36 results about "Deterministic control" patented technology

The invention relates to the field of artificial intelligence and energy efficiency control, and discloses a building energy efficiency optimization system and method, and the method comprises the steps: obtaining historical load data, real-time operation state data and target time meteorological data of a heating and ventilation system; inputting the historical load data, the real-time operation state data and the meteorological data of the target time into a dual-core optimization model constructed based on a Transformer-genetic algorithm and an expert rule to obtain an optimal control strategy; the power consumption corresponding to the optimal control strategy is lowest; a heating and ventilation system is controlled to execute an optimal control strategy, a dual-core-driven decision system is constructed, deterministic control logic based on expert knowledge is organically combined with a deep learning optimization algorithm based on mass data, a control center with complementary advantages and system operation is formed, meanwhile, the energy efficiency optimization effect corresponding to the control strategy is improved, and the system performance is improved. And low-energy-efficiency, high-comfort and high-safety control strategy output is realized.

The invention discloses a photovoltaic support flat single-axis tracking system, and relates to the technical field of photovoltaic support angle regulation and control systems, and the system comprises a time sequence reference circuit which is provided with high-steady-state clock hardware with an independent energy maintenance topology, provides an irreversible global timestamp index for the system, outputs a current precise timestamp, and has a time sequence error less than or equal to + / -1ms; meanwhile, a standby clock signal is provided to deal with an RTC fault scene, and continuous operation of the system is guaranteed. A photovoltaic support flat single-axis tracking system thoroughly eliminates tracking oscillation and misjudgment caused by random disturbance of environment illumination by constructing a deterministic control model decoupled from the environment, and realizes all-weather dimension trajectory robustness at the same time, so that the system can be used for tracking a photovoltaic support without relying on feedback of an external illumination sensor. A rigid instruction is output according to a built-in space-time model, and convergence and stability of tracking precision under any meteorological condition are ensured.

In a method for controlling translocation of a target polymer molecule through a nanopore, a clamp is reversibly bound at a site along the target polymer molecule length; the clamp and the target polymer molecule are disposed in an ionic solution that is in fluidic communication with a nanopore having an aperture diameter less than an outer diameter of the clamp. A constant translocation force is applied across the nanopore to induce travel of the target polymer molecule into the nanopore such that the reversibly bound clamp abuts the nanopore. A voltage pulse is applied across the nanopore that advances the target polymer molecule into the nanopore by one nucleotide, without either of chemical fuel and biochemical fuel provided to the clamp. The voltage pulse is repeatedly applied to cause a plurality of nucleotides to translocate through the nanopore. An indication of each nucleotide can be acquired during nucleotide translocation.

This application relates to the fields of artificial intelligence and energy efficiency control, and discloses a building energy efficiency optimization system and method. The method includes: acquiring historical load data, real-time operating status data, and meteorological data at a target time for the HVAC system; inputting the historical load data, real-time operating status data, and meteorological data at the target time into a dual-core optimization model constructed based on Transformer-genetic algorithm and expert rules to obtain the optimal control strategy; the optimal control strategy corresponds to the lowest power consumption; controlling the HVAC system to execute the optimal control strategy, constructing a "dual-core driven" decision-making system, organically combining deterministic control logic based on expert knowledge with deep learning optimization algorithms based on massive data to form complementary advantages, serving as the control center for system operation, and simultaneously improving the energy efficiency optimization effect corresponding to the control strategy, achieving a control strategy output with low energy efficiency, high comfort, and high safety.

The invention discloses an intelligent control method and device for an electronic transformer and a storage medium, and relates to the technical field of transformer control, and the method comprises the steps: obtaining the power demand information of a plurality of loads at the downstream of the electronic transformer, and obtaining the power demand information of each load based on the power demand information and the electrical characteristics of each load; generating a deterministic load sequence for defining a switching or power change plan of each load in a future time period; the core innovation of the invention lies in breaking through the traditional closed-loop regulation thought, and realizing open-loop feed-forward following control by obtaining a load plan in advance and generating a deterministic control curve. The key of the conversion lies in the accuracy of the deterministic load sequence, and the load demand can be accurately matched only when the load action is a control curve which can be planned and predictable in advance and is generated in advance, so that the output stability can be ensured without real-time feedback adjustment.

This invention discloses an FPGA-based F-P etalon length tilt adjustment method and device. It performs layered adjustment of "X and Y direction parallelism adjustment" and "Z direction cavity fixing," relying on an FPGA to construct a two-level priority scheduling mechanism with fixed underlying hardware. Utilizing the parallel processing advantages and nanosecond-level clock determinism of FPGA hardware logic, the X and Y direction parallelism determination is fixed as the highest hardware priority. In each control iteration, the FPGA performs threshold comparison with low latency. If the parallelism does not meet the standard, the system intercepts the Z-direction cavity fixing command within a deterministic control cycle and prioritizes the leveling branch. This "software algorithm hardwareization" strategy effectively suppresses multidimensional cross-coupling oscillations. The adjusted etalon achieves the theoretical peak transmittance and spectral resolution, and the area array detector exhibits a sharp interference ring with good contrast.

The invention discloses a telescope real-time control method and system based on a synchronous time service and memory sharing mechanism, the core of the method is to construct a hard real-time, high-synchronization and low-delay distributed control system for a telescope platform, and the method specifically comprises the following steps: constructing a real-time computing platform; constructing a high-precision time synchronization system; constructing a global shared memory network; defining and initializing a shared memory data area; the deterministic control logic based on the unified time reference is realized; and deploying a watchdog and a health monitoring mechanism. The method has a wide application prospect in the field of precise motion control of astronomical telescopes and the like. According to the method, the problems of poor real-time performance and low synchronization precision caused by network delay, clock asynchronization and process scheduling uncertainty of an existing telescope control system are solved.

The application relates to a kind of distributed corner module electric drive vehicle yaw stability robust cooperative control methods.The method comprises: obtaining the driving state data of corner module vehicle;According to lateral stability constraint condition and lateral dynamics model, nominal control model is constructed, and nominal control model is the part related to determining parameter in lateral dynamics model, wherein the target of lateral stability constraint condition is the error of yaw angular velocity and the error of lateral velocity tends to zero;Uncertainty control model is constructed, and uncertainty control model is the part related to uncertain parameter in lateral dynamics model;Driving state data is input into nominal control model and uncertainty control model, and yaw moment control parameter is determined;Based on yaw moment control parameter and rear wheel steering control parameter, stability cooperative control is carried out on corner module vehicle.By using the method, the yaw stability of corner module vehicle can be improved.

Described herein are methods for developing and maintaining pulses that are produced from compact resonant cavities using one or more Q-switches and maintaining the output parameters of these pulses created during repetitive pulsed operation. The deterministic control of the evolution of a Q-switched laser pulse is complicated due to dynamic laser cavity feedback effects and unpredictable environmental inputs. Laser pulse shape control in a compact laser cavity (e.g., length / speed of light<˜1 ns) is especially difficult because closed loop control becomes impossible due to causality. Because various issues cause laser output of these compact resonator cavities to drift over time, described herein are further methods for automatically maintaining those output parameters.

The invention relates to the technical field of optical storage scheduling, and discloses an optical storage system adaptive scheduling method based on multi-modal data fusion, and the method comprises the following steps: S1, collecting structured static data, time sequence monitoring dynamic data, external market data, and image data; s2, obtaining a space-time coupling feature matrix, a solar radiation predicted value and a power grid load predicted value, and constructing a multi-modal feature matrix through the space-time coupling feature matrix, the solar radiation predicted value, the power grid load predicted value, the structured static data and the external market data; s3, generating a random control strategy through the multi-modal data feature matrix and the three independent agents, optimizing the random control strategy to obtain a deterministic control strategy, and outputting the deterministic control strategy through a reinforcement learning controller; and S4, repeating the steps S1 to S3, and stably outputting a corresponding deterministic control strategy at each time step by the optical storage system. According to the invention, efficient response to complex environments and uncertain events can be realized, and the scheduling precision of the optical storage system is improved.

The invention relates to the technical field of industrial control systems, in particular to a full-process automatic control method and system for glass processing, and the method comprises the steps: converting the planning problem of an optimal state track into the generation of a section of programmed instruction sequence through a double-layer prediction control model; the instruction sequence comprises a series of program steps which are arranged according to a time sequence and are used for controlling a real-time pressure set value in a process flow. During online control, the system strictly follows the pre-generated instruction sequence to operate; meanwhile, the actual state is compared with the current step set value in the instruction sequence in real time through a feedback correction loop so as to compensate the execution deviation, and high-fidelity execution of the program track is ensured. According to the method, a complex model prediction technology is used for generating a deterministic control program, the accuracy of the control program is guaranteed through closed-loop execution, and high-precision programmed control over the nonlinear industrial process is achieved.

The present application provides a multi-domain control quick switching method and apparatus based on a novel industrial operating system, used for switching the control node of a device on a multi-area cloud. The method comprises: a current control node periodically measuring a first control delay between said control node and a device; when the first control delay is greater than or equal to the difference between a delay constraint of the device and a first set value, selecting a target node from other control nodes of the cloud, and enabling each target node to measure a second control delay for the device; and selecting one target node from among target nodes with the second control delays being less than the difference between the delay constraint and a second set value, and the current control node switching a control function of the device to the target node. The technical solution provided by embodiments of the present application is used for, in a cloud environment, when a device is out of an acceptable deterministic control range, quickly switching to a new control node, so that the cross-regional seamless switching of a control function of the device is realized.

This invention relates to the field of intelligent pre-adjustment of RV air conditioning systems. The solution collects structured path navigation data containing terrain and facility attributes, generates a 3D path topology map using a GIS engine, models road nodes, edges, and surfaces in a semantically hierarchical manner, and constructs a hierarchical rule knowledge base based on HVAC engineering principles and multi-source measured data. The system uses a rule graph engine to precisely match path topology features with air conditioning execution parameters, achieving rule-based triggering, temporal conflict resolution, and decision priority ranking, generating a traceable deterministic control command sequence, which is executed and fed back in real time by the microcontroller unit. This method improves the RV air conditioning's adaptive adjustment capability to dynamic terrain changes, achieving pre-adjustment that balances comfort and energy consumption. It also features rule verification and self-iterative optimization mechanisms, promoting system reliability and intelligence.

The embodiment of the invention provides a multi-domain control fast switching method and device based on a novel industrial operating system, which are used for switching a control node of a multi-domain cloud device, and the current control node periodically measures a first control time delay between the current control node and the device; when the first control time delay is greater than or equal to a difference obtained by subtracting a first set value from the time delay constraint of the equipment, selecting target nodes from other control nodes of the cloud, and enabling each target node to measure a second control time delay of the equipment; and selecting one target node from the target nodes of which the second control time delay is smaller than the difference obtained by subtracting the second set value from the time delay constraint, and switching the control function of the equipment to the target node by the current control node. The technical scheme provided by the embodiment of the invention is used for quickly switching to a new control node after the equipment is separated from an acceptable deterministic control range in a cloud environment, so that the cross-regional seamless switching of the control function of the equipment is realized.

The invention relates to the technical field of microscopic imaging motion positioning control, in particular to a microscopic imaging motion positioning intelligent control system based on artificial intelligence, and adopts the technical scheme that a feature dynamic extraction unit is constructed, a deep convolutional neural network and a graph neural network are adopted to extract appearance and geometric structure feature flows of a target in parallel, and the feature flows are extracted; robust characterization of the multi-dimensional attributes of the target is formed; designing a multi-modal motion reasoning unit, performing time sequence modeling on the fused double-flow features by using a gating circulation unit network, and expressing displacement hypothesis distribution by using a Gaussian mixture model; a self-adaptive strategy generation unit is introduced, and a control problem is converted into a reinforcement learning problem cooperatively decided by a strategy network and a value network; a layered real-time architecture is designed, and a high-frequency low-delay determined control task and a low-frequency asynchronous learning optimization task are decoupled; the feature identification and stability under the condition that the target form changes drastically are improved, and the defect that a traditional fixed template matching method is poor in adaptability is overcome.

The application discloses an intelligent control method and device of an electronic transformer and a storage medium, relates to the technical field of transformer control, and comprises the following steps: acquiring power consumption demand information of a plurality of loads downstream of the electronic transformer, and generating a deterministic load sequence defining load switching or power change plans of the loads in a future period based on the power consumption demand information and electrical characteristics of the loads; the core innovation of the application is to break through the traditional closed-loop regulation idea, to realize open-loop feedforward following control by acquiring the load plan in advance and generating a deterministic control curve. The key to this conversion lies in the accuracy of the deterministic load sequence. Only when the load action is planable and predictable in advance, the pre-generated control curve can accurately match the load demand, thereby ensuring output stability without real-time feedback regulation.

This invention discloses a physically isolated minimal deterministic safety actuator and its control method for intelligent driving, belonging to the field of functional safety technology for intelligent driving. The device adopts a hardware architecture physically independent of the main decision-making unit, possessing independent power supply and timing. Its runtime working set is no larger than 10KB, and it has no operating system or dynamic memory. Deterministic control is achieved through hardware-fixed logic, with a worst-case response time of no more than 50ms. The device is equipped with independent sensing paths and hardwired execution interfaces, enabling direct actuator driving without relying on the vehicle bus. Cross-domain health monitoring enables multi-node status monitoring and computing power management. This invention can provide a safety fallback in the event of a system-wide failure, resisting common-cause failures, meeting ASIL D functional safety level, and features low cost, small size, easy integration, and suitability for mass production. It solves the problems of insufficient independence and poor real-time performance of traditional safety islands.

Systems and methods are disclosed for operating-system-level deterministic identification and control of artificial intelligence (AI) execution on a computing device. Operating-system execution signals generated during application execution are collected and evaluated against a machine-evaluable AI execution pathway definition comprising trigger event types, a bounded temporal evaluation window, a mandatory signal set, ordering constraints, temporal correlation constraints, and exclusion conditions. A binary pathway match outcome is determined based on satisfaction of the execution pathway definition independent of executable identity, content inspection, or network traffic analysis. Upon determination of a pathway match, a machine-enforceable execution control instruction is generated and applied using a kernel-mediated execution control interface, including pre-initialization and in-execution gating operations that prevent, restrict, suspend, sandbox, or otherwise constrain AI-associated execution contexts. The disclosed approach enables selective governance of AI functionality within otherwise permitted applications while preserving non-AI application operation.

The application relates to a micro-thrust measurement heat-induced data processing method, system, device and medium. The method comprises the following steps: loading a mixed uncertainty variable set and a heat-induced nonlinear dynamics model, and constructing a mixed uncertainty control model; performing Latin hypercube sampling to generate a mixed uncertainty variable combination sample set, and substituting each mixed uncertainty variable combination sample into the mixed uncertainty control model to obtain a system displacement response; based on the system displacement response, a response time and the mixed uncertainty variable combination sample, a Gaussian process proxy model is constructed; a verification uncertainty parameter set is loaded, and based on the verification uncertainty parameter set and the Gaussian process proxy model, a verification uncertainty parameter sample set is sampled; based on the verification uncertainty parameter sample set, Sobol sensitivity analysis is performed on the Gaussian process proxy model to generate first-order Sobol sensitivity analysis result information. The method can accurately and efficiently simulate the heat-induced nonlinear effect.

The application relates to a distributed encoder system. The system comprises: a plurality of encoder sensors configured to output encoded sensing signals; a plurality of bus encoder modules, one of which is connected with one or more of the encoder sensors, configured to receive the encoded sensing signals of the connected encoder sensors, pre-process the encoded sensing signals to obtain encoded sampling signals, and publish the encoded sampling signals onto an industrial real-time bus; and a plurality of processing nodes, each of which is connected with a plurality of the bus encoder modules through the industrial real-time bus and obtains the encoded sampling signals of the encoder sensors from the industrial real-time bus to perform processing operations based on the obtained encoded sampling signals. The system can meet the requirements of high-precision cooperation and deterministic control.

An industrial controller supports deterministic execution of control programs (e.g., ladder logic, function block diagrams, structured text, or other such control code) and is also capable of executing non-deterministic execution cycles, including mathematical optimization algorithms—in which a systematic search in a solution space is performed to identify a desired solution—or machine learning algorithms, either of which can be used by the controller to dynamically update the deterministic control program or code based on current or predicted states of the automation system being controlled by the controller.

The invention belongs to the technical field of industrial automatic control systems, and particularly relates to an automatic metallurgical billet fishing control system based on a PLC (programmable logic controller). And the control module is responsible for executing preset sequence control logic, safety interlocking protection, emergency shutdown processing and control instruction interaction with the multi-degree-of-freedom fishing execution module. By fusing a multi-type sensing technology, real-time data processing and an AI decision algorithm, seamless integration with the deterministic control capability of the PLC is realized. According to the application, high-precision robust sensing and intelligent adaptive control of the steel billet in a severe environment can be realized, the PLC stability and reliability are realized, the energy consumption is reduced, and the efficiency is improved.

The application discloses an uncertainty control method of an automatic emergency braking system, comprising the following steps: (1) arranging a signal collection mechanism, (2) analyzing the source of uncertainty of the automatic emergency braking system and quantifying the source, (3) establishing a safety distance model of the automatic emergency braking system with the introduction of an uncertainty parameter, and (4) constructing a judgment strategy for triggering the braking of the automatic emergency braking system under different scenes with the consideration of uncertainty. The application can solve the safety problems related to the uncertainty of the automatic emergency braking system, thereby improving the safety and reliability of the automatic emergency braking system.

The invention relates to the field of intelligent interaction of Internet of Things and artificial intelligence fusion, and discloses an Internet of Things AI intelligent interaction method and system, gateway equipment and a storage medium, and the method comprises the steps: receiving a voice instruction, and analyzing an instruction intention; the instruction intention is classified into three types of deterministic control, intention reasoning or non-control interaction; if the control type is a deterministic control type, directly generating an action instruction; if the type is the intention reasoning type, reasoning is carried out based on a dynamic situation intention map to determine the most matched target situation; if the type is a non-control interaction type, calling an external interface to respond to the query; and finally, generating and executing an equipment control instruction according to the determined action instruction or target situation. By setting a multi-path decision-making mechanism, the real-time performance, the intelligence and the service range of interaction are considered. By utilizing a graph reasoning technology, the system can understand a fuzzy intention, and linkage rules between devices are dynamically configured through voice, so that the intelligent level and the user experience of the system are remarkably improved.

The present application relates to the technical field of micro-imaging motion positioning control, and particularly to a micro-imaging motion positioning intelligent control system based on artificial intelligence, which comprises the following technical solutions: a characteristic dynamic extraction unit is constructed, deep convolutional neural networks and graph neural networks are used to extract the appearance and geometric structure characteristic flow of a target in parallel, and robust representation of the multi-dimensional attributes of the target is formed; a multi-modal motion reasoning unit is designed, a gating cycle unit network is used to model the time sequence of the fused double-flow characteristics, and a Gaussian mixture model is used to express the displacement hypothesis distribution; an adaptive strategy generation unit is introduced, the control problem is converted into a reinforcement learning problem decided by a strategy network and a value network; a hierarchical real-time architecture is designed, the high-frequency low-delay deterministic control task and the low-frequency asynchronous learning optimization task are decoupled; the feature recognition and stability under the condition of dramatic changes in the morphology of the target are improved, and the defects of poor adaptability of the traditional fixed template matching method are overcome.

The present invention discloses an application monitoring and collaboration method, device and system to solve the problem of non-closed loop of deterministic control of multiple applications in the "edge-end-cloud" of the industrial Internet network. The method is used for the deterministic network middleware server side and includes the following steps: obtaining the task data packet corresponding to the application task, collecting task data, and generating or updating the application dependency graph; making policy decisions based on the application dependency graph and the task data packet, generating an overall deterministic policy, and splitting the overall deterministic policy into policies on each device; translating the policies on each device into corresponding device control commands or device configuration parameters, and issuing the device control commands or device configuration parameters. The present application also includes devices and systems for using the method. The present invention is particularly suitable for the industrial Internet within an enterprise.

A feedback controller collects a feedback signal indicative of the current state of the operation of the system subject to constraints and current uncertainty on the current state of the operation of the system and determines a robust controllable set for maintaining the state of the system employing closed-form expressions on a constrained zonotope defining the constraints on the state of the operation of the system and an affine transformation of the symmetric bounded set inclosing the current uncertainty into space of the constrained zonotope. The closed-form expressions include a closed-form approximation of a Pontryagin difference between the constrained zonotopic representation and the zonotopic transformation of the symmetric bounded set. The controller determines and submits a control command for controlling the operation of the system subject to the robust controllable set.

Described herein are methods for developing and maintaining pulses that are produced from compact resonant cavities using one or more Q-switches and maintaining the output parameters of these pulses created during repetitive pulsed operation. The deterministic control of the evolution of a Q-switched laser pulse is complicated due to dynamic laser cavity feedback effects and unpredictable environmental inputs. Laser pulse shape control in a compact laser cavity (e.g., length / speed of light <˜1 ns) is especially difficult because closed loop control becomes impossible due to causality. Because various issues cause laser output of these compact resonator cavities to drift over time, described herein are further methods for automatically maintaining those output parameters.

The invention discloses a visual servo state estimation method and system based on confidence self-adaption and predictive observation, and aims to solve the core technical problem that an existing deterministic control framework cannot effectively utilize probability attributes of depth perception, and perception vulnerability is caused in an unstructured environment. Through a confidence adaptive Kalman filter, real-time matching confidence is converted into dynamic measurement noise covariance in a Jacobian matrix estimation process in principle, and active evaluation and weighting of perception data quality are realized, so that active suppression of perception noise such as illumination change and shielding is realized from the source. Secondly, performing deep coupling on confidence adaptive estimation and a prediction observer, generating high-frequency and smooth virtual measurement in a window period of visual sampling, and constructing a continuous deterministic control loop; through verification, the method has remarkable superiority in convergence speed and positioning precision, and particularly in the aspects of robustness under extreme illumination change and serious dynamic shielding.

An electronic circuit may be configured to obtain an input including one or more hall sensor readings, determine a current motor position based on the input and a first lookup table, determine a desired motor position based on the first lookup table on the current motor position, determine a pulse width modulation (PWM) commutation pattern based on the desired motor position and a second lookup table, and output the PWM commutation pattern within a predetermined time from obtaining the input.