50 results about "Data driven prognostics" patented technology

The invention discloses a drainage basin water body heavy metal pollution prediction system based on multi-modal attention, and the system comprises a data collection module which is used for collecting multi-modal data related to drainage basin water body heavy metal pollution, and a preprocessing module which is used for carrying out the standardization processing of the obtained multi-modal data. The multi-modal attention fusion module is used for performing feature extraction and cross-modal interaction on the preprocessed multi-modal data to generate fusion features; the dynamic prediction module is used for outputting a spatial-temporal distribution prediction result of the heavy metal pollutant concentration in the drainage basin by constructing a spatial-temporal coupled prediction model; according to the method, the cross-modal interaction accuracy is improved by dynamically focusing the key association information of the multi-modal data through the intra-modal and inter-modal attention mechanism, meanwhile, the data-driven prediction model is constructed, the prediction precision of the high-risk area is optimized through the weighted loss function, the prediction error is effectively reduced, and the prediction efficiency is improved. And high-precision dynamic prediction of heavy metal pollution under the watershed scale is realized.

The invention provides a method for predicting the residual life of a fuel cell, which belongs to the technical field of fuel cells, and comprises the following steps: carrying out data preprocessing on collected fuel cell operation time-voltage data to obtain output voltage data of a time sequence; introducing the verified EIS data, and further analyzing and extracting attenuation characteristic parameters of the fuel cell through relaxation time distribution; analyzing a peak value and a frequency of relaxation time distribution analysis and a Pearson's correlation coefficient of output voltage data, distributing a weight, performing nonlinear fitting on a recession characteristic parameter, and establishing a time-frequency health index; constructing a fuel cell attenuation model, and performing optimization training; the attenuation characteristic parameters and the output voltage data are used as input and are sent into the fuel cell attenuation model after optimization training, and the residual life of the fuel cell is predicted and output. The defect that a conventional prediction method based on data driving cannot be suitable for fuel cell attenuation prediction is overcome, and the attenuation process can be quantitatively analyzed.

The invention relates to the technical field of motor control, discloses a direct current brushless motor control method and system based on current prediction, and aims to solve the problems of large torque ripple, low efficiency and poor stability caused by current loop lag in the prior art. The method comprises the following steps: acquiring a motor operation state signal in real time; determining a sector and an electrical angular velocity based on the rotor position and the rotational speed; inputting related parameters into the mixed current prediction model to obtain a three-phase current prediction value of the next period; a prediction error is calculated in combination with a current instruction, and an optimal voltage vector enabling a cost function to be minimum is solved through a model prediction control algorithm; and finally, a space vector pulse width modulation signal is generated to drive an inverter. According to the method, advanced control is realized by fusing a physical model and a data-driven prediction mechanism, the torque ripple is remarkably reduced, and the energy efficiency and robustness are improved.

The invention provides a traditional Chinese medicine symptom association prediction method based on similarity and a graph neural network. According to the method, multi-dimensional characteristics such as taste, nature, channel tropism and rising and falling of traditional Chinese medicines and characteristics such as exogenous causes, endogenous causes, qi, blood, body fluid and viscera of symptoms of the traditional Chinese medicines are extracted from a traditional Chinese medicine knowledge base, and a quantitative expression system is constructed. And constructing a three-dimensional similarity vector matrix of the traditional Chinese medicine and the symptoms by calculating the similarity of each first-level feature, and fusing the three-dimensional similarity vector matrix with the traditional Chinese medicine-symptom incidence matrix to form a GNN input graph structure. In the GNN, feature interaction between traditional Chinese medicine and symptom nodes is realized by using a message passing mechanism, node embedding is updated through three times of iteration, and a correlation score matrix is output in combination with a double-line decoder. And aiming at the problem of data imbalance, a weighted cross entropy loss function optimization model is adopted, a correlation threshold is automatically generated, and accurate prediction is realized. The method effectively excavates deep correlation between traditional Chinese medicine and symptoms, and provides a data-driven prediction tool for modern research of traditional Chinese medicine.

The invention provides a cable laying management system for an offshore wind plant, relates to the technical field of cable laying management, and realizes refinement and dynamic risk assessment by accurately dividing sections, deeply mining historical operation data and carrying out correlation analysis. According to the method, the fault probability of each section can be accurately estimated, a global risk map is generated to strengthen risk early warning, key nodes can be screened according to risk levels and association characteristics, monitoring resources are flexibly deployed, a scientific priority list is formed to optimize operation and maintenance resource configuration, and the response speed is increased; meanwhile, a full-chain safety guarantee system is constructed by visually identifying a risk area and setting an alarm threshold value, intelligent support is provided for operation and maintenance decisions by means of a data-driven prediction model and continuously optimized analysis logic, and finally the collaborative targets of controllable safety risk, efficient resource utilization, reduction of operation and maintenance cost and stable operation of the system are achieved.

The invention is based on a method for data-driven predictive control of a heat pump system (10), wherein at least one future input trajectory (28) of the heat pump system (10) and in particular at least one future output trajectory (38) of the heat pump system (10) is determined at least as a function of system data (30) of the heat pump system (10) measured at an earlier point in time, using a defined target function, which is in particular minimized, wherein the system data (30) comprise at least input measurement data (12) and output measurement data (14) of the heat pump system (10), wherein for the data-driven predictive control of the heat pump system (10), a control equation filled with the system data (30) is solved by means of a computing unit (22), wherein the computing unit (22, 22') uses the control equation to calculate the trajectories (28,38) of the heat pump system (10) are determined from a matrix-vector multiplication of at least one measurement data matrix with a decision variable vector, and wherein the measurement data matrix is ​​formed from at least two Hankel matrices written one above the other, each comprising only one measurement data type of the system data (30). , It is proposed that, in order to take into account a lower operating limit of the heat pump system (10), at least several entries of the future input trajectory (28) in the control equation are each assigned a binary variable, in particular by multiplication, wherein in particular the entries of the future input trajectory (28) each correspond to predicted time steps of a predicted input for the heat pump system (10).

The invention discloses a PINN-based mechanical arm error compensation method, which comprises the following steps of: acquiring tail end physical parameters of a mechanical arm, obtaining an initial DH parameter matrix of the mechanical arm, and constructing a PINN-based mechanical arm error compensation network for outputting a dynamic DH parameter compensation item under physical constraint and a predicted attitude angle driven by data, constructing a physical parameter dynamic correction layer based on the initial DH parameter matrix and the dynamic DH parameter compensation item to perform superposition correction so as to obtain a physical derived attitude angle, calculating a total loss function, calculating gradients of all learnable parameters in the physical information neural network based on the total loss function, and updating all learning weights and the dynamic DH parameter compensation item to obtain a physical derived attitude angle; and the learning rate is adjusted until training is completed, reasoning is conducted on the to-be-detected mechanical arm after training is completed, a high-reliability prediction attitude angle constrained by the physical law is output in real time, and meanwhile the initial kinematic model is updated and used for online identification of geometrical parameters of the mechanical arm and accurate estimation of the tail end attitude.

The invention provides a stainless steel corrosion rate prediction method based on virtual sample generation and transfer learning, and relates to the technical field of data-driven prediction models, and the method comprises the steps: S1, obtaining target stainless steel material corrosion data and low alloy steel corrosion data, and carrying out the standardization processing; s2, determining the direction and range of virtual sample data generation based on an SMOTE virtual sample generation method, and generating a stainless steel material data synthesis sample; s3, constructing a cross-domain transfer learning model of a stainless steel material, training an artificial neural network model by using low alloy steel corrosion data, and transferring to a target domain model; and S4, constructing a corrosion performance prediction optimization model of the target stainless steel material, and performing optimization output to obtain a corrosion prediction result of the target stainless steel material. Cross-domain corrosion rule migration is realized through a virtual sample generation technology and migration learning, and an efficient and reliable solution is provided for stainless steel corrosion rate evaluation by increasing the basic data volume.

The present disclosure relates to the technical field of electric energy dispatching, and provides a resource partition balancing aggregation, external characteristic representation and operation regulation method and platform. The aggregation method considers resource spatial distribution distance, aggregation cost, partition plan power deviation, and minimization of partition loss caused by factors such as partition balance between local consumption and cross-zone transaction power, determines an aggregation node and a partition corresponding to the aggregation node and a corresponding virtual machine group. The external characteristic representation method predicts the future output condition of flexible resources based on a data-driven prediction method to construct a resource feasible region and its aggregation feasible region considering the foresight. The operation regulation method considers resource output and climbing power to obtain an operation regulation decision that minimizes the maximum uncertainty loss through a two-stage combination of the maximum uncertainty loss model and the minimum maximum expected loss model. The partition aggregation optimization, external characteristic depiction accuracy, and regulation decision accuracy are realized respectively.

The invention discloses a multi-target dynamic optimization method for a coal-fired power plant SCR system, and aims to solve the problems of incomplete denitration and ammonia escape caused by variable-load or low-load operation of a coal-fired unit under deep peak regulation. According to the method, a prediction-decision closed-loop reinforcement learning framework based on data driving is constructed, and the method comprises the following steps: firstly, extracting a time sequence characteristic and long-distance dependency relationship of operation data of an SCR system through an LAT-2 model, and realizing high-precision prediction of NOx and ammonia escape concentration at an outlet; and then an intelligent decision-making agent is constructed based on a BiEcoDDPG model, multi-target rewards are dynamically integrated through Kalman fusion, noise interference is replayed and suppressed in combination with priority experience, and ammonia injection parameters are dynamically optimized. When the working condition of a unit changes frequently, NOx emission and ammonia escape concentration can be effectively reduced, the environmental protection property, economical efficiency and operation safety of an SCR system are improved, and support is provided for low emission and efficient operation of pollutants of a coal-fired power plant.

The invention discloses an electronic display glass kiln auxiliary control method and system based on artificial intelligence, relates to the technical field of kiln pressure predictive control, and solves the problems that in glass kiln control, a time period suitable for kiln pressure control is difficult to set according to kiln combustion characteristics and environmental factors, and the kiln pressure control is difficult to set. And the prediction of the relevance between the flue gas emission and the atmospheric pressure is neglected, so that the precise control of the kiln pressure is difficult to realize. According to the invention, time periods are divided based on environmental data, smoke data of a next time period are obtained through a smoke prediction module, and atmospheric pressure of the next time period is obtained through an atmospheric pressure prediction model; the smoke outlet area is determined based on the smoke data and the atmospheric pressure of the next time period, and a rotary gate plate in the smoke outlet is adjusted based on the smoke outlet area; according to the method, through a data-driven prediction model and a dynamic regulation and control mechanism, glass kiln pressure discharge control is upgraded from experience-driven control to intelligent prediction control, and the problem of response lag of kiln pressure control is solved.

The embodiment of the invention discloses a multi-time-scale prediction method and system for cyanobacterial bloom, and the method comprises the steps: obtaining a cyanobacterial bloom spatial-temporal distribution prediction result through a pre-constructed hydrodynamic water quality bloom model, and obtaining a cyanobacterial bloom spatial-temporal distribution prediction result through a pre-constructed prediction model based on data driving based on a current chlorophyll a concentration sequence. Obtaining a chlorophyll a concentration prediction value sequence, and finally generating cyanobacterial bloom prediction information of the first time scale. And based on weather forecast data, obtaining a chlorophyll a concentration predicted value of a second time scale through a hydrodynamic water quality and water bloom model. Based on the historical environment monitoring data, through a pre-constructed multivariate statistical regression model, obtaining a cyanobacterial bloom intensity index; based on a historical chlorophyll a concentration monitoring sequence, a cyanobacterial bloom prediction result of a third time scale is finally obtained by analyzing a chlorophyll a concentration periodic change rule; the predicted periods of the first time scale, the second time scale and the third time scale are increased in sequence.

The present invention discloses a campus security management method and system, the method comprising: obtaining a point cloud map of a target campus and a point cloud map of other campuses in the global jurisdiction of the target campus; determining multiple additional patrol areas based on historical security incidents occurring in the other campuses; calculating a set of point cloud map feature descriptors for the target campus and a set of point cloud map feature descriptors for the other campuses, and determining a transformation matrix of the two sets of point cloud map feature descriptors; aligning multiple similar areas in the target campus based on the multiple additional patrol areas and the transformation matrix; allocating security personnel in corresponding proportions based on the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas. The present invention achieves more efficient and intelligent campus security management through data-driven prediction, precise resource allocation, real-time behavior recognition, and a flexible dynamic adjustment mechanism.

The invention discloses a real-time monitoring system and method for photovoltaic power generation equipment, and the method comprises the steps: obtaining all attitude pressure distribution diagrams of a rotating center shaft of a tracking support in advance through employing an attitude sensor, and then calculating the direct stress condition of the rotating center shaft of the tracking support based on a plurality of real-time radial pressure values in the circumferential direction of the rotating center shaft obtained by a pressure sensor array, according to the method, a photovoltaic panel assembly is subjected to protection adjustment according to a calculation result, a preset pressure distribution diagram is combined, a dynamic load is monitored in real time, an early signal of instability of a rotating center shaft can be recognized, catastrophic collapse is prevented, and traditional passive, overall and empirical maintenance is converted into active, accurate and data-driven predictive management through real-time discovery and early warning of faults; the safety and the power generation efficiency of the photovoltaic power station are improved, the maintenance personnel terminal remotely masters the health states of all tracking supports in the whole field through the terminal for predictive maintenance, and the operation and maintenance cost can be reduced.

The invention relates to the technical field of intelligent traffic scheduling, in particular to an intelligent monorail vehicle-oriented passenger scheduling strategy optimization method and system, and the method comprises the steps: collecting multi-dimensional scheduling data through monorail vehicle-mounted sensing equipment, a platform monitoring unit and a passenger terminal, and building a dynamic database; based on a deep learning model, carrying out prediction analysis on the passenger getting-off demand, the station congestion state and the line operation parameters; a multi-objective optimization function is constructed in combination with a prediction result, and an optimal passenger getting-off scheduling scheme is solved by taking maximization of passenger getting-off efficiency, minimization of station residence time and optimization of line operation collaboration as objectives; a dispatching instruction is issued through a train-station-center three-level communication network, getting-off door control, platform guidance and train departure interval adjustment are executed in real time, and the dispatching effect is dynamically monitored for closed-loop optimization. According to the invention, through data-driven prediction analysis and multi-objective optimization, the intelligence and refinement of get-off scheduling and the operation efficiency of monorail traffic are improved.

The invention provides an intersection left-turn traffic organization scheme recommendation method, and relates to the technical field of traffic organizations, and the recommendation method specifically comprises the steps: data loading and preprocessing, construction of a prediction model, recommendation of an optimization logic scheme, intelligent recommendation of a suitable intersection left-turn traffic organization optimization scheme, construction of an interactive Web interface, and realization of interaction with a user. The predicted delay time and the recommended optimization scheme are clearly presented to the user; through integration of data processing, a machine learning model and a user interface, prediction of traffic delay time and intelligent recommendation of an intersection left-turn traffic organization scheme are realized, and the underlying logic covers data-driven prediction and rule-Based scheme recommendation, so that comprehensive decision support is provided for traffic management and planning, and the traffic delay time and the intersection left-turn traffic organization scheme are recommended intelligently. A user can input data through a visual Web interface to obtain an accurate prediction result and a reasonable optimization suggestion, so that the operation efficiency and safety of a traffic system are effectively improved.

The invention discloses a life prediction method for an automatic tool change system of a CNC machine tool based on a physical information neural network, which belongs to the technical field of health monitoring and fault prediction of CNC machine tools. The method first uses physical degradation modeling to establish a differential equation for the degradation process of the automatic tool change system of a CNC machine tool; constructs a neural network model 1, which predicts the remaining life by inputting vibration signals and time information; constructs a neural network model 2, which further describes the trend of the remaining life change in combination with the response of the physical equation, and performs a loss function with the prediction result of the neural network model 1; finally, the model is trained by designing a comprehensive loss function, so that the neural network can simultaneously learn the physical degradation law of the system and the data-driven prediction ability. In summary, the present invention has high prediction accuracy and practicality, is suitable for the remaining life prediction of the automatic tool change system of a CNC machine tool, is conducive to reducing maintenance costs, and ensures the safety and stability of the production process.

The present invention relates to an ESP decision optimization system for epidemiological modeling. ESP based modeling approach is used to predict how non-pharmaceutical interventions (NPIs) affect a given pandemic, and then automatically discover effective NPI strategies as control measures. The ESP decision optimization system comprises of a data-driven predictor, a supervised machine learning model, trained with historical data on how given actions in given contexts led to specific outcomes. The Predictor is then used as a surrogate in order to evolve prescriptor, i.e. neural networks that implement decision policies (i.e. NPIs) resulting in best possible outcomes. Using the data-driven LSTM model as the Predictor, a Prescriptor is evolved in a multi-objective setting to minimize the pandemic impact.

The invention discloses an intelligent regulation and control method for a pressure reducing valve, which comprises the following steps: acquiring sensor data in the operation process of the pressure reducing valve, constructing a digital twin basic physical model of the pressure reducing valve, and calculating by using the digital twin basic physical model to obtain a basic data calculation result of the current state of the pressure reducing valve; acquiring real-time acquisition data in a dynamic operation process based on the basic data calculation result, and preprocessing the real-time acquisition data to obtain processed standardized operation feature data; optimizing the digital twin basic physical model by using the standardized operation characteristic data, and constructing a predictive regulation and control model fusing physical modeling and data driving; and performing operation state prediction based on the prediction regulation and control model to obtain a voltage regulation prediction result in a future time period. Intelligent prediction of the voltage regulation state in the future is achieved, then the regulation instruction is given in advance, the control lag or over-regulation phenomenon is effectively restrained, and the response speed and stability of the whole system are improved.

The invention relates to a method (100), a computer program product, a control system (10) and a battery charging system (90) for determining a charging current limit for a charging process of a rechargeable battery device (1000). A measured variable (MP) is detected on the battery device (1000). Furthermore, a battery parameter (BP) is determined on the basis of the acquired measurement parameter (MP) by means of a process physics-based battery model. Furthermore, a predicted parameter (VP) for the occurrence of a metal deposition at the electrodes (1001, 1002) of the battery device (1000) is determined on the basis of an in particular data-driven predictive model, at least based on the battery parameter (BP) as a predictive model input parameter, at least a predicted occurrence time of the metal deposition is determined as the predicted parameter (VP). Control parameters (KP) for controlling the charging process are determined by means of a likewise, particularly data-driven control model, a charging current limit value being determined as at least one control parameter (KP) on the basis of the measured parameter (MP), the battery parameter (BP) and the predicted parameter (VP), and the determined charging current limit value being output for presetting a charging current for the battery charging system (90).

The invention is based on a method for a, in particular data-driven, predictive control of a heat pump system (10), wherein at least one future input trajectory (28) of the heat pump system (10) is determined at least as a function of system data (30) of the heat pump system (10) measured at an earlier point in time, using a defined target function which is minimized, wherein the system data (30) comprise at least input measurement data (12) and output measurement data (14) of the heat pump system (10). It is proposed that the, in particular data-driven, predictive control of the heat pump system (10) is limited to at least one first operating load range (16) of at least one heat pump (36) of the heat pump system (10) and to at least one second operating load range (18) of the heat pump (36) of the heat pump system (10), wherein the first operating load range (16) and the second operating load range (18) are spaced apart from one another and do not overlap.

This invention relates to the field of food security technology, specifically to a digital twin intelligent management system for the entire lifecycle of irrigation districts, oriented towards food security. The system includes: a data creation terminal, a scheme generation terminal, and a management execution terminal. The data creation terminal is used for data collection and preprocessing of the collected data to provide data support for subsequent modules. The scheme generation terminal builds a digital twin model based on the collected data and performs scheme deduction within the digital twin model. The management execution terminal selects the optimal scheme based on the scheme generated by the scheme generation terminal and performs fine-tuning during execution to achieve optimal results, while also storing system data. This system features efficient data interaction and linkage between modules, replacing traditional experience-based reliance with data-driven predictive models and intelligent optimization methods, and possesses capabilities for precise disaster response, quantitative risk-return assessment, and secure data reuse.

The invention relates to the technical field of model simulation, in particular to a flexible freight bag automatic equipment virtual debugging system and method based on a 3D model technology. The method comprises the following steps: constructing a three-dimensional digital twinborn model of the container bag automatic equipment, and collecting temperature distribution data, feeding tension data and environment humidity data in a running process of the equipment in real time; when it is detected that the change rate of the temperature distribution data in spatial distribution exceeds a preset threshold value, the material extension deviation value of the container bag is calculated; establishing a position deviation prediction model based on the hysteresis characteristic by calculating a cross correlation coefficient of feeding tension data and a cutting position deviation signal under different time delays; and carrying out vector superposition on the extension deviation value and a cutting position deviation value predicted by the position deviation prediction model to form a position compensation parameter. Through a data-driven prediction and compensation mechanism, the cutting precision and the material utilization rate are remarkably improved.

The invention relates to the technical field of grain safety, in particular to a grain safety-oriented digital twinborn irrigation area full-life-cycle intelligent management system, which comprises a data establishment end, a scheme generation end and a management execution end, the data establishing end is used for collecting data and preprocessing the collected data, and providing data support for subsequent modules; the scheme generation end establishes a digital twinborn model based on the collected data, and deduces the scheme in the digital twinborn model; the management execution end selects an optimal scheme for execution based on the scheme of the scheme generation end, performs fine adjustment in the execution process to achieve an optimal effect, and stores system data; according to the system, efficient data interaction linkage among modules is achieved, traditional experience dependence is replaced with a data-driven prediction model and an intelligent optimization method, and the system has the precise disaster response capacity, the risk income quantitative evaluation capacity and the data safety reuse capacity.

This invention relates to a method for predicting the performance degradation of airborne pressure sensors based on a physical information neural network, comprising the following steps: S1: Obtaining the operating environment temperature, operating time, and corresponding basic error data of the airborne pressure sensor, and constructing an airborne pressure sensor performance degradation index as a training set label; S2: Constructing a physical information neural network, performing training and parameter optimization, as follows: S21: The input is the ambient temperature T and operating time t of the airborne pressure sensor, which undergoes multi-layer nonlinear transformation, and the output is the airborne pressure sensor performance degradation index; S22: Constructing a joint loss function, including a data-driven prediction error term and a physical model constraint term; S23: Training the network using a gradient descent algorithm, minimizing the joint loss function, and obtaining an optimized prediction model; S3: Using the trained physical information neural network model to predict the performance degradation of the airborne pressure sensor.

The invention discloses an intelligent optimization method for an annealing temperature curve of a high-silica glass fiber, and relates to the technical field of high-silica glass fiber processing, which thoroughly gets rid of the dependence on artificial experience, can calculate a theoretical optimal annealing curve under a specific working condition by constructing a data-driven prediction model and utilizing an intelligent algorithm for optimization, and improves the processing accuracy of the high-silica glass fiber. Accurate temperature control is achieved, changes of working conditions such as the wire drawing speed and the fiber diameter can be sensed in real time, an annealing temperature curve is dynamically adjusted when the working conditions fluctuate, the uniformity and stability of product quality under different working conditions are ensured, and meanwhile through collaborative optimization of multiple targets such as residual stress and mechanical properties, the product quality is improved. According to the method, the residual stress of the high-silica glass fiber can be remarkably reduced, the strength and flexibility of the fiber can be improved, so that the yield is improved, the energy consumption is reduced, the method has a model self-adaptive updating capability, and through a production-detection-feedback-learning closed loop, the system can adapt to long-term working condition changes, and accumulation and iterative optimization of process knowledge are realized.

The invention relates to a method for data-driven predictive control of a heat pump system, in which at least one future input trajectory and in particular at least one future output trajectory of the heat pump system are ascertained at least on the basis of system data of the heat pump system measured at an earlier time using a defined objective function, the system data comprises at least input measurement data and output measurement data of the heat pump system, a control equation filled with the system data is solved by means of the computing unit, and a trajectory of the heat pump system is determined by means of the control equation according to a matrix-vector multiplication of at least one measurement data matrix and a decision variable vector, the measurement data matrix is composed of at least two Hankel matrixes which are stacked up and down and respectively comprise one measurement data type of system data. In order to take into account the operating lower limit of the heat pump system, binary variables are assigned to at least a plurality of elements of a future input trajectory in the control equation, respectively.

The invention relates to a method for predictive control of a heat pump system, in particular a data-driven predictive control method, in which, using a minimized defined objective function, at least one future input trajectory of the heat pump system is ascertained at least on the basis of system data of the heat pump system measured at an earlier time, the system data at least comprises input measurement data and output measurement data of the heat pump system. According to the invention, a predictive regulation of the heat pump system, in particular a data-driven predictive regulation, is limited to at least one first operating load range of at least one heat pump of the heat pump system and to at least one second operating load range of the heat pump of the heat pump system, the first operating load range and the second operating load range do not overlap each other and are spaced apart from each other.

The invention provides a virtual reconnection high-speed train dynamic interval prediction method and system based on collaborative trajectory prediction, and belongs to the technical field of train operation control. An operation control framework of a virtual reconnection train group is established, and a hierarchical collaborative prediction mechanism of a leading train and a following train is defined; based on a train longitudinal dynamic model, a position uncertainty safety boundary is constructed by considering factors such as positioning errors and communication delay; the LSTM neural network and physical constraints are fused, physical correction is carried out on the trajectory through acceleration amplitude limiting and kinematics recursion, then a prediction result driven by data and a prediction result driven by a physical model are fused, and high-precision prediction of the running trajectory of the front vehicle is achieved; and dynamically calculating the safety interval and the target interval between the trains based on the prediction result. According to the method, the problems of insufficient dynamism, prediction distortion and poor multi-train adaptability in the prior art are solved, the tracking interval is effectively reduced on the premise of guaranteeing safety, and the trafficability and the operation efficiency of a line are improved.

The present application relates to the technical field of model simulation, and more particularly to a kind of automatic equipment virtual debugging system and method of bag based on 3D model technology.The method comprises the following steps: constructing the three-dimensional digital twin model of bag automatic equipment, real-time acquisition temperature distribution data, feeding tension data and environmental humidity data in the process of equipment operation;When detecting that the change rate of temperature distribution data on spatial distribution exceeds the preset threshold, the material extension deviation value of bag is calculated;By calculating the cross-correlation coefficient of feeding tension data and cutting position deviation signal under different time delay, a position deviation prediction model based on the lag characteristic is established;The extension deviation value and the cutting position deviation value predicted by the position deviation prediction model are vector superimposed to form position compensation parameters.The present application significantly improves cutting accuracy and material utilization rate through data-driven prediction and compensation mechanism.