations. The signals are stored in a database via the signal receiving stations, and displayed on a server visual interface; analysis on the coal field fire zone acquired parameters is carried out using server operating software; tracing prediction, early warning, and back checking on coal field spontaneous firing tendency are realized; and measures can be adopted in time so as to avoid generation and enlarging of coal field fire.

The invention relates to the technical field of checking and pursuing of illegal toll evasion vehicles on a highway, in particular to a dynamic prediction checking method for an exit station and exit time of illegal vehicles on the highway, and the method comprises the steps: obtaining the data of an ETC door frame monitoring system and a highway toll collection system in real time, predicting a possible exit toll station and exit time of a vehicle on the basis of historical traffic data and a current traffic path of the vehicle passing through a highway ETC (Electronic Toll Collection) door frame, and according to the predicted exit toll station and the current passing door frame, obtaining the shortest path between the door frame and the predicted exit toll station and the passing time between door frames based on the topological graph so as to predict the time for the vehicle to arrive at the target toll station. The exit toll station and the exit time of the vehicle can be adjusted every time the vehicle passes through one door frame, and the prediction accuracy can be improved through newly obtained information.

The invention provides an image on-line sediment concentration measurement method of river sediment, comprising: sampling the image of river sediment, transferring the image, processing the image, calculating the sediment concentration based on the mathematical model. The features of the measurement method are: simple operation, convenient implementation, less labor intensity during sapling the image by the workman, continuous measurement and real-time detection of the sediment concentration, establishment of mathematics data and acquisition of sediment concentration data good for the timely prediction of the mountain land flood and drought in the future.

A diatom biological water quality monitoring system includes a biological cultivation and collection device 4, an aquatic organism experiment processing device 5, an aquatic organism identification device 7, and a biological classification and water quality determination system 9. A control sample point is arranged at a monitoring area generally, a diatom sample of the designed area is collected through the collection device, the diatom sample is pretreated in a laboratory to remove diatom organic matters and is treated to remove organic salts, a siliceous shell is obtained and then cleaned and dried to pre-prepare a diatom slide, preliminary testing is carried out, and after the slide is tested to be qualified, the slide is sealed by an adhesive with the refractive index of about 1.7. The slide 21 is subjected to diatom individual identification and counting by the identification device 7, diatom individuals are displayed in an image mode in the system 9, and the diatom sample can be photographed for preservation. The system 9 divides the identified diatom species into different class groups and identifies different types of indicator species, at the same time, the system 9 calculates various diatom indexes on the basis of various mathematical models, and thus diatom biological resource survey and biological water quality monitoring functions are achieved.

The invention provides a Hadoop-based electricity consumption feedback implementation method. The method is implemented mainly through seven steps such as electricity data acquisition, data aggregation, data forwarding, data storage, data processing, data display and feedback and electricity consumption prediction based on a cloud platform-combined big data analysis. Through the method, data can be processed effectively, stable data transmission is realized, data feedback can be timely and use-friendly, and data predication can be high in accuracy, so that enterprise users or individuals can clearly know own electricity consumption conditions, and improve own electricity consumption behaviors, benefits are brought to the enterprise users or individuals while electricity is aved, and meanwhile, the enterprise users or individuals actively make some contribution to energy saving and pollution reduction.

Embodiments of the invention disclose a method and a device for managing a central processing unit. Implementation of the method comprises the following steps of determining a first prediction condition and a second prediction condition, wherein the first prediction condition and the second prediction condition are both factors for influencing the wake-up time of the central processing unit (CPU); counting the accuracy for using the first prediction condition to predict the CPU to enter a low power mode (LPM); if the accuracy is higher than a predetermined threshold, continuing to use the first prediction condition to predict the next wake-up time of the CPU; otherwise using the second prediction condition to predict the next wake-up time of the CPU. When the prediction condition is utilized to predict the next wake-up time of the CPU, the influences of various factors on the next wake-up time of the CPU are considered simultaneously, and the next wake-up time of the CPU can be more accurately predicted, so that the CPU can select more appropriate PLM (Product Lifecycle management), and thus the power consumption and performance requirements of the CPU are considered; therefore, the higher CPU performance can be kept on the premise of keeping the low power consumption.

The invention discloses an automatic nowcasting method of a multi-monomer convection system short-time heavy rainfall event. The method comprises the following steps of identifying and tracking convection monomers; carrying out convection monomer identification by using a multi-threshold adaptive algorithm so as to acquire a convection monomer identification result simultaneously reserving a convection monomer core and surrounding related information; tracking the convection monomer by using an optical flow algorithm, and acquiring speeds of the convection monomers; identifying multi-monomer convection system; providing position prediction of the convection monomers at a next moment according to space-time correlation among the convection monomers in the multi-monomer convection system andthe monomer speeds, calculating a superposition coefficient among the convection monomers, establishing a correlation matrix according to the superposition coefficient, and obtaining an identification result of the multi-monomer convection system by using a transfer closure clustering method; and carrying out multi-monomer convection system diagram model establishment and short-time heavy rainfall event identification. By using the method, automatic multi-monomer convection system short-time heavy rainfall event nowcasting is realized, disasters are warned in time, and economic losses and casualties are reduced.

The invention provides a resonance packet wave spectrum monitoring data-based earthquake prediction method. The method includes the following steps that: monitoring precursor stations are established globally; resonance packet monitoring data generated by the monitoring precursor stations for regions where the monitoring precursor stations are located are acquired continuously; acquired resonance waves are aggregated and drawn into a resonance packet wave spectrum by using the waveform characteristics of resonance waves, and at the same time, the time difference of a time when fast waves arrive at the monitoring precursor stations and a time when slow waves arrive at the monitoring precursor stations in the resonance waves is recorded; the scale of an earthquake is predicted through calculating the periods of the resonance waves in a resonance packet, and an earthquake generating time is predicted through the growth waveforms of the resonance waves, and epicentral distances are determined through the time difference of the fast waves and the slow waves in the resonance waves; and the epicentral distances determined by the monitoring precursor stations are drawn into corresponding straight lines, and the intersections of the straight lines are the centers of earthquake regions where earthquakes are predicted to occur, and therefore, early warning notices can be emitted timely. The resonance packet wave spectrum monitoring data-based earthquake prediction method has the advantages of wide applicability and universality. With the method adopted, a long-awaited new era of earthquake prediction will come.

The invention discloses a river surface flow field accurate measurement radar based on computational intelligence, and particularly relates to the technical field of flow measurement. The radar comprises a software structure and a hardware structure. The radar system adopts a coding technology on a signal waveform to realize interference resistance, adopts a fuzzy clustering intelligent algorithm to ensure stability and reliability of observation data, adopts broken line array weighted optimization to realize high-precision river surface vector field synthesis under a large visual angle condition, adopts a variance weighted intelligent algorithm to reduce data jitter and improve stability of observation vector data, and adopts remote data analysis based on big data and an artificial intelligence technology. Intelligent algorithms such as an anti-interference means, an intelligent processing technology, a high-resolution broken line array angle resolution technology, a fuzzy clustering technology and a filtering jitter reduction technology are integrated, a corresponding hardware structure is designed for related intelligent technologies, and the problems existing in traditional equipment are effectively solved.

The invention discloses a method for predicting gas in direct-current-transmission conversion transformation oil. The method comprises the following steps of: acquisition of parameters of the method for predicting the gas in the direct-current transmission conversion transformation oil, wherein he parameters include gas parameters in the conversion transformation oil, conversion transformation operation parameters and basic information parameters of conversion transformation; and establishment of a conversion transformation characteristic quantity matrix and a basic sample database in the method for predicting the gas in the conversion transformation oil, determination of a similar sample of the gas in the conversion transformation oil to be predicted, initial prediction on the gas in the conversion transformation oil, and optimization of the parameters in the method for predicting the gas in the conversion transformation oil, thus obtaining a gas prediction result of the conversion transformation oil, namely implementing the method for predicting the gas in the conversion transformation oil. The method can be used for predicting a gas trend in the direct-current-transmission conversion transformation oil, performing fault diagnosis with combination of a three-ratio method, a Duval triangle method and other methods, and determining faults of the conversion transformation effectively and timely so as to timely guide run units to make decisions on conversion transformation stop, continuous operation, live testing, inspection strengthening, fault diagnosis, overhaul in factory, field maintenance and the like.

The invention discloses a marker for rapidly predicting whether a COVID-19 patient suffers from light-to-severe progression or not, a kit thereof and an establishment method of the marker. According to the method, the severity of the condition of an early-stage COVID-19 patient is predicted through proteomics data, then potential critical patients are screened, and specific analysis can be carried out only by obtaining the three feature data of OAF, MB and DDT of the patient when the patient is admitted to hospital. The marker and the detection kit can timely, rapidly, objectively and accurately predict the severity of the condition of a COVID-19 patient and whether the disease progresses from light to severe, and assist medical staff in timely finding potential critical patients to allocate enough medical resources and attention, which are advantages that a traditional evaluation mode does not have. Therefore, the invention has great clinical application value for early rapid prediction and screening of the potential critical patients of COVID-19.