149 results about "Mathematics model" patented technology

The invention discloses a multi-objective reinforcement learning man-machine cooperative assembly task allocation method based on neighborhood parameter migration, and the method comprises the steps: building a mathematical model which aims at minimizing the physiological fatigue accumulated value of a human operator and minimizing the maximum completion time for a multi-objective optimization problem of task allocation in a man-machine cooperative assembly system; a multi-target problem is decomposed into N standard sub-problems by adopting a weighting and decomposition strategy, and training is accelerated through a neighborhood parameter migration strategy; each sub-problem is solved based on a near-end strategy optimization algorithm of an Actor-Critic framework, Gaussian noise is added to an Actor network to simulate environment uncertainty, an action mask mechanism is introduced to process priority constraints of assembly tasks, and it is ensured that a generated task allocation scheme is always feasible. According to the method, the convergence speed and diversity of the Pareto solution set can be remarkably improved, and the assembly efficiency and operator fatigue are effectively balanced.

The invention relates to the field of intelligent temperature control, and provides a refrigeration house PID control parameter optimization method and device, equipment and a storage medium. The method comprises the steps of collecting temperature data and energy consumption data of the refrigeration house at a constant-temperature stage; based on the temperature data and the energy consumption data, a mathematical model representing the mapping relation between the temperature and the energy consumption of the refrigeration house is established; constructing a deep reinforcement learning model based on a preset reward function and a mathematical model giving consideration to the temperature stability and energy consumption optimization of the refrigeration house; and through interactive learning of the intelligent agent of the deep reinforcement learning model and the refrigeration house environment, determining optimization parameters used for adjusting refrigeration house PID control. According to the refrigeration house PID control parameter optimization method, device and equipment and the storage medium provided by the invention, the mathematical model of the temperature and energy consumption mapping relation of the refrigeration house can be effectively established, the deep reinforcement learning model is constructed through the reward function and the mathematical model, and the optimization parameters of refrigeration house PID control are adjusted through deep reinforcement learning.

The invention relates to the technical field of unmanned aerial vehicle management and control, and discloses a low slow small unmanned aerial vehicle countering method and system, which eliminates space-time deviation and redundant information of different sensor data by acquiring multi-source data and performing fusion processing. Furthermore, the target tracking trajectory of the low-slow small unmanned aerial vehicle is processed and generated through an adaptive Kalman filtering algorithm, and real-time smooth tracking of the trajectory is realized. Furthermore, probabilistic region prediction is performed by combining a Monte Carlo method and a kernel density estimation method, and a threat region prediction result of the low-slow small unmanned aerial vehicle is generated, so that the possible motion range of the target is comprehensively covered, and the motion intention of the target is accurately captured. Furthermore, in combination with a preset constraint condition set, a target tracking trajectory and a threat area prediction result, the interception success rate mathematical model is solved by using an improved particle swarm algorithm, and a collaborative countering strategy is obtained, so that the limitation of an existing countering method is avoided, and the accuracy and efficiency of countering are improved.

The invention provides a sepsis multi-task prediction method and system, and belongs to the technical field of disease prediction based on a mathematical model, and the method comprises the steps: obtaining a symptom data record of a to-be-detected patient; and processing the obtained symptom data records by using a pre-trained classification model to obtain a final task result. According to the method, a multivariable time sequence in medical health record data of a patient is utilized, time representation containing sepsis pathological characteristics is obtained through a time mode of modeling data based on a self-attention encoder, and the trend of the condition of the patient changing along with time is obtained; correlating different medical features according to features including patient condition change trends, so that each feature can perceive other features mutually, and mining global feature representation of the patient; and inputting the global feature representation into a task-aware hybrid expert system, and routing the unified global feature representation into different expert systems, thereby obtaining task-level representation and realizing multi-task prediction.

The invention discloses an ultrasonic guidance navigation system based on multi-modal detection and a CNB ejection mechanism, and belongs to the technical field of ultrasonic auxiliary diagnosis, multi-modal detection loads a directional bounding box model and a segmentation model when the system is initialized, and the directional bounding box model performs directional detection of a puncture needle on an input frame; in the result extraction stage, puncture needle information is extracted from a directional bounding box model detection result, a focus mask is extracted from a segmentation result, and the focus mask is adjusted to be the same as an input frame in size; when the focus mask is extracted, the validity of a segmentation result is verified, then first effective mask data are extracted from multiple types of segmentation results, the mask data are transmitted to a CPU from a GPU memory, a floating point probability value is converted into an integer binary mask, and puncture needle direction detection and segmentation of multiple types of anatomical structures are achieved. According to the CNB ejection mechanism, a mathematical model of the ejection process is established through an ejection trajectory calculation function, and a reliable mathematical basis is provided for CNB ejection operation diagnosis.

The invention relates to a cable-stayed bridge stay cable force data processing method and system based on an influence matrix. The method comprises the following steps: constructing a bridge model, and extracting a corresponding influence matrix through finite element software; taking the sum of squares of the tower deviation value, the linear difference value and the cable force difference value as a judgment function; a cable force influence matrix equation is obtained based on the superposition principle, the cable force adjustment amount of each stay cable, the initial tension vector of the stay cable, the tower deviation and the line shape of the main tower are obtained through solving, and then the cable force adjustment value vector of each stay cable is obtained through solving; establishing a mathematical model based on an optimization theory, and calculating to obtain an optimal cable force; wherein the difference value between the adjusted main tower deviation and the target tower deviation, the difference between the adjusted bridge surface line shape and the target line shape, the difference between the adjusted cable force and the mechanical cable force and the upstream and downstream deviation are used as constraint conditions, and the cable force variance is used as an optimization target function. According to the method, the uniformity of the bridge deck line shape, the offset of tower deflection and the cable force of the stay cable in the construction process can be effectively controlled.

The invention discloses a high-speed maglev train suspension constraint control method for coping with long-wave oscillation of a track beam, and belongs to the field of maglev track traffic. The method comprises the following steps: dynamically expanding high-speed maglev train model prediction suspension control under asymmetric preset performance constraints, and coping with safety constraint control of accurate suspension of the high-speed maglev train with long-wave oscillation of a track beam: establishing a track model of the long-wave oscillation of the track beam; designing the precise suspension dynamic expansion asymmetric preset performance constraint of the high-speed maglev train according to the long-wave oscillation information of the track beam; designing a high-speed maglev train suspension air gap mathematical model containing track beam long-wave oscillation information; obtaining a state space expression based on a reconstruction error according to the dynamic expansion asymmetric preset performance constraint and the conversion error; a prediction model is obtained through the expression, an optimal control problem is designed, and an optimal solution is solved; on the premise that the track beam oscillation reference air gap tracking precision is improved, suspension deadlock of the high-speed maglev train under long-wave oscillation of the track beam is avoided, and it is ensured that the high-speed maglev train runs safely in a small suspension gap with low power consumption under long-wave oscillation of the track beam.

The present application relates to the technical field of electrified railway control, and discloses a phase control closing method and a heavy haul locomotive circuit breaker, the method comprising: step one, establishing equivalent mathematical models for the heavy haul locomotive, traction substation, AT substation and traction network; step two, establishing a vehicle-network-station simulation model based on a MATALB / Simulink simulation platform; step three, obtaining the influence of different line loads on phase selection closing according to the vehicle-network-station simulation model; and step four, determining a phase control closing scheme and conducting test verification. The phase control closing and opening method of the heavy haul locomotive circuit breaker with the above structure can establish equivalent mathematical models for the heavy haul locomotive, traction substation, AT substation and traction network, and then establish a vehicle-network-station simulation model, analyze the influence of different line loads on phase selection closing, and determine a phase selection closing scheme according to the breakdown characteristics of the circuit breaker and the analysis results. The phase selection closing scheme determined through test verification can achieve the purpose of reducing the overvoltage of the closing system.

The invention provides a power distribution system island division and fault reconstruction method and system. The method comprises the steps of obtaining a topological structure, load characteristic data and renewable energy output characteristic data of a power distribution system, and generating a mathematical model of the power distribution system; performing optimization calculation based on a mixed meta-heuristic algorithm framework and an adaptive step length gradient descent method; performing fuzzy binning processing on the optimization result to obtain a calibrated reconstruction optimization result; and finally, carrying out island division and fault reconstruction based on a calibration result. According to the method, the uncertainty influence of renewable energy sources can be effectively processed, and the accuracy and reliability of island division and fault reconstruction of the power distribution system are improved.

This invention provides a method, apparatus, device, and readable storage medium for predicting the value of banking business, relating to the field of computer technology. The method includes: acquiring historical product data and demand analysis, whereby the demand analysis includes demand names, directories, associated systems, and demand rules; calculating a demand data set based on the historical product data and demand analysis, where each element in the demand data set represents the number of transaction demand modifications, the set of demand rules, and the transaction credit value corresponding to a transaction; establishing a mathematical model of product value based on the historical product data, using the demand data set as input, and solving the mathematical model to obtain a product value set, where each element in the product value set represents the number of product demand modifications, the proportion of new business rules, and the product credit value corresponding to a product; and calculating the product value prediction result based on the product value set. By establishing a value chain relationship between products and demands, the method quantitatively reflects the value attributes of a product, displays the direction of business changes and the quality of demands in real time, assesses the direction of business changes, thereby improving customer experience, reducing operating costs, and forming a positive cycle.

The invention relates to a technique for implementing, controlling and automating a task or process on a blockchain such as, but not limited to, the Bitcoin blockchain. The invention is particularly suited for, but not limited to, automated execution of contracts such as smart contracts for financial agreements. However, other types of tasks and non-financial contracts can be implemented. The invention can be viewed as the implementation or incarnation of a state machine or DFA on a blockchain by using the unspent outputs of blockchain Transactions to represents the states of the machine, and spending of those outputs as the transition of the machine from one state to another. The invention provides a technical realisation and implementation of a mathematical model of computation conceived as an abstract machine that can be in one of a finite set of states, and can change from one state to another (transition) when a triggering event of a finite set (called input) occurs. The invention comprises compilation and codification techniques for the DFA implementation.

The present application belongs to the technical field of workshop production scheduling optimization, in particular to a flexible workshop scheduling method and system based on a hybrid whale optimization algorithm. The method comprises S1, analyzing the flexible workshop scheduling problem and determining the mathematical model of FJSP; S2, continuously processing the discrete workshop scheduling; S3, initializing the position of the whale individual in the whale optimization algorithm through Tent chaotic mapping; S4, calculating the fitness of all whale individuals; S5, updating the whale position; S6, searching the neighborhood structure; S7, judging whether the number of whale position updates reaches the maximum iteration number, if not, returning to step S4, if yes, continuing to step S8; S8, outputting the best whale position; S9, outputting the maximum completion time of the found machine and drawing a Gantt chart. The present application has the characteristics of enhancing the local search ability of the whale optimization algorithm, thereby realizing the reasonable allocation of workshop scheduling and improving the production efficiency.

The application discloses a kind of trajectory tracking and vibration suppression methods of multi-helicopter flexible hoisting system, including in undirected communication topology, design virtual leader state estimator;Based on the boundary state of the mathematical model of multi-helicopter flexible hoisting system, a disturbance estimator is designed for the helicopter and payload under time-varying disturbance;Based on the leader state estimator, the disturbance estimator and the adaptive fault-tolerant control method, the control signal is designed, and the intermittent fault adaptive compensation law is designed.The application can improve the anti-interference and fault-tolerant capability of the system, ensure that the multi-helicopter accurately tracks the leader trajectory for hoisting and transportation while suppressing the vibration of the flexible sling.

The invention relates to the technical field of electric power, and particularly discloses a model-free adaptive control method for interconnected power grid AGC, and the method comprises the steps: constructing an interconnected power grid AGC system mathematical model in which multiple types of units participate; the pseudo gradient of the interconnected power grid AGC system mathematical model is calculated by using real-time input-output measurement data, and dynamic linearization is carried out on the interconnected power grid AGC system mathematical model at the operation point of each discrete moment of the interconnected power grid; constructing a weighted one-step forward control law, and adding additional regulatory factors and control items in the control law; and pre-optimizing parameters of the constructed model-free adaptive control method through an intelligent optimization algorithm. The method has the advantages that the limitation that a traditional AGC method depends on an accurate power grid frequency response model is solved, and the power grid frequency stability and the efficiency and robustness of power exchange control of all areas of the interconnected power grid are improved.

The application discloses a kind of oven heat dissipation temperature control system and method, specifically related to temperature control field, including system central processing unit module, system operation database, user information end, data acquisition module, data processing module, artificial intelligence prediction module, control strategy judging module, execution module and feedback and optimization module.The application is constructed multiple key coefficient mathematical models according to key features by artificial intelligence prediction module, realize all-around evaluation and prediction to oven heat dissipation performance, simultaneously, the execution result is collected in real time by feedback and optimization module, recalculate performance comprehensive evaluation coefficient, if not reach preset value, automatically adjust heat dissipation strategy and continue optimization, simultaneously, timely to user output coefficient and issue alarm, inform user oven state, facilitate user timely maintenance, improve oven use convenience and intelligent level, enhance user experience.

The invention provides an insurance industry meeting place seat number automatic distribution method. The method comprises the steps that client data are acquired through a system input interface and an API interface and preprocessed; calculating a customer value score based on a predefined mathematical model and generating a customer tag; configuring a seat distribution rule set, setting priorities, and establishing a mapping relation between rules and areas; executing automatic seat distribution by adopting a hierarchical-backtracking model, and optimizing a distribution result through a greedy algorithm and a backtracking mechanism; providing a visual interface to display a distribution result and supporting manual adjustment; and finally generating a complete seat arrangement report. According to the invention, the problems of low efficiency and poor accuracy of traditional manual distribution are solved, intelligent and precise management of seat distribution of the meeting place in the insurance industry is realized, and the distribution efficiency and customer satisfaction are remarkably improved.

This disclosure provides a similarity-based method and system for order batching and picking sorting for multiple picking stations. The method includes calculating the similarity of each order, determining whether different orders contain the same goods, and batching orders according to the objective of maximizing similarity. A mathematical model is constructed with the objective of minimizing the total number of goods entering and leaving the warehouse, and the picking order for different batches of orders is determined. The method fully considers the situation where the same goods appear in multiple orders, calculates the similarity of items in different orders, batches orders according to the principle of maximizing item similarity, and simultaneously sorts the picking order of different batches of orders with the objective of minimizing the number of goods entering and leaving the warehouse, thus determining a reasonable picking order and reducing operating costs.

Systems and methods are provided for reconciling untrusted data of a subject using trusted data pertaining to the subject. Systems and methods are directed to evaluating differences in predicted data with respect to corresponding received data. Systems and methods estimate metabolic states from a combination of trusted and untrusted metabolic inputs, along with optionally using a personalized mathematical model with parameter optimization. Systems and methods provide for reconciled untrusted inputs with their measured impact of the glycemic signals that is consistent with a metabolic model. Estimation of future metabolic states for decision support and automated insulin dosing is enabled. Replay of scenarios with estimated or reconciled data is also provided.

The application discloses an intelligent decision-making method based on layered A3C, and relates to the field of intelligent decision-making of air defense combat, and comprises the following method steps: S01: a mathematical model is established by taking the optimization targets of minimizing the probability of missing high-value targets, minimizing the loss of defending a key point, maximizing the probability of effective killing, and minimizing the resource consumption of an interception missile; S02: the state, action, reward and target in air defense combat are determined according to step S01; S03: air situation feature extraction based on a Bi-GRU network; S04: calculation of a multi-head attention mechanism; S05: parallel calculation and training are performed by using an A3C algorithm; the air situation information is subjected to feature extraction by the Bi-GRU network, and then the H-A3C algorithm is adopted for training; in the training process, the multi-head attention mechanism and the event-based reward mechanism are introduced, thereby helping the agent to train. Finally, the proposed H-A3C algorithm is verified in a digital battlefield environment, and is faster and better than a traditional algorithm.

This invention provides a method and system for wafer inspection data conversion based on physical constraint loss, relating to the field of semiconductor manufacturing technology. The method specifically includes: acquiring wafer inspection data at a source wavelength and determining the target wavelength to be converted; based on the wafer inspection data at the source wavelength and the target wavelength, matching a mathematical model from a pre-set physical law model library to describe the physical laws of the wafer inspection scenario; and based on the mathematical model, using a CycleGAN network based on physical constraint loss to map the wafer inspection data at the source wavelength to the target wavelength, obtaining the wafer inspection data at the target wavelength. This invention significantly improves the physical accuracy of cross-wavelength conversion through multi-task loss function design and physical feature embedding layer design in the generator, thereby adapting to the needs of wafer defect detection.

The invention relates to a single-thread and multi-thread power flow method for a comprehensive power transmission and distribution network, and the method comprises the following steps: S1, building a mathematical model of controllable energy, and obtaining an internal current source of an electronic interface distributed energy generator; s2, constructing a backward scanning subprogram based on an internal current source, and constructing a forward scanning subprogram; and S3, calling the backward scanning subprogram and the forward scanning subprogram to carry out a single-thread or multi-thread load flow calculation method of the integrated power transmission and distribution network until a convergence condition is met. Compared with the prior art, the method has the advantages that the number of single-thread iterations is reduced, and the like.

This invention discloses a method for predicting the droplet size of atomized nickel-cobalt-manganese ternary solutions. By collaboratively establishing a mathematical model with the state parameters of the ternary salt solution and the core parameters of the target atomization condition, the method accurately predicts the droplet size under the target atomization condition. This method deeply quantifies the coupling relationship between the four parameters and the droplet size, achieving precise quantitative prediction of the droplet size. It significantly reduces the optimization cycle and trial-and-error costs for droplet size, and provides technical support for the directional optimization of atomization process parameters in lithium-ion battery ternary materials. This lays the foundation for the subsequent preparation of high-performance ternary precursors and cathode materials.

The application belongs to the technical field of aircraft brake control, and discloses an aircraft anti-skid brake control parameter optimization method based on an improved particle swarm algorithm. The method comprises the following steps: establishing a mathematical model of an aircraft brake system and determining target parameters; obtaining model parameters of the mathematical model of the aircraft brake system; initializing parameters of the improved particle swarm algorithm; adjusting inertia weight and acceleration coefficient of the particle swarm algorithm by adopting a second-order oscillation link; updating and iterating particles; performing boundary crossing processing and anti-skid processing on the particles after updating and iteration; comparing the fitness value of each particle after updating with a current optimal fitness value, and updating the optimal value; performing a differential mutation operation on the particles, and updating the optimal value; and stopping until the maximum iteration number is reached. The method solves the problem that in the field of aircraft brakes, optimal brake control law parameters are difficult to select in order to achieve short-distance and high-efficiency braking.

The present invention relates to a method or the like performed by at least one device or a system comprising at least two devices, for example. The method comprises obtaining information about at least one production element of a production method for producing a building board. The method further includes determining at least one optimized first process parameter based on the information about the at least one production element and using an optimization function. The at least one optimized first process parameter is based on or corresponds to respective values of the at least one first process parameter of the production method, which values optimize the optimization function. Further, each of the first process parameters of the at least one of the production methods is associated with at least one of the production elements of the at least one of the production methods. The method further includes determining respective values of at least one second process parameter of the production method using a mathematical model such that at least one constraint related to the building board is satisfied when the production method is performed based on the values of the at least one optimized first process parameter and the at least one second process parameter. Furthermore, the method comprises providing values of the at least one optimized first process parameter and the at least one second process parameter for use in the production method.

The invention discloses an automatic design method for a line balance optimization algorithm driven by a large language model, and belongs to the technical field of mixed flow assembly lines. Establishing a mixed flow assembly line balance optimization mathematical model according to the acquired information and optimization requirements of the mixed flow assembly line; and performing line balance optimization algorithm automatic design on the mixed flow assembly line balance optimization mathematical model through the large language model, including solving the mathematical model through the automatically generated line balance optimization algorithm according to the obtained mixed flow assembly line information to obtain a target function value, and evaluating the performance of the line balance optimization algorithm through the target function value. And performing double evolution according to a feedback evaluation result to obtain a double-evolved line balance optimization algorithm, performing evaluation again, comparing with the line balance optimization algorithm obtained in the previous round, performing iteration continuously until a stop condition is met, and finally obtaining an optimal line balance optimization algorithm. According to the method, automatic design and evaluation can be realized, the optimal solution of the balance optimization problem of the mixed-flow assembly line is obtained, and the design efficiency is improved.

The invention discloses a variable length control method with a limited processing state. According to the method, an iteration length selection index is constructed, so that the state value of the system does not violate a given limit range. Under the framework of a backstepping method, vector parameter uncertainty and disturbance of the system are converted into a scalar form for analysis. A controller without a reversible control matrix is constructed to control a high-order system. Compared with a traditional control method needing an accurate mathematical model, the control algorithm provided by the invention is more novel and simple in application condition. When the method is used for repeated task operation, the control precision is effectively improved, and the method has good engineering application value.

The invention discloses a component prediction and length calculation method for a dissimilar steel continuous casting and mixed casting blank. The method comprises the steps that a tundish multiphase flow mathematical model and a casting blank solidification and mass transfer coupling model are established and verified; the different steel grade continuous casting process under different technological parameter combinations is simulated, new steel grade concentration change data at a tundish outlet are obtained, and the influence of the technological parameters on the mixed casting behavior in the tundish is analyzed; analyzing the influence of key process parameters on molten steel exposure, slag layer distribution and slag entrapment risk in a flow injection area in the liquid level descending and liquid level ascending processes; the concentration change data of the new steel grade at the outlet of the tundish is used as an input boundary condition of the casting blank solidification and mass transfer coupling model, distribution of key elements in the mixed casting blank is simulated and predicted, and the length of the mixed casting blank is calculated; and the optimal process control parameters with the aim of shortening the length of the mixed casting blank are determined by integrating the length of the mixed casting blank and the molten steel cleanliness risk analysis result. The method has the advantages of accurately predicting component distribution and length of the mixed casting blank, optimizing process control parameters and the like.

The invention belongs to the related technical field of hydraulic servo control systems, and discloses a humanoid robot hydraulic driver position servo self-adaptive control method and system oriented to variable load working conditions. The method comprises the following steps: establishing a mathematical model of a to-be-controlled object hydraulic driver and converting the mathematical model into a state-space equation; according to the state-space equation of the to-be-controlled object, establishing an extended state observer to observe the state and total disturbance of the to-be-controlled object in real time; according to the state and the total disturbance observed by the expansion state observer in real time, a backstepping controller is designed to control the to-be-controlled object, so that the actual displacement of the to-be-controlled object is close to the expected displacement, when the backstepping controller is designed, an adaptive law is established for the load quality in the backstepping controller, and the actual displacement of the to-be-controlled object is controlled. Therefore, the dynamic change of the load in practical application is met. According to the invention, the problems of low tracking precision and weak robustness of hydraulic driver position control under a variable load working condition are solved.

The invention discloses a collaborative improvement method and system for dynamic measurement key performance of an optical fiber current transformer. The method comprises the following steps: constructing a first mathematical model of forward channel gain and step response rise time; constructing a second mathematical model of forward channel gain and overshoot; constructing a third mathematical model of the common noise and the signal-to-noise ratio of the optical fiber current transformer system, and according to the first mathematical model and the second mathematical model, carrying out dual-target optimization by taking the forward channel gain as an independent variable and taking the minimum overshoot and step response as targets, determining the optimal forward channel gain, and realizing the minimum dynamic measurement performance (overshoot and step time) of the system; by taking an independent variable forward channel gain value obtained through optimization as a constraint condition, improving the target of maximizing the third mathematical model, and guiding the design of the optical fiber current transformer according to an optimization result, the optical fiber current transformer can be effectively ensured to have a relatively high signal-to-noise ratio while having good dynamic measurement performance; and the measurement performance of the optical fiber current transformer is improved.

Disclosed are computer visual guidance systems for guiding surgeons through arthroscopic debridement of bony pathologies, including by automatically generating annotations relating to characteristics of bony pathology in an image. The annotation may be generated in accordance with a determination as to whether a femoral head of the bony pathology is endospherical or exospherical. The annotation may be generated in accordance with a mathematical model created based on anatomies of subjects other than the patient. Further disclosed is a user interfaces for guiding a surgeon through arthroscopic debridement of a bony pathology, wherein intraoperative images are displayed simultaneously with a preoperative plan comprising interactive three-dimensional models of an anatomical feature of a patient. Further disclosed is a user interface for guiding a physician in categorizing images of a patient, wherein the interface comprises an image viewing window and an interactive checklist for different image categories to be captured.