1286 results about "Model extraction" patented technology

The invention provides an intelligent equipment fault diagnosis and reasoning method and system based on unsupervised learning. Belongs to the technical field of industrial equipment fault diagnosis and prediction. 2) unsupervised abnormal feature extraction and detection; (3) dynamic causal reasoning based on unsupervised learning; (4) a dynamic self-optimization inference engine; (5) intelligent fault reasoning and exploration; (6) enhancing the dynamic knowledge graph; and (7) fault prediction and decision support. Aiming at the problems that a large amount of annotated data is needed, causal analysis is lacked, and multi-source data fusion is difficult, non-annotated efficient detection and classification, fault mode diagnosis, prediction and decision support of equipment faults are realized through feature extraction of an unsupervised depth model, construction of a dynamic causal relationship, and fusion of a real-time self-optimization inference engine and a dynamic knowledge graph; therefore, the downtime and the maintenance cost are greatly reduced.

The invention discloses a multi-modal semantic and physical law driven remote sensing image generation method, belongs to the technical field of computer vision and remote sensing image generation, and aims to solve the problems of insufficient cross-modal semantic alignment, low reliability of a generation result and insufficient physical mechanism fusion. The four-stage method comprises the following steps: firstly, rejecting low-quality samples from original data and unifying a spatial scale; then, extracting a multi-modal semantic vector by adopting a BLIP model and a CLIP model, and introducing a remote sensing physical rule to carry out vector optimization; then position coding and physical constraint conditions are embedded in the submerged space, and multi-source information joint modeling is achieved through a cross-modal encoder; and finally, by taking text description, physical priori knowledge and diffusion time steps as joint conditions, performing de-noising reasoning based on a Transform architecture, and completing back diffusion reconstruction by means of a trans-attention mechanism. According to the method, physical rationality and semantic consistency are improved, and a more reliable technical normal form is provided for remote sensing image generation in the fields of disaster monitoring, military simulation and the like.

The invention discloses a data anomaly detection method based on multi-scale feature extraction, relates to the technical field of data anomaly detection, and sequentially performs multi-source data acquisition and environment calibration, noise robustness multi-scale feature extraction, context awareness anomaly detection and sensor redundancy check, and adaptive feedback and collaborative update decision. Intelligent threshold learning and scene self-adaption are realized; the method comprises the following steps: firstly, acquiring and marking acceleration, current, electromagnetic and other multi-path signals, and constructing an environment label; then, utilizing a TCN and LSTM fusion model to extract short-term impact and long-term trend; according to the elevator working condition and the noise index, the threshold value is dynamically adjusted, and the fault is subjected to redundancy check; the model, the sensor weight and the threshold value are corrected through false alarm and missing alarm backflow; and finally, a monitoring-detection-feedback-updating-self-adaptive closed loop is constructed by means of reinforcement learning or meta learning cross-seasonal adaptation, high precision, low false alarm and high robustness are achieved, and elevator operation safety and maintenance efficiency are remarkably improved.

The invention discloses a semiconductor packaging device electromagnetic compatibility comprehensive test method and system, and belongs to the technical field of electromagnetic compatibility testing. The method comprises the following steps: collecting structure parameters, packaging topology and predefined function states of a to-be-tested packaging device, and constructing a polymorphic working model; establishing a disturbance injection control model according to each state and configuring disturbance source parameters; implementing dynamic disturbance injection and acquiring response data in a real working state of the device; performing time domain and frequency domain conjoint analysis on the response data, constructing an electromagnetic response dynamic feature sequence, inputting the electromagnetic response dynamic feature sequence into a machine learning model, extracting multi-dimensional coupling features and predicting tolerance; calculating performance indexes such as an interference tolerance score and a coupling strength index based on model output indexes, comparing the performance indexes with a standard, and evaluating a compatible risk level in a full state; the method realizes quantitative evaluation of the EMC performance of the packaging device with high reduction degree and multi-state coverage, and has the advantages of comprehensive test, accurate prediction, explainable attribution and the like.

The invention discloses a building elevator detection, diagnosis and decision-making method based on a graph retrieval enhanced agent. The method comprises the steps that 1, elevator detection data are prepared and processed; step 2), knowledge extraction; step 3), knowledge fusion; step 4), visualization and optimization of the knowledge graph; 5) performing graph retrieval enhancement generation; step 6), diagnosing a decision-making agent; according to the method, triple information can be extracted from structural data, text data, visual data and other multi-modal data in the elevator detection field by guiding a multi-modal large model through an elevator detection technical specification, and an elevator detection visual target entity and a text named entity are automatically aligned based on a pre-trained vision-language model; the multi-modal knowledge graph in the field of elevator detection is accurately and efficiently generated, and building elevator detection intelligent diagnosis is carried out on the basis of the multi-modal knowledge graph and the fusion graph retrieval enhancement technology.

The invention discloses a tool wear loss prediction method based on physical information self-supervised learning under the condition of few marks, and belongs to the technical field of numerical control machining center tool wear state prediction. Comprising the steps of collecting monitoring signals such as cutting force, vibration and acoustic emission in the machining process; carrying out preprocessing operation of interception and Z score standardization on each sample; a mixed residual convolutional neural network tool wear monitoring model is designed, and information fusion and high-dimensional representation extraction are carried out on multi-source sensor signals; pre-training the tool wear monitoring model by using the auxiliary task I, and guiding the model to extract the invariance feature of the signal; according to the method, under the condition of scarce marked data, high-precision prediction and excellent generalization ability of tool wear are realized, the fluctuation amplitude of prediction errors can be effectively reduced, and the stability of a prediction result is kept. According to the method, a small amount of mark data is effectively utilized in model training, the stability and reliability of tool wear monitoring are ensured, and the requirements for monitoring precision and adaptability in actual production are met.

The invention provides a multi-mode control method and system for intelligent variable-frequency cooking equipment, and relates to the technical field of intelligent control, and the method comprises the steps: obtaining a food material image and weight data through an image collection device, extracting feature information through a deep learning processor based on a pre-trained food material feature recognition model, and generating a feature data packet containing food material type, weight and volume information. The controller matches initial cooking mode parameters according to the data packet, collects real-time operation data such as temperature, pressure, heating power and stirring motor rotating speed in the cavity, and calculates power-temperature and motor rotating speed-torque response curves. And the controller generates a frequency conversion control instruction according to the response curve and a preset multi-mode switching judgment rule, and controls the heating unit and the stirring motor to perform cooperative adjustment. In the cooking process, real-time operation data are continuously collected, multi-mode self-adaptive switching is carried out, and the frequency conversion control instruction is optimized until cooking is completed.

The invention discloses a role-playing chatting robot implementation method based on a human background big language model, and the method comprises the steps: collecting the text data of a large amount of literature works, extracting role dialogues, actions and abstracts through a big model, and extracting role setting information at the same time; extracting a double-person multi-round dialogue from the role dialogue, and matching with role setting to form a preliminary data set; converting the preliminary data set into a Json format, and constructing a structured multi-round dialogue data set; a LoRA method and a DPO method are adopted to carry out fine tuning on the large language model; building a chat robot based on the fine-tuned large language model, and integrating role information, background stories, historical dialogue abstracts and a small amount of example dialogues to form a dynamic cue word framework; an intelligent chat framework is constructed for a chat robot and comprises a time planning module, an active pushing module and a delayed chat module. By utilizing the method and the system, the dialogue quality, the role personalization, the role consistency, the interaction continuity and the user experience can be effectively improved.

The invention discloses a multi-sensor fusion tunnel smooth blasting monitoring system, and belongs to the technical field of artificial intelligence. The method comprises the following steps: preprocessing and integrating monitored data, constructing a tunnel digital model, and applying a static load and a dynamic load; obtaining a safety critical value of each parameter in the tunnel digital model to obtain a tunnel critical value digital model, extracting each parameter exceeding the safety critical value, generating a tunnel abnormal parameter digital model, and identifying an abnormal mode of smooth blasting by using a random forest algorithm; when the abnormal mode of smooth blasting is related to the interior of the tunnel, reconstructing a tunnel digital model; when the optimization suggestion is related to smooth blasting, new blasting parameters are obtained by using a support vector machine model in combination with expert suggestions; a tunnel-smooth blasting correlation model is constructed, correlation rules are identified, and the influence degree of blasting parameters on tunnel monitoring parameters is evaluated; and searching an optimal blasting parameter combination by applying particle swarm optimization to meet a set optimization target.

The invention discloses a charging robot automobile charging port pose vision measurement method comprising the following steps: 1, controlling a mechanical arm to drive a monocular camera to collect a charging port image, and constructing a charging port image data set; 2, extracting a charging hole contour in each image by adopting an improved Mask R-CNN instance segmentation model; step 3, performing robust ellipse fitting based on each charging hole contour to obtain center coordinates of each charging hole in the two-dimensional image; step 4, establishing a world coordinate system based on charging hole space distribution defined by the automobile charging port standard model, and determining three-dimensional coordinates of each charging hole; and 5, the multi-view two-dimensional center coordinates and the corresponding three-dimensional coordinates are input into the PnP graph optimization model, and the pose of the charging port in the mechanical arm base coordinate system is solved by fusing the re-projection error constraint, the structure prior constraint and the kinematics chain constraint. The invention further discloses a charging robot automobile charging port pose vision measurement charging method and a charging system.

The invention relates to the technical field of geological survey and measurement, in particular to a rock mass anomaly detection method based on vibration and visual data multi-modal fusion, which comprises the following steps: firstly, respectively acquiring vibration data and image data, and then performing data feature extraction and fusion through a deep learning model; specifically, a combined model of a long short-term memory network LSTM and a convolutional neural network CNN is used to extract time sequence features and frequency information of vibration data, a Swinin-T model is used to extract spatial features of image data, and then a shared Transform encoder and a cross attention mechanism are used to realize multi-modal data alignment and fusion. And inputting the fused features into an anomaly detection module for training and tuning, and finally deploying the trained model to edge equipment for anomaly detection of the rock mass. According to the invention, through multi-modal data fusion, abnormity can be accurately identified in various complex environments, so that the probability of false alarm and missing alarm is reduced, and meanwhile, by combining with an edge computing architecture, field deployment and real-time monitoring are facilitated, and the method is suitable for various application scenes.

The invention provides a defect identification method and device for substation equipment and electronic equipment, and relates to the field of image identification. According to the method, an infrared image, an electric field leakage map and a visible light image are obtained through a multi-channel imaging system deployed in a substation site, and a multi-channel image tensor is generated and input into a multi-channel recognition model to extract fusion features. And fusing the features, inputting the fused features into a YOLOv8 backbone network, constructing a joint attention domain in combination with an equipment prior structure, generating a high-confidence candidate box, and performing non-maximum suppression to obtain a detection result. And constructing an inter-frame residual tensor for a detection result to perform time sequence modeling, thereby improving the detection effect. And for equipment with complex shielding, complementing a structure contour through an edge prediction path, and finally outputting target boundary and defect positioning information. By implementing the technical scheme provided by the invention, defect identification of the substation equipment is facilitated.

The invention belongs to the technical field of smart ocean and computer vision, and discloses a cross-modal interaction-based ocean ship image-text positioning method, which comprises the following steps of: constructing a data set; constructing a coding-decoding structure model; extracting a visual feature # imgabs0 # and a linguistic feature # imgabs1 #, and generating a visual feature # imgabs2 # and a linguistic feature # imgabs3 #; fusing the above features to generate a coordinate prior # imgabs4 # and an alignment feature # imgabs5 #, enhancing an object query # imgabs7 # by using # imgabs6 #, and interacting with a multi-modal visual feature # imgabs8 # and a language feature # imgabs9 #; calculating a loss function value, and training for multiple rounds to obtain a final model. According to the method, the single-modal features are associated with other modal features, so that the semantic understanding of the model on visual and language features is improved; coordinate prior is utilized to enhance object query, a discrimination fusion module is introduced to enhance semantic consistency of multi-modal features, and finally efficiency and accuracy of a ship image-text positioning task are effectively improved.

The invention relates to a power grid business intelligent auditing method based on AI enhancement, and the method comprises the following steps: S1, collecting data from a power grid SCADA system and a financial system, integrating historical and real-time data, and constructing an auditing knowledge graph; s2, constructing an instruction recognition model by using RoBERTa to analyze a natural language instruction of an auditor, and combining knowledge graph information with a language model to improve the understanding and reasoning ability of an instruction background; s3, constructing a multi-task deep learning framework to realize processing and fusion of multiple auditing tasks; s4, on the basis of a natural language instruction input by an auditor, extracting query targets, conditions and parameters involved in the instruction according to the instruction recognition model, obtaining corresponding auditing data in the database, and obtaining intention classification; and S5, calling a corresponding auditing model based on the intention classification result and the auditing data, and obtaining an analysis result. According to the invention, efficiency and precision in power grid business auditing work are effectively improved.

The invention discloses an injection molding process fault diagnosis model training method and system based on a large language model and a fault diagnosis method. The model training method comprises the following steps: collecting and cleaning process parameters under the fault working condition of the injection molding machine, converting the process parameters into a natural language text, combining the natural language text with a fault label to construct a textualized data set, and dividing the textualized data set into a training set and a verification set according to a proportion; and in combination with the text data dimension and the fault category number, loading the pre-trained large language model and configuring a diagnosis model structure in a quantitative mode. And inputting the training set into a model to extract semantic features, processing the semantic features by a feature conversion module to generate a high-order feature vector, and inputting a classification head to output a fault category probability. And back propagation is carried out by using a loss function, and model parameters are efficiently and finely tuned in combination with low-rank adaptation and a layered freezing strategy. And repeating training until the performance reaches the standard, and outputting a final diagnosis model. The method is efficient in training, and can effectively reduce the maintenance and use cost of the model.

The invention discloses an industrial defect detection method based on self-supervised fine tuning, and solves the problems of scarcity of industrial scene defect samples and weak model generalization ability. The method comprises the steps that a data set is divided and preprocessed, and the data robustness is improved through size scaling, random luminosity transformation, geometric enhancement and the like; extracting a foreground mask by using a saliency model, synthesizing a Perlin Noise and DTD texture fused pseudo-abnormal image, carrying out self-supervised fine tuning on the ImageNet pre-trained WideResNet-50, and enhancing the industrial data feature extraction capability; a model containing a visual trunk, feature aggregation mapping, noise feature adaptation and a discriminator is established, local neighborhood features are fused through Unfold operation, Gaussian noise is superposed to generate pseudo-abnormal features, and an abnormal score is output by the discriminator after multi-scale fusion. And the training adopts binary cross entropy and focus loss optimization parameters. The innovation points of the method are that self-supervised fine tuning adapts to industrial data distribution, feature aggregation improves fine-grained detection, and multi-scale fusion considers different defects.

The invention discloses a time sequence modeling method for lithium ion battery performance evaluation, and aims to solve the technical challenges of a traditional method in the aspects of multi-scale feature extraction and fusion. The method specifically comprises the steps of obtaining battery capacity data and performing preprocessing; constructing an MTH3 model by combining a time convolutional network and a multi-head attention mechanism on the basis of a Mama model, and performing multi-time scale feature extraction by taking the preprocessed data as input; constructing a NetTDF model based on a U-shaped network, fusing the features extracted by the MTH3 model, and modeling a global relationship; and dividing a training set and a test set, and inputting the training set and the test set into the overall model to obtain a prediction result of the lithium ion battery health state. According to the method provided by the invention, the advantages of each model are fully exerted, an efficient prediction model for the capacity of the lithium ion battery, which can accurately capture local features and effectively model a global relationship, is provided, and reliable support is provided for performance evaluation of the lithium ion battery.

The invention provides a legacy system-oriented large-model-driven API document automatic generation system, belongs to the crossing field of artificial intelligence and software development, and provides a multi-modal data fusion and closed-loop verification mechanism aiming at the defects of a traditional API document generation method in the aspects of semantic comprehension, dynamic context capture and multi-technology stack adaptation. A code static feature and a dynamic track during operation are analyzed through a multi-source data acquisition module, and an interface semantic feature is extracted in combination with a field self-adaptive large model of a semantic enhancement analysis module; deducing an implicit service rule by fusing static / dynamic characteristics through a graph neural network, and generating a standardized document conforming to an OpenAPI specification through a parameterized template generative adversarial network (PT-GAN); and finally, performing three-level verification and closed-loop optimization through a sandbox environment. The method supports a heterogeneous system of 16 programming languages such as Java / C + + / Python, interface version changes can be automatically recognized, document patches are generated, the problems of missing and outdated system documents and low maintenance efficiency are solved, and maintainability and integration efficiency of enterprise-level systems are remarkably improved.

The invention discloses a TSFS sample generation method based on an improved generative adversarial network. The TSFS sample generation method comprises the following steps: step 1, acquiring TSFS data of a sample by using a three-dimensional fluorescence spectrometer; step 2, constructing a CA-WGAN-GP optimization model with a convolution attention mechanism, and performing data enhancement on an original TSFS sample; step 3, in a model training stage, storing generated data once after epoch training for a certain number of times, and enabling a generated sample coverage to have higher diversity by utilizing generator models of a plurality of training stages; 4, extracting enhanced sample features by using a pre-trained CNN model, projecting the sample features by using linear discriminant analysis LDA, and preliminarily screening samples according to a Mahalanobis distance and a set threshold value; and 5, performing secondary screening by using a K-means algorithm to obtain a final training sample set. According to the method, the time-consuming and labor-consuming problem of TSFS sample acquisition is effectively solved, the model over-fitting phenomenon is reduced, and the robustness of unknown data is improved.

The invention discloses a physical information fused aero-engine residual life prediction method, and belongs to the field of neural network residual life prediction. The method comprises the following steps: acquiring sensor data of the whole process from engine simulation operation to fault, and performing standardization and windowing preprocessing; establishing a time-space dual-channel multi-layer perceptron model, extracting time dimension and feature dimension information of the signal, performing self-attention fusion with original data, completing mapping to a life prediction value, and calculating an error with a real life; establishing a physical information neural network model, learning a hidden partial differential equation among a predicted life value, time and a hidden state, and performing error calculation with an equation in an equilibrium state; and performing self-attention fusion with the life error to obtain comprehensive loss so as to continuously train the model until the error is minimum, and finishing final life prediction. Physical information is fused on the basis of the multi-layer perceptron, the complexity of the model is simplified, and the prediction precision of the residual life of the engine is improved.

The invention discloses a regression test case determination method and device, a storage medium and electronic equipment, and relates to the field of artificial intelligence. The method comprises the steps of obtaining a target change code of a target program; the target change code is input into a vector machine model, code features of the target change code are extracted through the vector machine model, a potential defect score of the target change code is determined according to the code features, and the potential defect score is used for representing the probability that the target program is abnormal due to the target change code; and determining at least one regression test case for testing the target change code from the M test cases according to the potential defect score of the target change code, the code feature of the target change code and the case feature of each test case in the M test cases. The technical problem that in the prior art, the efficiency of compiling the regression test case is low is solved.

The invention provides a multi-modal knowledge graph completion model training method, a completion method and equipment, and relates to the field of computer systems based on specific calculation models. The method comprises the following steps of: extracting an image block feature vector, a word feature vector, a structure feature vector, a corresponding visual mark, a text mark and a structure mark by adopting a multi-modal knowledge graph completion model; based on each visual mark, the text mark and the structure mark, acquiring multi-modal fusion feature data of each entity by a graph attention mechanism; and complementing the original multi-modal knowledge graph according to each piece of multi-modal fusion feature data, and calculating the target loss of the complemented multi-modal knowledge graph to optimize the multi-modal knowledge graph complementing model. According to the method, fine-grained multi-modal feature extraction and application can be realized in the completion model training process, the reliability and effectiveness of the completion model training process can be effectively improved, and then the accuracy and reliability of multi-modal knowledge graph completion can be improved.

The invention provides a digital modeling method for enhancing connectivity of a low-porosity rock core, a medium and equipment, and relates to the field of digital modeling of rock cores, and the method comprises the following steps: reconstructing a Gaussian random field based on SAXS data to obtain an initial model of a three-dimensional digital rock core pore structure; extracting pore center points of the initial model, and constructing an initial network connecting all the pore center points; based on a minimum spanning tree algorithm, identifying mutually isolated pore clusters in the initial network, and selecting a most efficient seepage path skeleton connected with the isolated clusters; based on the seepage path skeleton, constructing a throat with fractal characteristics; and according to the total volume of the throat, performing morphological corrosion operation on an original pore area in the initial model, embedding the constructed throat into the corroded model, and then performing controllable morphological expansion operation until the volume variation of the final model is smaller than a preset error threshold. According to the method, the reconstruction precision of the digital rock core in microstructure and macroscopic connectivity is effectively improved.

The invention discloses a large-model-based knowledge graph construction method for the field of medical creativity, and the method comprises the steps: S1, carrying out the standardization of obtained multi-modal original medical creativity data, and obtaining a standardized multi-modal data set; s2, performing feature extraction and cross-modal dynamic feature fusion on the standardized multi-modal data set to obtain multi-modal feature representation; s3, inputting the multi-modal feature representation into a fine-tuned large model, and extracting based on the deep thinking ability of the large model to obtain an entity-relation pair; and S4, constructing or dynamically updating a corresponding knowledge graph in the field of department and wound based on the entity-relationship pair extracted by the large model. According to the method, the deep thinking ability of the large model is utilized to extract the entity-relation pair triad from the multi-mode medical and invasive data to construct the medical and invasive field knowledge graph, so that the accuracy, efficiency and quality of construction of the medical and invasive field knowledge graph are improved.

The invention relates to the technical field of track analysis, in particular to a track application reasoning method and system based on a track pre-training large model, and the method comprises the steps: obtaining a high-precision open-source track data set, cleaning the data set, and constructing a self-supervised training data set; constructing a track pre-training large model for extracting high-dimensional semantic features of the track; based on the self-supervised training data set, constructing a learning loss function to pre-train the track pre-training large model; aiming at a specific track downstream application, constructing a small sample labeling training data set; and cross-domain application training and reasoning are realized based on a small sample labeling training data set. According to the method, the semantic features of the track are extracted by using the track pre-training large model, and cross-domain application training and reasoning are carried out based on cross-domain data, so that the requirement on the number of application labeling samples in special fields can be remarkably reduced.

The invention provides a digital twinning application-oriented electrical equipment electromagnetic heat flow coupling rapid calculation method, and belongs to the technical field of electrical digital data processing.The method comprises the steps that firstly, a three-dimensional model of electrical equipment is acquired and preprocessed, and a full-order electromagnetic heat flow coupling calculation model is established and verified through a temperature rise test; generating an experimental point matrix by using a Latin hypercube sampling method, and constructing a current temperature power density relational data set; performing regional division on the power density field by applying a K-means clustering algorithm, and constructing an electromagnetic response surface model through a radial basis function; establishing a heat flow field order reduction model based on an intrinsic orthogonal decomposition technology, and extracting a dominant mode primary function; bidirectional coupling of an electromagnetic field and a heat flow field reduced-order model is achieved, an improved Lagrange multiplier method and a fixed point iteration method are adopted for processing the nonlinear coupling problem, finally, a software development kit supporting an open platform communication unified architecture protocol is packaged, and the electromagnetic heat flow coupling rapid calculation capacity needed by digital twinning application is achieved.

The invention relates to the technical field of industrial equipment predictive maintenance and asset management, in particular to a machine vision equipment operation and maintenance cost analysis intelligent management method, which comprises the following steps of: acquiring equipment operation state, external environment and historical operation and maintenance work order data through a sensor group and an equipment log interface, and fusing and removing redundancy to form a multi-source data stream; static and dynamic features are extracted by using a pre-trained health state evaluation model and fused by means of an attention mechanism, and a real-time health state index in a 0-1 interval is output; constructing a dynamic cost prediction model, taking health related parameters, spare parts, manpower and depreciation cost as input, and predicting expected operation and maintenance cost of a specific time window in the future; establishing an optimization decision model by taking minimization of the total operation and maintenance cost and maximization of the equipment availability rate as double targets, and generating an optimal maintenance, spare part purchasing and scheduling scheme; and executing the scheme and acquiring actual data, comparing the actual data with a predicted value for feedback, and iteratively optimizing the core model. The operation and maintenance management accuracy and economy are improved, and the method is suitable for intelligent operation and maintenance of the machine vision equipment.

The invention relates to a lithium ion battery life prediction method, and belongs to the field of battery life prediction and intelligent maintenance. The method comprises the steps that S1, a battery capacity degradation sequence is collected, and integrity is checked and normalized; s2, decomposing the sequence by using an improved complete set empirical mode decomposition algorithm, and dividing the sequence into a high-frequency component and a low-frequency component according to a zero-crossing rate; s3, modeling the high-frequency component: fusing multi-scale channel interactive attention, a time sequence convolutional network and a hybrid expert model, and extracting short-term fluctuation and capacity recovery features; s4, modeling a low-frequency component: introducing a two-way gating circulation unit network constrained by a double-index degradation model, and simulating a long-term trend; and S5, constructing a high-frequency migration module through tensor decomposition, improving cross-battery generalization, and fusing high and low frequency results to output a residual life prediction value. According to the method, a dual-channel framework combining signal decomposition, deep learning and physical modeling is combined, the prediction precision and adaptability under complex degradation are improved, and the method is suitable for various battery systems.

The invention discloses a grid-connected photovoltaic power station reverse power protection monitoring method and system, and the method comprises the steps: collecting the time sequence data of each grid-connected node, and carrying out the normalization and time sequence alignment processing; inputting the standardized data into a TimesNet model, extracting time sequence features and predicting a reverse power risk; generating a mathematical expression through symbol regression in combination with historical abnormal data and model output; a protection strategy is generated according to the prediction result and the expression, and the linkage device executes and collects feedback; and the feedback data is used for updating the model and the expression, and a self-adaptive closed-loop control mechanism is constructed. According to the invention, by introducing the time sequence depth model and the symbol regression fusion method, accurate prediction and adaptive protection control of a reverse power event are realized.

The invention relates to a knowledge base construction method, system and equipment based on a large model, and relates to the technical field of artificial intelligence, by adopting the method, system and equipment, a main body and a preset association attribute in original corpus data are extracted through the large model, so that candidate knowledge units associated with the main body and the preset association attribute are obtained through the large model, namely, the candidate knowledge units of the main body and the preset association attribute are obtained. Through flattening redundant storage and knowledge embedding driven by a large model, one-key knowledge unit construction is realized, and dependence of a traditional scheme on a complex association structure is eliminated.