205 results about "Nonlinear modelling" patented technology

The invention discloses a cable insulation life prediction method and system based on LSTM accelerated aging mapping, and relates to the technical field of submarine cable insulation life prediction. The existing method has the defects of insufficient multi-stress nonlinear modeling, laboratory and field data separation, difficulty in small sample modeling and the like, and the insulation life of the submarine cable is difficult to accurately predict. The method comprises the following steps: data acquisition: acquiring parameters of insulation electrical performance, physical and chemical performance and mechanical performance under an accelerated aging condition; carrying out data preprocessing: carrying out homodromous processing on the inverse indexes, improving box plot denoising, filling missing data with a space-time K nearest neighbor algorithm, and carrying out normalization; constructing an LSTM model: embedding a dielectric constant differential equation as a physical constraint, and introducing an index weight; and model training and evaluation: adopting five-fold cross validation, and quantizing prediction precision through mean square errors and decision coefficients. According to the technical scheme, the prediction precision is improved, the fault risk caused by insulation aging is reduced, the maintenance cost is reduced, and the reliability of the ocean energy transmission system is improved.

The invention relates to the technical field of intelligent manufacturing and numerical control machining control, and discloses a machine tool dynamic characteristic sensing and intelligent machining control method and system based on a knowledge graph and a large model, and the method comprises the following steps: extracting frequency domain parameters through a vibration sensor, obtaining vibration displacement in combination with laser displacement, and comparing the vibration displacement with modal data to construct a graph; processing parameters and displacement are synchronously sampled, time sequence characteristics are extracted to generate tensors, dynamic characteristics are predicted and corrected, and frequency response adjustment rotating speed is matched to generate optimized track control parameters which are converted into G code instructions. According to the method, a dynamic characteristic map is constructed by fusing vibration signals and displacement, a sliding window synchronizes processing parameters and vibration data, LSTM extracts joint characteristics, GRU predicts rigidity and damping ratio, an attention mechanism dynamically corrects weight, characteristic coupling analysis and prediction precision is improved, nonlinear modeling captures dominant frequency offset and harmonic distribution, response speed is enhanced, and the method has the advantages of being high in precision and high in precision. Cutting vibration is inhibited, and the process stability is guaranteed.

The invention discloses an energy-saving control method and system for a water chilling unit, and relates to the technical field of energy-saving control. During operation of the system, a data set is synchronously collected from a water chilling unit system through a multi-channel asynchronous sampling mechanism, time sequence compression and redundancy removal are carried out, an embedded perturbation calculation mechanism is used for calculating and generating a non-dominant control core coefficient, and the non-dominant control core coefficient is used for controlling the energy-saving control of the water chilling unit; a three-dimensional coefficient space is converted and output through an entropy state change structure and is used for constructing a state balance atlas, comprehensively calculating a control state index SEEI, evaluating the current energy state offset degree of a system, determining whether intervention is carried out or not, carrying out rule search and nonlinear modeling based on the control state index SEEI value, generating an adjustment matrix, and carrying out state balance analysis. And starting a data reconstruction micro-strategy of a short-time historical window, receiving an adjustment matrix, converting the adjustment matrix into a device-level instruction, executing an action through an edge controller, feeding back a response error epsilon (t) in real time, and predicting a potential performance degradation trend based on long-time system operation data.

The present invention relates to the technical field of oil and natural gas exploitation, and discloses a real-time monitoring and intelligent control system for hydraulic fracturing cracks in oil reservoirs, including: a real-time monitoring module, which is used to collect crack geometric morphology parameters and construction operation parameters in real time during crack expansion; a nonlinear modeling module, which is connected to the real-time monitoring module, and is used to construct a nonlinear dynamic model of crack expansion according to the collected crack expansion parameters and construction operation parameters, and output a predicted value of crack morphology; an optimization control module, which is connected to the nonlinear modeling module, and is used to calculate the optimized construction parameters according to the nonlinear dynamic model, including injection pressure, injection flow rate and viscosity of fracturing fluid. The present invention realizes precise control of crack expansion, intelligent optimization of construction parameters and efficiency improvement through the closed-loop linkage of real-time monitoring, nonlinear modeling, optimization control and feedback execution.

The invention discloses a package management and control method fusing multivariable dynamic analysis, relates to the technical field of package dynamic management and control, and covers a complete process from data acquisition to protection strategy implementation. Firstly, multi-source sensors are arranged at packaging and transportation nodes, stress, acceleration and environmental parameters are collected in real time, and multi-dimensional original data covering the whole process is formed; then, carrying out time domain alignment and feature extraction on the data by utilizing denoising filtering, wavelet decomposition and environment coupling methods to obtain structured data of a unified coordinate system; and accurately identifying a packaging fatigue risk through a microcrack jump function and an accumulated impact measurement model, and generating a crack propagation trend and failure prediction. And finally, according to the risk change of the section, executing a sectional protection strategy, and dynamically adjusting and optimizing a protection scheme to ensure efficient management and control. The limitation of traditional packaging control is overcome through nonlinear modeling and real-time adjustment and optimization, and the method has a wide application prospect.

The invention relates to a low-orbit communication satellite Doppler positioning method and device based on factor graph optimization. The method comprises the following steps: after required observation data is received and an initial state value of a ground receiver is solved, a factor graph framework is introduced to set a priori factor, a Doppler frequency shift factor, a state constraint factor and a state variable consisting of a three-dimensional position and frequency drift of the receiver according to a Doppler positioning observation model; and constructing a Doppler positioning factor graph model by taking the factors and variables as nodes, introducing a sliding window mechanism to update a factor graph in a factor graph optimization solution process, and solving state variables by adopting a Gaussian-Newton algorithm to finally obtain a Doppler positioning result. According to the method, factor graph modeling is carried out on the Doppler positioning observation model, the advantages of nonlinear modeling, global optimization and capability of fully utilizing historical observation of a factor graph optimization method are exerted, and a relatively small positioning error and a higher convergence speed can be obtained.

The invention relates to the technical field of intelligent water affairs, in particular to an intelligent water affairs management and control system based on the Internet of Things, and aims to solve the problems that in the prior art, multi-source water quality data and user behavior characteristics can be fused to construct a risk assessment model based on fuzzy logic and a Bayesian network, dynamic assessment of a complex water quality state cannot be achieved, and the risk assessment accuracy is poor. Abnormity cannot be quickly recognized through a similarity matching mechanism, and the response speed and accuracy of early warning are reduced; multi-source water quality data and user behavior characteristics are fused through the water quality intelligent early warning module, a risk assessment model based on fuzzy logic and a Bayesian network is constructed, the method has high nonlinear modeling and uncertainty processing capacity, dynamic assessment of a complex water quality state is achieved, abnormity is rapidly recognized through a similarity matching mechanism, and the risk assessment efficiency is improved. The method improves the early warning response speed and accuracy, combines the countercurrent tracking and GIS technology, accurately locates the pollution source, and enhances the emergency disposal and decision support capability.

The invention discloses a deep learning and machine learning fused soil moisture inversion construction method, and relates to the technical field of measurement of physical properties of materials, and the method comprises the steps: capturing complementary information and spatial context of multi-source data through a multi-source heterogeneous data space-time adaptive fusion step by using a cross-modal attention mechanism and a graph neural network; through a deep learning and machine learning dual-path collaborative inversion step, advantage complementation is realized by combining data-driven nonlinear modeling and a physical constraint interpretable model; according to the method, the defects of single data source, insufficient model generalization ability and incomplete physical mechanism consideration in the prior art are overcome, the inversion precision is improved by 12%-18% under the complex earth surface condition, and the method has the advantages that the method is suitable for large-scale popularization and application. And a high-precision, strong-generalization and reliable technical means is provided for precise monitoring of soil moisture.

The invention discloses an intelligent control method and system based on pole-mounted circuit breaker equipment, and relates to the technical field of power grid control, and the method comprises the steps: collecting environmental data of a pole-mounted circuit breaker, employing a Kalman filtering fusion algorithm, outputting a fusion state vector, constructing time series data, employing a photon to calculate an accelerated time series neural network, and obtaining a time series neural network model; and performing complex field mapping and optical phase shift modulation on the extracted features, and predicting a future current value. According to the method, complex field mapping is carried out on features extracted by a time convolution layer, the expression ability of nonlinear features is enhanced, optical phase shift modulation is introduced, phase and amplitude information is further adjusted, the nonlinear modeling ability of time sequence features is improved, and multi-modal data fusion and multi-scale consistency verification of fractal dimensions are combined, so that the time sequence features of the fractal dimension are optimized. Time scale deviation of different data sources is eliminated, and effectiveness and consistency of multi-dimensional feature fusion are improved.

The invention discloses an electrical element magnetic core loss prediction method based on a soft gating hybrid expert model, and relates to an electrical element magnetic core loss prediction method, which adaptively adjusts the expert weight, so that the model is more flexible and has strong adaptability when facing different types of data. Diversified expert model combinations can complement respective advantages, so that the overall robustness and generalization ability are improved, and the risk of overfitting is reduced; in addition, the modular design enables the model to be easy to expand and maintain, and the interpretability of the model can be enhanced by analyzing the output weight of the gating network; furthermore, automatic parameter adjustment and end-to-end training are carried out through an intelligent optimization algorithm, so that the performance of the model is further improved; and finally, the soft gating hybrid expert model can effectively process non-linear and complex relationships, the powerful non-linear modeling capability of the MLP is utilized to capture a complex mode in the data, and the calculation efficiency is improved through parallel calculation and dynamic resource allocation. The advantages enable the soft gating hybrid expert model to show higher accuracy and reliability when processing complex tasks such as magnetic core loss prediction and the like.

The invention discloses a method for dynamically predicting the underground water level during excavation of an overtopping ground layer foundation pit, and relates to the technical field of dynamic prediction of the underground water level, which comprises the following steps of: acquiring multi-source data related to the underground water level in an engineering range; comprising information of soil moisture content, stratum permeability coefficient, rainfall capacity, foundation pit excavation depth, foundation pit dewatering scheme and foundation pit waterproof and drainage measures; historical underground water level, underground aquifer data and Yangtze River water level change information are obtained. According to the method, data quality is optimized through multi-source data acquisition, correlation analysis and z-score standardization, nonlinear modeling is realized in combination with a support vector machine (SVM) and Bayesian optimization, and model precision and generalization ability are improved. Model parameters are dynamically adjusted through a real-time monitoring and feedback optimization mechanism, the adaptability to sudden hydrological changes is enhanced, engineering risks are effectively reduced, and construction safety and economical efficiency are guaranteed.

The invention discloses an oil reservoir production dynamic prediction method fusing discrete gradient information, and belongs to the technical field of oil reservoir development and artificial intelligence crossing, and the method comprises the steps: building a heterogeneous oil reservoir oil-water two-phase flow numerical simulation data set based on a numerical simulation method; designing a double-branch network structure and extracting spatial and physical characteristics of input field data in parallel, wherein the spatial and physical characteristics comprise a main characteristic coding branch and a differential operator branch; designing a backbone network to carry out deep nonlinear modeling; an efficient pressure and saturation field prediction neural network model is constructed based on a double-branch network structure and a backbone network, in a model training stage, spatial region observation points of part of time steps are used to participate in data item loss calculation, and meanwhile, physical control equation residuals are introduced into all time steps and a whole space to serve as physical loss items; a trained efficient pressure and saturation field prediction neural network model is obtained, and high-precision prediction of a full-time-sequence pressure field and a saturation field is achieved.

According to the multi-channel feature image-based improved MobileNetV2 voltage transformer fault diagnosis method, a partial overlapping sliding window technology is used to carry out data enhancement on a secondary side voltage signal so as to construct images capable of representing different features. Through fusion of multi-channel feature images representing structure information, transient change and frequency domain characteristics, combined extraction of voltage signal multi-dimensional features is realized. On the basis, an improved MobileNetV2 diagnosis model is provided, and the nonlinear modeling capability of the network to a complex feature mode is enhanced by introducing a Mish activation function; and a normalization-based attention module (NAM) is introduced to realize dynamic focusing of fault features. Meanwhile, a receptive field of a convolutional layer is expanded by using multi-scale expansion convolution, so that correlation modeling between features is enhanced. According to the framework, the diagnosis precision of the voltage transformer is remarkably improved while the light weight of the model is kept.

The invention discloses a magnetostriction liquid level meter temperature compensation method and system based on a support vector machine. The method comprises the steps that the currently captured original pulse number is obtained through a magnetostriction liquid level meter; the current environment temperature is detected in real time through a high-precision temperature sensor in the magnetostrictive liquid level meter; taking the original pulse number and the current environment temperature as input features, sending the input features to a pre-trained support vector machine regression model (SVM), and outputting a displacement error prediction value in the current temperature environment; and correcting the original measurement result according to the error prediction value to obtain a real pulse measurement value after temperature compensation. The system comprises a time-to-digital conversion chip, a temperature chip temperature measurement module, a support vector machine reasoning module, a pulse compensation module and a distance calculation module. According to the method, nonlinear modeling can be carried out on measurement errors caused by environment temperature changes, so that the liquid level measurement result is dynamically corrected, and the overall robustness and precision of a measurement system are improved.

The invention relates to the technical field of biological feature recognition, and particularly provides an anti-migration PPG recognition method based on rate perception and a state space model. The method comprises the following steps: performing physiological feature front-end extraction on an original single-channel PPG signal to obtain a high-dimensional shallow feature sequence; performing double-flow cooperative processing on the high-dimensional shallow-layer feature sequence, and distributing the high-dimensional shallow-layer feature sequence to two parallel branches, namely a control flow branch and a data flow branch; in the control flow branch, an amplitude spectrum and an instantaneous physiological rate curve are obtained; in the data stream branch, acquiring a deep global feature sequence with rate invariance; obtaining multi-scale refinement features based on the high-dimensional shallow feature sequence and the deep global feature sequence; according to the multi-scale refinement features, a final biological feature recognition result is obtained, the method can actively sense the physiological rate change, and efficient nonlinear modeling can be achieved with the extremely low parameter quantity.

The invention discloses a transient response calculation method for a complete machine model with a gap support. The method comprises the following steps that SS1, whole machine nonlinear modeling of a rotor-bearing-casing system is carried out, linear component modeling of a whole machine structure and nonlinear modeling of a gap bearing are included, linear component modeling of the whole machine structure comprises rotor modeling, casing modeling, linear bearing modeling and installation section modeling, and linear component modeling of the whole machine structure comprises linear component modeling of the rotor-bearing-casing system and linear component modeling of the gap bearing; the non-linear modeling of the gap support comprises non-linear modeling considering friction influence and contact influence, and a whole machine non-linear rotor dynamic model is constructed; step SS2, response calculation of a Newmark method based on variable step size control is carried out; and step SS3, extracting transient responses of each node of the rotor, the support and the casing. According to the method provided by the invention, the fit clearance between the rotor journal and the bearing inner ring and the influence of the casing are considered at the same time, the transient response of the rotor-bearing-casing system is calculated, the vibration characteristics of the whole machine with the clearance bearing are analyzed, and support is provided for the structural design of an engine.

The invention discloses an MEKF attitude estimation method based on a physical information neural network, and the method comprises the steps: dynamically predicting an observation matrix of an MEKF through the dynamic modeling capability and constraint embedding characteristics of the physical information neural network, and extracting sensor sequence features through the long-range dependence capturing capability of a time domain convolutional network; and meanwhile, the physical rule constraint is embedded into network training to ensure the physical rationality of a prediction result. Through data-driven nonlinear modeling and a recursive estimation framework of the MEKF, the limitation that the MEKF is high in dependence on noise covariance and poor in dynamic adaptability is effectively overcome, and the precision and the anti-interference capability of attitude estimation in a complex environment are remarkably improved.

The invention relates to the technical field of carbon flux monitoring, and particularly discloses a carbon flux monitoring method and system based on soil drought remote sensing data, and the method comprises the steps: respectively collecting soil humidity remote sensing data and a soil vegetation coverage remote sensing image through a microwave sensor and an optical remote sensing sensor; performing resampling on the soil humidity remote sensing data and the soil vegetation coverage remote sensing image to realize spatial resolution alignment, and performing spatial distribution feature extraction on the soil humidity remote sensing data and the soil vegetation coverage remote sensing image after spatial alignment by adopting a deep learning algorithm; and pixel-level significance enhancement and fusion processing are carried out on the captured soil humidity distribution characteristics and vegetation distribution characteristics, so that nonlinear modeling of a dynamic influence mechanism of the soil drought degree on the vegetation growth state is realized, and intelligent estimation of the carbon flux is realized on the basis. In this way, the nonlinear regulation and control effect of soil drought stress on vegetation respiration and photosynthesis can be effectively described, and the efficiency and coverage range of carbon flux monitoring are improved.

The invention discloses a multi-energy system closed-loop prediction control method, system, equipment and medium, and the method comprises the steps: carrying out the decomposition, dimension reduction and nonlinear modeling of the time sequence characteristics and environmental influence factors of photovoltaic output through a photovoltaic power prediction model, and outputting a future multi-period photovoltaic power prediction sequence; establishing a state equation and an output equation, integrating equipment operation constraints, and constructing a hydrogen-containing energy storage state space model; inputting local load power and a future multi-period photovoltaic power prediction sequence into the hydrogen-containing energy storage state space model, and solving an objective function through a rolling optimization algorithm to obtain a future multi-period optimal scheduling scheme; and applying a first hour control instruction of the optimal scheduling scheme to an actual system, and proportionally superposing the deviation between an actual measurement value and a historical prediction value to a photovoltaic power prediction sequence of a next period through a feedback correction item to realize closed-loop control. According to the method, the photovoltaic local consumption rate can be improved, and the power grid fluctuation rate is reduced.

The invention discloses a two-arm robot turnover skill learning method based on force control and a neural dynamic model, and the method comprises the following steps: carrying out the master-slave teleoperation through a teleoperation module, and constructing a space mapping model to achieve the master-slave motion matching of heterogeneous joints; a variable stiffness admittance control model is adopted for radial force control, and flexible contact force control is achieved by dynamically adjusting stiffness parameters; and constructing a neural dynamic model to perform coding modeling on the teleoperation data, constructing an energy function and a dynamic equation containing a learnable neural network, and realizing skill generalization and autonomous execution. According to the method, the contact stability is guaranteed through a force-position hybrid control strategy, the flexibility, the anti-interference capability and the skill generalization level of box turnover operation are remarkably improved in combination with the nonlinear modeling capability of the neural dynamic model, and a solution is provided for two-arm cooperative operation in a complex contact scene.

The invention provides a Mars mineral abundance inversion method and system. The Mars mineral abundance inversion method comprises the steps of firstly obtaining target Mars hyperspectral reflectivity data; and then generating simulated Mars hyperspectral image data based on the target Mars hyperspectral reflectivity data. Secondly, training the constructed mineral abundance inversion deep learning model based on the simulated Mars hyperspectral image data, and determining the trained mineral abundance inversion deep learning model; thirdly, acquiring to-be-processed Mars hyperspectral image data, and performing preprocessing; and finally, performing mineral abundance inversion on the preprocessed to-be-processed Mars hyperspectral image data through the trained mineral abundance inversion deep learning model to obtain a mineral abundance inversion result. Therefore, the weight distribution of each wave band of the hyperspectral image can be enhanced through the mineral abundance inversion deep learning model, and the non-linear modeling capability and the wave band characteristic response capability of abundance inversion are improved, so that the accuracy and the efficiency of Mars mineral abundance inversion can be effectively improved.

The invention provides a multi-dimensional data preferential analysis method and device based on a gradient boosting decision tree model, and relates to the technical field of data mining, in the method, a target gradient boosting decision tree model is adopted, the nonlinear modeling problem of strategy optimization in multi-dimensional data is solved, and the multi-dimensional data is optimized according to the target weight determined in the training process. According to the method, key features can be accurately identified, the processing efficiency and precision are high, compared with a traditional linear regression or single decision tree method, the accuracy and real-time performance of strategy optimization can be improved, high interpretability and robustness are achieved, an optimization strategy can be adjusted in a self-adaptive mode in a changeable environment, and the method is suitable for popularization and application. The method is widely applied to multiple fields of industrial optimization, intelligent decision making and the like.

The invention discloses a photovoltaic power generation power prediction and power system scheduling method and a system for realizing the method. The method comprises four steps of data acquisition and preprocessing, similar day selection and training set construction, GA (Genetic Algorithm)-fuzzy RBF (Radial Basis Function) neural network modeling and power scheduling plan generation. The method comprises the following steps: selecting a meteorological variable with high correlation degree through a Spearman rank correlation coefficient, and constructing a time sequence feature; similar days are utilized to construct training samples, and the generalization ability of the model is improved; a fuzzy RBF network optimized by GA is adopted to enhance the nonlinear modeling precision; and inputting a prediction result into the power system simulation model, and generating an optimal scheduling instruction by adopting dynamic programming. According to the method, the photovoltaic power prediction accuracy and scheduling efficiency can be remarkably improved, the power grid stability is enhanced, and the new energy consumption capability is promoted.

The invention discloses a split type three-box girder nonlinear vortex vibration steady-state amplitude intelligent prediction method, belongs to the field of bridge vortex-induced vibration control, and aims to solve the problem of low accuracy of three-box girder vortex vibration nonlinear modeling and amplitude prediction. The method comprises the following steps: acquiring displacement time sequence data through a reduced scale model wind tunnel test, preprocessing to obtain displacement, speed and acceleration dimensionless data, and dividing a data set; constructing a candidate function library containing high-order polynomial terms of the primary function; performing nonlinear system sparse recognition by taking acceleration data as a target item and combining an improved algorithm to obtain a preliminary feature set; a final feature set is obtained through energy-statistics-self-adaption three-stage screening; and finally, constructing a control equation to predict the steady-state amplitude. The method can accurately predict amplitude, coincide test and real bridge observation results, and is less in computing resource occupation and high in numerical value precision.

The invention relates to the technical field of vehicle thermal management, in particular to a prediction model construction method and device for vehicle thermal management, a control method and device and a vehicle, and the construction method comprises the steps: obtaining a historical sample data set of a vehicle thermal management system; preprocessing the historical sample data set; an initial prediction model is established based on a Transform network, the input of the initial prediction model is state data, the output of the initial prediction model is control data, and a loss function comprises a mean square error term and a physical constraint term; and taking the minimum loss function value as an optimization target, and performing iterative training optimization on the initial prediction model through the preprocessed historical sample data to obtain a prediction model of vehicle thermal management. According to the method, on the basis of strong nonlinear modeling capability of the Transform network, model parameters are optimized by introducing physical constraint terms, so that a model prediction result is ensured to be consistent with an actual physical rule, and a prediction error caused by violation of the physical rule is avoided, thereby improving the prediction precision.

The invention discloses a dynamic state prediction method and system for an electric heavy-duty vehicle and terminal equipment, and relates to the technical field of new energy vehicles. The method comprises the steps that heavy-load vehicle driving state information data are received and preprocessed, and the heavy-load vehicle driving state information data comprise the longitudinal acceleration, the transverse acceleration, the yaw velocity, the wheel rotating speed and the wheel rotating angle; and constructing a transverse speed model based on a Koopman operator according to the driving state information data, wherein the transverse speed model is used for predicting the transverse speed of the heavy-duty vehicle. Aiming at the problem that the transverse speed of the electric heavy-load vehicle is usually unmeasurable, a transverse speed model based on a Koopman operator is provided, the problem that the transverse speed cannot be obtained through a traditional method can be solved, a linear heavy-load vehicle dynamic model is provided to represent the nonlinear characteristics of the heavy-load vehicle, nonlinear modeling of a heavy-load vehicle system is avoided, and the method is suitable for the large-scale production of the electric heavy-load vehicle. And subsequent controller design is facilitated.

The invention provides an engineering drawing steel bar bulk sample annotation text detection method, system and device based on deep learning, and a storage medium. The method comprises the following steps: S1, preprocessing an engineering drawing image and labeling a steel bar bulk sample annotation text region data set; s2, constructing a staged multi-scale feature map extraction backbone network framework; s3, introducing compression excitation into each scale feature map; s4, adopting an ACON adaptive activation function in nonlinear modeling; s5, constructing a multi-scale feature pyramid structure based on the RSE-FPN, and superposing scales to reinforce fusion; and S6, outputting the approximate binary image to realize accurate prediction of the bounding box. According to the method, the OCR detection precision is remarkably improved, small character and complex background interference is effectively overcome, and missing detection and false detection are reduced; the model is lightweight to facilitate efficient deployment of equipment; the output boundary is compact and accurate, the semantics is reasonable, and subsequent recognition and analysis are facilitated; the method has excellent generalization ability, adapts to steel bar large sample drawings of different formats, definitions and styles, and is high in engineering practicability.

The invention discloses a crystal size distribution soft measurement method integrated with mechanism constraints. The method comprises the following steps: 1) data acquisition and integration; 2) modeling training and model testing: constructing a crystal size distribution soft measurement model integrated with mechanism constraint, training a training data set, injecting crystallization process dynamics knowledge into the Kolmogorov-Arnod network in a loss function form, improving the nonlinear modeling capability and credibility of the model, and performing model testing on the Kolmogorov-Arnod network; and verifying test set data by using the trained model. According to the method, the knowledge of the crystallization dynamic process is injected into the Kolmogorov-Arnod network in the form of the loss function, so that the prediction capability of the model on the crystal size distribution in the crystallization process and the credibility of the model are effectively improved.

The invention provides a road maintenance project carbon emission prediction method based on a fuzzy polynomial neural network, and the method comprises the steps: collecting and calculating the carbon emission data of a plurality of completed road maintenance projects, calculating the carbon emission through employing a method combining a quota method and an emission coefficient method, and constructing a basic data set; based on the basic data set, identifying an emission heat source, matching engineering quantity parameters, and primarily screening and selecting key indexes to construct input data of a prediction model; performing nonlinear modeling and generalization ability mining through a fuzzy polynomial neural network model, and constructing and training a prediction model based on the input data; and predicting the carbon emission of the road maintenance project through the prediction model. According to the highway maintenance engineering carbon emission prediction method based on the fuzzy polynomial neural network, rapid and accurate prediction of carbon emission can be realized only based on a small amount of key information in the early stage of the highway maintenance engineering.

The invention relates to the technical field of precision timing instrument testing, in particular to an atomic clock aging prediction method based on feature fusion and quantum constraint learning. According to the atomic clock aging prediction method based on multi-modal feature fusion and quantum constraint learning provided by the invention, a multi-modal tensor fusion means is adopted, and a time domain microwave probe signal, a space domain atomic cloud density distribution signal and a frequency domain lambda stripe signal are collected at the same time for feature extraction, so that the completeness of the features is improved; during nonlinear modeling, a Bloch equation constraint is adopted to ensure that a network model accords with a quantum physics rule. According to the method, the atomic clock aging feature expression effect can be improved through an artificial intelligence means, the defect of overfitting caused by purely depending on training data is effectively avoided, the atomic clock aging prediction model better conforms to the physical law, the atomic clock aging prediction precision is improved, and the prediction model complexity is optimized.