151 results about "Boundary values" patented technology

The invention discloses a power grid load prediction method and system based on a large model, and relates to the technical field of power grid load prediction. Comprising the following steps: S1, collecting multi-source load comprehensive data, and carrying out edge processing and data preprocessing; s2, monitoring a sudden change point in real time, constructing a behavior tag sequence, and identifying a high-frequency disturbance point; s3, constructing a prediction input vector of the multi-source load comprehensive data, performing load data prediction, and calculating a physical constraint regularization value; s4, performing dynamic credible interval evaluation, performing real-time judgment on a prediction result according to a credible boundary value interval, and feeding back a regulation and control instruction; and S5, performing error analysis and retraining triggering, comprehensively evaluating prediction accuracy and output stability, and performing model optimization, version management and feedback learning. The problem that the prediction model is easy to vibrate due to high load change speed in a high-density load scene is solved.

The invention relates to a test case generation method and system based on an industrial agent. The method comprises the steps that an industrial data set is acquired, and a system dependency model is constructed; generating a path coverage test sequence through the first agent; generating a boundary value test data set through the second agent; generating abnormal test scene information through a third agent; and generating a test case set based on the path coverage test sequence, the boundary value test data set and the abnormal test scene information. In conclusion, by constructing the system dependency model and utilizing the multi-agent collaborative analysis process logic path, boundary condition and dependency relationship, the multi-surface coverage of the industrial control system test scene is realized, the automation of the test case generation is realized, the effects of improving the generation efficiency and enhancing the comprehensiveness of the test coverage are achieved, and the method is suitable for industrial control system test. Especially for the coverage of boundary conditions, abnormal scenes and concurrent paths, the manual dependence is reduced, and the reliability and consistency of the test are improved.

The invention relates to the technical field of automatic testing, and discloses an automatic testing scheme generation method and device and a medium, and the method comprises the steps: matching a demand action in a test demand with a code entry name corresponding to a code segment, and determining a code risk level of a current demand code block; analyzing the code change frequency and the code dependency degree of the current demand code block according to historical test records in the test domain knowledge base, and determining the test dynamic priority of the current demand code block; constructing a control flow diagram and a data flow diagram of the current demand code block, and detecting risk nodes in the control flow diagram and the data flow diagram; generating a test scene of the current demand code block according to the risk node, and generating a boundary value test rule according to a key constraint condition in the data flow diagram; and querying an environment simulation rule of the current demand code block, and packaging the test scene, the boundary value test rule and the environment simulation rule into an automatic test scheme. According to the invention, the code coverage when the test scheme is generated can be improved.

The invention belongs to the technical field of bubble dynamics and multiphase flow and artificial intelligence, and particularly relates to a high-pressure bubble pulsation load prediction and initial parameter inversion method and system based on artificial intelligence. The underwater high-pressure bubble pulsation process is studied, and interface evolution data in the high-pressure bubble pulsation process are obtained; establishing a compressible VOF-PINN multiphase flow model, and predicting unknown parameters and pulsating load characteristics of bubbles in combination with the initial boundary value; dividing a prediction problem into a positive problem and an inverse problem according to known data; establishing a model which can be used for predicting forward and reverse models; for a positive problem, training and predicting the VOF-PINN model by using a gradient descent optimization algorithm; and for the inverse problem, bubble initial parameter identification is realized. The invention aims to solve the problems that recalculation is needed for changing calculation parameters in numerical simulation, grid division is complex and tedious, high-fidelity data cannot be directly included, and initial parameters in experimental research are uncertain.

The invention discloses a carbon quantity prediction method and device for coal-fired unit carbon emission, and a medium, and relates to the technical field of energy data intelligent analysis, and the method comprises the steps: calculating a carbon emission intensity prediction value and a confidence interval boundary value based on a real-time coal quality fusion operation parameter set and a device health index, and generating a dynamic carbon emission prediction package; comparing the dynamic carbon emission prediction packet with CEMS real-time monitoring data, calculating a prediction error rate, extracting a multi-dimensional error feature according to the prediction error rate, and generating a multi-dimensional error feature vector; and based on the multi-dimensional error feature vector, dynamically adjusting an equipment health index correlation factor and a coal quality confidence weight parameter, generating a dynamic correction instruction set, and generating a carbon emission prediction report in combination with a dynamic carbon emission prediction packet. According to the method, dynamic noise reduction, enhancement and feature quantization of the coal flow multispectral image are realized, the high-fidelity coal quality feature vector is directly generated, the problem of coal quality data lag is solved, and the coal quality sudden change response capability is improved.

The invention belongs to the technical field of vehicle software testing, and particularly relates to a test case generation method and system based on big language model and rule collaboration, and the method comprises the steps: analyzing a demand document, and mapping the demand document to a fault ontology model to generate a structured test demand; generating a plurality of groups of fault verification conditions based on equivalence class division and a boundary value analysis method by utilizing a large language model; a multi-dimensional mixed retrieval strategy is adopted to retrieve a reference case from a historical case library; in combination with the verification condition, the reference case and the standardized information base, preposed environment settings, serialized operation instructions and expected responses of the test case are generated in stages; and finally, the case quality is ensured through cooperative verification of a large language model and a rule engine. The problems that a traditional method depends on manpower, the coverage rate is low, errors are prone to occurring, and historical knowledge is difficult to reuse are effectively solved, and the automation degree, accuracy and integrity of BMS test case generation are remarkably improved.

The invention provides an intelligent door and window control method and system, and the method comprises the steps: S1, obtaining multi-source environment data; s2, inputting the multi-source environment data into a fuzzification module, and converting the multi-source environment data into a fuzzy variable through a preset ambiguity function; s3, dynamically generating an environment parameter weight vector according to the real-time scene parameters; s4, inputting the fuzzy variable and the environmental parameter weight vector into a fuzzy inference engine, executing logical operation of a fuzzy rule base, and outputting comprehensive evaluation values of window opening suitability, window closing urgency and shading demand; and S5, generating a final control instruction through a defuzzification strategy, and executing the final control instruction. According to the method, the problem of frequent invalid operation caused by fluctuation of the environmental parameters near the boundary value is solved, the environmental parameter weight vector is dynamically generated based on the time parameters, the user preset mode and the meteorological data confidence factor, adaptation to seasons, time periods, user states and other scenes is achieved, and decision logic can be flexibly adjusted according to actual requirements; and a contradictory decision under a traditional fixed rule is avoided.

The invention provides a residual terrain correction estimation method based on PINNs and a residual terrain model, and relates to the technical field of geodetic survey, a data set is randomly divided into a training data set and a test data set, a residual terrain gravity anomaly of each data set is obtained through RTM as an output, the network architecture of the PINNs is a full-connection neural network, and the network architecture of the PINNs is a full-connection neural network. Associating the output quantity and the gravitational potential quantity of the RTM model according to a basic equation of physics geodetics to serve as a boundary value condition; and taking the weighted sum of the physical loss function and the data loss function as a total loss function and an initial full-connection neural network weight parameter of the full-connection neural network, training the constructed full-connection neural network through a training data set, and achieving the requirements of small calculation amount, low required data complexity and high precision through the method.

The invention provides a self-adaptive regulation and control method for a hydrogen production system based on real-time parameter feedback, and relates to the technical field of process control, the method comprises the following steps: collecting an input instruction signal and a controlled state variable signal of the hydrogen production system, and comparing a fluctuation energy index with a preset identification dead zone threshold; if the fluctuation energy index is lower than the identification dead zone threshold value, the current controller parameter is kept unchanged; if the fluctuation energy index is higher than the identification dead zone threshold value, activating an online parameter identification step; calculating a dynamic confidence interval of process model parameters; judging whether the process model parameters estimated in real time fall into the dynamic confidence interval or not; if the process model parameters fall into the dynamic confidence interval, converting the process model parameters estimated in real time into control parameters of a PID (Proportion Integration Differentiation) controller, and updating the control parameters into a control loop of the hydrogen production system; and if the process model parameter exceeds the dynamic confidence interval, resetting an internal state vector of the recursive algorithm in the online parameter identification step by using a boundary value.

Some embodiments of a method may include: determining a first number by running a learning-based process, wherein the first number is associated with a current sample; obtaining a quantization parameter; determining a quantized value based on at least the quantization parameter for the first number; obtaining a sample set; responsive to determining that the current sample is not in the sample set, outputting the quantized value; and responsive to determining that the current sample is in the sample set, performing several steps comprising: determining a boundary value based on at least the quantization parameter and the first number; determining a second number based on the boundary value; and outputting the second number.

The invention provides a method and a device for predicting a parameter adaptability index of a new energy network inverter. The method comprises the following steps: acquiring actual measurement values of inverter parameters at n fixed time intervals, and determining parameter boundary values (namely the maximum value and the minimum value of the actual measurement values in each time interval); calculating a stability sensitivity index based on the measured value and the parameter boundary value, and performing square root operation on the stability sensitivity index to obtain a historical data weight; performing normalization processing on each inverter parameter according to the actually measured value and the parameter boundary value of the inverter parameter to obtain a normalized parameter matrix; and multiplying the normalized parameter matrix by a weight vector formed by historical data weights to obtain a parameter prediction value of the inverter at the next moment. According to the method, the inverter parameters can be accurately optimized by predicting the adaptability index of the new energy grid-forming type inverter parameters, the safe and stable operation level of a new energy base can be improved, and challenges caused by strong fluctuation and uncertainty of new energy power generation can be effectively handled.

The invention discloses a hardware-in-the-loop automatic test method and system, and the method comprises the steps: receiving a technical specification document and a historical failure case library of a tested device, analyzing a technical specification through a natural language processing model to extract key test parameters, carrying out the correlation analysis of the key test parameters and a fault mode in the historical failure case library, and obtaining a fault mode of the tested device; generating a structured test demand table, wherein the structured test demand table comprises test target priorities, constraint conditions and boundary value definitions; based on the structured test demand table and equipment working condition data acquired in real time, generating a plurality of test cases covering boundary conditions and extreme working conditions by using a genetic algorithm; the test cases covering the boundary conditions and the extreme working conditions are screened out from the multiple test cases to obtain a test case sequence, and each case in the test case sequence comprises a fault injection parameter, an expected response threshold value and an execution priority label. According to the method and system, the test coverage rate and efficiency are improved, and manual intervention is reduced.

Some embodiments of a method may include: determining a first number by running a learning-based process, wherein the first number is associated with a current sample; obtaining a quantization parameter; determining a quantized value based on at least the quantization parameter for the first number; obtaining a sample set; responsive to determining that the current sample is not in the sample set, outputting the quantized value; and responsive to determining that the current sample is in the sample set, performing several steps comprising: determining a boundary value based on at least the quantization parameter and the first number; determining a second number based on the boundary value; and outputting the second number.

The invention is suitable for the technical field of electric power transaction, and provides a multi-target transaction strategy and system for water-wind-light power generation based on an improved hybrid algorithm, and the strategy comprises the following steps: collecting system parameters of a hydropower station, a photovoltaic power station, a wind power station and a pumped storage power station, and determining boundary values of constraint conditions; constructing a multi-objective optimization scheduling model, wherein the multi-objective optimization scheduling model comprises an objective function and a constraint condition; an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm are adopted, and global optimization is carried out on the multi-objective optimization scheduling model through a double-population strategy; and displaying an optimization result at a client through a graphical interface, wherein the optimization result comprises the power generation plan of each power station, the change of the reservoir capacity and the economic benefit of the system. By combining the genetic algorithm of fast non-dominated sorting and the time-varying multi-objective particle swarm optimization algorithm, global optimization is carried out by adopting a double-population strategy, the advantages of the two algorithms are effectively combined, and the search efficiency is improved by dynamically adjusting the strategy and parameters.

The invention relates to the technical field of seismic engineering, and provides a method and system for solving a seismic wave propagation equation based on a physical information neural network, and the method comprises the steps: determining a space domain, a time domain, an initial condition and a boundary condition of a one-dimensional seismic wave equation; initial boundary value coordinate points are randomly extracted to serve as a training data set constraint network, and Latin hypercube sampling is utilized to generate space-time domain configuration points to meet partial differential equation constraint; a physical information neural network model is established, after space-time coordinates are input, equation residual errors are calculated through automatic differential, and initial boundary value loss and physical residual errors are combined to construct a composite loss function for training; and proposing a self-adaptive region sampling strategy based on residual errors, resampling a high residual error region according to an average residual error value of the configuration points in a training period, and iteratively optimizing network parameters after a newly added point and an initial configuration point are fused. According to the method, by dynamically enhancing the sampling density of a high-error region, the L2 relative error of a prediction solution is reduced by one order of magnitude, the network is effectively prevented from falling into local optimum, the convergence efficiency is remarkably improved, grid discretization or prior data support is not needed, and a high-precision meshless solution scheme is provided for a one-dimensional seismic wave equation.

The invention discloses a test case generation method, system and device and a storage medium. The method comprises the steps of obtaining a target test scene; based on the target test scene, acquiring a data generation rule corresponding to the test scene from a preset rule base; generating basic test data according with normal business logic according to the business rule; modifying at least one field in the basic test data according to the exception rule to generate exception test data for simulating abnormal input; according to the boundary rule, boundary value analysis is carried out on parameters in the basic test data, and test data used for verifying a parameter limit range is generated; and combining the normal basic test data, the abnormal test data and the boundary test data to generate a test case set.

The invention discloses a logic drive test case generation method based on a large language model, and belongs to the technical field of software testing. The method comprises the following steps: extracting key information from a code to be tested; based on the key information, a logic driving thinking chain prompt template is adopted to guide a large language model to generate a test case; running the test case and calculating a coverage rate; and judging whether the test case needs to be repaired or not based on the test case operation result and the coverage rate, if yes, repairing the test case by adopting a layered repairing strategy, and if not, outputting the test case. According to the method, a big language model is systematically guided to generate the test case through a logic driving thinking chain, fusion path coverage, condition combination coverage, boundary value analysis and an equivalence class division strategy, and the problems of path missing and incomplete condition combination when a traditional LLM generates the test case are thoroughly solved; and the test case is repaired by adopting a layered repair strategy, so that the manual intervention demand is obviously reduced.

The application discloses a turbine disc die forging process reasoning method and system, and the method comprises the following steps: (1) selecting key points of a turbine disc which need to be controlled in organization; (2) extracting deformation information of the key points through finite element simulation of the whole forging process of the turbine disc; (3) establishing a target optimization function, and respectively setting requirements for the average grain size and the recrystallization fraction of the key points, and setting corresponding weight values for the final organization targets of the key points; (4) setting boundary values and a penalty function of process parameters according to the actual situation of forging, and when the inferred process exceeds the boundary, the penalty function starts to execute; (5) embedding the target optimization function and the penalty function into a multi-objective optimization algorithm, and simultaneously inferring multiple forging process parameters. The method can achieve the effect of optimizing the grain organization of multiple regions of a forging, and effectively protects a die, thereby providing a theoretical basis and technical support for realizing high-quality forging.

The invention discloses a level set field reconstruction method and system based on a three-dimensional finite element grid and a medium. Relates to the technical field of geometric reconstruction. Positioning a space Cartesian grid area intersected with the boundary surface grid based on a separation axis theory; calculating a geometric space point-surface position relation, calculating a directed projection distance from a space Cartesian grid center to a two-dimensional boundary surface grid, and correcting the positive and negative characteristics of a Cartesian grid level set value based on a three-dimensional eight-direction rapid scanning method, so that the grid level set value is consistent with a region boundary value; according to the method, the geometric reconstruction problem of the deformable body which is complex in appearance and free of explicit analytic expression can be efficiently and accurately solved, a coupling approach between a finite element grid and a Cartesian grid is established under a non-conformal grid system, and the flexibility and universality of explicit calculation of a level set function under the Cartesian grid are improved.

The method for calculating the fastest adjustment time of the primary frequency modulation of the hydroelectric generating set comprises the following steps: step 1, establishing a primary frequency modulation system structure model; 2, constructing a primary frequency modulation system structure model transfer function; 3, establishing a corresponding differential equation according to the model transfer function; 4, converting the differential equation into a standard rhodan form; 5, listing an equation and a boundary value condition of the minimum adjustment time of the primary frequency modulation according to an optimal control principle, and solving a corresponding control law; step 6, solving switching point time and final adjustment time according to the trajectory equation; step 7: algorithm and controller code; and 8, according to the step 7, constructing a corresponding control flow of the fastest primary frequency modulation regulation method. The technical problem to be solved by the invention is to provide the method for calculating the fastest adjustment time of the primary frequency modulation of the hydroelectric generating set so as to realize the most accurate and rapid adjustment of the primary frequency modulation.

The present invention provides a method for identifying the evolution path of voltage sag consequences, relating to the technical field of voltage transient assessment. The method comprises obtaining voltage sag characteristic parameters and voltage sag impact parameters; analyzing the corresponding boundary values ​​of the equipment tolerance curve and the process parameter curve based on the voltage sag characteristic parameters to obtain consequence characteristic data; analyzing the energy flow and material flow of the production process based on the voltage sag impact parameters to obtain consequence severity data; and analyzing the transfer characteristics based on the consequence characteristic data and consequence severity data using a voltage sag consequence transfer model to obtain the voltage sag consequence evolution path, thereby completing the identification of the voltage sag consequence evolution path. The present invention can promptly identify implicit consequences, avoiding the problem of implicit consequences being transferred and superimposed, leading to the aggravation of explicit consequences.

The invention discloses a monitoring data quality control method based on deep learning and a self-built rule. According to the method, the reliability and the practicability of the natural resource monitoring data are remarkably improved by combining flexible rule configuration and an advanced time sequence analysis technology. Firstly, the method supports a user to self-define multi-dimensional quality inspection rules according to actual scene requirements, the multi-dimensional quality inspection rules comprise abnormal values, threshold values, sudden change values, time continuity, logicality and the like, and the limitation of traditional fixed rules is broken through. By introducing time logic check, the system can effectively identify abnormalities caused by seasonal or periodic changes in the data, such as reasonable fluctuation ranges of vegetation indexes in different seasons, thereby more accurately capturing time features of the data. Besides, the multi-device consistency comparison function realizes cross verification of cross-device data, device faults or local environment anomalies can be found in time, and logic consistency and overall credibility of multi-source data are ensured.

The application discloses a kind of based on MPVL algorithm's finite element fast sweep method and device, belong to electromagnetic full-wave simulation technical field, method includes: according to the port type and / or boundary type of electromagnetic field model, construct finite element boundary value equation and finite element variational equation;The finite element boundary value equation is substituted into finite element variational equation to obtain new finite element variational equation;According to the characteristics of wave number in new finite element variational equation, wave number or square root of wave number is extracted as the frequency-related common factor of each term in new finite element variational equation and is arranged, to obtain arrangement equation;Arrange equation is reconstructed as the matrix equation that can use MPVL algorithm to solve, and based on MPVL algorithm, the matrix equation at given expansion frequency point is solved to obtain electromagnetic field value under different excitation.The application realizes fast sweep, and sweep result has higher accuracy.

This invention provides a fast prediction method for airfoil icing shape based on empirical wavelet transform, comprising: acquiring icing meteorological parameters; inputting the icing meteorological parameters into a pre-trained target neural network to predict the empirical wavelet transform boundary values ​​of the icing thickness curve signal under airfoil icing conditions and the first K order Fourier modes of the icing thickness curve signal, where K is a positive integer; constructing a bandpass filter based on the empirical wavelet transform boundary values ​​of the icing thickness curve signal under airfoil icing conditions; obtaining empirical wavelet transform modes of each order based on the bandpass filter and the first K order Fourier modes of the icing thickness curve signal; superimposing the empirical wavelet transform modes of each order to obtain the icing thickness curve signal; and performing a target transform on the icing thickness curve signal to obtain the airfoil icing shape. By implementing this invention, high prediction accuracy can be maintained under different conditions, the prediction generalization ability is enhanced, and the prediction efficiency is improved.

The application discloses a phase loss detection method, a phase loss detection system, a compressor and a refrigeration device. The phase loss detection method comprises the following steps: dividing the running time of a predetermined position stage into several time periods in sequence; detecting the three-phase current of a rotor in each time period and analyzing whether each phase has a phase loss risk; if a certain phase has a phase loss risk in at least two time periods, it is determined that the phase has a phase loss fault; after the predetermined position stage ends, entering a stable running stage, estimating the increment of the rotor position angle in each control period Ts, comparing the increment with a set boundary value, and making further analysis according to the comparison detection result. Different phase loss detection logics are adopted in the predetermined position stage and the stable running stage, the reliability of phase loss detection is effectively improved, single-phase phase loss can be detected, and two-phase phase loss or three-phase phase loss can also be detected.

The present invention relates to the field of privacy protection technology, and discloses a method for publishing the number of range subgraphs based on differential privacy, including inputting a point attribute graph and privacy parameters; sorting the nodes in ascending order according to the value of the attribute; initializing an intermediate vector; enumerating all copies of the pattern graph in the point attribute graph; constructing a differential privacy range tree with all Euclidean space points as input; obtaining a new discretization boundary value according to the discretization range of each query; and recursively traversing the differential privacy range tree generated in step four according to the attribute range to obtain the number of copies of the pattern graph in the point attribute graph within the attribute range. The present invention can realize an efficient ε-DP method with the same additive error for the range subgraph counting problem with edge attributes through simple transformation. The method of the present invention is concise and easy to deploy, and its time complexity is consistent with that of the non-private range subgraph counting method.

This invention discloses a high-precision density reversal method and system for gravity anomalies based on regular, stable, and high-speed solution. [Solution] Based on the above-mentioned field source regularization solution, we propose using data with false anomalies at the field source imaging depth as boundary value conditions. Again, by solving the upper space of the first class boundary value problem of Laplace's equation, we calculate gravity anomalies on the ground and perform least-squares optimization iterative solution with the actual ground anomalies to obtain high-precision anomaly imaging data at the field source depth that does not contain false anomalies due to the Gibbs effect. This depth is used as the top interface of the field source, and the top interface is divided into grid prisms to construct the field source morphology. Density inversion is performed on each prism top surface in the frequency domain to obtain the density distribution of the field source morphology. Since this algorithm is implemented in the frequency domain and the inversion is performed at a known field source depth, the present invention is a gravity density inversion method with high speed, high precision, and high resolution characteristics, and provides a new concept for realizing the solution of gravity field source density parameters.

The embodiment of the invention provides a space bounding box calculation method for a three-dimensional model. The method comprises the steps that continuous parameterized expression of the surface of a target three-dimensional model on a parameter domain is determined; according to the continuous parameterized expression, analyzing a plurality of profile curves obtained by projecting the target three-dimensional model on a plurality of mutually orthogonal coordinate planes in a three-dimensional coordinate system; according to the parameterized expressions of the plurality of profile curves, determining two-dimensional bounding boxes respectively corresponding to the plurality of profile curves on the corresponding coordinate planes; and performing extreme value selection operation on the boundary value of the two-dimensional bounding box in the coordinate axis direction to generate a three-dimensional space bounding box of the target three-dimensional model. A projection profile curve is directly analyzed through continuous parameterization expression, the geometric boundary of the model is locked in mathematics essence, the defect that extreme points are missed in discrete sampling is avoided, and the calculation precision is improved; and three-dimensional extremum search is converted into two-dimensional profile curve analysis and two-dimensional bounding box construction on a plurality of orthogonal coordinate planes, so that the calculation complexity is reduced.

The invention discloses an energy system scheduling method and device and a medium, and the method comprises the steps: inputting an energy characteristic parameter corresponding to an energy system into a preset energy prediction model, and outputting a corresponding energy demand prediction result; wherein the energy demand prediction result refers to a confidence interval formed by energy demand prediction values with different confidence degrees under each prediction time step; according to the boundary value of the confidence interval, constructing a power balance constraint relationship of the energy system, and based on the balance constraint relationship, solving a pre-constructed multi-objective optimization function to obtain a plurality of scheduling strategies; and selecting a target scheduling strategy from the plurality of scheduling strategies, and scheduling the energy system through the target scheduling strategy.

The invention relates to a method for calculating a northbound gradient of a meridian component of a sea plumb line deviation, and provides a method for calculating the northbound gradient of the meridian component of the sea plumb line deviation aiming at the compensation requirement of the meridian component of the plumb line deviation of an inertial navigation system under the constraint of the position error of a sea motion carrier. And based on the completely normalized global gravitational potential coefficient, constructing a sea area plumb line deviation meridian component northbound gradient calculation model, and realizing sea area plumb line deviation meridian component northbound gradient calculation. The invention aims to improve the meridian component compensation capability of the vertical line deviation of the inertial navigation system under the constraint of the position error of the motion carrier and improve the navigation precision of the inertial navigation system.