190results about How to "High intelligence" patented technology

The invention relates to the technical field of intelligent household electrical appliances, and discloses an image acquisition device, comprising: a camera module configured to acquire an image of a target area; a first communication module configured to receive detection data; and the information processing module is configured to input the acquired image and the received detection data into a target information processing model, and control the operation of target equipment according to a control instruction output by the target information processing model. According to the device, the target information processing model is localized, and quick response and timely control can be realized in household appliance control. In particular, during cooking, potential risks can be prevented or intervened, the intelligent degree of cooking can be improved, and the cooking time investment of a user is reduced. The invention further discloses a household appliance and a smart home system.

The invention discloses an optical domain intelligent reconstruction high-integration modular optical fiber data chain and an operation method, and the optical fiber data chain comprises a high-integration optical fiber data chain platform based on an all-optical switching and electro-optical / photoelectric conversion dense array. The platform comprises an intelligent main control computer, an electro-optical conversion dense array card, a high-integration VPX standard case, a photoelectric conversion dense array card and a high-integration all-optical switching matrix board card. The electro-optical conversion dense array card and the photoelectric conversion dense array card are connected with the high-integration VPX standard case, and the high-integration VPX standard case is connected with the high-integration all-optical switching matrix board card; the intelligent main control computer is connected with the high-integration VPX case through an Ethernet interface; and the optical fiber data link platform realizes optical domain intelligent reconstruction of a high-integration modularized optical fiber data link based on a high-isolation all-optical switching technology under the control of the main control computer. The system has the advantages of being good in intelligent degree, high in integration degree, high in reliability, good in universality, extensible, replaceable, upgradable and easy to operate.

The invention is suitable for the technical field of unmanned driving, and provides a double-wheel differential warehouse logistics robot chassis calibration method, which comprises the following steps of: presetting a moving distance, and issuing a moving speed to a trolley; continuously monitoring the distance between the base coordinate system of the trolley and the odometer coordinate system (odom), and when the distance between the base coordinate system and the odometer coordinate system (odom) is detected to be smaller than a first preset range, determining that the trolley reaches a preset moving distance; and the difference value between the actual moving distance of the trolley and the detected distance between the coordinate systems is measured. The linear velocity and the angular velocity of the double-wheel differential moving chassis can be quickly and accurately calibrated, so that the chassis can more accurately position and move a target point during automatic navigation, and the accuracy and the reliability of the chassis during task execution are ensured; therefore, the intelligence degree of the double-wheel differential warehouse logistics robot chassis calibration method is improved.

The invention belongs to the technical field of electric appliances, and particularly relates to a display screen control method, device and equipment and a computer storage medium. State information of a water heater is obtained, when the state information of the water heater is a running state and / or an operation state, the display screen of the water heater is controlled to start brightness display, and the environment brightness of the water heater is obtained; the environment brightness is used for indicating the brightness of the space where the water heater is located, the target brightness of the display screen is determined according to the environment brightness, and the display screen is controlled to display according to the target brightness; according to the method, the problem of electricity waste caused by the fact that the display screen of the water heater is normally on is avoided, and the intelligent degree of display screen brightness control is improved.

The invention provides an intelligent monitoring system and method for well drilling overflow well leakage, and relates to the field of intelligent monitoring, and the method comprises the steps: firstly, collecting the mass flow at an inlet and an outlet of a well drilling circulation system, transmitting the mass flow to a data processing cloud, and then carrying out the feature extraction of the collected data through employing a data analysis and processing algorithm based on artificial intelligence, and the overflow condition and the well leakage condition of the well drilling are monitored by using the time sequence collaborative change between the mass flow time sequence data at the inlet and the mass flow time sequence data at the outlet. Thus, by comprehensively analyzing the time sequence characteristics of the inlet and outlet mass flow, the dynamic relevance of flow change in the drilling process can be comprehensively captured, the monitoring coverage is improved, and therefore the intelligent degree of drilling overflow well leakage monitoring is improved, and the safety and efficiency of drilling operation are improved.

The invention relates to the technical field of coating preparation, and provides a polyurethane conformal coating preparation method which comprises the following steps: S1, inputting requirements of a conformal coating product and used environmental conditions into a weighing module by an operator, and triggering the weighing module to automatically adjust the ratio of raw materials; s2, sequentially adding the weighed polyurethane resin, curing agent, diluent and assistant into a mixing module, mixing to form a mixed raw material, and collecting state data in the mixing process; s3, obtaining the state data through an evaluation module, and carrying out the evaluation to form an evaluation result; s4, if the mixing qualified threshold value is met, heating the mixed raw material through a heating module; s5, transferring the heated mixed raw material into a reaction kettle to form a reaction raw material; s6, rapidly cooling the reaction raw materials to room temperature, and removing impurities to obtain a conformal coating mother solution; and S7, adding the pretreated nano filler into the mother liquor of the conformal coating, and adding a multi-interface reinforcing agent to form a conformal coating product.

The invention relates to the field of intelligent monitoring, and discloses a building safety intelligent monitoring system and method based on the Internet of Things, and the method comprises the steps: obtaining a set of image data of fire-fighting facilities in a building from a cloud platform; and image semantic feature extraction of the image data of the fire-fighting facilities in each building is carried out by adopting an artificial intelligence image analysis and extraction technology, so that whether each fire-fighting facility is abnormal or not is automatically judged according to representation of image semantic coding features of the fire-fighting facilities in each building after hierarchical spatial domain enhancement. And generating an abnormal value of the fire-fighting facility. Through the mode, the advanced semantic information in the image can be better understood, so that whether the fire-fighting equipment is abnormal or not can be more accurately judged, and misjudgment caused by shape or model difference is reduced. Meanwhile, non-target objects in the background and changes of the fire-fighting equipment can be distinguished, false alarms caused by background interference are avoided, and therefore the intelligent degree of fire-fighting equipment abnormity judgment is improved.

The invention relates to the technical field of power systems, and provides a power distribution network structure dynamic deduction method and system based on time sequence dynamic analysis, and the method comprises the steps: carrying out the embedded coding and principal component time sequence aggregation of time queues of power generation side data, power grid side data and user side data through employing a data processing algorithm based on deep learning; and intelligently obtaining a short-term prediction value of carbon emission according to the time-space significant joint representation among the power generation side data feature principal component time sequence aggregation representation, the power grid side data feature principal component time sequence aggregation representation and the user side data feature principal component time sequence aggregation representation. Therefore, by integrating the multi-source data of the power generation side, the power grid side and the user side, the complex time sequence dynamic relationship in the power distribution network can be captured more accurately, so that the prediction of the carbon emission is more accurate, and the real-time performance, the comprehensiveness and the intelligent degree of the carbon emission prediction are remarkably improved.

The invention provides a photovoltaic energy storage scheduling management system. The photovoltaic energy storage scheduling management system comprises a data acquisition module for collecting real-time data; the operation simulation module simulates a future working state based on the data; the decision making module generates a charging and discharging scheduling strategy; the execution module controls the photovoltaic module to interact with the energy storage battery according to the strategy; according to the invention, through real-time data acquisition and accurate simulation and prediction of a working state, an optimal charging and discharging strategy is formulated, and the energy utilization efficiency is improved; an intelligent scheduling mechanism automatically adjusts strategies according to meteorological conditions and load consumption, and the response speed, flexibility and reliability of the system are improved; the automatic execution module reduces human intervention, simplifies the maintenance process and improves the stability and availability of the system; the efficiency and economical efficiency of a photovoltaic system are improved, application of renewable energy sources is promoted, and sustainable development of the environment is promoted.

The utility model discloses a current monitoring and alarming circuit, which relates to the technical field of monitoring and alarming, and comprises a power supply module for supplying power; the load module is used for accessing electric equipment and controlling the electric equipment to stop working; the current detection module is used for current detection and signal processing; the over-current detection module is used for over-current detection, and during over-current, the signal control module carries out self-locking to control the alarm work of the alarm module and controls the working state detection module to start to detect the working state of the load module; and the self-reset control module is used for controlling the signal control module to reset when the working state detection module detects that the load module is restarted and the overcurrent detection module detects overcurrent. When overcurrent occurs, the current monitoring alarm circuit of the utility model stops the work of the load module and gives an alarm, and when the load module is restarted and the overcurrent disappears, the alarm and the work state detection work are automatically stopped, the alarm can be automatically closed, and the alarm means is simple and easy to implement.

The invention relates to the technical field of electric digital data processing, and provides an intelligent interactive commercial display projection screen and multi-screen display system, which comprises a server, display equipment, a circulation module, an interaction module, a display module and an environment perception module, and is characterized in that the interaction module is used for interaction of the display equipment so as to determine an equipment identification code of the display equipment; the environment sensing module senses the environment where the display device is located so as to obtain environment data of the display device, the circulation module enables the interactive display device to conduct circulation of display content and dynamically feeds back display state data of the display device to the display module, and the display module obtains the environment data collected by the environment sensing module and sends the environment data to the display module. And dynamically adjusting display parameters of the display equipment. Through cooperation between the interaction module and the circulation module, the whole system has the advantages of high interaction comfort, high circulation interaction capability, good synchronous display effect and high intelligent degree.

The utility model discloses an intelligent goods shelf for preventing goods from being overweight, and relates to the technical field of intelligent goods shelf production, the intelligent goods shelf comprises a base and a placing groove, an auxiliary mechanism is arranged in the placing groove, and the auxiliary mechanism comprises a bottom plate movably connected to the bottom position of the placing groove and a movable plate at the top position of the bottom plate; a screw rod is fixedly connected to the interior of the movable plate, a crossed supporting rod is arranged outside the screw rod, a standing plate is fixedly connected to the top end of the crossed supporting rod, sliding blocks on the two sides of the bottom plate are slidably connected with sliding grooves of the containing grooves, and a nut base is movably connected to the interior of the movable plate and is in threaded connection with the screw rod; the crossed supporting rod is driven by the screw rod to ascend and descend to a proper height. Compared with an existing common intelligent goods shelf, the intelligent goods shelf capable of preventing the goods from being overweight has the advantages that all goods information and storing and taking conditions of a user can be checked through the face recognition system, the user can conveniently and rapidly take the goods, and the goods taking convenience of the user is improved.

The invention discloses a fault diagnosis method and system for a transmission system. The method comprises the steps that a friction power generation sensor is installed on a coupler of the transmission system; collecting output signals of the friction power generation sensor of the transmission system under different working conditions; performing feature extraction and calibration on the output signal to obtain a data set; training and testing a support vector machine by using the data set to obtain a fault diagnosis model; and intelligent fault diagnosis of the transmission system is carried out based on the fault diagnosis model. The friction power generation sensor is installed on the elastic body of the coupler in a specific installation mode, the amplitude of output signals of the friction power generation sensor is effectively improved, the characteristic difference of the output signals under different working conditions is made to be obvious, the accuracy of subsequent model fault type recognition is effectively improved, the structure is compact, installation is convenient and fast, and the application range is wide; a machine learning algorithm is combined to realize automatic identification of transmission system fault types, and the intelligent degree of industrial automation is improved.

The invention discloses a power grid fault processing scoring method and device based on adaptive weight primitives, and the method comprises the steps: responding to a fault event, and determining fault equipment based on the real-time parameters of a power distribution network fault recovery decision auxiliary model; according to the fault equipment, analyzing a fault range in a first directed acyclic topological graph based on a power distribution network fault recovery decision auxiliary model, and determining a fault accident type, the fault accident type including a single-point fault and a multi-point fault; based on the type and the parameter of the affected equipment in the fault range and the fault accident type, determining a matched quick response plan and a weight prime combination scheme; and based on the weight prime combination scheme, performing scoring operation on each quick response plan. According to the method, multiple sets of personalized power supply recovery schemes can be provided, the system intelligence degree is improved, and automatic fault processing is more efficient and reliable.

The present application discloses a method and device for space modeling and planning of a pallet, wherein the method and device for space modeling and planning iteratively segment the model image of the pallet space in multiple cycles, and determine the cycle process with the largest number of segmentation results as the optimal plan, which can improve the utilization rate of the pallet space when the size of the filling material filling the pallet matches the non-integer multiple of the pallet size. Palletizing is performed based on the relevant space planning method, and on the basis of improving the utilization rate of the pallet, the approaching area of ​​the pallet is determined according to the result of the optimal plan, and after the filling material enters the approaching area, the approaching path is determined according to the segmented area and the approaching area entered by the filling material. On the basis of palletizing with the highest space utilization, the filling material is ensured to approach with the shortest path while avoiding the collision between the current filling material and other filling materials, thereby ensuring the safety of the filling material during the stacking of the filling material.

The invention provides a vehicle distance measurement method and device based on a boundary map, equipment and a storage medium, and can be applied to the technical field of autonomous vehicle perception. According to the method, point cloud data are determined through a positioning device and a radar system, algorithm processing is carried out based on the point cloud data to obtain a boundary map, discrete point taking is carried out on the boundary map to obtain a plurality of target interval points, the target interval points are projected to a target detection image detected by a vehicle camera, a plurality of contour projection points are obtained, and a boundary contour is formed. And according to the plurality of contour projection points and the target detection frame position of the to-be-targeted vehicle, distance measurement of the to-be-targeted vehicle can be completed. According to the method, the boundary map information is utilized, so that visual target distance measurement can be accurately and quickly completed.

The invention discloses an intelligent automatic hanger machine for hot galvanizing of iron accessories, and relates to the technical field of industrial machinery, a linkage type circulating arrangement and transfer mechanism is arranged at the top of a mounting rack main body, and the linkage type circulating arrangement and transfer mechanism is used for arranging and transporting workpieces to be galvanized; according to the multi-point magnetic attraction device, through mutual cooperation of the multiple sets of magnetic attraction installation boxes and the multi-point electromagnetic attraction pieces, the electromagnetic attraction pieces with the proper number and position can be selectively driven to conduct attraction according to the shape and the weight of the iron accessories to be attracted, and therefore the workpieces can be hung on the outer sides of the corresponding hanging tools in order. The transverse position, the longitudinal position and the arrangement density of the iron accessories are adjusted, then it is ensured that the iron accessories can be conveyed forwards in a neat arrangement mode in the hanging process, the hanging frame can rapidly hang the iron accessories conveyed to the tail end of the circulation driving belt, and then the working efficiency of the hanging tool machine is effectively improved; and the working intensity of operators is reduced.

The application discloses a kind of semantic boundary guided robot operation scene point cloud segmentation methods. Firstly, the three-dimensional point cloud of robot operation scene is obtained;Then, the semantic boundary point in the scene three-dimensional point cloud is predicted using point cloud learning network;The scene three-dimensional point cloud is input into point cloud Transformer model for feature extraction, and the semantic boundary point is used as the extended key point of self-attention mechanism in Transformer model, wherein for the point feature of each boundary region, a contrast learning loss function is added to reduce the semantic ambiguity of boundary point feature;Finally, based on the point feature of each point, the semantic class of each point is predicted to obtain the point cloud semantic segmentation result. The application enhances the learned point feature by introducing semantic boundary information in the point cloud feature extraction process, and improves the misclassification problem caused by boundary ambiguous features, effectively improves the point cloud segmentation quality of robot operation scene, and has good engineering practical value.

The embodiment of the invention provides a control method and device of a mobile robot, a storage medium and electronic equipment, and the method comprises the steps: transmitting a target detection signal to a sensing range of a metal sensor through a transmitter of the metal sensor disposed on the mobile robot, a target reflection signal matched with the target detection signal is received through a receiver of the metal sensor, and the sensing range of the metal sensor is located outside the mobile robot; target detection is conducted on the received target reflection signal, a target detection result is obtained, and the target detection result is used for indicating whether a metal object exists in the sensing range of the metal sensor or not; under the condition that it is determined that the target metal object exists in the sensing range of the metal sensor according to the target detection result, the mobile robot is controlled to execute equipment operation matched with the target metal object; according to the invention, the precision of metal object recognition can be improved.

The invention relates to the technical field of near infrared spectrum analysis, in particular to a near infrared spectrum analysis method and system based on spectrum image feature fusion. The method comprises the following steps: acquiring physicochemical properties corresponding to a batch of samples, measuring near infrared spectrums of the samples and forming a modeling sample set; randomly selecting two near infrared spectrums from the sample set to construct a two-dimensional grey-scale map; extracting near infrared spectrum characteristics from the two-dimensional grey-scale map, and preprocessing the near infrared spectrum characteristics; processing the near infrared spectrum features by using a principal component analysis technology to generate feature vectors; constructing a regression model based on the feature vector and the physicochemical property data of the sample to fit the relationship between the feature vector and the physicochemical property data of the sample; and inputting the feature vector of a to-be-analyzed sample to the regression model, and outputting a prediction result of the physicochemical properties of the to-be-analyzed sample. According to the method, the near infrared spectrum analysis precision is improved by adopting a directional rapid rotation brief feature image extraction technology.

The present invention relates to the technical field of cable manufacturing. The present invention provides a manufacturing system for a low-smoke halogen-free flame-retardant cable, comprising a raw material processing module, a multi-layer co-extrusion module, a clamping module, a collection module, a quality assessment module, an adjustment module and a cooling module. The raw material processing module heats and stirs an insulating raw material and a flame-retardant raw material respectively, and supplies the heated and stirred insulating raw material and the flame-retardant raw material to the multi-layer co-extrusion module. The multi-layer co-extrusion module sequentially extrude the insulating raw material and the flame-retardant raw material and wraps them around the outer periphery of a conductor to form an insulating layer and a flame-retardant layer of a double-layer structure. The clamping module clamps and fastens the insulating layer and the flame-retardant layer of the formed double-layer structure. The cooling module cools the clamped and fastened double-layer structure. The quality assessment module evaluates the insulating layer and the flame-retardant layer of the cable according to the state data collected by the collection module to form an evaluation result. The adjustment module triggers adjustment of extrusion parameters of the multi-layer co-extrusion module according to the evaluation result.

The utility model relates to the technical field of pumped storage, in particular to an intelligent lampshade for a pumped storage power station unit, which comprises a lampshade body, a lighting unit, a central control device and a unit running state indicating unit. The cover body comprises a top cover plate and a closed-loop side plate, and a collector ring chamber is formed in the cover body; an access door is formed in the closed-loop side plate; the lighting unit is arranged on the top cover plate and / or the closed-loop side plate and is electrically connected with the central control device; the unit operation state indicating unit is installed on the closed-loop side plate and electrically connected with the central control device. The central control device is located in the collector ring chamber and is installed on the closed-loop side plate. The technical scheme is a device with unit state display and intelligent illumination control functions, is installed on a collector ring body of a generator layer, can indicate the operation state of a unit, can automatically control an illumination and ventilation system in an outer cover, and achieves the purpose of intellectualization of the outer cover.

The utility model relates to the technical field of fire-fighting equipment, in particular to an intelligent fire detection fire-fighting linkage system, which consists of a linkage control cabinet, a plurality of field control boxes, a fire detector and a fire extinguishing device, each field control box is connected with at least one fire detector and one fire extinguishing device, and the field control box is also connected with a manual control panel; the linkage control cabinet is provided with a multi-channel signal module, an equipment parameter setting module and remote control fire extinguishing, the field control box is provided with a signal acquisition module and an equipment control module, the fire detector is provided with a communication interface module, and the fire extinguishing device is provided with a fire extinguishing device communication module. The intelligent fire-fighting device is compatible with various types of fire-fighting equipment, various signal detection modes and various equipment communication modes, compatibility of various automatic and manual fire extinguishing intervention modes is realized, and the applicability is greatly improved.

The present disclosure relates to a method, device, storage medium and equipment for controlling intelligent devices to improve the intelligence of intelligent device control. The method includes: in response to receiving a control instruction initiated to a target device, controlling a target virtual device in a virtual world to execute the control instruction, and obtaining virtual operation information, wherein the target virtual device is a mapping object of a target device in the real world in the virtual world, and the virtual operation information includes the scope of influence of the target virtual device on the virtual world after executing the control instruction; determining the target virtual objects in the virtual world within the scope of influence, and the degree of influence of the control instruction on the target virtual objects; determining the instruction execution strategy according to the degree of influence; and controlling the target device to execute the control instruction according to the instruction execution strategy.

The invention relates to a vehicle light control method and device, a controller and a storage medium. The method comprises the steps that the mass center position of a vehicle performance site and the target performance position of any performance vehicle are acquired; according to each target performance position and the mass center position, obtaining a light sequence index of each performance vehicle and a special effect granularity of each performance vehicle; constructing light control information of each performance vehicle according to each light sequence index and each special effect granularity, and constructing a control command of each performance vehicle according to each light control information and each target performance position; and sending each control command to each performance vehicle to indicate each performance vehicle to execute light performance according to the special effect granularity and the light sequence index after arriving at each target performance position. By adopting the method, the light performance can be executed according to the special effect granularity and the light sequence index, so that the intelligent degree of the light performance is improved.

The invention relates to a QEC (Quality Error Correction) maintenance safety supervision method and system based on AR (Augmented Reality). According to the method, after a maintenance general task is generated, the maintenance general task is decomposed into a plurality of sub-tasks and sent to pre-obtained online AR equipment, and a maintenance piece where each sub-task is located and a target model are obtained; obtaining an associated sub-task set according to the maintenance piece associated sub-tasks; when the current sub-task is executed, acquiring a marked sub-task from the associated sub-task set of the current sub-task; acquiring a real-time model of a maintenance piece where the marked sub-task is located, and executing the next sub-task if the real-time model meets a first preset condition before and after the current sub-task is executed; if the real-time models of the maintenance pieces where all the sub-tasks are located in the current associated sub-task set meet a second preset condition, the associated sub-task set is qualified; and when the completion time of all the sub-tasks and the total task real-time model meet a third preset condition, the maintenance total task is qualified. Compared with the prior art, the method has the advantages of improving data analysis efficiency and accuracy in QEC maintenance work and the like.

The application discloses a robot operation target 6D pose tracking method based on time sequence point cloud fusion. First, a point cloud video sequence of a robot operation scene is acquired and an operation target is segmented from the point cloud video sequence, then, dense corresponding relations among time sequence observation point clouds are established in a reverse prediction mode, and the dense corresponding relations are taken as a fusion criterion to perform point-by-point feature fusion on the time sequence observation point clouds, on the basis of the point-by-point feature fusion, a transformation pose between adjacent frames is predicted from the time sequence fused features in a confidence degree regression mode, finally, the transformation pose between the adjacent frames is continuously regressed to realize continuous pose tracking of the operation target. The application tracks a 6D pose of a robot operation target from a three-dimensional point cloud video sequence based on a deep learning technology, in view of irregularity and disorder of three-dimensional point cloud data, time sequence correlation information among observation point cloud data is fully utilized and effective feature fusion is performed, accurate and stable tracking is realized, and the application has good engineering practical value.

This application provides a cleaning method and apparatus for a condiment machine, a storage medium, and the condiment machine itself. The method includes: in response to a cleaning command, determining at least one target cleaning pipe of the condiment machine, wherein the target cleaning pipe is a condiment conveying pipe of the condiment machine; acquiring cleaning parameters for each target cleaning pipe; and, based on the cleaning parameters, controlling the operation of a cleaning pump corresponding to each target cleaning pipe, so that cleaning material flows out of the target cleaning pipe under the action of the cleaning pump. The method of this application achieves automatic cleaning of the condiment conveying pipe, improving the level of intelligence.

The invention relates to water supply equipment, and relates to the technical field of household appliances. In the application, the bracket comprises a base, and the base is provided with a bearing surface for bearing the water container; a water outlet of the water supply assembly is formed above the bearing surface; the water supply equipment has a manual triggering mode and an automatic triggering mode, in the manual triggering mode, the control assembly controls the water supply assembly to supply water to the water outlet based on manual triggering of a user, and in the automatic triggering mode, the control assembly controls the water supply assembly to supply water to the water outlet based on the water level of the water container; the in-place detection assembly responds to the situation that the water container is placed on the bearing face to generate an in-place instruction. The control component disables the manual trigger mode and enables the automatic trigger mode in response to the seating indication. According to the invention, more operation modes can be provided for control, and the control requirements of the user are enriched. In addition, the intelligent degree can be improved.

This invention provides a motion control method and apparatus for a multi-legged robot. The method includes controlling the multi-legged robot to switch to a preset control mode when the force acting on the multi-legged robot changes. This invention solves the problem of motor idling and loss of control in multi-legged robots that are suspended in the air, a problem present in related technologies. It effectively controls the movement of the multi-legged robot's legs, improves the robot's intelligence, and reduces damage to the robot.