1014 results about "Neural net architecture" patented technology

The invention relates to the field of road traffic, in particular to a multi-feature fusion fatigue driving detection method and a fatigue driving detection system. The method comprises the following steps: extracting facial features from a face image of a driver; extracting vehicle features from the vehicle driving parameters of the vehicle driven by the driver; and fusing the facial features and the vehicle features to judge whether the driver is in fatigue driving. Extracting facial features by designing a CNN model; extracting basic convolution features; extracting local convolution features; extracting global convolution features; performing pooling operation; aggregating global features; and carrying out dimensionality reduction mapping. A self-encoder is designed to extract vehicle characteristics; a symmetric deep neural network structure is adopted, and high-dimensional time sequence data is compressed to a low-dimensional potential space through nonlinear mapping; through combination and matching of the CNN model and the auto-encoder, the technical defects of feature redundancy, noise interference, information loss and suboptimal decision existing in an existing multi-feature fusion fatigue driving detection system are thoroughly solved.

The invention discloses an integrated energy system economic dispatching model method based on deep reinforcement learning, and the method comprises the steps: constructing a park equipment environment model, and carrying out the mathematical description of a park integrated energy system low-carbon economic dispatching problem through taking economy and carbon emission as targets; secondly, the scheduling problem is expressed as a Markov decision process framework, and a state space, an action space and a reward mechanism of the system are reasonably designed; then, a near-end strategy optimization algorithm is adopted to carry out low-carbon economic dispatching decision making, and an action noise dynamic updating strategy is provided to gradually improve the exploration capability and learning capability of a network model; according to the method, the action space, the state space, the reward mechanism, the neural network structure and the like of the intelligent agent are designed in detail, the minimization of the system operation cost is considered on the basis, and a deep reinforcement learning method is adopted for scheduling simulation. The method provided by the invention can perform optimal scheduling according to the load demand of the system, and has good scheduling performance and self-learning ability.

The invention relates to the technical field of exception prediction, in particular to a storage cabinet exception trend prediction system based on time series data analysis, which comprises a state monitoring module, an interval sensing module, a path reconstruction module, a symptom activation module and an evolution prediction module. According to the method, the state vectors including the temperature, the voltage, the current and the door lock state are constructed and combined with the timestamp information to form the time sequence data sequence, and the dynamic expression mode of state change is established; a jump characteristic is analyzed by using a ratio of a time interval to a state change amplitude, a short-time disturbance path and a trend evolution path are distinguished by combining a jump rate statistical index, and an evolution activation signal is identified based on trend maintenance and non-fallback characteristics. On the basis, a neural network structure with long-time dependent learning ability is introduced to capture an aperiodic thermal anomaly trend in a state sequence, and the accuracy and timeliness of anomaly recognition are improved through multi-dimensional parameter cooperative processing and path construction logic.

The invention discloses a power plant equipment fault prediction method based on a time sequence large model, and the method comprises the following steps: S1, collecting and preprocessing the time sequence data of a multi-source sensor of a power plant, and generating a standardized time sequence data set; s2, constructing a time sequence large model, inputting standardized data, and outputting a future operation state predicted value; s3, comparing the running state prediction value with an actual measurement value to generate a prediction residual sequence; s4, constructing a Bayesian neural network model, inputting a prediction residual sequence, and outputting error probability distribution; s5, optimizing a Bayesian neural network structure and hyper-parameters by adopting an ant colony optimization algorithm; s6, confidence interval estimation is executed, and whether the state is a high-risk state or not is judged; and S7, outputting a running state label, and dynamically acquiring a data closed-loop updating model. According to the invention, high-precision prediction and uncertainty evaluation of the operation state of the power plant equipment are realized, so that the accuracy and response time efficiency of fault early warning are improved.

The invention discloses a reinforcement learning method and system for source network load storage collaborative multi-scene optimization, and the method comprises the steps: constructing a power distribution network optimization model with the minimum cost, and converting a mixed integer nonlinear problem into a solvable mixed integer second-order cone optimization problem; converting a mixed integer second-order cone optimization problem into a reinforcement learning decision model, and performing multi-round assignment on boundary condition parameters by using different operation scene data to form a multi-scene training task set; designing a reinforcement learning decision model multi-scene training loss function, combining the reinforcement learning decision model to construct a strategy neural network, an evaluation network neural network and a scene representation embedded neural network, and completing reinforcement learning decision adaptive to multi-scene optimization; and training a power distribution network multi-scene optimization decision model based on the multi-scene training task set, the multi-scene training reinforcement learning loss function and the neural network structure, and deploying the power distribution network multi-scene optimization decision model to an actual system to complete reinforcement learning decision model application oriented to source network load storage collaborative multi-scene optimization.

The invention belongs to the technical field of urban water supply, and relates to an urban real-time water supply flow prediction method and system and a water supply scheduling method and system.The prediction method comprises the steps that environmental parameters of historical and prediction time points and historical water supply flow monitored in a pipe network SCADA system are obtained; the current water supply flow in the pipe network SCADA system is monitored in real time; preprocessing historical water supply flow and historical environmental parameters, constructing a data set, and dividing the data set into a training set, a verification set and a test set; constructing a water supply flow prediction model based on an LSTM neural network structure, and performing training and verification through the training set and the verification set; and inputting data in the test set into the water supply flow prediction model to obtain predicted water supply flow. The scheduling method is based on the predicted water supply flow and the current water supply flow, and the water supply flow is increased and decreased by opening and closing the water pump or combining the water pump characteristic curve to adjust the water pump operation frequency. The water supply flow can be accurately predicted, and water supply optimal dispatching is achieved.

The invention discloses a dual-mode communication signal identification method based on deep learning, relates to the technical field of communication signal processing, and aims to solve the problems that a simple neural network structure is generally adopted in a traditional deep learning algorithm, the attention of a model to important features is insufficient, gradient disappearance is likely to occur and the like. The method comprises the following steps: S1, signal acquisition and preprocessing are carried out; s1.1, receiving a signal; receiving a dual-mode communication signal from the intelligent traffic communication system; in an intelligent traffic communication scene, communication signals come from vehicle networking communication among vehicles, communication between the vehicles and road infrastructures, communication between a traffic management center and traffic nodes and the like; s1.2, carrying out adaptive sampling; an advanced self-adaptive sampling technology is used for sampling; the technology dynamically adjusts the sampling frequency and the number of sampling points according to the characteristics of signals. The method has the advantage of improving the processing capability and the recognition precision of the model on complex features.

The invention discloses a tight reservoir three-dimensional crustal stress field modeling method based on an improved neural network. The tight reservoir three-dimensional crustal stress field modeling method comprises the steps that S1, a unified-format multi-source geological physical data tensor set is constructed; s2, constructing a frequency domain hierarchical enhancement-SIREN implicit neural network structure based on the unified format multi-source geological physical data tensor set; s3, inputting the candidate hyper-parameter configuration into the frequency domain hierarchical enhancement-SIREN implicit neural network to complete one-time model training; s4, aiming at each candidate hyper-parameter configuration, initializing an inner-layer population of the black widow optimization algorithm, completing second model training, and obtaining an optimal model parameter of the frequency domain hierarchical enhancement-SIREN implicit neural network; s5, tight reservoir fracturing parameter optimization and real-time safety window adjustment are achieved. According to the method, the continuous stress field can be quickly generated at the resolution of 1 m, real-time well section updating and fracturing scheme optimization are supported, and the fracturing transformation effect, the fracturing safety margin and the reliability of economic productivity prediction are remarkably improved in practical application.

The invention discloses a lithium battery residual life prediction method and system and terminal equipment, and relates to the technical field of lithium battery health management. The method comprises the following steps: receiving a battery capacity attenuation sequence as an original input sequence, detecting and filtering abnormal data by adopting a 3 sigma criterion, and carrying out noise suppression processing on the battery capacity attenuation sequence through a Dropout mask; and carrying out normalization processing on the preprocessed battery capacity attenuation sequence, dividing the battery capacity attenuation sequence into a training set, a verification set and a test set through a sliding window algorithm, and generating a time sequence characteristic matrix and a corresponding residual service life label. According to the method, a neural network structure fusing trend prior perception and dynamic attention regulation is constructed, a multi-scale capacity modeling strategy is introduced to separate a degradation trend, fluctuation disturbance and high-frequency noise, and compared with a traditional time sequence neural network or a single attention model, pseudo fluctuation characteristics caused by capacity regeneration can be more effectively recognized, and the method is more efficient and more reliable. And the judgment accuracy of the model in a complex degradation scene is improved.

The invention discloses an image classification method of a hybrid quantum neural network model based on PQC, and belongs to the technical field of quantum computing. On the basis of a classic neural network structure, a classic convolutional layer is replaced by the parameterized quantum circuit, the trainable parameter quantity in the network structure is reduced, the designed entangled structure Ub is added in the parameterized quantum circuit, and the feature capture capability of the structure and the learning efficiency of the whole network are improved. A mixed quantum neural network architecture is utilized, a corresponding entanglement structure Ub is designed according to a given label sample and acts on a parameterized quantum circuit, and the entanglement structure Ub is combined with a classification module formed by a classic matrix product state network structure; the feature extraction capability of the parameterized quantum circuit structure and the performance of the overall network structure are continuously improved, so that a better classification effect is achieved, prediction is performed on a test set to evaluate the model performance, and finally parameter optimization and iterative updating in the model are performed by using a classical optimization method. And a hybrid quantum neural network structure with excellent performance can be obtained. Compared with an existing network structure, the performance is improved well.

The invention discloses a millimeter wave SAR icing thickness inversion algorithm based on deep learning, and aims to solve the problems of insufficient icing monitoring precision and poor real-time performance under complex meteorological conditions. According to the algorithm, high-quality input is provided for deep learning modeling through data preprocessing including slope distance correction, polarization denoising, back scattering characteristic extraction and data enhancement. A multi-branch deep neural network structure is adopted for feature extraction, and in combination with a Swin Transformer V2 trunk, a Gated MLP module, cross-modal attention fusion and physical consistency constraint, the adaptability of the model to millimeter wave SAR data and multi-modal input is improved. Meteorological parameters and line operation data are integrated through multi-modal data fusion, and model robustness is enhanced. Finally, an icing thickness prediction value is output through real-time reasoning, intelligent early warning is triggered in combination with confidence analysis, end-to-end real-time response is achieved, the intelligent level of safe operation of a power grid is remarkably improved, and the method has wide application value.

The invention relates to the technical field of artificial intelligence and information propagation analysis, and discloses a deep learning-based network information trend prediction method and system.The deep learning-based network information trend prediction method comprises the steps of performing neural architecture search through combination of an evolutionary algorithm and reinforcement learning; an optimal neural network structure suitable for different types of network information is automatically found; dynamic reconstruction of a model structure is realized through an environment perception and event triggering mechanism; according to a deployment environment resource constraint, adopting an importance-perceived neuron self-adaptive pruning technology; turning point features in network information propagation are specially extracted and enhanced; knowledge migration from a large-scale high-precision model to a lightweight model is realized; an online learning and continuous optimization mechanism is adopted to prevent disastrous forgetting; according to the method, the key turning point of network information propagation can be accurately predicted, the prediction accuracy is improved, the early warning time is shortened, and the computing resource consumption is reduced.

The embodiment of the invention provides a mobile tower crane border crossing detection method and device. Tower crane design drawing data are imported into a virtual simulation engine, a three-dimensional model is constructed, and warning tape marks are set. A physical engine is creatively utilized to simulate tower crane moving tracks under different working conditions, and a border crossing behavior data set is generated based on intersection-to-union ratio calculation. A deep neural network structure is constructed, a trunk feature extraction module and a target detection module are included, and model parameters are optimized through a cross entropy loss function. According to the method, the limitation of traditional mechanical limiting and manual monitoring is broken through, real-time intelligent monitoring of the movable boundary of the tower crane is achieved, and reliable technical support is provided for safety management of a construction site.

The invention relates to the technical field of industrial robot control, and discloses an industrial robot trajectory optimization control method based on an intelligent algorithm. The method comprises the steps that joint position information, tool center point coordinates and a motion time sequence when a robot executes multiple tasks are collected and stored in a track database; after cleaning and screening data, extracting a feature set containing a path point sequence, speed distribution and an acceleration contour; constructing an intelligent optimization algorithm model of a neural network structure, and training by using the feature set to learn a trajectory optimization strategy; analyzing a target position coordinate and a motion constraint condition of the current task to obtain an initial track parameter; and inputting the initial parameters into the trained model, outputting an optimized track sequence containing a path point list and a speed curve, and generating a control instruction to drive the robot to move. The method can adapt to different tasks, improves track rationality and motion stability, and fits industrial production practice.

The invention belongs to the technical field of fluid velocity pressure field deduction, and discloses a fluid velocity pressure field deduction method and system based on a fusion network. The method comprises the following steps: obtaining a flow field information data set required by training by utilizing a computational fluid dynamics method; a KAN network is constructed; constructing a fusion network based on the KAN and the PINN; and the constructed training set is used for training of the constructed KAN and PINN-based fusion network, verification is carried out by using the verification set, and finally a flow field deduction result is obtained. According to the method, the neural network data set is established, the KAN type neural network structure is constructed, and the neural network is constrained by using the fluid-related physical equation, so that the values of the speed and the pressure in the flow field are predicted in real time, the surrounding flow field condition can be predicted in real time in the ship traveling process, and speed and pressure field deduction can be performed for a specific fluid domain.

The invention relates to the technical field of data analysis and processing, in particular to an identity data analysis method based on a spatial frequency sensing fusion network, and the method specifically comprises the following steps: collecting identity data to be detected, and marking real identity information; preprocessing the collected identity data, and dividing the collected identity data into a training set and a test set in proportion; constructing a spatial frequency sensing multi-scale network for real-time deep identity analysis, and training the network; inputting the identity data in the test set into the trained network for forgery detection and prediction, and outputting a probability score that each identity is true or false so as to obtain an identity analysis result. By constructing a lightweight deep neural network structure which combines space and frequency feature perception and has a multi-scale fusion capability, the method can be used for efficiently detecting identity information in actual scenes such as video conferences and social media.

The invention discloses a microseismic source positioning method, device and system, and a storage medium. The method comprises the following steps: dividing a microseismic data sample data set into a training set and a test set; according to the training set, constructing a microseism inversion subnet containing a Swin Transform encoder, and according to the training set, constructing a microseism inversion subnet containing a Swin Transform encoder; the micro-seismic forward modeling subnet realizes seismic wave field continuation by inputting a micro-seismic source position and a speed model and utilizing a recurrent neural network structure and a convolution operator, and establishes a forward modeling subnet based on a wave equation; constructing an inversion-forward modeling closed-loop neural network according to the micro-seismic inversion subnet and the forward modeling subnet based on the wave equation; and inputting the test set into the inversion-forward closed-loop neural network to carry out micro-seismic source positioning. By adopting the technical scheme of the invention, the limitations on physical constraint, feature modeling and anti-noise capability in the prior art are overcome.

The invention discloses a tunnel lining steel frame recognition method based on GAR-Net and related equipment, spatial domain enhancement is performed on geological radar data to improve the robustness of a neural network structure, a GAR-Net network model is constructed, the network model comprises a mileage recognition model, a lining thickness recognition model and a steel arch recognition model, and the mileage recognition model, the lining thickness recognition model and the steel arch recognition model are used for recognizing a tunnel lining steel frame. The lining thickness recognition model and the steel arch recognition model perform lining thickness recognition and steel arch recognition on the basis of the mileage recognition model respectively, whether a tunnel lining steel frame has defects or not can be judged according to the lining thickness and positioning information of the tunnel steel arch, and the defects of traditional radar image interpretation are overcome. The method can achieve the automatic recognition of the tunnel steel arch and lining thickness, and remarkably improves the precision and recognition efficiency of the automatic recognition of a geological radar image.

A medical code allocation method based on hierarchical association and diversity enhancement comprises the following steps: S1, data preprocessing and graph construction: based on a tree hierarchical classification architecture of ICD codes, adopting a hierarchical graph model to perform visual representation on the tree hierarchical classification architecture, and constructing a co-occurrence matrix of the clinical record text and the ICD codes for the clinical record text; s2, applying a Graph-BERT graph neural network structure to perform graph structure conversion on a tree structure of an ICD code system, and learning based on an encoder structure of a graph transformer to obtain embedded representation of ICD codes; s3, performing word segmentation processing on a clinical text, inputting the processed clinical text into a bioBERT model to obtain a feature vector of the clinical text, and unifying semantic features of clinical records, hierarchical features of ICD codes and related association information between the semantic features and the hierarchical features through a multi-modal fusion mode; s4, after the final feature vector of the clinical record text is obtained, correlation enhancement prediction is performed by using a CorNet network, so that a related probability matrix is generated, a binary cross entropy loss function is expanded, the binary cross entropy loss function, hierarchical diversity loss and semantic diversity loss jointly form a diversified loss function, and the diversified loss function and a classic model are subjected to comparative analysis, so that the final feature vector of the clinical record text is obtained. Therefore, the accuracy and effectiveness of the method are verified.

The invention discloses an automatic driving system extreme environment decision-making method based on a neural evolutionary game. The method comprises the following steps: S1, collecting and constructing a real-time environment data set around a vehicle through an automatic driving system; s2, generating an environment feature vector; s3, based on the environment feature vector, analyzing the environment feature data through an extreme environment identification module; s4, activating a corresponding multi-target dynamic reward mechanism based on the extreme environment label, and setting a dynamic reward weight for the neural evolution process; s5, gradually evolving to generate an optimal neural network structure and parameter configuration suitable for different extreme environments; s6, generating a multi-target game strategy in combination with the environment feature vector; s7, generating an optimal driving path, vehicle speed adjustment, obstacle avoidance mode and direction control decision; and S8, inputting real-time feedback data into the neural evolution model, and further adjusting the structure and parameter configuration of the neural network. The automatic driving system can make a safer, more accurate and more efficient driving decision in an extreme environment.

The invention relates to a basin flood simulation optimization method based on a physical information neural network, and aims to construct a basin flood acceleration solution mode based on PINNs, and ensure the continuity and the physical characteristics of mass conservation during model operation, and the method comprises the following steps: simulating basin flood by using an urban flood space-time simulation model; obtaining a data set required for constructing the physical neural network; physical rules are integrated and simplified into limiting conditions, so that integration of a neural network structure is facilitated; establishing a partial differential equation (PDE) used for describing river flood routing, and taking the partial differential equation as a loss function of the physical information neural network model; constructing and training a PINNs drainage basin flood model constructed on the basis of a CNN (Convolutional Neural Network); and establishing a model evaluation index and performing evaluation. The method has the beneficial effect that the speed and precision of basin flood simulation are improved.

Aspects of the present disclosure provide methods and apparatuses for learning an artificial intelligence or machine learning (AI / ML) model over a self-organized topology to enable heterogeneous neural network structures in distributed AI / ML training processes. The method comprises: a first node receives a first AI / ML model from a second node and transmits the first AI / ML mode and a model collection indicator to one or more nodes associated with the first node. The first node receives reports related to respective associated AI / ML models of its associated node(s) and generates, based on the reports, a second AI / ML model having a neural network (NN) structure equivalent to that of the first AI / ML model. However, the AI / ML models of the first node's associated node(s) may have NN structures that differ from the NN structure of the first and second AI / ML models.

The invention relates to an underwater target detection method based on a pulse neural network, which can realize underwater target detection with high precision and low power consumption. By fusing the cross-stage partial network and the YOLO architecture, the problem of pulse degradation is effectively solved, and the feature extraction capability of the model is enhanced; in order to solve the problem of underwater noise interference, the pulse-based underwater image denoising method is designed, only integer addition is used in the method, a pulse neural network structure can be seamlessly embedded, and the quality of a feature map is enhanced; in order to solve the problem that a traditional normalization method is low in precision in the spiking neural network, separate batch normalization is provided, by independently normalizing a feature map in multiple time steps and optimizing a residual structure, the time dynamic state of the SNN can be effectively captured, and the detection precision is improved. The network shows excellent performance in underwater target detection, and compared with an artificial neural network of the same scale, the network has higher performance and lower energy consumption.

The invention discloses an end-to-end image lossless compression method based on two-dimensional inseparable wavelet transform. According to the method, the image is decomposed through multistage wavelet transform, and sub-band coefficients of different sizes are obtained. And inputting the coefficients into an entropy coding model, and using a context model to drive an arithmetic encoder to compress the coefficients into a bit stream. According to the method, two-dimensional inseparable wavelet transformation is adopted, a lifting structure of the wavelet transformation is used, three prediction filters and an updating filter are included, and the filter structure is a convolutional neural network structure. The entropy coding module also uses a neural network structure. Carrying out the overall optimization of all parameters through deep learning, training the network until convergence, and achieving the lossless compression of an image through a trained model. The end-to-end image lossless compression method shows excellent performance in the aspect of lossless compression, is remarkably improved compared with a traditional JPEG2000 lossless compression method, and is also superior to an end-to-end image lossless compression method based on traditional separable wavelet transform.

The invention relates to the field of machine vision and image recognition, and particularly discloses a smoke detection system, which comprises a data preprocessing module used for carrying out normalization, data enhancement and clipping and zooming on an input image to obtain preprocessed image information; the feature extraction module is used for performing feature extraction by using a convolutional neural network structure, generating multi-scale feature representation, obtaining a feature extraction image, and obtaining a multi-scale feature fusion image through a multi-scale feature fusion technology in combination with feature maps of different levels; and the CBAM attention mechanism module comprises a space attention sub-module and a channel attention sub-module, and the space attention sub-module is used for enhancing features of an important space region in the multi-scale feature fusion image according to a space attention mechanism. By adopting the technical scheme of the invention, real-time detection can be realized on resource-limited equipment in a lightweight and efficient manner, and the method has high recognition accuracy for small-target and dynamically changing smoke in a complex scene.

The invention discloses a skin cancer focus segmentation method based on a discrete neural memory ordinary differential equation, and the method comprises the steps: determining the form of a basic differential equation in a model, and collecting an image data set; discretizing a neural memory ordinary differential equation by applying Taylor formula derivation, and preliminarily screening the collected skin disease data set; discretizing the neural memory ordinary differential equation by using a linear multistep method; according to a neural network structure, a neural memory ordinary differential equation which is derived by applying a Taylor formula and discretized by applying a linear multi-step method is changed into a proper form, and a second-order Taylor method decoder and a linear multi-step method decoder which are suitable for the U-shaped network are designed; and embedding the decoder into a U-shaped network to form a skin cancer focus segmentation model, and inputting the augmented data set into the model for training. According to the method, the problems of high complexity and high calculation cost of the existing medical image segmentation model are solved, the model performance is not damaged, and the method is a lightweight scheme with high compatibility and high transferability.

The invention provides an oil and gas reservoir geological modeling method and system based on deep learning, and the method comprises the steps: obtaining multi-source typical geological data of different reservoirs according to the classification of a reservoir geological knowledge system, and inputting the data in a formulated storage data format; a geological knowledge management system is designed and established according to different types, dimensions and scale characteristic functions of data, a geological data knowledge base corresponding to a reservoir is constructed, mining of various geological knowledge information is carried out by using deep learning in combination with the constructed integrated digital outcrop, a training image library, a sample library and a prototype model data set are constructed, and the data are subjected to data processing. Creating a neural network structure, and designing a loss function to train a target neural network model, so as to generate a matched reservoir three-dimensional geologic model based on the earthquake and wellbore data of the required reservoir; the problems that in the prior art, sample data are difficult to obtain, and the accuracy of a geologic model is limited by the sample scale are solved, the sample library is enriched in a multi-level mode, and a basis is provided for high-quality convolutional neural network training.

The invention discloses a low-sample neural network structure reliability evaluation system and evaluation method, and relates to the technical field of engineering structure safety monitoring, and the evaluation system comprises a cloud server which is used for constructing a recurrent neural network model containing a static variable embedding mechanism, completing model training and converting a model format; the edge calculation terminal is used for receiving and preprocessing real-time data of the sensor, executing multi-step prediction to output a future time period response sequence, and calculating a future failure probability through virtual Monte Carlo simulation; the sensor assembly is used for collecting structure state time sequence data; and the communication module is used for realizing data interaction and alarm signal transmission operation. According to the method, collaborative modeling of time-varying and static uncertainty is realized by adopting a static variable embedded recurrent neural network model, failure probability distribution is generated at an edge computing terminal in combination with a virtual Monte Carlo technology, failure risk prediction in a future time period is supported, and real-time and accurate reliability early warning can be realized in a resource limited scene.

The invention provides a method for predicting tunnel excavation water inflow through horizontal drilling, and relates to the technical field of tunnel construction water inflow prediction.The method comprises the steps that water inflow time sequence data and geological parameter data are obtained; calculating the permeability coefficient of the position where each monitoring point is located according to the water inflow time sequence data by using a Goodman formula based on rock integrity correction; decomposing the water inflow time sequence data to obtain a plurality of intrinsic mode functions and a residual term; forming a training data set; constructing a prediction model comprising a GRU neural network structure and a physical constraint mechanism, training the prediction model by using the training data set until the loss function converges, and obtaining a trained prediction model; and obtaining current monitoring data, inputting the current monitoring data into the trained prediction model, and predicting the water inflow and the water inflow risk level of the to-be-excavated section. According to the method, refined and high-precision prediction of the water inflow in the tunnel excavation process can be achieved, and potential safety hazards caused by coarse-grained prediction of a traditional method are avoided.

The invention discloses a livestock and poultry health state intelligent evaluation method based on multi-sensor fusion and an AI prediction model, and belongs to the technical field of livestock breeding, and the method comprises the following steps: setting multiple types of sensors in a livestock and poultry breeding area, collecting multi-source data such as temperature, humidity, carbon dioxide concentration, ammonia gas concentration, illumination intensity, weight and current, and carrying out the analysis of the data; wherein the weight data is obtained through the weighing platform, and the current data is used for sensing the operation state of drinking, ingestion, ventilation or lighting equipment; various types of sensors such as temperature and humidity sensors, carbon dioxide sensors, ammonia gas sensors, illumination sensors, weight sensors and current sensors are deployed in livestock and poultry breeding areas, all-directional data acquisition of environments and behavior states is realized, and dynamic modeling and feature extraction of key behavior nodes are realized by introducing a deep neural network structure of a gating circulation unit and an attention mechanism.