66 results about "Plant models" patented technology

Disclosed is a method for monitoring and / or controlling a chemical plant (12) with multiple assets via a distributed computing system (10) with more than two deployment layers (14, 16, 30, 32, 34), wherein the deployment layers (14, 16, 30, 32, 34) comprise at least two of a first processing layer (14), a second processing layer (16, 32, 34) and an external processing layer (30), the method comprising the steps of: providing (60) a containerized application (48, 50) including an asset or plant template specifying input data, output data and an asset or plant model, deploying (62) the containerized application (48, 50) to execute on at least one of the deployment layers (14, 16, 30, 32, 34), wherein the deployment layer (14, 16, 30, 32, 34) is assigned based on the input data, a load indicator, or a system layer tag, and executing the containerized application (46, 52, 54) on the assigned deployment layer(s) (14, 16, 30, 32, 34) to generate output data for controlling and / or monitoring the chemical plant (12), providing (66) the generated output data for controlling and / or monitoring the chemical plant (12).

The invention relates to the technical field of power plant supervision, and particularly discloses a BIM-based power plant safety supervision method and platform, and the method comprises the steps: obtaining a BIM model of a power plant, and building a three-dimensional power plant model based on the BIM model; operating parameters of equipment are collected, and a risk area with the equipment model as the center is created in the three-dimensional power plant model according to the operating parameters of the equipment; obtaining a position relationship between the human body model and the risk area, and generating prompt information pointing to the human body model according to the position relationship; and acquiring the real-time position of each human body model in a work cycle, and performing work rating on the human body models according to the relationship between the risk area and the real-time position. According to the method, the recognition result of the camera system is counted by means of the BIM model and then displayed, the risk area with a prediction function is introduced in the display process, risk recognition is performed on the staff according to the predicted risk area, the prompt information is generated, and the safety degree of the staff is improved.

A method and system for optimizing power management for a hybrid system of a machine are provided. The method includes generating a plant model based on a machine recipe of the machine; generating, in an algorithm library, algorithms for a plurality of scenarios simulated based on selected key performance indicators (KPIs) associated with the machine recipe, optimization connections, and machine requirements of the machine; selecting an algorithm from the algorithm library based on computational capabilities of a controller associated with the machine and machine requirements for the algorithm; simplifying the algorithm based on removing one or more KPIs of the selected KPIs; refining the algorithm based on weighing one or more remaining KPIs of the selected KPIs; and integrating the algorithm into machine operation to be performed by a control module of the machine.

The invention provides a simulation system and method for a typhoon rainstorm induced combined flow-slip disaster, and the system comprises a side slope simulation box which is used for simulating a side slope covered by vegetation; the wind load control system is used for simulating a wind load applied to the slope simulation box and controlling a wind load time history according to a set typhoon level; the rainfall control system comprises a variable-frequency water pump and is used for determining the rainfall intensity according to the set typhoon level, determining the target power of the variable-frequency water pump according to the rainfall intensity, simulating rainfall and controlling the rainfall time history; and the spatial three-dimensional visual data acquisition system is used for acquiring multi-section visual three-dimensional data of the three-mechanism coupling catastrophe simulation process of the slope model in real time under the action of the wind load, rainfall and the plant model. Through the application, the three-mechanism coupling catastrophe process of the slope model under the action of wind load, rainfall and the plant model is accurately simulated, the three-mechanism coupling catastrophe mechanism in the soil body is disclosed, and dynamic three-dimensional analysis of engineering is realized.

The invention provides a plant three-dimensional reconstruction method and system based on image segmentation and projection guidance, and is applied to the technical field of plant three-dimensional reconstruction, and the method comprises the steps: obtaining a multi-view image sequence of a target plant, the multi-view image sequence being plant images of the target plant collected from a plurality of angles; inputting the multi-view image sequence into a target detection model to obtain a plant positioning image set and a plant positioning frame output by the target detection model; taking the plant positioning frame as prompt input, and inputting the plant positioning image set into a preset image segmentation model to obtain a plant mask of the target plant output by the image segmentation model; performing mask processing on the multi-view image sequence based on a plant mask to obtain a pure multi-view image; and performing three-dimensional reconstruction based on the pure multi-view image through a 3D Gaussian scattering framework to obtain an initial three-dimensional plant model corresponding to the target plant. According to the invention, the interpretability and the three-dimensional contour definition of the plant structure can be improved.

Methods and systems are disclosed for modeling and decoding neural activities. A brain machine interface (BMI) measures neural activities. A processor receives signals corresponding to the neural activities from the BMI. The processor generates by applying a neural dynamics model signals corresponding to a de-noised state of the neural activities. By applying a BMI decoding model to the de-noised signals, the processor generates a control signal, which is used by a BMI plant model to generate a movement vector. An object is moved according to a predetermined path, in response to the movement vector and the current state of the object. In response to the object's movement, the BMI continuously measures the neural activities. Coefficients of the neural dynamics model and the BMI decoding model are iteratively updated, by executing a learning algorithm, in response to the BMI's continuous measurement.

The invention provides a virtual model generation method and device and electronic equipment, and the method comprises the steps: determining model morphological parameters in response to a model generation instruction for a plant model; wherein the plant model comprises a leaf part and a rhizome part; the model morphological parameters comprise leaf morphological parameters and rhizome morphological parameters; generating a basic leaf model based on a preset leaf contour of the plant model, and updating the form of the basic leaf model based on the leaf form parameters; generating a basic rhizome model based on a preset rhizome shape of the plant model, and updating the form of the basic rhizome model based on the rhizome form parameters; and combining the updated basic leaf model and the updated basic rhizome model to generate a plant model. According to the method, when the plant model is generated, the plant model with the vivid form can be generated through the related form parameters input by the user or the form parameters randomly generated by the system, the generation efficiency of the plant model is improved, and the labor cost is reduced.

The present disclosure provides a plant model processing method and device and electronic equipment. An initial plant model is obtained. The initial plant model includes a plurality of sub-models and a texture map. The texture map is used to indicate the color displayed on the surface of the sub-model and the transparency of the surface of the sub-model. Based on the texture map, a patch model in the plurality of sub-models is determined, and a corresponding entity model of the patch model is generated. Based on the initial plant model and the entity model, a target plant model is generated. This way can generate a high-precision plant model based on a low-precision plant model, improve the generation efficiency of the high-precision plant model, and reduce the labor cost.

To provide a method and a system for monitoring and / or controlling a chemical plant having a plurality of assets.SOLUTION: A method includes the steps of: providing containerized application including input data, output data, and an asset or plant template for specifying an asset or plant model; deploying the containerized application, and executing the deployed application in at least one of deployed layers; allocating the deployed layers on the basis of the input data, a load indicator or a system layer tag; executing the containerized application in the allocated deployed layer, and generating the output data for controlling and / or monitoring a chemical plant; and providing output data generated to control and / or monitor the chemical plant.SELECTED DRAWING: None

A method is disclosed for monitoring and / or controlling a chemical plant (12) with multiple asset sets through a distributed computing system (10) with more than two deployment layers (14, 16, 30, 32, 34), where the deployment layers (14, 16, 30, 32, 34) comprise at least two of a first processing layer (14), a second processing layer (16, 32, 34), and an external processing layer (30). The method comprises the steps of: - providing (60) a containerized application (48, 50) that includes an asset or plant template specifying input data, output data, and an asset or plant model, - deploying (62) the containerized application (48, 50) to run on at least one of the deployment layers (14, 16, 30, 32, 34), where the deployment layer (14, 16, 30, 32, 34) is assigned based on input data, a load indicator or a system layer label, and the application runs in containers (46, 52,54) in the assigned deployment layer(s) (14, 16, 30, 32, 34) to generate output data to control and / or monitor the chemical plant (12), - providing (66) the generated output data to control and / or monitor the chemical plant (12).,

The invention relates to a hybrid model-based power plant diagnostic system. A computer-implemented method of diagnosing a fault in a power plant includes: acquiring plant data through an interface for coupling with at least one power plant; creating a database according to the factory data provided by the data acquisition layer, and managing and accessing the database; training a plant model for providing an estimated plant output based on a series of training observation input variables selected from the plant data; validating the trained plant model based on plant data from the at least one power plant and / or database; and continuously providing an estimated plant output using the trained model based on a current observed variable of the power plant during operation of the power plant. The plant model is a Gaussian mixture model with an orchestrated number of states, training includes performing a first expectation maximization process, and verifying includes performing a second expectation maximization process.

The application provides a kind of multi-dimensional sound scene ecological element space layout optimization method and system, belongs to mechanical vibration measurement technical field field, this method includes integration three-dimensional point cloud and environmental parameter construction digital basement, establishes the native plant model containing growth and acoustic characteristics, generates the space sound effect contribution degree pressure field representing the noise reduction potential by reverse sound wave ray tracing, constructs the plant growth agent driven by the pressure field, runs the symbiotic simulation engine to generate the morphological dynamic evolution sequence, calculates the acoustic performance, ecological stability and landscape robustness index, and uses it as the fitness evaluation basis of evolution algorithm, iteratively optimizes the initial planting layout, the application realizes the coupling of acoustic physical simulation and plant growth competition logic, is used to guide the long-term planning and species configuration of ecological garden, improves the sound environment quality and succession stability of landscape.

The computer-implemented method for providing a plant operation support system includes obtaining a plant model that models the operation of a plant. It involves simulating, by means of the plant model, different possible futures of a plant state at a time starting from an initial simulation plant state at an initial time, where each possible future of a plant state corresponds to an adjustment action among a plurality of potential adjustment actions and / or a fault source among a plurality of potential fault sources associated with an alarm and / or an unexpected plant behaviour. The method further includes analysing and scoring, by means of an exploratory method, the possible futures of a plant state to obtain, for the possible futures of a plant state, a respective benefit score of the corresponding potential adjustment action and / or a respective likelihood score of the corresponding potential fault source. It determines at least one of the following: one or more proposed adjustment actions among the plurality of potential adjustment actions based on the benefit score of the corresponding potential adjustment action; a ranking of adjustment actions among the plurality of potential adjustment actions in terms of their outcome based on the benefit score of the corresponding potential adjustment action; a proposed fault source among the plurality of potential fault sources, wherein the proposed fault source is predicted to be a root-cause of and / or to contribute to the alarm and / or the unexpected plant behaviour based on the likelihood score of the corresponding potential fault source; a ranking of fault sources among the plurality of potential fault sources in terms of their outcome based on the likelihood score of the corresponding potential fault source.

One of the purposes of the present disclosure is to provide a plant management device and the like which are capable of supporting plant inspection work. A plant management device according to an embodiment of the present disclosure is provided with: a display control unit that displays a plant model on a display device, the plant model being an image of a facility included in a plant; and a reception unit that receives an operation by a user on the plant model displayed by the display device. The display control unit displays, on the display device being operated by the user, information corresponding to a role of the user and the operation of the user.

The invention relates to the technical field of nuclear island structure testing, and provides a nuclear island structure contact surface mechanical property detection device and method. Comprising a vibration table, a second plant model arranged on the table top of the vibration table in a pouring mode, a first plant model arranged on the second plant model in a pouring mode and a sensor unit arranged on the first plant model and / or the second plant model, and the sensor unit is at least used for obtaining mechanical parameters. By pouring the first plant model on the second plant model, the device can truly reproduce the contact relation of pouring first and pouring later and the interface forms of concrete-concrete and concrete-steel plates, and the vibration table is used for applying earthquake dynamic load and can be integrated with a weighting device, a temperature control system and the like to realize a static load-temperature-dynamic coupling test.

The invention discloses a post-disaster structure prediction method and device, a storage medium and electronic equipment, and the method comprises the steps: collecting the three-dimensional data of a nuclear power plant building, obtaining a building model, and constructing a structural finite element model according to the building model, the building model comprising a plant model and a containment model; determining a simulation working condition, performing calculation and analysis according to the structural finite element model and the simulation working condition to obtain a damage type and calculation time consumption, and determining an evaluation model according to the damage type and the calculation time consumption; and arranging a displacement sensor and a strain sensor on the nuclear power plant building according to the evaluation model and the sensor arrangement rule, collecting displacement data generated by the displacement sensor, and constructing a state initialization analysis model according to the displacement data.

A method for evaluation of chiller plant operation economy is disclosed. The method comprises receiving a first set of data associated with each chiller over a training interval; generating a ML model for each chiller; deploying the generated ML model to a model of each chiller over a ranking interval; receiving a second set of data associated with each chiller, from the sensors; averaging second set of data for each type of sensor across chillers; determining a power consumption of the ML model of each chiller and comparing it over the ranking interval to determine a best ML model; deploying the ML models to an non-degraded chiller plant model and the best ML model to an ideal chiller plant model; comparing the sum of measured actual power consumptions of chillers with calculated consumptions of a non-degraded chiller plant model and ideal chiller plant model to determine estimated potential of savings.

This invention provides a real-time bending and shaping method for virtual plants based on adjustable stiffness weights. The method involves configuring virtual plant parameter information and generating a parameterized plant model. The parameter information includes at least plant parameter information, plant control parameter information, and environmental parameter information. When the interactive mode is activated and the plant end is dragged, the end of the plant model is acquired and fixed at the target dragged position. Based on the target dragged position, the dragged virtual plant structure undergoes weighted inverse dynamic bending processing and interpolation. Based on the updated dragged virtual plant structure, other branch structures of the virtual plant are updated synchronously. The overall updated virtual plant structure is subdivided and subjected to Catmull-Rom curve interpolation. The interactive mode is then terminated, and the currently updated virtual plant structure is solidified. This invention uses gradual stiffness, mass curves, and weak bending moment constraints to make the bending shape of the virtual plant highly similar to the stress on real branches.

The present invention comprises: an input unit; a grid setting unit that converts a three-dimensional space into a grid that is a three-dimensional grid space; an input tensor generation unit that generates, for each loop, a grid-entity matrix according to unique information of entities and a statistical existence probability for each grid of each entity, and an input tensor for an attention calculation of each loop; a memory storing attention weights and linearity item information; an attention unit that calculates an entity arrangement result of a loop by performing the attention calculation according to attention variables corresponding to each loop; and a control unit that determines an arrangement position of each entity in the three-dimensional space, detects entities to be connected by a linearity item, determines a trajectory and the type of the linearity item connecting the entities, and generates a plant model including arrangement positions of the entities and a linearity item arrangement including the determined trajectory and the determined type of the linearity item.

Provided in this disclosure is a system and methods for wind compensation of an electric aircraft. More specifically, provided in this disclosure is a controller of an aircraft configured to use a plant model for compensating for wind forces. The processor is configured to receive, from the sensor, at least a geographical datum of the electric aircraft.

This application relates to a visual navigation method, system, device, and medium for a servo robot, applied to the field of robot navigation technology. The method includes obtaining panoramic image data and image scale data of a target farmland; constructing a three-dimensional farmland model of the target farmland based on the panoramic image data and image scale data; obtaining crop identification data and weed identification data of the target farmland, a servo robot's peripheral visual image, and robot position information; generating a three-dimensional plant model based on the crop identification data and weed identification data; constructing a working farmland environment model based on the three-dimensional farmland model and the three-dimensional plant model; and constructing a visual navigation route for the servo robot based on the peripheral visual image, robot position information, and the working farmland environment model. This application has the effect of enabling precise navigation and control of the robot based on actual environmental characteristics.

The present invention discloses a blast furnace gas network balancing system and a gas control method through power generation regulation, constructs a pressure-related model, including a pressure change model from production difference to pressure, a single power plant model, and a multi-power plant model; calls the pressure-related model in real time, predicts future pressure changes, and dynamically determines the optimal regulation strategy, and finally outputs a power generation suggestion based on the gas regulation amount for each power plant, and each power plant executes the suggestion to stably control the network pressure within the upper and lower limits of the pressure warning value. It can accurately predict future pressure changes, improve the real-time and response speed of regulation, has strong adaptability, flexible regulation strategy, reduces energy waste, improves system efficiency, and enhances system stability and safety.

To provide a pumped storage power generation plant simulation device, a simulation method and a simulation system capable of simulating a power generation status of a plant mounted with a plurality of water pumps that can form a circulation water passage.SOLUTION: A pumped storage power generation plant simulation device comprises: a scenario generation section; a plant model generation section; an execution section; and a selection section. The scenario generation section generates a plurality of first scenarios for a first water pump and a plurality of second scenarios for a second water pump. The plant model generation section generates a pipe conduit system model simulating pressure fluctuations in a pipe conduit and a water pump model including a plurality of turbine models. The execution section causes the water pump model to perform a simulation test for each combination of the plurality of first scenarios and the plurality of second scenarios. The selection section selects a combination of scenarios in which the pressure fluctuation in the pipe conduit meets a predetermined criterion based on the simulation tests.SELECTED DRAWING: Figure 1

A method (200) and system (700) for optimizing power management for a hybrid system (300) of a machine (100) are provided. The method (200) includes generating (202) a plant model based on a machine recipe (710) of the machine (100); generating (214), in an algorithm library (720), algorithms for a plurality of scenarios simulated based on selected key performance indicators (KPIs) (712) associated with the machine recipe (710), optimization connections (714), and machine requirements (716) of the machine (100); selecting (214) an algorithm from the algorithm library (720) based on computational capabilities of a controller associated with the machine (100) and machine requirements (716) for the algorithm; simplifying (216) the algorithm based on removing one or more KPIs of the selected KPIs; refining (218) the algorithm based on weighing one or more remaining KPIs of the selected KPIs; and integrating (220) the algorithm into machine operation to be performed by a control module (132) of the machine (100).

This invention discloses a method and system for constructing a simulated plant model based on 3D modeling, belonging to the field of 3D modeling technology. The method includes the following steps: constructing a spatial association mapping of skeletal nodes; calculating initial values ​​of weight distribution between nodes based on spatial distance, angle, and torsion direction parameters; and performing adaptive weight redistribution operations on branch and joint regions based on the established initial weight distribution values. By dynamically adjusting the weight ratio along the energy conduction path, a smooth transition of weights is achieved at locations where the energy transfer rate changes. This invention, by constructing a spatial association mapping of skeletal nodes and initializing the weight distribution, combined with adaptive weight adjustment, energy direction tracking, and zonal constraint control, ensures continuous energy conduction along the skeletal path and introduces closed-loop feedback to dynamically update the weight relationship, thereby suppressing energy reflection and error accumulation, and improving the morphological continuity, mechanical stability, and long-term dynamic realism of the simulated plant model.

This invention belongs to the field of computer vision technology and discloses a data synthesis and enhancement method based on digital twins and generative AI. It constructs a digital plant model through 3D image reconstruction, utilizing multi-view images and computer vision technology. A dataset is synthesized based on the 3D model. Two-dimensional images and annotations are obtained through 3D graphics software design and rendering. The synthesized dataset is then tested, and a 3D plant model is generated using generative AI. The synthesized data is used for training. This invention utilizes computer-generated data enhancement to solve the problem of insufficient training data for deep learning algorithms such as image segmentation. Furthermore, it enhances the synthesized data using generative artificial intelligence and digital twin technology. It constructs a digital model of a real-world plant using 3D reconstruction technology and generates a 3D digital plant model using generative AI technology. This method of generating synthesized data solves the problem of difficulty in obtaining training data in image segmentation tasks.

The invention relates to the technical field of computer graphics and digital content generation, and discloses a programmed digital plant growth simulation method and system. The method comprises the following steps: firstly, carrying out skeletal preprocessing on an input three-dimensional plant model, extracting a point sequence through an iterative algorithm based on a plane starting point, and constructing a hierarchical skeletal system; then, a growth path and a form rule are defined by using the nodal visual special effect graph; then, adopting a physically guided skeleton spreading algorithm, and controlling natural bending growth of the skeleton through vector force; and finally, performing multi-platform rendering output adaptation, and generating special effect resources compatible with a game engine and a film and television rendering pipeline. According to the technical scheme, high-efficiency and high-precision programmed plant growth simulation is achieved, and the technical bottleneck of a traditional method in the aspects of natural form spreading and artistic control is solved.

The invention discloses a data extraction method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a plant model, wherein the plant model is a three-dimensional model of a plant; according to the grid information of the plant model, structural data of a plant in the plant model is extracted, the structural data comprises hierarchical structure data and pivot point data, the hierarchical structure data represents hierarchies included in the plant model, and the pivot point data represents data related to joint positions of plant growth in the plant model; based on the structure data of the plant, a data structure chart corresponding to the plant model is generated, and the data structure chart is used for generating animation related to the plant. According to the method, the data extraction efficiency is improved.

The embodiment of the invention provides a three-dimensional plant generation method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a two-dimensional image of a plant; generating an initial grid structure of the plant based on the two-dimensional image, wherein the initial grid structure is used for representing a rough three-dimensional model of the plant; sampling the initial grid structure to obtain an initial point cloud of the plant, the initial point cloud being used for representing a three-dimensional architecture of the plant; based on the initial point cloud, a branch point cloud of the plant is generated, and the branch point cloud is used for representing a three-dimensional branch vein of the plant; generating branches of the plant based on the branch point cloud; and adding leaves on the branches to obtain a fine three-dimensional model of the plant. According to the method, the three-dimensional model of the plant can be generated directly based on the original picture or the photograph of the plant without depending on a sketch drawn by a user, detail features of the plant can be better captured, and the generated fine three-dimensional model is more vivid.

The invention provides a plant model processing method and apparatus, and an electronic device. The method comprises the steps of obtaining an initial plant model; the initial plant model comprises a plurality of sub-models and a texture map; the texture maps are used for indicating colors displayed on the surfaces of the sub-models and transparency of the surfaces of the sub-models; based on the texture map, determining a surface patch model in the plurality of sub-models, and generating an entity model corresponding to the surface patch model; and generating a target plant model based on the initial plant model and the entity model. According to the mode, the high-precision plant model can be generated based on the low-precision plant model, the generation efficiency of the high-precision plant model is improved, and the labor cost is reduced.