1795 results about "Dynamical optimization" patented technology

The invention provides a large model lightweight reasoning deployment method under limited hardware resources, and the method comprises the steps: quantifying the weight importance of a large model through a composite index of gradient sensitivity and activation frequency, and carrying out pruning operation in combination with an improved index weighted moving average strategy, thereby obtaining a structured sparse model; the sparse model is divided into sub-networks by adopting double rules, a routing decision network is trained, and an adaptive feature shunting architecture model is constructed; a multi-precision weight set is generated through a nested quantization technology, quantization bit width is dynamically adjusted, and edge equipment hardware parameters are adapted to complete reasoning environment initialization; after a reasoning request is received, an optimal sub-network is selected based on the trained routing decision network, corresponding weights are loaded in parallel, and a reasoning result is fused and output; and converting a reasoning result format, and dynamically optimizing a scheduling strategy based on a system real-time monitoring index. The method is compatible with a mainstream large model and a hardware platform, and an efficient and universal deployment scheme is provided for end-side AI engineering landing.

The invention discloses a key place-oriented abnormal behavior intelligent identification and pre-processing system, which is characterized in that a preliminary abnormal event sequence is generated by collecting multi-modal environment data, the preliminary abnormal event sequence and a preset scene knowledge graph are subjected to semantic fusion to form composite abnormal event description information, and then a dynamic processing plan is generated based on large language model reasoning; the central scheduling agent is decomposed into a cooperative control instruction set to drive the video analysis agent, the broadcast grooming agent and the security and disinfection linkage agent to execute cooperative processing operation, situation evolution information is generated in a shared event canvas through environment feedback data, and dynamic optimization and adjustment of a processing strategy are achieved. According to the system, the whole process intelligence of the abnormal event from identification to disposal is realized, the semantic understanding ability of the system to a complex scene and the multi-agent collaborative response efficiency are improved, and the pertinence and the adaptive adjustment ability of a disposal plan are enhanced.

The invention relates to the technical field of ecological restoration, discloses an ecological restoration planning monitoring method and system based on a multi-source data technology, and aims to solve the problems that in existing ecological restoration monitoring, dynamic change perception of an ecological system is insufficient and restoration planning management is lagged due to static discretization and multi-source heterogeneous data integration deficiency of a traditional means. According to the invention, through constructing a multi-source heterogeneous data acquisition and preprocessing module, a multi-modal data fusion feature extraction module, an ecological system dynamic state modeling evaluation module, an ecological restoration planning dynamic optimization module and a real-time monitoring and effect evaluation module, closed-loop management is realized through feedback. According to the technical scheme, traditional monitoring limitation can be overcome, deep data fusion is achieved, planning dynamic optimization and decision accuracy are improved, and scientificity and effectiveness of ecological restoration are remarkably improved.

The invention discloses a zeolite adsorption and desorption integrated treatment system, and particularly relates to the field of zeolite separation treatment, and the zeolite adsorption and desorption integrated treatment system comprises a process sensing module, a dynamic partition control module, a global optimization control module and a cooling regeneration module. According to the zeolite adsorption and desorption integrated treatment system, the problem of blind operation in the traditional technology is solved through the process sensing module, a data basis is provided for dynamic partition, the intelligent monitoring level is improved, and the performance of an adsorbent is fully exerted; the problem of non-uniform heat and mass transfer of a bed layer is effectively solved through the dynamic partition control module, the desorption heat utilization efficiency is improved, and meanwhile, the service life of an adsorbent is prolonged; a dynamic optimization function is constructed through the global optimization control module, energy consumption, solvent recovery income and stability are comprehensively considered, self-adaptive adjustment of operation parameters is achieved, the energy consumption is reduced while the processing efficiency is guaranteed, and the environmental benefits are remarkably improved.

The invention relates to the technical field of chip design, and discloses a chip dynamic power consumption scheduling method and system based on an intelligent algorithm. The method comprises the following steps of: firstly, acquiring instruction stream data operated by a chip in real time, extracting a feature vector comprising an instruction dynamic change vector and context associated data, and determining a power consumption prediction mapping parameter according to the feature vector; and when the parameter exceeds a preset threshold value, an accurate power consumption prediction result is generated by adjusting the weight of the convolutional neural network. Subsequently, a synchronous timing demand is calculated based on the instruction switching frequency and the data dependency, and an initial power supply configuration is determined. By monitoring task load classification signals, the power consumption distribution proportion is adjusted when the signals are lower than a threshold value, the optimized power supply configuration is obtained, and the improvement index of the resource distribution efficiency is calculated according to the optimized power supply configuration. And finally, according to the index, dynamically adjusting a limiting condition of a scheduling period, and forming a self-adaptive optimization framework, thereby realizing accurate prediction and dynamic optimization scheduling of the chip power consumption.

The invention discloses a steam turbine safe operation health assessment method and system, and belongs to the technical field of steam turbine monitoring. The method comprises the following steps: acquiring running data of a steam turbine in real time through a multi-source sensor network deployed on key components of the steam turbine; the method comprises the following steps: preprocessing original operation data of a steam turbine by adopting edge computing equipment to generate a time domain waveform analysis diagram or a time sequence analysis diagram; transmitting the preprocessed structured feature data to an operation and maintenance management platform, inputting a fault diagnosis model for analysis, pre-training through a historical fault case library, and aligning feature distribution of the historical case library and current equipment data through a domain adaptive algorithm in transfer learning; and inputting a diagnosis result into a self-adaptive dynamic evaluation model based on a reinforcement learning engine, dynamically adjusting a model weight and an alarm threshold according to real-time working condition parameters, outputting a health score and a maintenance decision, and forming a closed-loop process of perception-edge processing-cloud diagnosis-dynamic optimization-decision output.

The invention relates to a rock slope support model construction scheme generation method and device, equipment and a medium. According to the method, a three-dimensional geological model fusing geological information and rock mass parameters is constructed, an initial damage field is obtained in combination with micro-seismic monitoring data and statistical learning inversion, and then a constitutive model capable of reflecting the damage and plastic coupling evolution law is established and calibrated; the model is used for dynamically predicting a spatio-temporal evolution path of a potential slip plane in the excavation process, the supporting opportunity and position are accurately judged based on the stress and damage state in the path, a spatio-temporal sequence scheme is generated, and finally optimal supporting parameters are solved through the multi-objective optimization model. And finally, a set of dynamic support construction scheme capable of actively controlling damage development and giving consideration to safety and economical efficiency is integrated and output, technical spanning from passive reinforcement to active intervention and from static design to dynamic optimization is achieved, and the accuracy and reliability of slope support are effectively improved.

The invention relates to the technical field of multi-modal data processing, and discloses a multi-modal data analysis method, which comprises the following steps: carrying out data cleaning and preprocessing on multi-modal data by adopting dynamic noise detection, cross-modal standardization and meta-learning driving methods; performing cross-modal feature fusion and analysis on the multi-modal data subjected to data cleaning and preprocessing through potential association between dynamic weight distribution and graph neural network mining modes to obtain a fusion feature vector with high feature association degree; obtaining a multi-modal large model through lightweight training and field fine tuning, and inputting the fusion feature vector into the multi-modal large model to obtain a multi-modal decision result; and displaying a multi-modal decision result, carrying out dynamic optimization and iteration on the multi-modal decision result, and adjusting and optimizing parameters of the multi-modal large model through a real-time evaluation and feedback mechanism. The method breaks through the efficiency and precision bottlenecks of existing multi-modal data analysis, and has the advantages of high efficiency, robustness and expandability.

The invention discloses an autonomous decision-making system of a multi-level intelligent agent in an urban area and an operation method thereof. Each end-side decision-making unit broadcasts an equipment state variable to a side-side decision-making unit; the side decision-making unit determines a global reference state and generates a control instruction of each end decision-making unit; after the equipment executes the control instruction, each end-side decision-making unit updates an equipment state variable according to the real-time operation data of the equipment, and when an abnormal event is judged to occur, a side decision-making unit predicts a decision-making variable of each piece of equipment based on a collaborative optimization model of an equipment target and an urban area target; the cloud regulation and control platform predicts a global consistency variable based on the collaborative optimization model of all the side decision units; predicting a regulation and control instruction of each side decision-making unit according to a global dynamic optimization target under a system operation constraint; and the side decision-making unit decomposes the regulation and control instruction into the control instruction of each end decision-making unit, so that the problems that the global cooperative capability of the urban regional integrated energy system is weak and cooperative scheduling is not timely under extreme events are solved.

The invention relates to a fabricated building management method and system based on BIM and digital twinning. The method comprises the steps that a BIM project model is constructed; generating project plan information; building a project digital twinborn model based on the BIM project model and the project plan information; driving a project flow process to be executed; receiving feedback information of the Internet of Things to perform space-time constraint rule verification, and driving state evolution update of the digital twin model; when the risk information is recognized, the risk type is judged, and an adaptive regulation and control strategy is executed; according to the method, a bidirectional mapping mechanism of the BIM project model and the digital twinborn model is constructed, time-space constraint verification and state evolution updating are carried out on the construction process in combination with real-time data of the Internet of Things, an adaptive regulation and control strategy is triggered when the risk is identified, real-time monitoring and dynamic optimization of the whole process of the fabricated building are realized, and the construction efficiency is improved. The method has the advantages of improving the collaboration of the construction process, reducing the rework rate and guaranteeing the project progress and quality.

The invention relates to the technical field of gift packaging three-dimensional modeling, and discloses a construction method of a gift box packaging design three-dimensional model. The method comprises the following steps: collecting natural language description, a freehand sketch image and a physical material attribute parameter; analyzing a natural language to construct a design intention map, and analyzing a sketch to generate a geometric feature code; performing knowledge alignment fusion on the two to form enhanced design semantic representation; generating an initial three-dimensional design framework by using a generative design algorithm; material parameters are integrated, compatibility simulation test is carried out, parameter self-adaptive adjustment circulation is started according to a feasibility evaluation report, and component parameters are dynamically optimized; and rendering and outputting a final model. Through deep fusion of multi-modal design information and preposed dynamic optimization of physical attributes, the accuracy of design intention expression and the producibility of a three-dimensional model are improved, and automation and intelligentization of a design process are realized.

The invention discloses a real-time quality monitoring method based on a production process parameter dynamic optimization model, relates to the technical field of intelligent quality monitoring, and solves the technical problems of empirical parameter adjustment and insufficient pertinence of exception handling. The method captures time sequence association of process parameters, process variables and quality indexes through a dynamic optimization model, quantifies uncertainty in combination with a probability density function, avoids limitation of a fixed threshold value, realizes early warning accuracy through deviation degree grading, reduces false alarm and missing alarm, screens core influence parameters based on model feature importance, and improves early warning accuracy. Quantitative adjustment suggestions are generated in combination with historical cases and inversion calculation, and empirical operation is replaced; multiple parameters are ranked and adjusted according to influence degrees, coupling interference is avoided, a single-point problem and a linkage problem are distinguished through parameter association chain analysis, a processing flow is formulated in a targeted mode, the single-point problem focuses on local repair and rapid recovery, the linkage problem focuses on cutting off a conduction chain and radically treating the source, and invalid intervention is reduced.

The invention relates to the technical field of online education, and discloses an online course learning management method based on a knowledge graph. The method comprises the following steps: acquiring multi-modal learning behavior data of a learner, and extracting a deep learning state vector reflecting knowledge understanding depth, learning input degree and cognitive confusion through semantic fusion; and dynamically calculating and updating the logical relationship strength among the knowledge points in the course knowledge graph by using the vector, so that the knowledge structure can adaptively evolve along with the actual cognitive state of the learning group. And generating a real-time personalized learning path based on the updated knowledge graph and the current state vector of the learner. Meanwhile, according to cognitive confusion features in the state vector, intervention measures such as pushing of remedial resources, adjusting of content sequence or starting of self-adaptive testing are triggered in real time. According to the method, the dynamic optimization of the knowledge graph and the accurate and immediate response of learning intervention are realized, and the adaptability and management efficiency of online learning are improved.

The invention discloses an energy consumption optimization management method and system for compressed air of an energy storage aquifer, and relates to the field of energy consumption optimization management.The method comprises the steps that an initial adjustment frequency threshold value is set by dynamically selecting regulation and control parameters, the adjustment effect is verified through a model, and equipment maintenance or replacement is automatically triggered when the threshold value is exceeded; the timeliness and the accuracy of exception processing are obviously improved; further setting a monitoring period, circularly executing data acquisition and parameter adjustment, combining real-time monitoring of maintenance cost and working time length data, dynamically optimizing an adjustment strategy and recording historical data when a threshold value is exceeded, and finally constructing a total maintenance cost-working time length mapping model to realize continuous optimization; besides, by introducing a second threshold maximum adjustment frequency and a sensor redundancy mechanism, when the adjustment does not reach the standard, a standby sensor is automatically added, and the optimization process is repeated, so that the reliability of data acquisition and the stability of the system are effectively enhanced.

The invention relates to an engineering construction stage user multi-dimensional demand analysis system and method, and the system comprises a multi-modal semantic model construction module which integrates a multi-source knowledge base, and extracts triple description statements from the provisions of the multi-source knowledge base to construct an engineering object ontology knowledge graph; the demand structured guidance and intelligent analysis engine module dynamically identifies an engineering stage and a user role, guides a user to perform text demand input, and performs semantic completion and standardization processing; the demand conflict detection and coordination correction module is used for detecting conflicts in user demands and generating a conflict influence analysis report and a coordination processing scheme; the intelligent drawing and dynamic optimization module is used for automatically drawing according to the triple obtained through demand analysis; and the demand analysis visualization and flow closed-loop module is used for generating an executable parameterized demand document and an association chart, and completing demand-design-verification engineering closed-loop management, so that intelligent analysis and standardization of user multi-dimensional demands are realized, and the system has the advantages of high efficiency, accuracy and intelligence.

The invention discloses a dynamic routing parameter efficient fine tuning method and system based on LoRA-MoE, and relates to the technical field of large model fine tuning. The method comprises the following steps: firstly, constructing a heterogeneous expert architecture-based LoRA module pool based on a multi-field data set; and secondly, coding the hidden layer features of the task through a dynamic gating network, realizing continuous differentiable expert activation, and improving the balance of expert allocation by adopting temperature attenuation and entropy regularization constraint. And then, dynamically selecting and carrying out weighted fusion on a plurality of LoRA parameter increments according to task semantics in a reasoning stage, so as to realize low-cost model adaptive updating. Finally, the module pool is continuously optimized through the confusion degree and manual evaluation feedback, low-efficiency modules are automatically eliminated, and a new LoRA module is generated to maintain task coverage. According to the method, the accuracy and generalization ability of the model in a complex scene can be remarkably improved on the premise of ensuring light weight, and rapid adaptation and dynamic optimization of a large model under a low-resource condition are realized.

The invention provides a rock mineral analysis test management method and system, and the method comprises the steps: collecting rock mineral sample multi-modal data, and constructing a digital twinborn model; constructing a geological knowledge map, and injecting and fusing the two knowledge to generate a virtual test data set; performing self-supervision pre-training by using the data set to obtain a self-adaptive mineral phase recognition model; deploying the model to a block chain-Internet of Things double-chain traceability system to obtain an identification result and an optimization instruction; and executing a sample preparation process and removing unqualified samples. According to the method, diffusion steps are adjusted through adaptive noise scheduling and a space-time alignment algorithm, data are integrated, a high-reality-sense virtual test data set is generated, and a self-supervised pre-training and knowledge distillation technology is combined, so that the model has space-time feature extraction and dynamic optimization capabilities; and finally, full-process closed-loop control is realized through a double-chain traceability system and a modular robot, and the recognition precision of a complex scene is improved.

The invention relates to the technical field of land reserve, in particular to a multi-source integration and dynamic updating method and system for land reserve data, and the method comprises the steps: obtaining multi-source land data, constructing a unified space-time database through hierarchical coordinate fusion, and achieving the data integration. And then, land parcel ownership characteristics are extracted, compliance evaluation is completed, and policy change data are synchronously analyzed to generate planning constraints. Idle risk assessment is carried out based on spatio-temporal data and policy constraints, land value fluctuation is predicted, and accurate valuation data is obtained through idle risk weighted correction. And finally, according to risk assessment and policy constraints, a low-efficiency land taking strategy is generated, all data and strategies are uploaded to a management platform in real time, value abnormal block marking and land reserve dynamic optimization tasks are executed respectively, and full-process closed-loop management from data integration to intelligent decision making is realized.

The invention discloses a CFD calculation method and system based on a neural network and adaptive parameter optimization, and belongs to the technical field of computational fluid dynamics. Initializing a flow field by reading calculation parameters and a grid file; solving the N-S equation, recording solving parameters and outputting an intermediate flow field; inputting the intermediate flow field into a pre-trained physical constraint neural network, sequentially applying boundary condition hard constraint and soft constraint based on control equation residual error, and outputting a corrected flow field; based on the convergence dynamic characteristics and the solving parameters, outputting a parameter adjustment amount through a strategy network of reinforcement learning training, and dynamically optimizing the solving parameters; and taking the corrected flow field as an initial flow field of the next iteration step, updating solving parameters, and circularly executing until convergence. According to the method, the physical prior is embedded into the neural network, intelligent self-adaptive regulation and control of solving parameters are realized through reinforcement learning, and the prediction precision and convergence efficiency of complex flow simulation are remarkably improved.

The invention discloses a multi-agent debate-based content auditing optimization method, which comprises the following steps of: 1, acquiring and preprocessing multi-source content data: integrating to-be-audited content and associated context data, and constructing a comprehensive and reliable input data basis through standardization processing and quality verification; 2, intelligent agent role design based on domain knowledge: designing a specialized intelligent agent role in combination with audit scene characteristics, and injecting a domain knowledge module to enhance the understanding ability for complex semantics and rules; and step 3, a multi-agent debate and dynamic optimization framework: adopting a debate stream and arbitration stream parallel multi-agent debate optimization framework, mining deep semantics through multiple rounds of structured debate, and combining a dynamic arbitration mechanism to integrate multi-party viewpoints. According to the method, accurate identification, fair judgment and efficient processing of complex contents are realized through multi-agent structured debate and a full-process optimization mechanism.

The invention discloses an adhesive tape binding self-adaptive control method based on harness size real-time feedback, relates to the technical field of automatic control management, and is used for solving the problem of insufficient stability in an adhesive tape binding process. According to the method, a closed-loop control flow of multichannel data acquisition, state identification and control adjustment is constructed, accurate identification and response of size sudden change, edge offset and tension abnormity in the binding process are realized, a control target is generated through gray box prediction and scene identification, and time delay compensation and phase alignment are completed by adopting equivalent advance, so that the accuracy of the binding process is improved. Under the condition that the bandwidth is limited or the time delay fluctuates, stable parameter issuing is ensured through event-driven communication and instruction beat calibration, meanwhile, hysteresis and minimum retention time mechanisms are introduced, so that a control strategy has the anti-disturbance capability, and finally, a control closed-loop result is used for dynamic optimization of a material and environment parameter library and strategy rule entries. And a continuous self-learning mechanism is constructed, so that the binding quality stability and the equipment adjustment accuracy are improved.

The invention discloses a power distribution network cluster local control method and device, equipment and a medium. The method adopts a cloud edge end three-level collaborative architecture, and comprises the following steps: acquiring electrical parameters through a terminal equipment layer; constructing a graph model based on an electrical distance at the edge calculation layer; performing initial cluster division and issuing on the cloud computing layer; dynamically optimizing cluster division in an edge calculation layer through a lightweight deep reinforcement learning model; local control strategies such as voltage reactive power cooperative control, frequency active power balance control and fault rapid isolation and self-healing are executed based on the final division. The system comprises a terminal device layer, an edge computing layer and a cloud computing layer. According to the method, decoupling of global optimization and local real-time control is realized through cloud-side cooperation, the problems of high data processing pressure, high communication delay, expanded local fault influence range and the like of centralized control are effectively solved, and the real-time performance, reliability and disaster resistance of the power distribution network are remarkably improved.

The invention belongs to the technical field of ship course control, and discloses an unmanned sailboat sail-rudder cooperative active-disturbance-rejection course control method based on ESO, and the method comprises the following steps: building a nonlinear course motion mathematical model; designing a self-adaptive tracking differentiator to smooth the expected course; the course, the yawing angular velocity, the sail aerodynamic moment and the comprehensive disturbance are observed in real time through ESO; based on a nonlinear state error feedback control law, in combination with the output of the tracking differentiator and the observed value of the ESO, generating a rudder torque control quantity, performing constraint processing on the rudder torque control quantity, and outputting a rudder angle instruction; and a dynamic optimal sail angle is decided according to the lift-drag ratio parameter, the apparent wind speed and the relative wind angle of the sail aerodynamic model corrected in real time, and a sail angle instruction is generated after the dynamic optimal sail angle is compensated and constrained by combining the course deviation. The adaptive capacity to the time-varying wind field and the model uncertainty is enhanced, and the anti-interference performance and the energy efficiency of the system are improved through dynamic optimization and compensation of the sail angle.

The invention provides an intelligent progress management and control method and system for information engineering supervision, and relates to the technical field of information, and the method comprises the steps: pushing early warning information to a first-party system and a second-party system through message middleware, collecting a feedback state to complete closed-loop cooperative processing, and updating a processing result to a central database; based on the central database, combining historical project data, performing pattern recognition analysis to extract a progress deviation rule, and dynamically optimizing a plan node threshold and buffer time of a subsequent stage according to the progress deviation rule to obtain an optimization strategy; and on the basis of the optimization strategy, constructing a configurable progress management and control template library, so as to quickly adapt and generate a corresponding progress management and control node and an early warning threshold value in the new-type project. According to the invention, a full-process closed-loop management system from data integration, intelligent optimization to dynamic adaptation is constructed, and the fundamental transformation of project progress management and control from passive response to active prediction and from experience driving to data driving is realized.

According to the efficient water treatment system based on the reverse osmosis membrane and the control method provided by the invention, gradient anti-pollution membrane arrangement and reconfigurable intelligent waterway design are creatively combined, so that a foundation is laid for high-flux and low-pollution operation from a physical structure; meanwhile, a full-closed-loop intelligent control system is constructed, and by fusing fuzzy logic, an optimization algorithm and a neural network prediction model, the system can integrate multi-dimensional information such as inlet water quality, membrane pressure difference and water yield, judge pollution risks in real time and adaptively and seamlessly switch among a high recovery mode, a segmented flushing mode and a prediction cleaning mode, so that the system is high in recovery efficiency and high in reliability. Meanwhile, parameters such as pump frequency and valves are dynamically optimized to find an optimal balance point of recovery rate and energy consumption; according to the invention, the recovery rate can be stably improved, the membrane pollution rate is greatly reduced, the chemical cleaning period and the service life of the membrane element are prolonged, and finally, the comprehensive operation and maintenance cost of the system is remarkably reduced while the water treatment efficiency and the water quality safety are improved.

The embodiment of the invention provides an intelligent recommendation method and system based on child digital picture book reading. The method comprises the following steps: constructing a recommendation model based on self-supervised learning and a convolutional neural network CNN; in the self-supervised learning module, feature representation of a comparison mechanism optimization model combined with user cognition is introduced; constructing a dynamically updated user portrait, wherein the user portrait comprises a current cognitive level label of the user; in response to a reading request of a user, self-adaptive fusion is carried out on a user portrait and the reading request, an age-worthiness evaluation factor of the picture book is introduced in the fusion process, and the age-worthiness evaluation factor is determined based on the matching degree of the character difficulty, the picture complexity and the user cognitive level of the picture book. And taking the fused label vector as the input of a trained recommendation model to obtain a recommendation list. According to the embodiment of the invention, the feature representation of the model is dynamically optimized in combination with the cognitive development stage of the user, the reading ability difference of different age groups is accurately adapted, and the recommendation accuracy and adaptability are improved.

The invention discloses a photovoltaic station unmanned aerial vehicle three-dimensional autonomous route planning method and system based on deep reinforcement learning, and belongs to the technical field of unmanned aerial vehicle autonomous navigation. The method comprises the following steps: constructing a grid map based on three-dimensional point cloud data of a photovoltaic station, and generating an initial path population by adopting a segmented intermediate transition point strategy; the core innovation lies in that deep reinforcement learning and a genetic algorithm are deeply fused, crossover variation strategy selection of a deep Q network dynamic optimization genetic algorithm is constructed, and a multi-target reward function is designed; experience playback and a target network mechanism are combined in training to improve stability; and finally, deploying the lightweight model to an unmanned aerial vehicle system to realize real-time autonomous flight integrating online re-planning and multiple safety barriers. According to the method, the problems of slow convergence, poor quality and insufficient real-time performance of path planning in a complex environment are solved, and the inspection efficiency and safety are remarkably improved.

The invention discloses an intelligent equipment life cycle information fusion operation and maintenance optimization method, and relates to the technical field of intelligent equipment fusion operation and maintenance, and the method comprises the following steps: based on a judged nested task execution state, extracting state jump features from state data of load, current, vibration and the like collected in an equipment operation process, calculating state change amplitude, duration and frequency by using a time sequence window comparison algorithm, and obtaining a state hopping feature set associated with task switching; and based on the task level mapping table and the state jump feature set, constructing a graph convolutional neural network model, taking a nesting relationship between tasks as a topological structure, inputting each task node and the corresponding state jump feature into the model, and identifying each stage of the life cycle of the intelligent equipment. According to the method, the problem that life cycle division is affected by nested tasks is solved, and accurate state recognition of the intelligent equipment and dynamic optimization of operation and maintenance parameters are realized.

The invention relates to the technical field of intelligent wharfs, in particular to a wharf container truck dynamic optimization scheduling method and system combining machine learning and path planning. Comprising a behavior data acquisition and feature coupling unit; a learnable incentive and behavior guide unit; a scheduling demand prediction unit; and a path planning and scheduling unit. According to the method, on the basis of the coupling characteristics, the excitation coefficient is optimized through reinforcement learning, the excitation instruction is dynamically pushed, and targeted guidance of the non-operation staying behavior of the container truck is achieved; according to the method, based on standardized time series data, an association rule of a historical staying period and a working condition is learned through an LSTM model, a prediction result is optimized in combination with real-time data, a prospective constraint basis is provided for scheduling, and meanwhile, a time, space, resource and priority multi-dimensional path constraint system is constructed through a structural causal model; container truck-berth matching and dynamic path planning are completed by matching with an improved A * algorithm fused with dynamic weights, and scheduling conflicts are effectively avoided.

The invention discloses a coal mine intelligent ventilation optimization regulation and control method and system based on digital twinning, and belongs to the technical field of coal mine safety ventilation. The method comprises the following steps: determining a three-dimensional space topological relation of a coal mine ventilation system based on mine structure data, and mapping real-time ventilation state data to corresponding roadway nodes and branch paths to obtain a twin ventilation state; and performing simulation calculation based on a three-dimensional space topological relation to obtain a theoretical ventilation distribution state, comparing the twin ventilation state with the theoretical ventilation distribution state, determining an air volume deviation region and a gas concentration abnormal region, and obtaining ventilation deviation characteristics to perform virtual rehearsal. Determining an adjustment scheme meeting the ventilation demand constraint and the energy consumption constraint, and generating an optimization regulation and control instruction; and the entity ventilation facility is controlled to execute the adjustment action, and the three-dimensional space topological relation is updated through feedback data. Accurate regulation and dynamic optimization of the ventilation system are achieved, and the safety and the energy-saving effect of coal mine ventilation are improved.