193 results about "Predictive modelling" patented technology

The present invention relates to a system and method for cross-domain predictive modeling using Bedrock-based foundation models and blockchain-anchored data. The invention integrates large-scale foundation model reasoning with distributed ledger-based data provenance to enable verifiable, secure, and explainable predictive analytics across heterogeneous domains such as finance, healthcare, logistics, and environmental systems. The system comprises a data ingestion unit for receiving and normalizing multi-domain datasets, a blockchain anchoring unit for generating cryptographic hashes and recording data provenance into a distributed ledger, a cross-domain harmonization processor for aligning heterogeneous feature representations into a unified latent space, a foundation model processor configured to execute Bedrock-based predictive inference with adaptive domain contextualization, a verification processor for validating predictions against blockchain-anchored ground truths, and a governance processor for maintaining immutable audit trails of model evolution.

The invention discloses a medical health cost prediction system and method based on multi-source data fusion, and relates to the technical field of medical data analysis, the system firstly fuses a plurality of heterogeneous medical information sources to generate structured data; then, multidimensional features related to the cost are extracted to construct a feature representation vector; and the cost prediction modeling module constructs a cost prediction model through graph structure modeling and semantic embedding, carries out joint optimization by combining a graph attention mechanism and semantic similarity, and outputs a prediction result by fusing a time sequence and static characteristics. A joint optimization algorithm of graph semantic comparison loss and prediction deviation loss is introduced into model training, and positive and negative sample pairs are constructed through a cost label distance. And the feedback optimization module triggers model updating when the prediction deviation exceeds a threshold value, and dynamically adjusts a model structure and parameters through a deviation index and a sample confidence factor. And the prediction interpretation module analyzes influence factors based on intermediate layer features or gradient propagation, outputs an interpretation report, and improves the transparency and credibility of the model.

The invention discloses a behavior-driven twinborn prediction method, and relates to the technical field of intelligent information processing and prediction modeling, and the method comprises the following steps: building a unified event time baseline, collecting nanosecond clock offset information of each data source, building a cross time sequence suspicion chart, recognizing time synchronization abnormal nodes, and forming a credible time anchor point set; and based on the trusted time anchor point set, executing anti-fact playback, reconstructing a historical evolution process of behavior data, generating a time offset vector set, and constructing a corresponding time sequence offset spectrum. According to the method, through construction of a unified time baseline, trusted anchor points, anti-fact replay, causal topology and time reversal control, time sequence dislocation identification, calibration and false trajectory elimination of multi-source behavior data are realized, a dynamic self-healing closed-loop prediction mechanism is established, and the twin system prediction accuracy and stability are improved.

In general, various aspects of the techniques enable predictive modeling for forged components. A computing device comprising a memory and a processor may be configured to perform the techniques. The memory may store a trained machine learning model that associates training features extracted from data representative of a plurality of training forged components to a plurality of training model results. The memory may also store data representative of a target forged component. The processor may perform a geometrical analysis with respect to the data representative of the target forged component to extract target features, and apply the trained machine learning model to the target features to obtain predicted model results for the target forged component. The processor may also output the predicted model results.

The invention relates to the technical field of network slicing, and discloses a wireless network multi-link communication method based on dynamic link configuration. The method comprises the following steps: collecting state data of heterogeneous links such as cellular links, Wi-Fi links and satellites in real time, and constructing a global network state view; analyzing the network slice SLA and converting the network slice SLA into a quantitative performance constraint; predicting the future performance of the link by using a gating circulation unit neural network; generating a global optimal data flow routing and distribution strategy meeting the QoS (Quality of Service) requirements of the slices in the central controller based on reinforcement learning; and compiling the strategy into a configuration instruction and issuing the configuration instruction to the terminal and the access point for execution. The system comprises a state sensing module, a strategy analysis module, a prediction modeling module, a strategy generation module and a configuration execution module. By means of predictive planning and intelligent decision making, dynamic, fine and on-demand scheduling of heterogeneous resources is achieved, and the network resource utilization rate and the multi-service service quality guarantee capacity are remarkably improved.

The invention provides a hematologic tumor cord blood transplantation treatment prognosis index evaluation decision generation method and system based on prediction modeling, a medium and electronic equipment, and relates to the technical field of medical artificial intelligence. The method comprises the following steps: acquiring multi-source data of a key time point in a whole process of blood tumor umbilical cord blood transplantation treatment of a patient; integrating expert knowledge to form an expert knowledge network, taking the expert knowledge network as priori knowledge of multi-target prediction, and performing multi-dimensional prognosis prediction by using multi-source data; periodically acquiring time sequence multi-source data, capturing time evolution characteristics of patient states, and automatically triggering an updating mechanism at a key clinical time point to dynamically adjust a prediction result; generating a risk assessment grade, a feature importance analysis result and an individualized interpretation report based on the prediction result, and performing visualization; and generating a clinical decision using the large language model. According to the technology, accurate evaluation and individualized clinical decision support for hematologic tumor cord blood transplantation prognosis are achieved.

The invention discloses a sparse coding and graph space-time attention fused coagulant addition prediction method, and relates to the technical field of time sequence data modeling prediction. According to the method, through the combination of a Transform encoding-decoding architecture and a sparse self-attention and top-k sparse strategy, the missing data complementation precision is effectively improved, and high-quality and missing-free input data is provided for subsequent prediction modeling; in the aspect of spatial feature expression, node association of multiple subsystems of a water production system is captured by means of a graph attention network, and by dynamically calculating association weights among nodes and aggregating neighbor features, the information entropy of spatial features is improved, and the expression ability of the spatial features to a multi-node coupling relationship is greatly enhanced; in the aspect of time sequence prediction performance, a time attention mechanism can dynamically focus on key time sequence nodes, the utilization rate of key time sequence features is further improved, and the accuracy of coagulant adding prediction is improved.

The invention provides a cross-omics sparse feature selection system and method based on hierarchical causal modeling, and the system comprises a data input and preprocessing module which is used for receiving multi-omics original data of a multivariate sample; the hierarchical causal structure learning module is connected with the data input and adaptive preprocessing module and is used for constructing a cross-omics hierarchical causal topology; the causal-oriented sparse feature selection module is connected with the hierarchical causal structure learning module; and the model retraining and integration module is used for constructing a three-layer weighted integration discrimination model based on the screened markers, optimizing the fusion weight of each layer through a gradient descent algorithm, and outputting a final prediction result. According to the method, the protein-metabolism biological hierarchy relationship and serum-urine complementary information are fully utilized, and the method has good generalization ability and can be widely applied to marker mining and prediction modeling of cancers, metabolic diseases and the like, so that the accuracy and reliability of precise medical treatment are improved.

The invention discloses a multi-mode induction display screen response method fusing voice interaction, and relates to the technical field of man-machine interaction, and the method comprises the following steps: in a user interaction process, calling a built-in sensor through an interface component real-time state monitoring mechanism, continuously monitoring a rendering process of a target interface component at a millisecond-level time granularity, and displaying the rendering process of the target interface component; collecting multi-dimensional availability state parameter information of the interface component; the method comprises the following steps: preprocessing collected interface component multi-dimensional availability state parameter information, and extracting key indexes reflecting potential asynchronous triggering risks from preprocessed data through a feature engineering method; by sensing the state of the interface component in real time, extracting the asynchronous risk index and combining machine learning recognition and TCN prediction modeling, dynamic regulation and control of the induction triggering window and the animation rhythm are achieved, the problem of mispointing or dislocation of the induction component is avoided, the accuracy and safety of interaction response are improved, and the user experience is improved. The method is suitable for high-precision scenes such as vehicle-mounted, medical and industrial control.

A navigation system and method are disclosed for operation in GPS-denied environments using quantum-inspired sensor fusion, dynamic virtual anchor points (VAPs), and predictive environmental modeling. The system represents multiple position hypothesis using wavefunction-like expansions and integrates VAP-based triangulation for drift correction. A predictive modeling module ingests solar, geomagnetic, and environmental data to proactively adjust sensor weighting. A cybersecurity module employs quantum-algebraic key generation and location-derived ephemeral keys to secure inter-device communication. The system includes an augmented reality (AR) interface to visualize and edit anchor references, and a neurofeedback module that adapts the AR interface based on real-time physiological signals from the user. The method further enables anchor optimization via AI-driven repositioning and supports low-power edge execution using approximate amplitude filtering. Additional modules may include fractal antennas, neuromorphic processors, and adaptive forecasting layers to maintain positional accuracy and user experience in subterranean, multi-floor, or magnetically complex environments.

The invention belongs to the technical field of intelligent traffic and deep learning modeling, and particularly relates to a cross-layer low-rank fusion space-time traffic flow prediction modeling method. The method comprises the following steps: firstly, carrying out standardization, complementation and coding processing on historical traffic data, time labels and road topology, and constructing a space-time embedding representation; then, through node aggregation and agent number adaptive estimation, a double-stage attention modeling structure is established so as to reduce the calculation complexity; efficient fusion of cross-layer information is realized through output pairing and feature splicing of adjacent layers in combination with low-rank bottleneck compression and gating residual fusion; and a robust prediction result is generated by adopting a hybrid expert decoding structure and combining time dimension aggregation, routing weight initialization and multi-target constraint. According to the method, the problems of high-dimensional redundancy, calculation bottleneck and distribution drift in large-scale traffic flow prediction are effectively solved, and the prediction precision and the model efficiency are improved.

The invention discloses a liquid cooling heat dissipation control system of a charging pile, relates to the technical field of energy storage charging piles, and solves the problems of low-frequency oscillation and energy consumption fluctuation caused by independent closed-loop adjustment of a pump and a fan and fault false alarm and failure alarm caused by fixed threshold diagnosis in the prior art. The collection module is used for synchronously collecting and filtering the cooling liquid inlet and outlet temperature, the power module temperature, the pump current and the fan rotating speed; a first prediction modeling module is adopted to generate thermal load prediction and time delay compensation parameters; constructing a self-adaptive baseline relationship between the pump flow and the heat exchange efficiency of the fan through a second baseline modeling module; performing dynamic anomaly judgment based on the residual sequence through a residual detection module; the cooperative scheduling module is used for solving the control track of the pump and the fan by combining the prediction result, the baseline parameter and the abnormal label on the basis of a model prediction control framework; according to the invention, the coordination of liquid cooling heat dissipation control and the adaptability of fault diagnosis are greatly improved.

The invention discloses an AI large model and competitiveness analysis-based address pre-warning and intelligent matching method, which comprises the following steps of: (a) dynamic portrait construction: constructing five-dimensional indexes including enterprise vitality, market expansion capability, resource adsorption capability, innovation growth potential and risk resistance capability, based on historical enterprise data quantitative indexes and in combination with industry characteristic dynamic distribution weights, an enterprise dynamic competitiveness portrait is formed; (b) migrated address prediction modeling: taking the five-dimensional index in the step (a) as a core, fusing a regional land cost fluctuation rate and a policy matching degree, inputting an industry special prediction model optimized by transfer learning, and outputting an enterprise migrated address dynamic risk value; and (c) industrial chain collaborative early warning: when the risk value in the step (b) exceeds a preset threshold value, starting an industrial chain collaborative early warning mechanism. According to the method, the enterprise competitiveness portrait is dynamically constructed, the address migration risk is accurately predicted, the industrial chain influence is cooperatively pre-warned, and a dynamic optimization closed loop is formed.

The invention discloses a method for detecting the content of salidroside in a rhodiola rosea extracting solution based on artificial intelligence. The method comprises the following steps: S1, performing spectral scanning of different wavebands on an extracting solution sample in a plurality of near-infrared wavelength ranges; s2, performing multi-dimensional interference suppression processing and signal purification; s3, carrying out spectral feature compression calculation to obtain a salidroside feature intensity factor; s4, carrying out salidroside characteristic signal-to-noise ratio enhancement and purity index calculation; s5, predicting the content of salidroside and outputting a content prediction score; and S6, mapping the content prediction score into the final salidroside content. According to the method, spectral signal purification, nonlinear feature extraction, dynamic noise enhancement, artificial intelligence prediction modeling and a secondary recheck mechanism are utilized to realize adaptive analysis of extracting solutions from different sources, so that the detection accuracy and stability are remarkably improved, and rapid and traceable salidroside content detection can be realized under the condition that a large precise instrument is not needed.

Systems and methods are disclosed for identifying relationships between complex datasets and / or high-dimensional datasets for predictive modeling. The method includes clustering data associated with one or more entities in a first dataset based on distance data; clustering the data associated with the one or more entities in a second dataset based on longitudinal data; consolidating the first dataset and the second dataset into a third dataset based on weights assigned to one or more edges between one or more nodes in the first dataset and the second dataset; generating a diagnosis space indicating a condition of the one or more entities based on the third dataset; and determining, via input of the diagnosis space into a machine learning model, an optimization of a weighting scheme for assigning weights to one or more features within the longitudinal data.

The invention provides a disease population middle-aged and elderly category structure prediction method based on gray component prediction modeling, which comprises the following steps: collecting multi-component elderly population structure data influenced by a specific disease, and analyzing component data features; building a modeling framework integrating a time elastic mechanism and component structure analysis according to the data features; establishing a novel dynamic nonlinear gray component prediction model of multi-parameter combination optimization adaptive to the irregular time sequence component data based on the framework; and gray component prediction model parameters are solved, and the structural evolution of the old-age disease crowd with each component is estimated, so that the problems of old-age category structure prediction and health management of the disease crowd based on small sample sequence modeling are solved. According to the method provided by the invention, the proportion change rule of the old people in different health states of the disease population can be accurately described, so that the health management personnel can more accurately grasp the change trend of the old people in the disease burden, and thus a more reasonable resource allocation and intervention strategy is formulated.

The invention discloses a rolling time domain reactive power optimization method and system containing a distributed photovoltaic power distribution network, and the method comprises the steps: firstly, employing a probabilistic prediction model to carry out the prediction of photovoltaic active power, and obtaining a future output expected value and an uncertainty interval; secondly, the prediction result is substituted into a multi-objective optimization problem with line loss, voltage deviation and reactive compensation as optimization objectives, and opportunity constraints are established by using the uncertainty interval so as to ensure the safety margin of the power grid voltage; and finally, performing rolling solution on the problem by adopting a multi-objective evolutionary algorithm guided by a power grid sensitivity index to obtain an optimal reactive compensation scheme. According to the method, through a closed-loop rolling mechanism of prediction, modeling and solving, prospective, collaborative and robust control of reactive power resources is realized, and the stability and economical efficiency of operation of the power distribution network under high-proportion photovoltaic access are improved.

A digital documentation system for preparation of engineering documents utilizing one or more artificial intelligence (AI) algorithms is provided. The system includes a user interface for selecting and populating templates with data, and one or more AI algorithms for creating and recommending templates, and preparing documents based on the recommended templates. The system uses natural language processing and semantic analysis algorithms to understand the content of the templates, documents, and associated engineering data, and to generate and recommend relevant templates to the user based on user prompts. The system also uses machine learning and predictive modeling and decision-tree algorithms to assist with the preparation of documents, by generating suggestions for data fields and values based on the user's previous inputs and the overall context of the document and available engineering data, including model data and metadata from digital models accessed in a zero-trust framework.

A system monitors impression data from a plurality of media channels including attributes of content presented on a respective media channel. The system inputs the impressions data and conversion data into a machine learning predictive model. The machine learning predictive model is trained by determining an impact of historical impression data on historical conversion data for each media channel. A machine learning predictive model incorporates an impressions / conversions predictive model that generates coefficients to measure attribution of different channel / campaign combinations to predicted conversions. The machine learning predictive model also incorporates an optimization model to effectively allocate marketing budget among various channels and campaigns in order to realize incremental conversions. The optimization model utilizes a constrained optimization framework based upon user-inputted budgets and budget constraints. Disclosed mixed media marketing predictive modeling provides a better understanding of budget allocation strategy for mixed media marketing factors.

The invention discloses an asphalt concrete structure performance quantitative mapping method fusing multi-source parameters, and particularly relates to the field of road engineering materials, and the method comprises the following steps: S1, selecting asphalt concrete test pieces with uniform gradation and the same cementing material type and compaction mode, and carrying out a loading test by adopting a semicircular bending-tensile test, a UTM test system is combined with a DIC system to obtain mechanical response indexes including a macroscopic peak load Fmax and a microscopic maximum level principal strain Exxmax, and a test piece mechanical property response database is constructed; and S2, performing high-resolution image acquisition on the section of the test piece by using a digital image processing technology, and combining gray enhancement, edge detection and morphological operation. According to the method, the technical problems that structural parameter analysis is isolated, a coupling mechanism between parameters is missing, the prediction modeling capability is insufficient, and performance optimization cannot be performed under a fixed material system can be effectively solved.

The invention discloses a mountain land low temperature refined monitoring prediction method and system based on satellite-ground fusion and deep learning, and belongs to the technical field of ecological meteorological monitoring and agricultural disaster prevention and reduction. The invention aims to solve the problems of insufficient mountain low-temperature monitoring space coverage, neglect of local factors, rough prediction resolution and poor terrain adaptability in the prior art. The method comprises the steps of multi-source data acquisition, high-density meteorological station, multi-source satellite and meteorological mode data acquisition, spatial-temporal feature analysis, correlation analysis, key variable screening and weather type association, satellite-ground fusion air temperature reconstruction, generation of refined monitoring data based on a CNN-ANN deep learning framework, and short-term and temporary prediction modeling. And LSTM is combined with a terrain attention mechanism to construct a prediction model, and two-dimensional reliability verification is carried out. According to the method, the mountain low-temperature monitoring precision and the predicted terrain adaptability can be improved, accurate support is provided for low-temperature disaster prevention and reduction of mountain economic crops, and the method has remarkable practical value.

The invention discloses a dynamic unbalance force prediction modeling method and system for a pneumatic control valve element, and relates to the technical field of fluid control, and the method comprises the steps: constructing an initial physical information neural network model; constructing a loss function of the initial physical information neural network model according to the weighted sum of the data fitting item and the physical constraint item; and optimizing the initial physical information neural network model based on the loss function, and gradually increasing the weight of the equation residual loss in the physical constraint term, the dynamic balance data fitting term and the physical constraint term to obtain the physical information neural network model with real-time dynamic unbalance force prediction. According to the method, the loss function is constructed through the weighted sum of the data fitting item and the physical constraint item, model optimization and dynamic adjustment of the weight ratio of the data fitting item and the physical constraint item are carried out in sequence, the real-time dynamic prediction capability of the unbalance force of the valve element is further enhanced, the calculation efficiency is greatly improved while the prediction precision is guaranteed, and the method is suitable for large-scale popularization and application. And a new technical means is provided for dynamic performance prediction and design optimization of the pneumatic control valve.

The invention discloses a multi-energy management control method for a hybrid power system, and the method comprises the steps: S1, multi-source information processing, S2, working condition prediction modeling, S3, energy distribution optimization, S4, control execution and state monitoring, and S5, model and parameter adaptive adjustment. Future working conditions and required power are accurately predicted through multi-source information fusion and an LSTM model, and a prospective basis is provided for energy distribution. A dynamic weight multi-objective optimization algorithm is adopted, fuel consumption, battery SOC and emission indexes are planned as a whole, an optimal power distribution scheme is solved, and the energy efficiency and the environmental protection property are remarkably improved. Meanwhile, the temperature change rate of the component is calculated in real time through a heat flow evolution algorithm, a cooling system is dynamically adjusted, and precise heat management is achieved. The system further introduces a multi-dimensional deviation closed-loop correction mechanism, key parameters are adaptively adjusted through feedback data, and efficient, stable and reliable operation under different working conditions and environments is ensured.

The invention discloses a power equipment operation abnormal behavior prediction system based on big data analysis, and the system comprises a data collection module which is used for collecting multivariable operation monitoring data; the data preprocessing module is used for preprocessing the multivariable operation monitoring data; the sliding window construction module is used for generating an input window and a prediction target; the improved prediction modeling module is used for constructing a neural network structure formed by stacking task decomposition type structured basic blocks in sequence and outputting a prediction component and a reconstruction component respectively; the comparative learning modeling module is used for extracting hidden state representation; the multi-target prediction module is used for outputting a main task and an auxiliary task based on the prediction output vector; the frequency domain residual detection module is used for generating a reconstructed time domain residual sequence; and the abnormal score fusion module is used for outputting an abnormal judgment result and corresponding early warning information. The method is suitable for stability monitoring and intelligent early warning scenes of new energy equipment under complex working conditions.

The invention provides an NFC information interaction and management method for an intelligent signboard of power equipment, and the method comprises the steps: extracting field problem feedback data from an obtained synchronous data flow, carrying out the mode recognition and priority sorting of the feedback data through a support vector machine algorithm, and determining a high-priority problem list; according to the determined high-priority problem list, a deep neural network algorithm is adopted to carry out prediction modeling on list data, the future equipment fault trend is judged, and a predictive maintenance suggestion data set is obtained; the obtained predictive maintenance suggestion data set is fused with the real-time interaction content, a closed-loop feedback instruction is generated in a background system, and guidance information update for field operation is obtained; and extracting verification parameters from the obtained guidance information update, performing integrity verification on the parameters through a hash function, judging the reliability of the updated data, and obtaining the finally confirmed closed-loop management information.

The invention provides an interpretable text classification method based on large model concept generation, and relates to the field of natural language processing. In the training stage, firstly, stable and interpretable concept features and corresponding dimensions are extracted and marked for each sample through a large model, so that a task-aware concept system is constructed; and then coding each labeled sample to carry out prediction modeling to obtain a text classification model with high interpretability. In the reasoning stage, firstly, experience samples are screened for new samples on the basis of a screening strategy combining dual semantic consistency and sample diversity enhancement; and then marking concepts of new samples and dimensions corresponding to the concepts through a large model by utilizing a task-aware concept system and an experience sample, and then feeding back a marking result to a text classification model to finish final prediction. According to the method, the processing efficiency and the prediction accuracy of the text classification task are improved, the transparency, the stability and the business controllability of classification model output are enhanced, and application scene requirements with relatively high interpretability requirements are met.

The present invention is directed to a software-based technology system for managing and executing high volumes of work on complex projects across multiple organizations involving multiple users that results in superior outcomes at significantly reduced time and cost. Litigation is the initial application of this invention; each case is handled as a project. As applied to litigation, the system of the invention empowers a novel method of end-to-end case assessment, planning, execution and management by integrating tools, processes and procedures allowing for more informed decision-making and deliberate execution of all case-related actions as well as enhanced coordination and communication among all constituents, resulting in efficient achievement of targeted outcomes. The system provides intuitive, menu-driven functionality for inputting, processing and utilizing vast amounts of information, including company and case-specific information, attorney discretionary evaluation and input, document templates and monitoring and reporting requirements. A threat algorithm cross-correlates via multivariate analysis critical data points with customized company-specific information and business logic to generate a numeric threat score as an output. The system also predicts the expected settlement range with a high degree of precision for a specific case as the output of one or a combination of multiple artificial intelligence (AI) / machine learning algorithms. The system then generates a unique case strategy (which includes an expected outcome, including projected outcome, Case Plan and estimated attorneys' fees and costs). System logic learns from thousands of examples of similar cases and directs highly effective and efficient execution of a specific Case Plan providing each attorney and staff member assigned a role in a case with a prioritized task list that is updated in real time as other users complete tasks and litigation priorities change. For each user, the system integrates assigned tasks across multiple cases and multiple client portfolios into a single, prioritized task list. The execution features become increasingly valuable given the volume and complexity of projects across multiple organizations and users, allowing users to focus on their area of expertise and avoid the wasted time and distraction of trying to determine what they should be working on or recording notes to communicate what they have been doing since the system automatically performs these functions and directs the various users' next steps while monitoring their progress against the plan. Integration of administrative functions, including automated time tracking, billing and reporting without the need to rely on users to update this information, further increases quality and efficiency of legal services. Key objectives of the system of the present invention include eliminating gaps between business objectives and litigation strategy and optimizing communication and coordination of case-related tasks and priorities in a fully automated fashion, which are all achieved by leveraging data and technology to enable a fundamentally different approach that becomes smarter and more precise via machine learning and predictive modeling.

The invention discloses a power load optimal value prediction method based on an improved raccoon algorithm. In the prior art, the problems of population convergence degradation, easy falling into local optimum and insufficient global search performance in high-dimensional load prediction modeling are difficult to solve. According to the method, after a power load prediction model and a power load prediction error objective function are constructed respectively, the power load prediction model and the power load prediction error objective function are processed through a raccoon algorithm to obtain an optimal load prediction value under the maximum number of iterations; the power load prediction error target function is initialized according to the improved raccoon algorithm, fitness values of all individuals in the target function are obtained through calculation, after current optimal individual parameters are determined and reserved from the fitness values of all the individuals, the improved raccoon algorithm is secondarily utilized to update the optimal individual parameters, and the optimal individual parameters are obtained. And after the position of the optimal individual is correspondingly determined, the iteration times of the parameters of the optimal individual are judged.

The invention provides a mechanism model and data driven air compressor energy consumption hybrid estimation method and system, and relates to the technical field of industrial energy conservation and intelligent control. The method comprises the steps that firstly, a large number of obviously irrelevant characteristic quantities are rapidly removed through Pearson correlation analysis, and a set is obtained; capturing a nonlinear relationship by using a random forest feature analysis method, and comprehensively mining potential features to obtain a set; a correlation analysis result is taken, and an optimal feature subset is prepared for subsequent modeling; on the basis that a core mechanism model framework is reserved, a Lasso intelligent algorithm is used for learning and compensating for residual errors which cannot be covered by a mechanism model, and air compressor energy consumption prediction modeling is achieved. The hybrid model has high precision and strong generalization ability; meanwhile, the model is lightweight, calculation is efficient, and a real-time control system can be embedded conveniently.

The invention provides an asphalt material softening point prediction modeling method based on an infrared spectrum, and belongs to the technical field of road engineering material performance prediction. The method comprises the following steps: collecting infrared spectrum data of a multi-source asphalt sample and carrying out standardization pretreatment; fusing and extracting functional group quantitative features, wavelet multi-scale features and principal component dimension reduction features; constructing a high-stability feature subset by adopting a progressive feature optimization strategy guided by a physical mechanism; a self-adaptive Stacking fusion model is constructed and trained, the model integrates four base learners including PLSR, SVR, random forest and gradient boosting regression, and Bayesian ridge regression is used as a meta-learner to realize uncertainty quantification of a prediction result. The method can quickly output the predicted value of the softening point without a physical test, solves the technical problems of low efficiency and poor consistency of a traditional method, and is suitable for production quality control, on-site quick detection and formula optimization of asphalt materials.