434 results about "Online optimization" patented technology

The invention discloses an environmental data processing method and system based on ocean engineering, and relates to the technical field of data processing, and the method comprises the steps: receiving an original observation data flow through a multi-source data preprocessing module, and carrying out the dynamic noise filtering and abnormal value adaptive detection; fusing the multi-source heterogeneous data through a multi-scale data fusion module, and embedding the fused multi-source heterogeneous data into a marine kinetic equation as a soft constraint; non-linear evolution features are extracted from the fusion data through a feature extraction and state representation module, and a high-dimensional environment state vector is constructed; real-time prediction of model parameters is executed through online learning and an inference engine; and performing uncertainty propagation calculation on the processing flow through a confidence evaluation module and generating a final environment state report. According to the method, the adaptive capacity of data preprocessing can be remarkably improved, the physical consistency of multi-source data fusion is improved, the nonlinear evolution law of ocean phenomena is accurately captured, and continuous online optimization and edge side low-delay response of model parameters are achieved.

The invention discloses a three-dimensional modeling method and system, and relates to the technical field of intelligent perception and three-dimensional reconstruction, and the method comprises the steps: taking BIM as a priori, sampling a geometric entity as a visibility evaluation point cloud, and constructing a graph structure environment state under the constraints of a field of view, distance measurement, an incident angle, overlapping and other sensors; on the basis, a deep reinforcement learning agent which is pre-trained by a synthetic scene and subjected to domain randomization migration is introduced, stations and scanning parameters are selected online according to an observation-decision-execution-update closed loop, visibility and coverage are re-estimated after each step of scanning, and self-adaptive correction is carried out on an unexecuted sequence in combination with online optimization; compared with an off-line global optimization method, the method has the advantages that a search space is effectively compressed through candidate station pre-generation and visibility gating, and continuous and adjustable balance is formed among coverage, point cloud quality and operation time by multi-target awards; for engineering constraints such as temporary shielding, site reachability, registration overlapping degree and the like, the strategy can be dynamically replanned in an execution period.

The invention relates to the technical field of refrigeration house energy-saving control and digital twinning, in particular to a refrigeration house fan energy-saving operation method and system, and the method achieves the whole-field temperature deduction of a sensor-free area by constructing a CFD reference model and simulating and predicting the three-dimensional transient airflow and temperature distribution in a refrigeration house. Model parameters are calibrated through measured data, and the order of the model is reduced by adopting intrinsic orthogonal decomposition and Galerkin projection, so that the calculation amount is remarkably reduced, and online optimization is supported. And in combination with a data assimilation algorithm, the prediction result of the reduced-order model is continuously corrected, and the adaptability to environment change and system aging is improved. The optimization control stage takes minimization of the total energy consumption of a fan as a target, solves an optimal fan control sequence under the hard constraint that the whole-field temperature does not exceed the cargo safety upper limit and does not exceed the cargo safety lower limit, and adopts a rolling time domain mode for execution to realize collaborative optimization of safety and energy conservation.

The invention discloses a thermal spraying coating thickness online optimization control method based on digital twinning, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: synchronously collecting multi-modal online observation data and process control observation data in a thermal spraying process, carrying out the time-space alignment, and generating a multi-modal observation set; performing adaptive optimization of multi-modal uncertainty gating on the candidate control set according to the credible thickness field confidence distribution map to generate a control instruction sequence; and the control instruction sequence acts on the thermal spraying process, response feedback data are continuously collected in the execution period, a new multi-mode observation set is generated according to the response feedback data, and real-time closed-loop optimization control is kept. According to the method, the thickness field with high credibility and the credible thickness field confidence distribution diagram can be generated through forward generation and uncertainty quantification of physical guidance, and depth coupling of multi-modal data and physical rules and accurate mapping of uncertainty are achieved.

The invention provides an AGC hydropower station intelligent control method based on multi-source data fusion. Constructing a control feature vector of the multi-dimensional feature; performing spatial-temporal feature modeling on the control feature vector, and extracting a time sequence dependency relationship between power grid load change and hydraulic dynamic response and a spatial coupling effect between units; establishing a multi-objective optimization function, and dynamically adjusting the weight coefficient of each objective through fuzzy logic according to the current working condition; a self-adaptive differential evolution algorithm is adopted to carry out on-line optimization on an active power distribution coefficient of a unit and PID parameters of a speed regulator, and the requirements of guide vane opening change rate constraint and water hammer effect avoidance are met. According to the method, multi-source heterogeneous data such as power grid, hydraulic engineering and equipment states can be effectively fused, multi-target dynamic optimization control is realized through the space-time attention model and the adaptive differential evolution algorithm, and the control precision, the response speed and the equipment operation safety of the hydropower station AGC system are remarkably improved.

The invention discloses a multi-objective optimization method and system for a regional integrated energy system, and the method comprises the steps: constructing a multi-source input sequence sample; inputting a multi-source input sequence sample into the wind power and photovoltaic prediction model for processing, obtaining a current wind power and photovoltaic output optimization prediction result, calculating the current wind power and photovoltaic output optimization prediction result and a really constructed sample, obtaining a combined loss function value to train the model, obtaining the trained wind power and photovoltaic prediction model, processing the sample collected in real time, and obtaining a wind power and photovoltaic output prediction result. Outputting current wind power and photovoltaic output optimal values; and constructing an online optimization model of the integrated energy system, performing online optimization solution on the constructed model by an accelerated particle swarm optimization algorithm to obtain a control strategy of the energy system, issuing the control strategy to the energy equipment, and performing multi-target optimization scheduling. According to the method, the wind power and photovoltaic prediction model is combined with the accelerated particle swarm optimization algorithm, prediction errors are fully considered, and the stability and flexibility of the regional integrated energy system are enhanced.

The invention relates to the technical field of large model driven reasoning, and particularly discloses a multi-agent interaction intention understanding and cooperative control method based on a large model, and the method comprises the following steps: S1, environment and multi-source heterogeneous interaction information perception; s2, large model driven hierarchical intention understanding; s3, generating an intention-guided collaborative strategy; s4, action execution and closed-loop online optimization are carried out; through full-link technical innovation, the intention understanding precision, cooperative control efficiency and scene adaptation capability of the multi-agent system are remarkably improved, core technical support is provided for multi-agent cooperative application in a complex scene, and the method has extremely high engineering application value and industrial popularization potential.

The invention belongs to the technical field of crossing of artificial intelligence and computer system architecture, particularly relates to a computing power center equipment power supply intelligent system of a knowledge graph, and aims to solve the problem of low energy efficiency caused by extensive power supply management, unbalanced energy consumption and lagged load response. The system comprises a task analysis module, a dynamic load prediction module, a multi-source power supply scheduling module, an equipment-level power supply control module and a feedback optimization module, through load prediction and multi-source power supply cooperative scheduling driven by task semantics, voltage and current dynamic adjustment and sleep wake-up control are achieved, and a strategy is optimized online based on operation feedback. The scheme improves energy efficiency, equipment life and system stability.

The invention discloses an intelligent analysis and management method and system for an integrated controller, relates to the field of integrated control, and aims to complete complex air conditioning system identification model training and off-line optimization of an optimal PID parameter strategy by using historical data at a cloud end with sufficient computing power. And generating an expert strategy library containing various working conditions and corresponding optimal control parameters thereof. Then, a lightweight proxy model with small calculation amount and high reasoning speed is trained based on the strategy library; the proxy model is deployed on a resource-constrained edge controller. Therefore, the edge end does not need to execute complex online optimization calculation, and only needs to input the real-time working condition data into the agent model, so that the current optimal PID parameter can be quickly deduced. According to the cloud training and edge reasoning architecture, online, real-time and intelligent self-tuning of controller parameters is realized, and a gap between an advanced algorithm and industrial landing is effectively filled up.

The invention relates to the technical field of ship power system control, in particular to a ship shaft power generation energy management and efficiency optimization method based on multi-working-condition adaptation, and the method comprises the steps: a data collection and processing step: collecting and preprocessing multi-source heterogeneous operation parameters capable of comprehensively representing a ship propulsion system, a power system, a motion state and an external environment in real time; a working condition dynamic identification step; an optimization model dynamic construction step; an online optimization and control step; and an adaptive learning step: based on new data generated in a system operation process, performing periodic incremental training on the time sequence deep learning model to update network parameters of the time sequence deep learning model. The self-adaptive learning enables the system to continuously optimize the working condition identification precision along with the time lapse of ship operation and the change of the external environment, and improves the long-term stability and adaptability of the system.

The invention provides a file positioning management method and system based on artificial intelligence, and relates to the technical field of artificial intelligence. According to the method, files are collected from multiple sources and subjected to standardization processing, an element set is generated in combination with multi-modal analysis of texts, images, audios, videos and tables, cross-modal alignment is achieved through a semantic representation model, hierarchical indexes of semantics, keywords and relations are constructed, and a unique traceability identifier is generated; in the query stage, intention recognition and joint retrieval are carried out, a result subjected to permission verification and traceability information labeling is output, online optimization and incremental reconstruction are executed based on user feedback, and comprehensiveness, accuracy, traceability and self-adaptive optimization of file positioning are achieved.

The invention discloses a rotor unmanned aerial vehicle visual navigation method and system for an unknown forest region, and the method comprises the steps: firstly, combining a depth camera with a Sobel gradient filtering mechanism, and effectively eliminating interference information; secondly, pixel-level segmentation and three-dimensional positioning of the trunk are realized by segmenting a cascade model of a convolutional network and a residual network, visual information is accurately mapped to a world coordinate system, and the problem of positioning drift caused by similar textures in a forest scene is solved; based on starting point-target point-terminal point minimum jerk trajectory planning, a smooth trajectory is generated through polynomial optimization and quadratic programming, flight jitter is inhibited fundamentally, and the mechanical loss is reduced while the image acquisition quality is guaranteed; and finally, through real-time target point updating and trajectory dynamic correction of the depth camera, a sensing-planning-execution closed loop is formed, so that the unmanned aerial vehicle has dynamic obstacle avoidance and path online optimization capabilities, autonomous crossing is finally realized, and navigation safety and stability in a complex environment are significantly improved.

The invention relates to the technical field of electronic weighing equipment, in particular to an ORS electronic hoist scale temperature and humidity compensation method and system based on an adaptive neural network, and the method comprises the steps: collecting multi-source heterogeneous data related to an ORS electronic hoist scale; performing parallel processing on the multi-source heterogeneous data through a double-branch adaptive attention neural network; determining a working condition membership degree based on the working condition dynamic quantitative index, and fusing the static compensation amount and the dynamic compensation amount to obtain a total compensation amount; and combining the total compensation amount with an original weighing value, outputting a compensated weighing value, and performing online optimization updating on the double-branch adaptive attention neural network. The technical problems of low measurement precision, poor working condition adaptability, insufficient real-time performance, poor long-term stability and the like in temperature and humidity compensation of an existing ORS electronic hoist scale are mainly solved.

The invention provides a sewage treatment process modeling control optimization method based on mechanism-data dual drive, and the method comprises the steps: collecting basic data of a sewage treatment process, constructing an ASM2d model of a sewage treatment plant, carrying out the sensitivity analysis and parameter calibration of ASM2d model parameters, constructing an environment and a data set, screening input features according to the data set, and carrying out the modeling control optimization of the sewage treatment process. A training set and a test set are divided according to a proportion, an ASM2d-LSTM mixed water quality prediction model is established based on an ASM2d model, the ASM2d-LSTM mixed water quality prediction model is trained based on the training set, an MPC control framework is integrated on the basis of the trained ASM2d-LSTM mixed water quality prediction model, an optimized operation sequence is generated by using the model, and the operation sequence is optimized. And evaluating the control effect of the optimization strategy by taking the collected real control parameters as a reference. According to the method, through a series of programs such as ASM2d-LSTM sewage quality prediction model construction based on mechanism-data dual drive, MPC control based on energy consumption and carbon emission reduction target optimization, key index online optimization strategy output in the sewage treatment process is realized.

The invention belongs to the field of track planning and intelligent control of a reusable vehicle, and relates to an intelligent track planning method for a cruise section of the reusable vehicle. The method comprises the following steps: constructing a three-degree-of-freedom centroid motion dynamics model of a cruise section vehicle, generating an offline optimal trajectory sample library covering wide working conditions based on a Gaussian pseudo-spectral method, designing a mapping relation between deep neural network learning task parameters and trajectory features, and outputting a high-quality trajectory planning initial value online. The distribution of collocation points is dynamically adjusted in combination with a self-adaptive collocation point method, a nonlinear programming problem is iteratively solved with a high-quality initial value as a starting point, and efficient and accurate optimization of the trajectory is achieved. Simulation results show that the method significantly reduces the sensitivity of online optimization to initial guess, still has fast response ability and high robustness under complex constraint and uncertainty working conditions, effectively improves the autonomous trajectory planning ability of the cruise section of the reusable vehicle, and ensures flight reliability and control precision.

The invention belongs to the field of artificial intelligence, particularly relates to an agent strategy generation and online optimization method based on dynamic scene perception, and aims to solve the problems that in a dynamic environment, strategy response is slow, optimization is difficult under sparse rewards, and online learning is unstable. The method comprises the following steps: constructing a multi-modal fused dynamic scene semantic perception module, and generating a high-dimensional scene representation; historical behaviors and environment contexts are fused through an attention mechanism, and an initial probabilistic strategy is output; executing an action and collecting real-time feedback to form an experience tuple; performing incremental strategy updating by adopting a non-parametric Bayesian framework and combining with a multi-peak exploration operator; a Lyapunov stability criterion and a strategy distillation mechanism are embedded to guarantee convergence robustness. According to the scheme, strategy generation within 50 milliseconds is achieved, the convergence speed of sparse reward tasks is increased by three times, strategy fluctuation is controlled within 8%, the system availability reaches 99.5%, and the real-time decision-making capacity and group cooperation efficiency of an intelligent agent in a complex dynamic scene are remarkably improved.

The invention relates to the technical field of industrial automation control, and discloses a desulfurization system pH value intelligent pre-control feedback control method based on big data learning, and the method comprises the following steps: S1, collecting full-chain process data related to pH control; s2, preprocessing the original data and constructing feature vectors; s3, dividing working conditions by adopting unsupervised learning, and independently training an LSTM prediction sub-model for each working condition; s4, solving a comprehensive cost function, and outputting a dynamic optimal pH set value; s5, performing dynamic weight fusion on prediction results of the sub-models to obtain an intelligent feed-forward regulation quantity; s6, fusing the feedforward adjusting quantity and the feedback correcting quantity to form a final control instruction; and S7, periodically retraining all the models to realize self-learning and iterative updating of the system. According to the method, through multi-working-condition model fusion prediction, multi-target online optimization and self-learning iteration, the control precision is improved, the operation cost is reduced, and long-term self-adaption of the control system is realized.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a federated learning-based ship water gauge intelligent identification model online optimization method and system. The method comprises the following steps: a central server distributes an initial global model to an edge node and establishes an encryption channel; and the edge node monitors scene change in real time, triggers a local model updating process when the new scene data accumulation exceeds a threshold value or the recognition accuracy is lower than an alarm value, enhances the anti-interference capability of the model by generating an adversarial sample, and encrypts and uploads the optimized local model. The central server optimizes the model uploaded by each edge node by using a secure aggregation algorithm, generates a new global model and distributes the new global model, the edge nodes compare the performance of the new and old models through parallel reasoning, the new model is switched when a preset condition is met, the model performance and scene change are continuously monitored, a trigger threshold value and training parameters are dynamically adjusted, and an optimization closed loop is maintained; and on the premise of protecting data privacy, a novel model optimization mechanism continuously adapts to diversified and dynamic recognition scenes.

The invention discloses an Internet of Things intelligent risk processing method and related equipment thereof, belongs to the technical field of artificial intelligence, and is applied to intelligent risk control and transaction risk management of a financial system. According to the method, the device state, the time sequence data and the spatial topological relation are combined by obtaining the multi-dimensional parameters such as the device operation state, the network environment and the service scene and constructing the context feature vector. In a risk early warning analysis link, the layered intelligent agent accurately predicts local and global risks through a space-time association mechanism, and feeds back a prediction result to a state space to drive dynamic adjustment of control parameters. And in combination with the online optimization capability of the reinforcement learning algorithm, the control strategy can automatically adapt to the real-time change of the equipment state, and the collaborative effect of quick response of the equipment end, local optimization of the edge end and global regulation and control of the cloud end is realized. According to the invention, the timeliness and accuracy of risk early warning are improved, and the adaptive and intelligent management capability of the system in a complex network environment is enhanced.

The invention provides a multi-station cooperative control method based on event triggering and look-ahead synchronization. The multi-station cooperative control method comprises the following steps: S1, defining nominal motion parameters for each station; s2, when the physical completion event of the current station is detected, calculating to obtain an accumulated time deviation up to the current station; s3, on the basis of the cumulative time deviation, executing online optimization calculation in a prediction time domain containing a plurality of stations in the future so as to determine an optimal target operation duration used for compensating the cumulative time deviation; and S4, according to the optimal target operation duration, generating and issuing a new motion curve for a first station in the prediction time domain, taking the station as a new current station, and circularly executing the steps S2 to S4. According to the method, the system can actively eliminate tiny time deviation caused by uncertainty factors such as material difference and mechanical wear, and the accumulative effect of errors is avoided.

The invention discloses a dissolved oxygen closed-loop regulation and control method used in a sewage treatment process. The method comprises the following steps: acquiring real-time dissolved oxygen concentration in a reaction tank through a distributed sensor array, and performing temperature compensation; an online water quality analyzer is used for collecting water inlet flow, chemical oxygen demand, ammonia nitrogen and water temperature to construct a comprehensive input feature vector; establishing a nonlinear dynamic mapping model based on a deep neural network, and outputting a target dissolved oxygen set value changing along with working conditions; an aeration adjusting instruction is generated by adopting a feedforward-feedback composite adaptive fuzzy PID control algorithm; dynamically adjusting the air volume of an air blower and the opening density of a partition aeration disc to match the aerobic rate of microorganisms; and the control performance is evaluated regularly, and a model parameter online optimization mechanism is triggered to continuously improve the setting precision. According to the method disclosed by the invention, the dissolved oxygen can be accurately controlled, so that the aeration energy consumption is reduced by not less than 18%, the control precision is within + / -0.3 mg / L, and the robustness, the automation level and the low-carbon operation capability of the system are remarkably improved.

The invention discloses an energy storage converter predictive current control method based on data driving model self-learning, and belongs to the technical field of power electronic converter control. The energy storage converter is a half-bridge bidirectional DC-DC converter, and the method comprises the following steps: collecting the state quantity of the energy storage converter through a sensor in each control period, forming a data driving prediction model constructed by an input vector input neural network online parameter identification module, and outputting an initial duty ratio prediction value; constructing a value function, performing online optimization on an initial value through a gradient descent method to obtain a final optimal duty ratio, and simplifying a scene to directly use the initial value; comparing the optimal duty ratio with a carrier wave to generate a PWM (Pulse Width Modulation) signal to drive a power switch tube; actual inductive current is collected, an ideal duty ratio enabling the value function to be minimum is reversely solved to serve as a supervision signal, and the model weight is trained and updated online through a sample. The technical problem that traditional continuous set model predictive control depends on an accurate mathematical model is solved.

The invention provides a self-organizing flight planning method based on behavior parameter dynamic adjustment, and belongs to the technical field of unmanned aerial vehicle flight planning. Each unmanned aerial vehicle obtains and updates own state and environmental threat information through a sensor, and establishes a cluster member level interaction model to interact neighbor motion states; comprehensively considering the interaction between members in the cluster and the interaction between the members and the external environment, respectively calculating an internal interaction effect and an external interaction effect, and further obtaining an overall interaction effect; on the basis of an asynchronous optimization criterion triggered by an event, online optimization adjustment is carried out on a behavior parameter set of the unmanned aerial vehicle in combination with an optimization guard interval, a flight state is predicted through a motion model, an optimal parameter is determined by means of a local performance evaluation function, a final control input driving state is generated and updated, and autonomous flight planning is realized. According to the method, the online cooperative flight requirement of the unmanned aerial vehicle cluster in a dynamic unknown environment is met.

The invention provides an optimal primary frequency control method based on reinforcement learning. The method comprises the following steps: establishing a dynamic model of a power system; designing a frequency control strategy based on a deep reinforcement learning algorithm; the system frequency deviation is used as a reward signal, and a control strategy is trained through interaction with a power system; lyapunov function stability constraints are introduced into the reinforcement learning algorithm; a neural network is adopted to carry out parameterization design on the controller; discretizing the frequency dynamic equation, and proposing a multi-node collaborative optimization target; and deploying the trained control strategy to an actual power system, and adjusting control parameters in real time through an online optimization technology to adapt to the dynamic change of the system operation state. By means of the method, the frequency control accuracy and stability of the power system are improved, and the global optimal performance of frequency control of the whole power grid is achieved in actual deployment.

The invention discloses a double-master-control dynamic cooperation hybrid power system and a control method. The system comprises a double-master-control dynamic cooperation framework, a master control unit A and a master control unit B synchronize data through a communication bus and dynamically distribute tasks according to a load rate; the hybrid energy storage expansion unit is formed by connecting a lithium iron phosphate battery pack and a capacitor bank in parallel through a bidirectional DC / DC converter; a dual-channel redundancy communication mechanism is adopted, a CAN bus is adopted for parallel communication with the Ethernet, automatic switching is achieved in the case of faults, and no data is lost; the predictive fault switching module is used for predicting a fault risk based on the LSTM neural network and starting standby main control unit preloading; and a machine learns a load optimization engine, deploys a reinforcement learning algorithm to dynamically adjust an output ratio and performs online optimization. The method comprises the steps of system initialization, master control task allocation and the like. The task processing efficiency and flexibility of the system are improved, reliable and stable communication is guaranteed, the fault risk is reduced, and the adaptability to load change and the energy utilization efficiency are improved.

The invention relates to the technical field of energy storage optimization, and discloses an energy storage scheduling method and system based on digital twinning and reinforcement learning. The method comprises the steps of constructing an energy storage scheduling optimization model, performing multi-battery cooperative control, constructing a power grid twinborn model, optimizing the energy storage scheduling optimization model, and realizing energy storage scheduling based on the optimized energy storage scheduling optimization model. The system corresponds to the method. According to the application, an intelligent closed-loop architecture of'decision-verification-evaluation-learning 'is established, pre-security verification of the strategy is realized through a digital twin technology, quantitative auditing is performed on the strategy aftereffect through a multi-objective performance evaluation system, and finally, the evaluation result is used as an evolution feedback signal to drive online optimization of a core decision model, so that the decision-verification-evaluation-learning efficiency is improved. And the problems of mismatching and performance degradation of the existing energy storage scheduling model are fundamentally solved.

The invention relates to the technical field of unconventional oil-gas exploration, in particular to a well-seismic integrated geological model intelligent construction and reservoir gas-bearing prediction system, which is characterized in that a data acquisition and preprocessing module generates multi-dimensional feature mapping through wavelet transform denoising and principal component analysis; the well-seismic integrated modeling module adopts a Transform and BiGRU hybrid model to fuse well-seismic data, and constructs a three-dimensional geologic model adaptive to a fracture network; the dynamic gas-bearing prediction module is used for predicting an adsorbed gas / free gas ratio and gas saturation based on a Monte Carlo-Bayesian framework; the real-time iteration module corrects model parameters through online optimization and multi-source data feedback; and the output and visualization module generates a dynamic distribution diagram and an uncertainty interval, and through efficient multi-source data processing, construction of a high-precision three-dimensional geologic model, dynamic prediction of gas content and quantification of uncertainty, prediction precision, timeliness and decision reliability of exploration are improved in combination with real-time iterative optimization of the model and visualization output.

The invention discloses a machine learning-based data intelligent governance decision-making method and device and a medium, and relates to the technical field of intelligent optimization decision-making, and the method comprises the steps: collecting multi-source business and environment data, executing missing value completion, anomaly detection and normalization processing, and forming a data standardization set; generating a multi-dimensional baseline index based on the set, extracting statistical and trend features, and obtaining a feature vector set; calculating a joint influence degree in combination with the feature vector set and a lineage relationship to form a candidate decision set; predicting the potential gain, uncertainty, risk and cost of the candidate items, generating a joint priority score, and sorting to obtain a candidate set; executing online optimization according to a sorting result, distributing gray flow, and generating an execution plan; and acquiring index, risk and cost data through the execution plan, and attributing to obtain a unit economic index. According to the method, dynamic optimization of income, risk and cost is realized by introducing joint priority scoring and closed-loop updating and combining gray level optimization.

The invention relates to the field of water turbines, and provides a water turbine speed regulation system PID parameter optimization method and device, and the method comprises the steps: evaluating whether the system performance under the current operation condition meets the performance requirements or not based on a digital twin model of a water turbine speed regulation system; if not, optimizing the PID parameter corresponding to the current operation condition on the digital twin model by applying a trained BP neural network to obtain an optimized PID parameter; the BP neural network is obtained by training through an error back propagation algorithm based on the sample signal and the corresponding expected output. According to the PID parameter optimization method and device for the water turbine speed regulation system, an online optimization mechanism combining the digital twin model and the BP neural network is introduced, a group of adaptive new parameters can be rapidly and automatically output according to the current working condition information, calculation depending on artificial experience or a fixed formula is replaced, and the calculation efficiency is improved. And real-time and accurate tracking optimization of the complex time-varying system is realized.

The invention relates to the technical field of metal purification, and discloses a two-stage rectification purification method of high-purity superfine zinc powder, which comprises the following steps: first-stage rectification is performed on a crude zinc raw material, and a collaborative purification control process is adopted in the first-stage rectification to remove low-boiling-point impurities, so that preliminarily purified zinc liquid is obtained; the collaborative purification control process comprises the steps that first state data of a first rectifying tower are obtained in real time, the future state of the first rectifying tower is predicted based on a first dynamic model, a first optimal control instruction is obtained through online optimization calculation according to a prediction result, and the first optimal control instruction is executed. According to the method, the process tomography technology and the self-calibration dynamic digital twinborn model are combined, real-time and accurate sensing and prediction of the internal fluid dynamic state in the rectification process are achieved, the operation stability of the whole rectification process is remarkably improved, and meanwhile effective separation of cadmium and lead can be achieved.