7215 results about "Multiple target" patented technology

The invention provides an industrial environment monitoring and accident prediction method fusing multi-modal data, and relates to the technical field of data processing, and the method comprises the steps: carrying out the semantic collection and causal association preprocessing of multi-modal heterogeneous data collected in real time through constructing a dynamic industrial knowledge graph; a customized deep learning model is adopted to extract deep abstract features of each mode, and weak signals and potential risks are accurately represented and uncertainty is quantified; a high-fidelity digital twin model is utilized to drive a deep reinforcement learning algorithm, and dynamic optimization and verification are performed to generate a multi-level and multi-target preventive intervention strategy combination; an intervention strategy is executed through an edge-end-cloud three-layer collaborative intelligent architecture, and online learning and system sustainable evolution are realized by using a closed-loop data feedback mechanism. According to the method, the sensing and early warning capability of the early weak and complex abnormal state of the industrial environment can be remarkably improved, the accident evolution path is accurately predicted, and credible explanation is provided.

The invention provides an industrial park multi-target collaborative optimization scheduling method and system based on artificial intelligence, relates to the technical field of intelligent scheduling of industrial parks, and aims to establish a digital twinborn model and a dynamic topological graph, perform resource flow relationship modeling by using a graph neural network, and perform resource demand analysis in combination with a multi-model prediction framework. A multi-agent reinforcement learning algorithm is adopted to generate a scheduling strategy, migration from a global strategy to a local decision module is realized through a strategy distillation technology, robustness of the scheduling strategy is simulated and verified in a digital twin model, the strategy is adjusted according to a simulation result, and finally efficient scheduling of park resources is realized. The method effectively improves the intelligentization and collaboration level of the operation of the industrial park, reduces the energy consumption and carbon emission, enhances the ability of the park to cope with complex scenes, and is suitable for the efficient management of the modern industrial park.

Embodiments of the invention provide a task processing method, a task platform, a computing device and a computer readable storage medium. The image processing method comprises the steps of obtaining a task description text of a target task; extracting task elements of the target task from the task description text by using a large language model, determining a plurality of target agents and target skills of the target agents from the candidate agent set based on the task elements, and generating a structured execution protocol corresponding to the target skills of the target agents; based on the structured execution protocols corresponding to the target skills of the multiple target agents, performing dependency analysis on the target skills of the multiple target agents to obtain a skill combination; and scheduling a skill tool corresponding to the skill combination to execute the target task to obtain a task result. The accuracy and the expandability of calling and processing the target task by skills and tools in an open scene are realized.

The invention discloses a portal crane grab bucket control system and method based on multi-sensor fusion, and particularly relates to the technical field of portal crane grab bucket control. Image acquisition equipment and multiple types of sensors are arranged in a portal crane operation area, a multi-dimensional input data set under a unified time sequence is constructed, an optimized visual detection model and an attention mechanism are combined, high-precision recognition and abnormity judgment of the grab bucket state are achieved, and the system not only can automatically plan a grabbing path and a posture adjusting instruction, but also can automatically adjust the grabbing posture of the grab bucket. And control parameters can be dynamically optimized according to the grabbing effect and pose feedback, the grab bucket recognition accuracy, the control stability and the system intelligence level are remarkably improved, and particularly higher robustness and reliability are shown in the small-size, complex-pose or multi-target operation environment.

The invention relates to the technical field of engineering data monitoring, in particular to a hydraulic engineering data intelligent monitoring method and system based on digital twinning, and the method comprises the following steps: collecting real-time operation data through physical sensors disposed at different nodes of a hydraulic engineering; a self-adaptive digital twinborn model capable of being automatically adjusted is generated through a meta-learning method, and the self-adaptive digital twinborn model dynamically adjusts the internal structure of the self-adaptive digital twinborn model according to the change of real-time data; and on the basis of the adaptive digital twinborn model, constructing a simulation module of a plurality of target scenes, and performing decision simulation in a virtual environment in real time. According to the method, the accuracy and the stability of the digital twinborn model in a complex environment are improved, the model can quickly adapt to real-time changes in the operation process of a water conservancy project through the self-adaptive mechanism, and the prediction precision and the response of the model in a dynamic complex scene are improved.

The invention discloses a target echo signal simulation method and system with unmanned aerial vehicle rotor frequency spectrum characteristics, and the method comprises the steps: obtaining an original radar echo signal, carrying out the preprocessing and feature enhancement, and obtaining an enhanced rotor feature signal; sequentially performing dynamic component decomposition, nonlinear phase coupling analysis, adaptive parameter estimation and trajectory prediction to generate probability distribution of a feature trajectory; probability feature space mapping and dynamic feature fusion are carried out to obtain a fusion feature vector; constructing a nonlinear dynamic model, and performing adaptive signal synthesis to generate a synthesized signal; performing quality evaluation on the composite signal to generate a quality evaluation report and an optimization parameter set; based on the quality evaluation report and the optimization parameter set, performing multi-target parameter optimization and monitoring system performance to obtain a performance evaluation result; system parameters are updated, stability analysis is carried out, and a system stability report and regulation and control suggestions are generated. According to the invention, the calculation efficiency and the simulation precision are both improved.

The invention discloses a drilling key parameter automatic regulation and control method based on an improved DDPG algorithm. The method comprises the following steps: collecting and preprocessing drilling data, and constructing a complete data set for training; a drilling speed (ROP) time sequence prediction model is constructed and trained on the basis of a self-attention mechanism (self-attention); building a simulation environment by using the trained ROP prediction model, and defining a state space, an action space and a multi-target reward function of a reinforcement learning DDPG algorithm model; a deep deterministic strategy gradient algorithm (DDPG) is adopted to train a reinforcement learning model, through an Actor-Critic network structure, an intelligent agent learns an optimal bit pressure (WOB) and rotating speed (RPM) regulation strategy in a simulation environment, and dynamic optimization of the drilling speed (ROP) is achieved. According to the method, through automatic and intelligent parameter regulation and control, the efficiency and stability of the drilling process are improved, the drill bit wear rate and the operation cost are reduced, and the method has good adaptability and multi-target optimization capacity and is suitable for drilling operation under the complex stratum condition.

The invention relates to the technical field of power line inspection, and provides a line holographic anomaly detection method and system based on cross-modal intelligent cooperation. The method comprises the following steps: acquiring multi-modal data; performing cross-modal fusion to generate an association tensor; the abnormal joint reasoning uses a time sequence diagram neural network and reinforcement learning to output abnormal confidence; the dynamic knowledge driven decision adaptively adjusts a detection threshold through Bayesian calculation and transfer learning; local real-time response is realized through layered edge calculation; and multi-target collaborative optimization feedback improves the detection precision. The system is composed of a multi-mode perception fusion layer, an intelligent analysis layer, an edge execution layer and an optimization control layer. According to the method, the problems of multi-modal information isolation, response delay and environmental adaptability are solved, and the defect detection rate and the system robustness are remarkably improved.

The invention discloses a power industry robot collaborative inspection and fault self-diagnosis system and method, and belongs to the technical field of power inspection, and the system comprises a management module which receives an inspection task instruction and obtains inspection task information according to the inspection task instruction; the environment identification module is used for acquiring inspection environment data and identifying obstacles; the path planning module is used for generating an inspection path set by adopting a multi-target particle swarm optimization algorithm according to the obstacle and inspection task information; the scheduling module is used for acquiring the state data of each robot and distributing the routing inspection paths in the routing inspection path set to each robot; the fault feature extraction module is used for acquiring multi-sensor data acquired by the robot and generating a fault feature vector; and the fault diagnosis module performs fault analysis on the fault feature vector to obtain a fault risk analysis report. The obstacle is recognized by acquiring the environment data, the inspection path set is generated by combining the inspection task information and adopting the multi-target particle swarm optimization algorithm, and the method can adapt to the complex inspection environment.

The invention provides a directional energy multi-target interference system based on an ultra-wideband phased array technology, and the system integrates signal perception, target recognition, interference signal generation and phased array control, so as to achieve the precise interference of an unmanned aerial vehicle cluster. The signal sensing module scans an airspace target through the ultra-wideband phased-array antenna array and obtains spectrum characteristics of a target signal. The target identification module analyzes signal features, identifies an individual target and predicts a motion track and a communication protocol of the individual target. And the phased array control module calculates and adjusts antenna beam forming parameters, and dynamically controls the radiation direction, phase and transmitting power of the antenna. The interference signal generation module generates a matched interference waveform based on the target communication protocol and the trajectory information. The ultra-wideband phased-array antenna array adopts a digital beam forming technology. According to the invention, efficient and accurate directional energy interference can be realized under multiple frequency bands, the confrontation capability of the unmanned aerial vehicle cluster is improved, and the method is suitable for defense tasks in electronic warfare and complex electromagnetic environments.

The invention relates to the technical field of digital factory production management, and discloses a digital factory-oriented multi-target production plan optimization method and system, and the method comprises the steps: decomposing an enterprise order into a plurality of subtasks through a production task decomposition module, and extracting related information; the resource dynamic evaluation module collects data in real time to generate a resource state matrix; the multi-objective optimization algorithm module constructs a model and adopts an improved non-dominated sorting genetic algorithm to solve; the dynamic priority distribution module adjusts the priorities of the sub-tasks according to the real-time data; and the conflict resolution unit is used for solving resource allocation conflicts. The method can accurately decompose tasks, evaluate resources in real time, collaboratively optimize multiple targets, flexibly deal with abnormities, efficiently resolve conflicts, comprehensively improve the production efficiency and benefits of the digital factory, and effectively solve the complex problems in the production plan making and optimizing process of the digital factory.

The invention belongs to the technical field of multi-target global dynamic production scheduling, and discloses a manufacturing resource dynamic production scheduling data comprehensive processing method, which comprises the following steps: acquiring multi-source heterogeneous data, constructing a field mapping table, constructing an equipment fingerprint database in combination with historical equipment performance data, dynamically adjusting confidence coefficient weight, and further judging an equipment state. Based on an equipment state judgment result, integrating operator report data and multi-source heterogeneous data through a preset rule base trigger event, and generating an abnormal event flow with a context tag; based on the abnormal event type and the equipment state judgment result, a recommendation scheme is constructed through a production scheduling knowledge graph, and a production scheduling instruction set is generated; according to the production scheduling instruction set, generating a local optimization scheme and a global optimization strategy, and forming a final execution scheme; calculating a resource utilization rate and a bottleneck process index through the 3D virtual workshop model, and generating a difference analysis report; according to the method, global resource scheduling and closed-loop iteration are realized, and the production efficiency and the system robustness are improved.

The invention relates to the technical field of navigation and positioning, in particular to an intelligent positioning and navigation early warning system and method for ships and boats. The method comprises the following steps: collecting and carrying out sea condition sensing and positioning signal evaluation according to a multi-source sensor synchronous data set to obtain a sensor reliability score table; performing target motion situation analysis according to the sensor reliability score table to obtain a fusion situation vector diagram; performing target motion state judgment according to the fused situation vector diagram to obtain a target motion state judgment result; performing multi-target collision risk assessment according to the target motion state judgment result to obtain a risk degree assessment matrix; performing navigation maneuvering performance constraint according to the risk assessment matrix to obtain a route planning maneuvering constraint rule set; and performing route trajectory search according to the route planning manipulation constraint rule set to obtain a navigation trajectory scheme. According to the invention, through the positioning navigation early warning technology, the positioning precision, the navigation safety and the early warning system practicability of the ship in a complex environment are obviously improved.

The invention discloses a multi-target scene visual SLAM (Simultaneous Localization and Mapping) method fusing target semantics and Gaussian splashing. The method comprises the steps that input data are preprocessed, two-dimensional space masks and semantic information corresponding to the two-dimensional space masks are extracted, global semantic identifiers are distributed to the two-dimensional space masks corresponding to a background and each target, and a target semantic segmentation map is obtained; reading first frame RGBD data as a current frame, acquiring a target semantic segmentation map corresponding to the current frame, and initializing camera pose parameters; respectively establishing an initial target Gaussian splashing model for the background and each target; adopting a Gaussian splash algorithm to render all the target Gaussian splash models to a next frame, and generating an RGB rendering image, a depth rendering image and a target semantic rendering image of the next frame; and designing a loss function between the next frame of rendered image and the corresponding real image, optimizing the pose of the camera, and updating the parameters of the target Gaussian splash model. According to the invention, simultaneous positioning and map construction of multiple target scenes are realized.

The invention discloses a multi-target intelligent optimization air conditioner control method and system based on multi-dimensional machine learning, and aims to acquire outdoor environment data by acquiring personnel flow and environment data inside and outside a building in real time and combining weather forecast information and the like, and predict future personnel flow trend and environment change conditions by utilizing a machine learning algorithm, so as to realize intelligent optimization of the air conditioner. And data support is provided for an artificial intelligence control strategy of the air conditioning system. Based on the prediction results, a multi-target optimization control algorithm is used for conducting multi-dimensional parameter regression on the air conditioner operation effect, and operation parameters such as the temperature, the humidity and the wind speed of the air conditioner system are dynamically adjusted. The air conditioning system is suitable for various large buildings such as office buildings, shopping malls and airports, the energy utilization efficiency of the air conditioning system is remarkably improved and the energy consumption is greatly reduced on the premise that the indoor environment comfort is ensured, and the air conditioning system has remarkable energy-saving and carbon-reducing effects, wide application prospects and remarkable economic and environmental protection benefits.

The invention provides a multi-target tracking and interference cooperation method and system based on a millimeter wave radar. The method comprises the following steps: firstly, acquiring an original detection signal in real time by using a millimeter-wave radar carried by an unmanned aerial vehicle, establishing a track correlation sequence of each moving target, extracting interference waveform characteristics formed by signal coupling among a plurality of moving targets in the original detection signal, and then, according to a spatial distribution parameter of the interference waveform characteristics, determining a track correlation sequence of each moving target; correcting the space-time continuity judgment rule of the trajectory correlation sequence, and finally outputting an anti-interference cooperative tracking result based on the corrected space-time continuity judgment rule. According to the technical scheme provided by the invention, the industry pain point that waveform distortion interference of the millimeter wave radar in a dense target scene cannot be eradicated is solved, and the error correlation rate in a dense formation scene is also reduced.

The invention discloses an event and RGB image fused SNN target tracking method and system, and the method comprises the steps: converting an event flow from an event camera into an event frame image through a representation method based on time stacking, and enabling the event frame image to be aligned with an RGB frame image from an RGB camera in time and space; performing target detection on the event frame image # imgabs0 # and the RGB frame image # imgabs1 # after alignment by using a spiking neural network SNN, wherein the spiking neural network SNN comprises a feature extraction module, a feature fusion module and a detection head; and learning the similarity of the targets by using the anchor frame extracted by the spiking neural network SNN and the fusion feature map # imgabs2 # to perform multi-target tracking. The invention aims to realize fusion of the fusion event and the RGB image so as to ensure high precision and high efficiency of multi-target tracking, and keep stable detection performance and tracking performance in static and high-motion scenes.

The invention relates to the field of transformer parameter regulation and control, in particular to a parameter optimization method and device for a coupling type transformer. The method comprises the following steps: acquiring multi-dimensional real-time working monitoring parameters and real-time working environment state parameters of the coupling type transformer; performing nonlinear dynamic analysis and global state sensing modeling on the multi-dimensional real-time working monitoring parameters so as to construct a transformer global state sensing model; performing multi-parameter combination definition on the multi-dimensional real-time working monitoring parameters, performing dynamic operation simulation based on a transformer global state sensing model, and collecting operation simulation response data of a plurality of schemes; performing multi-target dynamic balance analysis on the operation simulation response data of the plurality of schemes to obtain an optimal transformer working parameter combination; and carrying out environment dynamic parameter change analysis on the real-time working environment state parameters, and constructing a real-time environment condition distribution field. According to the invention, efficient and self-adaptive adjustment transformer parameter optimization is realized.

The invention relates to the technical field of digital twinning, in particular to a multi-machine running-in test distributed control system and method based on digital twinning. The method comprises the steps that a sensing execution unit collects equipment operation state data based on a multi-source sensor module and carries out preliminary data processing and detection; the digital twinning unit receives multi-dimensional sensing data of the sensing execution unit based on a dynamic twinning modeling module, establishes an equipment state model, and performs simulation verification and parameter optimization on a control strategy through a Q-learning strategy to obtain optimized control parameters; the intelligent control unit constructs an optimal decision-making model of multi-machine cooperative control based on a cooperative decision-making module, adjusts parameters of an execution mechanism in real time through a PID control algorithm and feed-forward compensation, and generates a self-adaptive control instruction; and the fusion analysis unit constructs a multi-dimensional equipment operation knowledge base based on the knowledge graph module, and generates global optimization parameters through a multi-target genetic algorithm.

The invention provides a chip production logistics optimization method and system based on a multi-target genetic algorithm, and relates to the technical field of chip production scheduling, and the method comprises the steps: collecting the real-time operation data of a production line, extracting task execution features and equipment layout features through a dual-channel deep neural network, and carrying out the feature fusion through a recurrent neural network, generating a production state vector containing a multi-dimensional scheduling index predicted value; constructing a multi-dimensional optimization target set based on the production state vector, and generating an initial population by adopting a double-layer gene coding structure; executing non-dominated sorting and crowding degree distance calculation based on the fitness value, and selecting high-quality individuals to form a parent population; and performing adaptive crossover, tabu search optimization and adaptive mutation operation on the parent population, iteratively selecting a new generation of population until convergence, and outputting an optimal scheduling scheme.

The invention discloses a multi-target task and resource intelligent modeling method, particularly relates to the field of complex adversarial simulation, is used for solving the problems of dynamic constraint optimization and robustness improvement in multi-dimensional task planning, and aims at realizing multi-dimensional coupling of space-time resource parameters by constructing a three-dimensional hypergraph model, mining a parameter association rule by means of tensor decomposition, and realizing multi-dimensional optimization of the space-time resource parameters. Dynamic constraint quantization is supported, multi-dimensional index priority evaluation is fused in a constraint layered injection stage, hard constraints are recognized, a solution domain is compressed, a hybrid optimization strategy regulates and controls balance between global exploration and local optimization, and after annealing is simulated to jump out of a local extreme value, a multi-target particle swarm algorithm is used for screening a space-time resource equilibrium solution in a trimming solution domain. Digital twinborn verification promotes physical and virtual space interaction data closed loop, a parameter correlation degree matrix is corrected, scheme robustness is enhanced, efficient generation and adaptive optimization of a task planning scheme under complex constraints are realized, and system stability and multi-target cooperation capability under sudden disturbance are improved.

The invention relates to the technical field of image processing, and provides a training data set labeling method and device for AI visual identification, and the method comprises the steps: obtaining and processing original image data, extracting feature mapping, inputting a target detection model to obtain a preliminary labeling result, carrying out the analysis, and determining a clustering center and a candidate target set; the candidate target set is classified based on the clustering center, the confidence degree of the classification labeling result is calculated, labeling data with the confidence degree higher than a threshold value serve as high-confidence-degree labeling data, rechecking and consistency checking are conducted on data with the confidence degree lower than the threshold value, and consistency labeling data are generated; and the target detection model is optimized in combination with the high-confidence data, the low-confidence data is re-labeled by using the optimization model, and the high-confidence data and the re-labeled data are combined to generate a complete labeled training set to train the recognition model. Through the above scheme, the consistency and confidence of the data are ensured, and the problems of inconsistent labeling and missed labeling and false labeling in complex scenes and multi-target recognition are effectively improved.

The invention discloses a mold parameter adjustment method and system based on a multi-objective optimization algorithm, and relates to the technical field of mold manufacturing. The method comprises the following steps: calling a production database, carrying out production state division, and establishing a production state division result; executing process data acquisition, and synchronizing a process data acquisition result to a data processing center through an MQTT protocol; matching a process data acquisition result with a production state division result by using a data processing center, and constructing a real-time dynamic weight; updating the multi-objective evaluation function by using the real-time dynamic weight, and establishing a configuration optimization priority; adjusting and optimizing the mold parameters according to the multi-objective evaluation function and the optimizing priority, and optimizing the mold parameters based on an adjusting and optimizing result. The technical problems that in the prior art, the die production efficiency is low, and the quality is unstable are solved, the die parameters are adjusted through the multi-objective optimization algorithm and the real-time dynamic weight, and the technical effect of improving the die production efficiency and the manufacturing quality is achieved.

The invention discloses an unmanned vehicle formation cooperative hunting method, device and equipment based on pilot following, and a medium, and relates to the technical field of multi-agent control. The method comprises the following steps: determining role division of a leading vehicle and a following vehicle, planning a path by the leading vehicle through an improved fast random exploration tree algorithm, sending the path and a control strategy to the following vehicle in stages, dynamically adjusting the position and speed by the following vehicle according to an instruction, ensuring formation consistency and task execution, and realizing information sharing between unmanned vehicles through a communication network. The pilot vehicle broadcasts a path and a task instruction in real time, and the following vehicles receive and analyze the path and the task instruction and then dynamically adjust the motion trail, thereby ensuring the cooperative consistency of the formation and the efficient stability of information transmission; each vehicle executes a hunting task according to a task instruction and adjusts a motion track and speed in real time, the following vehicle keeps a formation according to a path instruction, the pilot vehicle dynamically adjusts a global path according to environment change and a target position, the instruction is updated in real time through a communication network, and finally effective hunting and capturing of a target are realized. The method is suitable for a target hunting task in a complex environment, and reliable technical support is provided for a multi-target complex scene.

The invention discloses a flexible load multi-target collaborative scheduling system and method, and relates to the technical field of collaborative optimization of power systems. The method is used for solving the problem of lack of accurate prediction and multi-target coordination of agricultural electricity and water utilization regulation and control. Firstly, based on meteorological data, soil moisture content and crop growth characteristics, an irrigation demand prediction model is constructed, irrigation water demand is predicted, and a water pump load power baseline is generated; then, a dynamic baseline constraint condition is generated in combination with historical behavior data and water pump start-stop logic; establishing a power grid side objective function, a user side objective function and a water affair side objective function, and introducing an underground water and carbon emission punishment mechanism; thirdly, dividing the power distribution network into sub-regions, adopting an alternating direction multiplier method to solve a region regulation and control strategy in parallel, coordinating water resource distribution conflicts through virtual interactive variables, and outputting a global scheduling instruction; and finally, collecting real-time response data and correcting the prediction model on line to realize closed-loop adaptive optimization.

The invention provides a talent cultivation recommendation method based on federal learning and natural language processing, and the method comprises the following steps: processing multi-source heterogeneous data, and obtaining standard data; constructing a talent knowledge graph capable of performing incremental updating; performing anonymization and desensitization processing on the sensitive data, and performing joint modeling by using a federated learning framework on the premise of not sharing original data to obtain a local model; talent portraits and post portraits are generated, and a talent matching model is obtained in combination with multiple target factors and a dynamic weight preset matching algorithm; continuously monitoring the similarity difference between the talent portrait and the post portrait, and dynamically generating a course optimization scheme and a post optimization scheme; and performing visual explanation or keyword description on the recommendation process. According to the method, matching precision and efficiency can be improved, data islands can be broken, privacy security can be protected, market demand changes can be dynamically adapted, personalized demands of multiple parties can be met, and accurate connection between education and employment can be promoted.

The invention provides an underground cavern construction method generation method and system based on multi-source data fusion, and the method comprises the steps: collecting geological exploration, construction machinery operation and environment monitoring data, carrying out the time-space alignment processing, generating a standardized monitoring data set, carrying out the multi-source feature extraction of the standardized monitoring data set, and carrying out the multi-source feature extraction of the standardized monitoring data set; obtaining a construction state feature set and a geological risk feature set, inputting a reinforcement learning model for multi-target parameter optimization to obtain a preliminary construction method parameter set, inputting the preliminary construction method parameter set into a digital twin simulation system for simulating mechanical response, and iteratively optimizing parameters when a preset safety threshold is exceeded to obtain a preliminary construction method parameter set; the optimized construction method parameter set is matched and verified with a preset construction specification knowledge base, manual correction is carried out when illegal items exist, finally, full-period risk prediction is carried out on the corrected construction method parameter set, dynamic regulation and control are carried out according to a construction risk distribution map, a final construction method instruction set is generated, and scientific and intelligent construction method generation is achieved.

The invention discloses a multi-modal dynamic fusion and incremental learning fault diagnosis method for deep vertical shaft equipment, which belongs to the technical field of industrial equipment fault diagnosis, and comprises the following four steps of: constructing a pre-training large model to perform feature extraction, and relying on a multi-layer Transformer encoder and a dual loss function, establishing a multi-modal dynamic fusion and incremental learning fault diagnosis model; mining cross-modal universal fault features from vibration, temperature and current multi-modal time sequence data; according to the method, multi-modal features are fused, multi-modal association is constructed, modal weights are dynamically adjusted through a modal gating unit and a time delay compensation attention mechanism to adapt to signal quality changes, and meanwhile time sequence deviation is corrected to achieve accurate association; incremental learning is realized by using a decoupling projection layer, and a lightweight projection module is designed for a newly added fault task to suppress disastrous forgetting; network training is optimized, pre-training loss, incremental learning loss and attention regularization loss are integrated through a multi-objective loss function, and model stability and diagnosis precision are improved. The method has the advantage that the model stability and the diagnosis precision are improved.

The invention discloses an accurate dosing control system for water treatment, relates to the technical field of dosing control, and is used for solving the problem of poor dosing control accuracy in the water treatment process. Comprising a data acquisition module, a condition library construction module, a multi-target processing module and an optimization decision module. According to the method, a sensor is arranged in a water body to collect pollutant parameters, data are preprocessed, the types and the concentrations of pollutants are recognized through a support vector machine model, after recognition, an optimal processing parameter combination is called from a removal condition library, the condition library is dynamically updated by using an Apriori algorithm, and when multiple pollutants coexist, the optimal processing parameter combination is called from the removal condition library. Removal conditions are automatically adjusted according to interaction rules among pollutants, collaborative removal is realized, an optimal decision is solved by constructing a multi-objective optimization model with removal efficiency, medicament cost, processing time and environmental adaptability as targets and combining a genetic algorithm and a particle swarm optimization algorithm, intelligent dosing control is realized, and the system is suitable for large-scale popularization and application. And the accuracy and efficiency of water treatment are improved.

The invention discloses a method for dynamically establishing a knowledge graph based on multi-source heterogeneous data fusion, and belongs to the field of intelligent robot systems. Firstly, multi-source heterogeneous data fusion is carried out, a distributed Kalman filter network is constructed, filters are designed for different sensors, and data space-time alignment is realized; carrying out conflict detection and resolution by adopting an improved D-S evidence theory, and dynamically adjusting a fusion weight through a confidence evaluation model; secondly, constructing a dynamic knowledge graph, and establishing a three-layer graph structure comprising an environment entity, a space-time relationship and probabilistic reasoning; designing an event-triggered incremental updating algorithm, starting local reconstruction when the environmental change degree exceeds a threshold value, and introducing an LSTM memory network to enhance the time sequence reasoning capability; and finally, constructing a reinforcement learning model based on the dynamic knowledge graph, designing a multi-target reward function, and finally training until the model is converged. According to the method, the positioning error is reduced through EKF / UKF combined filtering, the multi-sensor data space alignment error is reduced through a conflict resolution mechanism, and the execution efficiency and the coping capacity of the omni-directional mobile robot in a complex dynamic environment can be improved.