688 results about "Work site" patented technology

To predict the working time of sorting work for taking out merchandise and sorting it for each shipping destination.SOLUTION: The prediction device 100 includes a prediction unit 113 that predicts a work time of sorting work, which is work of taking out and sorting articles from a storage that stores the articles, based on a plurality of orders related to the articles (commodities), and calculates the work time as a predicted work time. The prediction unit 113 calculates the predicted working time based on the input information including the type of article to be taken out from the storage, the number of articles to be taken out from the storage, and the number of articles included in each order. The storage may be a storage shelf that the transport robot carries to a work place of the sorting work. The item may be transported along a predetermined path to a work location of a sorting operation. Further, a worker who performs the sorting work may move to a place where the storage is placed and perform the sorting work.SELECTED DRAWING: Figure 3

The invention discloses a video analysis-based multi-scene operator violation behavior identification method and system, and belongs to the technical field of intelligent operation safety monitoring and artificial intelligence identification, and the method comprises the steps: collecting a real-time video stream of a multi-scene operation site; recognizing a continuous action time sequence in the real-time video stream by using an action recognition depth model; constructing the continuous action time sequence into an action behavior sequence; the action behavior sequence is constructed into a directed behavior graph with time, space and action labels, the directed behavior graph is compared with a directed behavior graph corresponding to the standard action behavior sequence, and illegal behaviors are recognized; and carrying out multi-mode early warning on the identified illegal behaviors. According to the method, the bottleneck that the traditional image recognition technology is weak in action sequence semantic understanding and poor in environmental adaptability is broken through, and accurate recognition and real-time early warning of illegal behaviors in multi-scene operation are achieved.

The invention discloses a power worker behavior detection method and related equipment. The method comprises the following steps: acquiring first data in a scene where a worker is located through a camera in a working site; the first data comprises continuous frame images or a video sequence lasting for preset time; analyzing the first data to obtain a current first identification result of the operator; the first identification result is used for representing whether the operator lacks of wearing the protective equipment and / or carries illegal articles; determining the current posture of the operator from the first data; and fusing the first recognition result and the current posture to obtain the operation risk level of the operator. The method can be widely applied to the technical field of artificial intelligence.

The invention discloses an operation analysis method and system for a mobile robot fused with an industrial mechanical arm, and the method comprises the steps: receiving a work order, then splitting a task, determining sub-task parameters, and optimizing the predicted time based on historical data; mapping and positioning are synchronized in the moving process, and the positioning precision is guaranteed through an SLAM model and prediction-correction logic; planning a global path and a residence position, and coping with a dynamic obstacle through a weighted scoring method and an MPC model; the operation position is precisely aligned to compensate the ground unevenness error; recognizing a workpiece and selecting an optimal grabbing point; the contact force and rigidity are dynamically adjusted when operation is executed, and automatic retreating and fine adjustment are performed when abnormity occurs; the grabbing quality and the advancing safety are confirmed; and data is updated after ending, and low-power automatic charging is realized. According to the method, the problems that a traditional technology path and operation planning are separated, sensing is single, robustness is poor, an operation strategy is difficult to adapt, and a standardized quick change and calibration mechanism is lacked are solved.

The invention discloses an iron tower operation safety early warning system and method, and relates to the technical field related to intelligent safety early warning, and the system comprises a data obtaining unit which is used for obtaining Beidou three-dimensional coordinate data and an operation site panoramic image in real time; the operation scene model establishing unit is used for establishing a dynamic three-dimensional operation scene model; the prediction model building unit is used for tracking the motion trail of each operation target based on the coordinate data and building a prediction model fusing kinematics rules and machine learning; and the risk level judgment unit is used for carrying out risk level judgment according to the spatial position and the attribute characteristics of the intersection area and generating operation early warning information. The technical problems of insufficient safety early warning accuracy and timeliness caused by insufficient high-altitude operation target dynamic track monitoring precision and risk early warning lagging in the prior art are solved, and the purposes of accurately identifying the movement track intersection risk in real time, dynamically evaluating the safety level and improving the safety early warning efficiency are achieved. And the early warning accuracy and timeliness of the operation safety of the iron tower are improved.

The invention relates to the technical field of wireless positioning, in particular to an intelligent positioning analysis method and system for a safety tool, and the method comprises the steps: collecting the video data and voice data of a high-altitude operation site in real time through a video collection module worn by an operator; the method comprises the following steps: acquiring far-end high-altitude operation video data through a ground camera, and when the far-end high-altitude operation video data is lower than a preset value, acquiring three-dimensional position data of personnel in real time through a wireless positioning module; establishing a three-dimensional electronic fence model on the monitoring platform, and synchronizing the three-dimensional position data to the three-dimensional electronic fence model; when the monitoring platform detects that the three-dimensional position data exceed the three-dimensional electronic fence, early warning is triggered; after early warning is triggered, video data and voice data of the aerial work site in the corresponding time period are obtained, personnel posture information in the video data is analyzed, and abnormal types are recognized in combination with voice keywords. Therefore, personnel supplementary positioning under the condition of low visibility can be realized, and the reliability of the positioning monitoring system is improved.

A system for autonomous or semi-autonomous operation of a vehicle is disclosed. The system includes a machine automation portal (MAP) application configured to enable a computing device to (a) display a map of a work site and (b) provide a graphical user interface that enables a user to (i) define a boundary of an autonomous operating zone on the map and (ii) define a boundary of one or more exclusion zones. The system also includes a robotics processing unit configured to (a) receive the boundary of the autonomous operating zone and the boundary of each exclusion zone from the computing device, (b) generate a planned command path that the vehicle will travel to perform a task within the autonomous operating zone while avoiding each exclusion zone, and (c) control operation of the vehicle so that the vehicle travels the planned command path to perform the task.

The invention relates to the technical field of risk assessment based on big data, and provides a post-disaster regional operation risk assessment method based on a Beidou technology, and the method comprises the steps: building an impact analysis model based on disaster types through multi-dimensional information, and combining with the condition of a target work site, so as to assess the risk of post-disaster field operation. In order to achieve the purpose, the post-disaster regional operation risk assessment method based on the Beidou technology is provided and comprises the steps that daily multi-source data collection and standardization processing are carried out on a target region, and indoor and outdoor scene dynamic judgment models are established respectively for risk index calculation; and after the disaster occurs, detecting the target area again, comparing the detection result with the comprehensive risk index, and accurately evaluating the risk again. According to the method, after-calamity risk assessment is converted from fuzzy judgment to quantitative accuracy, operation preparation is converted from experience driving to data driving, and direction guidance is provided for after-calamity safe and efficient operation in the power industry through risk assessment.

An unmanned vehicle management system includes: an inter-vehicle distance determination unit that determines an inter-vehicle distance between a sprinkling vehicle and an unmanned vehicle traveling behind the sprinkling vehicle in a same direction as that of the sprinkling vehicle based on a sprinkling state from a sprinkling spray provided in the sprinkling vehicle traveling in a work site; and an output unit that outputs, to the unmanned vehicle, inter-vehicle distance data indicating the inter-vehicle distance determined by the inter-vehicle distance determination unit.

The utility model discloses a labeling and sleeving integrated device which comprises a labeling mechanism, the labeling mechanism structurally comprises a rotary conveying mechanism, a self-rotation driving mechanism capable of driving a container to rotate is arranged at each station of the rotary conveying mechanism, and a container input mechanism, a labeling assembly and a container output mechanism are arranged on the outer side of the rotary conveying mechanism. The container output mechanism comprises an output star wheel assembly, the output star wheel assembly comprises an output star wheel, a plurality of clamping and blocking grooves are evenly formed in the circumference of the output star wheel at intervals, and at least one set of labeling mechanism is arranged above the path, rotating outwards from the rotary conveying mechanism, of the output star wheel. The labeling machine has the advantages that the structure is simple and extremely compact, the length of the conveying mechanism is greatly shortened, so that the space occupied by equipment is effectively saved, and labeling and labeling are efficient, rapid and stable.

The invention provides a mechanical arm teleoperation system adaptive to a quadruped robot and a control method, and relates to the technical field of robot control. According to the method, firstly, a far-end main mechanical arm is introduced on the basis of a mechanical arm of the quadruped robot to form a main-end mechanical arm system and a slave-end mechanical arm system, and a remote operator remotely maps an action instruction to the slave-end mechanical arm system by controlling the main-end mechanical arm; then, a clamping jaw module with an image and tail end contact force sensor is installed at the tail end of the slave end mechanical arm, and image data collection and tail end contact force collection on a working site are achieved; secondly, the image information and the tail end contact force are remotely transmitted to a remote operator in real time through a wireless transmission module and a remote man-machine interaction module; and finally, a remote operator controls the main end mechanical arm in real time according to the real-time image information and the tail end contact force, remote operation of the quadruped robot mounting mechanical arm in a complex scene is achieved, and the operation efficiency and the operation precision are improved.

The invention discloses a facility agriculture voice interaction system based on a large model, and relates to the technical field of voice interaction. Comprising a voice signal acquisition and enhancement module, a voice recognition and semantic standardization processing module, a feature extraction and emergency degree quantification module, an intelligent evaluation and emergency instruction judgment module and a priority scheduling and response execution module, voice signals are continuously monitored through a multi-microphone array of the wearable terminal, the direction of a voice source is enhanced by using a far-field beam forming technology, the signals are processed through a time domain / frequency domain noise reduction algorithm, and finally voice streams are cached in real time with millisecond-level sampling precision. Through the multi-microphone array and far-field beam forming technology, voice capture is optimized, noise is reduced, real-time voice recognition and semantic analysis of the edge server are combined, the priority of emergency instructions is quantified, it is ensured that resources are rapidly scheduled to process emergency tasks, the agricultural production efficiency is improved, and crop losses are reduced.

The invention discloses a stacker fault diagnosis method based on lightweight MobileViT, and relates to the field of stacker fault diagnosis, and the method comprises the steps: S1, deploying a sensor group based on a stacker work site, and obtaining original sensing data of eight modes; s2, preprocessing the obtained original sensing data based on a multi-sensor data fusion preprocessing process of noise reduction reconstruction-fusion-two-dimensional coding to obtain corresponding two-dimensional image data; s3, dividing the obtained two-dimensional image data, and training a MobileViT model based on the training set and the verification set; s4, inputting the test set into the trained MobileViT model to perform fault diagnosis, and performing visual analysis on the result, the lightweight MobileViT model designed by the application can greatly reduce the parameter quantity of a traditional deep learning model; the method has good classification performance, and especially has good practicability in the field of fault diagnosis of the stacker.

The invention provides a man-machine interaction safety dynamic early warning method based on digital twinning and behavior prediction, and the method comprises the steps: S1, collecting the real-time data of a working site through a sensing layer, and enabling the data to comprise the personnel position, equipment state and environment information; s2, constructing a digital twin model based on the acquired data, wherein the model maps the dynamic state of a working site in real time; s3, generating a personnel behavior track and an equipment action range through a prediction algorithm, and calculating a dynamic risk field to evaluate space-time conflicts; s4, according to the risk value of the dynamic risk field, triggering a multi-stage early warning mechanism to reduce the risk of the operation field; and S5, displaying the real-time state and risk information in the digital twinborn model through a visual interface. According to the invention, through deep fusion of digital twinning and dynamic risk prediction, real-time monitoring and accurate prevention and control of the safety risk of the operation site are realized, and the safety management efficiency and the operation safety are greatly improved.

The invention discloses a robot system. The robot system comprises a robot and an AI vision device. Comprising an imaging module used for shooting a video image of a robot working site in real time; the partitioning module is used for partitioning the shot video image into a plurality of different regions; the identification module is used for identifying whether a person enters the plurality of different areas or not; and the control module communicates with the robot and is used for controlling the robot according to the recognition result of the recognition module. The control module comprises a plurality of different areas, the plurality of different areas comprise a first virtual guardrail area surrounding the robot, and when the identification module identifies that a person enters the first virtual guardrail area, the control module sends a control instruction for stopping operation to the robot so as to control the robot to stop operation immediately. Therefore, the safety of the guardrail-free robot system can be improved.

The invention provides an intelligent laser cutting device for machining steel special for a machine tool, and relates to the field of laser cutting, the intelligent laser cutting device comprises a waste collecting assembly, the waste collecting assembly is composed of a switching mechanism and triggering mechanisms, and the two triggering mechanisms can be alternately used under the action of the switching mechanism; therefore, the phenomenon that waste overflows and scatters into a working environment after being full of the waste is avoided, waste cleaning buffer time is provided for workers through an automatic switching mechanism, neatness and orderliness of a working site are guaranteed, the waste collecting efficiency is improved through a flexible alternate use mode, and the waste collecting efficiency is improved. The working pressure of manual inspection and emergency cleaning is reduced, and the problems that waste generated by cutting of the laser cutting device usually directly falls into a manually-placed collecting box, an operator needs to regularly check the waste accumulation condition in the collecting box, and if the waste is not cleaned in time, the waste can overflow out of the collecting box and scatter into the working environment are solved.

The invention provides a power transformation maintenance management and control method based on an intelligent safety helmet, and belongs to the technical field of power transformation maintenance. Comprising the following steps: analyzing a maintenance operation work ticket, and obtaining maintenance items, operators and operation areas; a worker wears an intelligent safety helmet to complete local networking; matching and associating the intelligent safety helmet with an operator; an electronic fence is determined according to the operation area, and coordinate information of the electronic fence is synchronized to all the intelligent safety helmets in the group; in a working site, the intelligent safety helmet is used for safety management and control. The method can achieve the automatic analysis of the work ticket, carries out the electronic identity matching of an operator, and guarantees that the operator accords with the regulation of the work ticket. In the operation site, the intelligent safety helmets worn by the maintenance responsible person provide global safety control, and the intelligent safety helmets worn by other operators realize mutual auxiliary monitoring, so that an omnibearing control system for the operation site is constructed, the control coverage range is obviously improved, and the system is more comprehensive.

A work support system for an excavator, including the excavator; an environment detection device configured to detect environment information of a work site of the excavator; and a simulation device configured to acquire the environment information detected by the environment detection device during a motion of the excavator, and to generate a three-dimensional virtual space model of the work site.

The present disclosure provides a work machine capable of setting a restricted area on the basis of an instruction in a natural language. This work machine (shovel 100) comprises an attachment (AT) for work, an information acquisition unit (301), a language conversion unit (303), an instruction acquisition unit (302), and an area setting unit (306). The information acquisition unit (301) acquires information pertaining to the posture of the attachment (AT) and the surrounding environment. The language conversion unit (303) converts the information acquired by the information acquisition unit (301) into a natural language. The instruction acquisition unit (302) acquires an instruction in the natural language from an operator. The area setting unit (306) sets restricted areas (RA1 to RA10) in which entry or operation speed is restricted at a work site. The area setting unit (306) sets the restricted areas (RA1 to RA10) on the basis of a result obtained by interpreting, using a language model (LM), the instruction acquired by the instruction acquisition unit (302) and the information converted into the language by the language conversion unit (303), or on the basis of a result obtained by interpreting the instruction acquired by the instruction acquisition unit (302) using the language model (LM), in combination with the information acquired by the information acquisition unit (301).

The invention relates to an engineering machinery remote control method and device based on the Internet of Things, equipment and a medium. The method comprises the following steps: acquiring multi-source data of a working site, and after preprocessing, separating key features by using an optimized support vector machine model to obtain a key feature set; based on the set, utilizing a deep neural network to fuse multi-source data to generate an integration state model, and synchronously and dynamically adjusting data acquisition frequency according to network bandwidth fluctuation to obtain a final integration state model; the transmission delay of the data is evaluated, semantic classification and compression are carried out on the optimized data, and a visual interface is generated after transmission analysis; and acquiring interface interaction data, converting the interface interaction data into a control instruction, calculating a signal parameter modification value, verifying control delay compliance, and finally generating remote control response data containing execution confirmation information. By adopting the method, the intelligent level and the operation safety of remote control of the engineering machinery are remarkably improved, and the labor and operation and maintenance cost is reduced.

The invention discloses a safety operation whole-process intelligent management and control method, system and device and a storage medium, and relates to the technical field of safety operation and intelligent management and control, and the method comprises the steps: collecting operation admission data, carrying out the matching of an operator and a task according to a preset rule, and generating operation permission information and an operation bill; on the basis of the work permission information and the work bill, work site sensing data of the authorized work personnel in the work process are collected in real time, and work behavior analysis is conducted on the work site sensing data; and based on the operation behavior analysis result, performing collection, association and marking processing on the operation admission data and the operation bill, and outputting marking information. According to the method, compliance matching between operating personnel and tasks is ensured, personnel without qualification or with inconsistent conditions are prevented from entering an operation link, structured management of operation full life cycle data is realized, and subsequent tracking, analysis and intelligent supervision are facilitated.

To allow even a youth worker to efficiently perform danger prediction activity and check before work with the same level as that of a veteran worker.SOLUTION: A danger prediction training system comprises: a worker terminal 20 used by a site worker; a site information DB 40 in which information about a work process registered beforehand is conserved; an accident case information DB 50 which manages safety information related to a site; and a work input unit 60 which exchanges information with the worker terminal 20. The work input unit 60 extracts the day's work from the work process registered beforehand about a work site identified by the site worker who operates the worker terminal 20, extracts a pre-checking item matching with the work content on the basis of each information on the site information DB 40 and the accident case information DB 50, and issues a danger prediction sheet on the basis of the extracted pre-checking item to transmit the sheet to the worker terminal 20. The worker terminal 20 presents the information on the danger prediction sheet transmitted from the work input unit 60 to the site worker.SELECTED DRAWING: Figure 1

This increases the possibility of improving workers' work efficiency and transferring know-how from the work site to the next level. [Solution] A molding support device comprising: an objective information acquisition unit that acquires objective information indicating the purpose of work on a molding apparatus; an operation information acquisition unit that acquires operation information indicating the operator's operations during the work; and a writing unit that writes the operation information acquired by the operation information acquisition unit to a storage unit in association with the objective information acquired by the objective information acquisition unit.

The utility model relates to the field of insulation resistance detection tools, in particular to an insulation resistance detection tool for a hot-line work site, which is characterized in that a pull rod I and a pull rod II which are connected with each other are mounted in the middle of a handle piece in a limiting and sliding manner, one side of the pull rod I is connected with the pull rod, and a pair of clamping claws is rotationally mounted at one end of the pull rod II through an adapter plate. According to the utility model, the transverse rod is pulled to drive the clamping claw to move through the pull rod assembly, the clamping claw is in extrusion contact with the inner wall of the handle piece in the moving process and deflects inwards to clamp the test piece, and the clamping claw can stably clamp the test piece along with the movement of the transverse rod; and meanwhile, the wire penetrates through the pull rod assembly and is mounted on the rotating column of the clamping jaw for connection testing, so that the stability and the safety during detection are effectively ensured.

The invention provides a self-adaptive non-invasive physiological regulation and equipment cooperation method for high-altitude operating personnel, which comprises the following steps of: gathering physiological parameters, environment monitoring data and task information of the operating personnel in real time through edge computing nodes deployed in an operating site, and dynamically evaluating altitude stress risk levels and inducements of the operating personnel based on preset rules; according to the risk assessment result and the current working mode, an accurate parameter regulation and control instruction for personnel protection equipment is intelligently matched and executed, collaborative operation suggestions for forestry operation equipment such as chain saws and patrol unmanned aerial vehicles are generated, and the operation parameters or operation behaviors of the forestry operation equipment are guided to adapt to the physiological states of personnel. According to the invention, closed-loop linkage and self-adaptive cooperation among the personnel physiological state, the environmental load and the operation task are realized, continuous and personalized non-invasive physiological support and safe operation guarantee can be provided for the operation personnel under complex field conditions, and the intelligent level and operation safety of high-altitude forestry management are remarkably improved.

A detection system for a work site includes: a current terrain data storage unit that stores current terrain data of the work site where a work machine operates; a first detection data acquisition unit that acquires detection data of a first sensor that detects surroundings of the work machine; and a determination unit that determines whether specific data detected by the first sensor is noise or an obstacle on the basis of the current terrain data.

The invention relates to the technical field of building construction, and discloses an intelligent control method and system for super high-rise building construction, and the method comprises the following steps: S1, carrying out the real-time positioning of a super high-rise building high-altitude operation worker through intelligent safety monitoring equipment which is integrated with a high-precision position sensor and integrates GNSS and UWB technologies, enabling the positioning precision to reach the centimeter level, and enabling the positioning precision to reach the centimeter level; meanwhile, the motion state of a person is sensed cooperatively through acceleration and tilt angle sensors, environmental parameters such as wind speed, temperature and humidity of a working site are monitored through multiple environmental parameter sensors, collected data are transmitted to an edge calculation module for preliminary screening and analysis, and abnormal behavior recognition is conducted through a preset abnormal behavior recognition algorithm; and triggering local early warning within millisecond-level time. Through a high-precision positioning technology, the position of an operator is accurately determined, an optimal rescue path is planned, surrounding rescue workers and equipment are reasonably allocated, the rescue progress is tracked in real time until rescue is completed, and the accident loss is reduced to the maximum extent.

The invention relates to the field of monitoring systems, and particularly discloses a work site safety behavior monitoring system based on AI video monitoring, which comprises a data acquisition module used for acquiring a high-definition video stream of a work site in real time; the edge calculation module is used for preprocessing the video stream; the behavior recognition module is used for detecting and classifying safety behaviors in the video stream through a deep learning model and outputting behavior types and coordinates; and the dynamic weight library comprises a weight configuration unit, an environment factor acquisition unit, a dynamic adjustment unit and a weight output unit. According to the operation site safety behavior monitoring system based on AI video monitoring, environmental factors are fused in real time through the dynamic weight library, the safety behavior risk weight is automatically adjusted, the risk assessment precision in a complex scene is remarkably improved, and false alarm and missing alarm caused by environmental interference are reduced.

This utility model provides an expansion joint cleaning device, comprising: a suction frame connected to a garbage collection bin for sucking garbage into the garbage collection bin; a suction assembly connected to a high-pressure centrifuge, wherein there is at least one suction assembly, which is fixed downwardly at least on one side of the suction frame for sucking up smaller pieces of garbage from the road and bridge expansion joint; a spray washing assembly hinged to the upper part of the suction assembly for rinsing up smaller pieces of garbage from the road and bridge expansion joint; and a sealing assembly rotatably installed at the lower part of the suction assembly for sealing the suction assembly. This utility model cleans the internal gaps of the expansion joint through high-pressure washing by the spray washing assembly, regardless of the depth of the expansion joint; and sucks up mud, garbage, and water used for cleaning from the expansion joint through the suction force of the suction assembly, achieving not only thorough cleaning of the internal gaps of the expansion joint but also collecting mud, garbage, and cleaning water all at once, ensuring a clean and aesthetically pleasing work site.