133results about How to "Realize intelligent processing" patented technology

The invention discloses a remote data acquisition and analysis system for a numerically-controlled machine tool. The remote data acquisition and analysis system comprises an equipment layer, a data acquisition layer, a server layer and a client layer, wherein the equipment layer comprises the numerically-controlled machine tool; the data acquisition layer comprises a data acquisition device, and the data acquisition device is used for acquiring data of the numerically-controlled machine tool; the server layer is communicated with the data acquisition layer and is used for receiving and processing data transmitted by the data acquisition layer and storing the processed data in a database; the client layer interacts with the server layer to feed processing results of the server layer back toa user.

The invention relates to a relevant technical field of power grids, in particular to a power grid running maintenance automatic system, which comprises a power grid running monitoring analysis subsystem, a power transforming equipment online monitoring analysis subsystem, a power transmission equipment online monitoring analysis subsystem and an emergency command subsystem. According to the power grid running maintenance automatic system disclosed by the invention, the application functions of different services are established on a basic platform through the design of platformization, integration and standardization. Meanwhile, a plurality of automatic functions such as power transmission and transforming equipment running state acquisition and analysis, and emergency command are integrated in the system, so that system support information is acquired and shared sufficiently, and functions such as intelligent processing and auxiliary analysis decision of information, and intelligent alarming and fault diagnosis based on power grid running information are realized.

The invention discloses a public parking lot berth quantity confirming method. The method includes a first step of confirming factors which influence the berth quantity of a public parking lot, investigating data of the factors and dividing the data into a training data group and a prediction data group, a second step of building a back propagation (BP) neural network which comprises an input layer, a hide layer and an output layer, a third step of carrying out preprocessing to the data of the training data group, a fourth step of inputting preprocessed training data into the BP neural network to generate the data of the output layer, comparing the data of the output layer with an actual value, adjusting the variable quantity and the weight of the hide layer, and carrying out iteration training until errors meet the accuracy requirement, and a fifth step of inputting data of the prediction data group into the BP neural network to be subjected to processing and generate the data of the output layer. The data is the berth quantity of the public parking lot. The public parking lot berth quantity confirming method is simple in modeling, parameters are easy to obtain and collect, and intelligent processing to the big data is achieved. The public parking lot berth quantity confirming method can be widely applied to urban construction, large commercial district programming or district programming.

The invention discloses a milling flutter recognition method based on variation modal decomposition and energy entropy, and belongs to the technical field of machine tool machining flutter recognition. The milling flutter recognition method comprises the following steps of S1, establishing a VMD mathematical model; S2, establishing a mathematical model of the energy entropy; S3, conducting three sets of milling machining experiments representing three cutting states, including stable cutting, a weak flutter and a severe flutter, and obtaining three sets of milling force signals through a dynamometer; S4, conducting FFT analysis on the three sets of milling force signals, and proving that the three sets of milling force signals represent the states of stable cutting, the weak flutter and the severe flutter respectively; S5, determining the number K of optimal modals of VMD decomposition and a penalty factor alpha through a VMD parameter automatic selection method based on a kurtosis value; S6, solving instantaneous frequencies of multiple IMF, and determining a milling flutter characteristic frequency band; S7, adopting a hammering experiment to obtain the modal of a knife; S8, extracting a flutter characteristic vector of each IMF based on the energy entropy. According to the milling flutter recognition method based on the variation modal decomposition and the energy entropy, the VDM decomposition effect is improved, and automatic flutter recognition is achieved.

The invention discloses a subway shield door fault monitoring and early warning intelligence system. The system comprises a user login and quit module, a parameter management module, a platform operation monitoring module, a door control system monitoring module, an integration query statistics module, an external interface isolation module, a system setting management module, a fault diagnosis module and a nerve network fault early warning module. When a subway shield door component or a component reaches early warning setting or the subway shield door generates a fault, the platform operation monitoring module or the door control system monitoring module transmits emitted early warning information or fault information to the fault diagnosis module and the nerve network fault early warning module so as to carry out classification and grading, and then a result is fed back to a user through a display. In the invention, a fault type and a fault address can be rapidly and accurately determined; early warning can be performed on a predictable fault in advance; and simultaneously, through data statistics and analysis, a data basis can be provided for establishing rail traffic large data based on an aerospace vehicle ground integration private network.

The present invention discloses an intelligent processing method and system of video data. According to the method, an alarm rule is set at an intelligent camera. The method comprises the steps that the intelligent camera carries out video data collection, analyzes the collected video data in real time, and generates intelligent data if the alarm rule is satisfied, and the intelligent data comprises an encoder identification and movement trajectory information; the intelligent camera capsulates the video data and the intelligent data together to be data stream and sends the data stream to the frame analysis component in a cloud storage system; the frame analysis component decapsulates the received data stream, obtains the video data and the intelligent data, and the video data and the intelligent data are stored in a storage component; the storage component sends the storage addresses of the video data and the intelligent data to an index server to carry out respective recording. According to the scheme of the invention, the collected video data can be intelligently processed in real time.

The invention discloses a furnace hearth flame detecting method based on an intelligent-control computer vision technology. The furnace hearth flame detecting method comprises the following steps of: using a CCD (Charge Coupled Device) camera to take a picture for furnace hearth flame by an optical fibre image sensor, and transmitting the taken image information signal to a real-time signal processor; using a wavelet packet arithmetic to perform de-noising processing to the signal of the image information in the real-time signal processor; and using a BP (Back Propagation) neural network module to detect and distinguish the de-noised image information. The computer vision technology based on the wavelet packet and the BP neural network is applied to the image information analysis and treatment of the power plant furnace hearth flame, so that the intelligent treatment of the power plant furnace hearth flame information can be achieved, and the signal noises in background flame can be effectively removed to acquire a more real and accurate signal; the combustion condition of each combustor can be relatively grasped in a quantitative manner to keep the best combustion condition of a boiler, so that the safe and high-efficient operation of the device is achieved.

The invention belongs to the technical field of intelligent machining and manufacturing and discloses an all-electric digitization two-freedom-degree force control grinding head device. The all-electric digitization two-freedom-degree force control grinding head device is used for grinding and polishing complex curved surface parts. The all-electric digitization two-freedom-degree force control grinding head device comprises a two-freedom-degree servo platform, a force sensor, a grinding head motor, a grinding head and a control assembly. The force sensor is connected with the two-freedom-degree servo platform and the grinding head motor. The grinding head is connected to the grinding head motor. The control assembly is connected to the force sensor, the grinding head motor and the two-freedom-degree servo platform. The all-electric digitization two-freedom-degree force control grinding head device is high in automation degree, low in cost, high in machining efficiency and relatively high in flexibility, the machining deformation of the workpieces and the stress concentration of a machining area can be reduced, and nonuniformity of polishing is avoided.

The invention provides an on-satellite small cluster information processing system, and belongs to the technical field of on-satellite real-time and near-real-time information processing. The system aims to solve the technical problem that an existing remote sensing satellite is weak in on-satellite information processing, long in image data acquisition period and poor in real-time performance. The system comprises a high-performance X86 application layer computer, an embedded multi-core DSP computer, an external interface unit, a power supply unit and a VPX high-speed data exchanger, whereinthe VPX high-speed data exchanger adopts an OpenVPX system-level bus standard, and achieves mutual connection of high-speed data buses, satellite keeping control buses and power supplies of all functional modules in the system. The on-satellite small cluster information processing system can achieve intelligent processing of on-satellite remote sensing images, an open hardware platform architecture based on the OpenVPX bus standard is utilized, the functions and the calculation of the hardware platform are achieved by increasing and decreasing the number of the embedded multi-core DSP computers so as to meet different requirements of an optical remote sensing satellite for data processing tasks, and the system is good in universality and high in expanding capability.

The invention provides a method, a device and a system for processing command information. The method comprises the following steps of: receiving the command information input by a user and confirming if the command information is voice information by a mobile terminal, and obtaining corresponding response information and showing to the user by the mobile terminal according to the confirmed type of the command information. According to the method provided by the invention, the man-machine interactive intelligent processing is realized and the user experience is increased.

The invention discloses a farmland intelligent monitoring control system based on Internet of Things high-definition camera shooting integrated gateways. The farmland intelligent monitoring control system comprises multiple groups of Internet of Things high-definition camera shooting integrated gateways, multiple groups of data acquiring modules, multiple groups of electrical control modules, and a total control table. The data acquiring module comprise a temperature sensor, a humidity sensor, a wind speed sensor, a PH value sensor, an illumination sensor, and a PH2.5 tester. The electrical control module comprises a fireproof safety alarm, a temperature controller, a humidity controller. The Internet of Things high-definition camera shooting integrated gateway comprises a processor and a high-definition camera. The total control table is a computer. The farmland intelligent monitoring control system may effectively detect various data of agricultural products in growth processes, the data including illumination, temperature, humidity, wind speed, soil acility and alkalinity, and soil water content or the like, and pertinently adjusts the agricultural products with a microprocessor according to the various data in order to maximize and optimize production effect.

The invention discloses a group message processing method and device. The method comprises the following steps: receiving a group message sent by a group chat group, determining the matching degree between the group message and candidate data in a behavior database according to a pre-constructed behavior database, detecting the size of the determined matching degree and a preset threshold, and ifthe detected matching degree is less than the preset threshold, shielding the group message; and if the detected matching degree is greater than or equal to the preset threshold, sending the group message. According to the group message processing method provided by the invention, the intelligent processing of group messages is realized, and the shielding of useful group messages is avoided.

The invention discloses an efficient town sewage treatment and recycling device and process. The efficient town sewage treatment and recycling device comprises a device body and a remote environmental medicine expert diagnosis and control system, wherein the device body comprises three modules of a biochemical reaction module, a mud-water separation module and an equipment integration module; tank bodies of the biochemical reaction module and the mud-water separation module are communicated through partition water holes or overflow weir water holes; a water outlet pipe of a sedimentation tank is connected with an ultraviolet sterilizer in the equipment integration module; the biochemical reaction module comprises a pre-deoxidating mud film tank, a phosphorus-releasing mud film tank, a denitrifying phosphorus-accumulating mud film tank and an aerobiotic mud film tank which are communicated in sequence; a set of intermittent gas disturbance equipment is arranged at the bottom of the denitrifying phosphorus-accumulating mud film tank. According to the efficient town sewage treatment and recycling device and process, the short-flow phenomenon in the tanks is overcome, the microbial community structure distribution of the tanks is optimized, the function of the sedimentation tank is enhanced, the total nitrogen and total phosphorus treatment efficiency is higher, the gas-stripping energy consumption is low, the structure is compact, the occupied area is small, and the sludge floating phenomenon and the effluent suspended matter content can be significantly reduced.

The invention discloses a wire strand defect detection method for a transmission line. Through the method, a wire strand defect of the transmission line can be intelligently recognized. According to the wire strand defect detection method for the transmission line, an image is preprocessed; then wires are separated from a background image through image partitioning; next, feature extraction is performed on a wire image; and finally strand recognition is performed on the wires. The whole process can be automatically completed through a computer, intelligent processing of transmission line inspection data can be realized, the wire strand defect of the transmission line can be intelligently recognized, and recognition efficiency is greatly improved; and moreover, problems existing in manual observation can be greatly reduced with the efficiency, misjudgment or missing judgment caused by manual experience or working strength fatigue is avoided, overall working efficiency is improved, a fine management mode is improved, the intelligent level is raised, a large amount of manual checking time is saved, and a lot of economic investment is saved. The method is suitable for application and popularization in the technical field of image recognition.

The invention relates to the technical field of control systems and discloses an intelligent image acquisition control system. The system comprises an equipment main body, a face identification camera, a hanging vertical plate, a smoke and induction module, an electronic tag reader, an electric switch, a multifunctional interface switch and a video monitoring device are installed on the equipmentmain body, and the equipment main body internally comprises an intelligent assembly operation terminal, a server system, a handheld terminal APP and a display terminal; the intelligent assembly operation terminal comprises station operation terminals and is characterized in that the station operation terminals are arranged on all stations, the station operation terminals are arranged in a moving mode according to on-site station requirements, the station operation terminals are designed in a modular industrial mode, and station coverage within a certain operation radius is achieved. The intelligent image acquisition control system can solve the problems that an existing image acquisition control system is poor in use effect and cannot achieve accurate tracing of management calibration.

The invention discloses a judgment method for alarm of damage to a street lamp in intelligent illumination. The judgment method comprises the following steps: a street lamp control center controls on-off states of a single lamp or power supplying voltage of the single lamp; the street lamp control center sends a regular patrol instruction to a single lamp controller, and the single lamp controller uploads detected single lamp patrol data to a street lamp control box; the street lamp control box feeds back the single lamp patrol data to the street lamp control center; the street lamp control center calculates power factor data in real time according to the uploaded single lamp patrol data, compares the power factor data with a preset single lamp voltage threshold value, a preset current threshold value and a preset power factor threshold value, and judges that the single lamp is in a damaged state and an alarm is sounded if the real-time single lamp patrol data exceed the preset single lamp voltage threshold value, the preset current threshold value and the preset power factor threshold value within a preset time period; judging that the single lamp is in a light source normal state and no alarm is sounded if the real-time single lamp patrol data fall within the preset single lamp voltage threshold value, the preset current threshold value and the preset power factor threshold value within the preset time period.

The invention provides a high-speed train power quality monitoring system comprising a monitoring unit, a data pre-processing unit, a normalization unit, a clustering unit, an outlier detection unit and a power quality database, wherein the data pre-processing unit screens out power quality data of only one vehicle running on a power supply arm according to power quality data when a vehicle runs and the running time of a high-speed train on the power supply arm, and the data pre-processing unit performs missing complement processing and abnormality detection processing on the power quality data; and the clustering unit clusters the power quality data of a sample having undergone normalization processing, to acquire power quality data classes of different vehicle types; the outlier detection unit performs outlier detection on the power quality after clustering processing, obtains an outlier set and sends the outlier set to the power quality database for storage.

The invention provides a high-speed train electric energy quality data processing system comprising a data acquisition unit, a data preprocessing unit, a normalization unit, a clustering unit, an abnormal point detection unit and an electric energy quality database. The data preprocessing unit screens out the electric energy quality data in case of only one train operating on the supply arm according to the electric energy quality data in case of train operation and the operation time of the high-speed train on the supply arm and preprocesses the electric energy quality data. The clustering unit clusters the sample electric energy quality data after normalization processing so as to acquire electric energy quality data classes of different train types. The abnormal point detection unit performs abnormal point detection on the electric energy quality data after clustering processing so as to obtain the abnormal point set and transmit the abnormal point set to the electric energy qualitydatabase to be stored.

The invention discloses a hierarchical design method and system for a multimedia host. A multimedia host software is divided into a driving layer, a media control encapsulation layer and an application layer, wherein the media control encapsulation layer provides a driving layer encapsulation interface for the driving layer to perform encapsulation to the driving layer, so that shielding of the multimedia host hardware platform is realized; the media control encapsulation layer provides an encapsulation interface for a operating system and performs shielding to the operating system; the media control encapsulation layer provides an application layer encapsulation interface for the application layer, a processing parameter loaded by the application layer through the application layer encapsulation interface is acquired directly, and intelligent processing is performed to multimedia data according to the processing parameter. Therefore, through the scheme of the invention, the intelligent processing performed to the multimedia data can be realized, and meanwhile, cross-platform and cross-system transplanting of the multimedia host software is realized.