57 results about "Gradient projection" patented technology

The invention relates to the technical field of heat management of energy storage systems, and discloses a heat management method of an intelligent distributed liquid cooling energy storage system. The method comprises the following steps: acquiring operation state parameters of a plurality of single batteries and optimizing timestamp synchronization; and processing the temperature data by adopting small-batch time series decomposition, and extracting change trend characteristics and abnormal hot spot positions. And based on the information, optimizing a heat exchange control rule base parameter set through a non-dominated sorting strategy, and generating optimized control parameters and priority rules. And in combination with inlet temperature and flow parameters of the liquid cooling system, a tabu search mechanism is utilized to decide a cooling liquid flow distribution scheme, and a branch control instruction is output. And finally, a flow constraint boundary is dynamically adjusted by adopting an approximate gradient projection technology, and a branch and bound strategy is fused to discretize and optimize a distribution path, so that the branch flow is finely regulated and controlled, and the thermal management precision and reliability of the energy storage system are improved. According to the method, the accuracy, adaptability and stability of thermal management of the liquid cooling energy storage system are improved.

The invention relates to an edge computing network-oriented micro-service and distributed database collaborative deployment system. The system comprises a database copy number dynamic optimization unit which obtains a dynamic optimization strategy of the copy number of a database based on a queuing gradient projection elastic scaling algorithm; a deployment strategy dynamic adjustment unit calculates end-to-end time delay based on the micro-service routing path and the database routing path; calculating a data inconsistency measurement index based on the number of each copy of the database; dynamically adjusting the deployment strategy based on the resource constraint between the end-to-end time delay and the data inconsistency measurement index and the dynamic optimization strategy of the number of copies of the database; the deployment strategy comprises micro-service instance deployment, database copy deployment and optimal routing path selection; according to the MEC scene-oriented distributed database design and fine-grained collaborative deployment optimization method, a message queue, a queuing theory and a Canal database incremental updating mechanism are integrated, and the micro-service application performance and the data query efficiency / reliability are improved.

The invention relates to the field of artificial intelligence control, in particular to a world model and reinforcement learning collaborative optimization method based on constraint perception gradient projection, which comprises the following steps: constructing a world model based on Transform architecture, performing unified modeling on an environment state, system dynamics and a reward function, and training the model based on reference model data to predict an environment future state; training a reinforcement learning strategy based on a virtual track and a reward signal generated by the world model, and calculating strategy gradient information; an explicit gradient projection operator of constraint perception is designed, a strategy gradient is corrected in real time according to future constraint conditions predicted by the world model, and it is ensured that the gradient updating direction meets the safety constraint and the optimization target at the same time; and synchronously updating world model parameters and reinforcement learning strategy parameters by using the gradient after projection correction to realize collaborative optimization of the world model parameters and the reinforcement learning strategy parameters. According to the method, the key problems of local optimal trap, low convergence speed, insufficient stability and the like in the collaborative optimization process of a traditional method are solved.

The invention provides an attack detection method and system based on Bayesian incremental learning and a storage medium, and the method comprises the steps: 1, collecting a data set, and dividing the data set into a plurality of tasks according to years; 2, using a Bayesian continuous learning framework, taking posterior distribution obtained by learning of a previous task as prior distribution of a current task, and adopting a gradient projection method to project a gradient of the current task to an orthogonal subspace of an old task feature space to obtain projection parameters; step 3, performing label deviation and noise processing on the task; 4, minimizing new task loss to obtain parameters, and adopting a training strategy according to a label deviation and noise processing result; 5, finding an optimal combined solution; and step 6, taking the combined model parameters as initialization parameters of the next task, returning to the step 2, and entering the next round of iteration until training of all tasks is completed. The method has the beneficial effects that the knowledge retention capability can be remarkably improved, and the problem of disastrous forgetting is effectively solved.

The invention discloses a color steel coil production cost optimization method and device and a medium, and the method comprises the steps: determining the production cycle of a single coil according to the time information of a new coil ready signal and a coil unloading completion signal; collecting power data of production line equipment in the production cycle, and determining energy consumption cost according to the energy unit price; according to the preset auxiliary material unit price and the production parameters in the production cycle, the auxiliary material cost is determined; constructing a feature matrix and a unit area cost vector according to a preset batch of single volume production data to train a cost prediction model; according to a preset constraint condition, determining an optimal parameter combination through a gradient projection method so as to minimize the unit area cost; and according to the parameter combination, the coating process parameters and the formula parameters in the next production process are adjusted, so that cost optimization closed-loop control is achieved. The cost accounting error is greatly reduced by defining the single-roll production cycle and accounting the energy consumption and the auxiliary material consumption; and meanwhile, a closed loop is driven through data, so that the production cost of the color steel coil is optimized.

The application belongs to the technical field of load identification of structural health monitoring, and provides a concentrated load positioning method based on principal stress constraint and strain gradient trajectory identification, which comprises the following steps: arranging strain sensors in a monitoring area of a planar structure plate and collecting strain data of measuring points, constructing a strain field inversion function based on a radial basis function and establishing an error optimization function containing a fitting error term and a smooth constraint, introducing a principal stress direction constraint and a gradient projection smooth constraint to form a comprehensive error function and solving to obtain an optimal strain field distribution, then calculating strain gradient vectors of each grid node and tracking a gradient trajectory through a gradient descent method, and finally performing an iterative clustering analysis based on distance statistics on a trajectory end point to output a cluster center as a concentrated load application position identification result. The application can improve the concentrated load positioning accuracy, enhance the anti-noise capability, and realize fast, stable and large-sample-free load position identification.

The invention belongs to the technical field of block chain and artificial intelligence crossing, and particularly relates to a fair federal consensus method and system based on gradient projection. The objective of the invention is to solve the problem that the fairness of a global model is reduced due to unfair client contribution evaluation and improper projection target selection in a gradient conflict resolution mechanism under the condition of non-independent identically distributed data (Non-IID). The method comprises the following steps: initializing a client key and parameters; randomly selecting m clients for local training in each round; calculating an effort value according to the loss change and the accuracy rate, and preferentially assigning a block creator; the server detects gradient conflicts and performs selective projection resolution, and a gradient with a large length is projected to an orthogonal plane with a gradient with a small length; aggregating the conflict-free gradient to update the global model; and circulating to a preset round number and outputting a final model and a creator sequence. According to the scheme, model performance and participation fairness are considered, and consensus efficiency and excitation compatibility of federated learning in a heterogeneous environment are improved.

The application discloses a land-air collaborative composite traffic network design method considering park-and-ride, and plans and designs a land-air collaborative composite traffic network with a vertical take-off and landing field as a center in a future land-air collaborative composite traffic network background, and proposes a corresponding network design model and a solving algorithm, mainly including: (1) a two-level planning model related to site selection, capacity allocation and integration of a landing field of an electric vertical take-off and landing aircraft (eVTOL) and ground parking facilities; (2) for a network equilibrium model in the two-level planning model, a modified improved gradient projection (M-iGP) algorithm is designed in an augmented Lagrange multiplier (ALM) framework; (3) a sensitivity analysis (SAB) algorithm is used to solve the two-level planning model, and the model and the algorithm are verified and analyzed in a Sioux Falls network.

The invention provides an electric vehicle power controller parameter adaptive setting method and system, and relates to the technical field of electric vehicle control, and the method comprises the steps: obtaining a motor torque feedback signal, carrying out the wavelet decomposition, extracting a working condition identifier, determining a phase margin and an amplitude margin offset based on Fourier transform, and obtaining a motor torque feedback signal; parameters are adjusted in combination with a gradient projection algorithm and a primal-dual interior point algorithm, and an optimal parameter vector is obtained through a multi-target particle swarm optimization algorithm. According to the invention, on-line adaptive adjustment of the control parameters is realized, and the power performance and the energy efficiency performance of the electric vehicle are improved.

This invention provides a collaborative optimization method for titanium plate annealing process parameters using multi-agent reinforcement learning, belonging to the field of reinforcement learning technology. The method includes collecting and standardizing annealing process data, encoding process parameters through a multi-layer feature extraction network, and constructing a parameter coupling perception matrix to quantify the collaborative strength. A dual-branch encoding structure is used to extract single-parameter features and interaction features, and the fusion weights are dynamically adjusted based on the coupling perception matrix to complete the state collaborative representation. The collaborative representation is input into a constraint-aware policy network to generate adjustment decisions, which are then executed in a real-world scenario and feedback is collected. Based on the feedback, a reward value is calculated, and training samples are sampled with priority to construct a composite loss function. A gradient projection method is used to update the policy network parameters to within the process feasible region, achieving continuous optimization of the policy network.

According to the electric vehicle charging load prediction method based on the Markov chain, the Markov chain and the improved Kalman filter are fused, and accurate prediction of the electric vehicle charging load is achieved. In the off-line stage, the charge state is discretized into 28 states based on historical data, 96 intra-day time slots are divided, a three-dimensional time-varying state transition matrix is constructed, filtering parameters are set, and state and power mapping is established, and in the on-line stage, charge state priori prediction is obtained through a Markov chain, real-time observation data are fused, and the real-time state of charge is obtained. Lawful optimal charge state distribution is obtained through Kalman filtering recursion and gradient projection method constraint optimization, finally, the distribution serves as a starting point, a transfer matrix is iterated to predict the future charge state, transfer path expected power is accumulated, and the total charging load is output. According to the method, the problems of error accumulation, poor robustness and the like of a traditional model are solved, and the method has high interpretability and engineering practicability.

The invention discloses a large-model-driven charging operation multi-agent collaborative decision-making method and system, and relates to the technical field of electric vehicle charging management. The method comprises the following steps: receiving meteorological data, power grid SCADA data, user electric vehicle data and historical constraint violation cases, and constructing a multi-source heterogeneous data set; and according to the constructed data set, a Stiefel-LoRA fine tuning algorithm is adopted to carry out parameter fine tuning on the pre-trained large language model, an adapter matrix is optimized through Riemannian gradient projection and a QR contraction updating algorithm, a fine-tuned large language model adapted to a charging decision task is obtained, and the fine-tuned large language model outputs an initial charging decision scheme. According to the method, the large model efficiency is improved through Stiefel-LoRA fine tuning, a physical information perception neural network is utilized to ensure that a charging decision strictly meets power grid security constraints, multi-agent collaboration and lexicographical order optimization are realized based on a standardized protocol, the problems of scheme ineffectiveness and decision deadlock of a traditional method are avoided, and the method is suitable for large-scale popularization and application. And safe, reliable and economical intelligent charging operation is realized.

The present disclosure provides computer-implemented method for training a model using a central node and a plurality of client nodes, comprising, at one or more of the plurality of client nodes: receiving a set of model parameters and an initial seed from the central node; determining an update direction based on the initial seed; computing scalar reflecting a sign and a size of an approximation of a projection of a gradient of a loss function on the update direction, using the set of model parameters; sending the scalar of the approximated gradient projection to the central node; receiving a model update scalar from the central node; and updating the set of model parameters in the update direction based on the model update scalar.

A computing system including one or more processing devices configured to receive a weight tensor of a neural network. The one or more processing devices are further configured to execute a gradient descent optimizer that updates the weight tensor over a plurality of projection matrix update intervals. Each of the projection matrix update intervals includes computing a gradient over the weight tensor in each of a plurality of gradient descent iterations. Each of the gradient descent iterations further includes projecting the gradient into a reduced-rank subspace using a projection matrix and updating the weight tensor by performing gradient descent using the projected gradient. Each of the projection matrix update intervals further includes computing a projection matrix error value associated with the projection matrix and updating the projection matrix based at least in part on the projection matrix error value.

The invention provides a hot area identification self-adaption method and system based on density residual errors, and aims to solve the problem that the performance of an existing hot area identification model is reduced due to data distribution differences during cross-domain deployment. The method comprises the following steps: constructing a cross-domain density residual index to quantify the difference of abnormal spatial distribution of a source domain and a target domain; in domain adaptation training, a pseudo-gradient projection mechanism is adopted, and an adversarial weight lambda is dynamically adjusted according to the change trend of the density residual error, so that the model adapts to a target domain; after deployment, macroscopic performance indexes including a false drop rate and an omission rate are monitored through modes such as user feedback, and adaptive updating and incremental training are carried out on the model and hotspot generation parameters based on a monitoring result to form a continuously optimized closed loop. According to the method, a complete closed loop from measurement, adaptation to feedback is established, so that the challenge of hotspot identification in a cross-domain scene is effectively solved, the adaptability and robustness of the model are remarkably improved, and intelligent management of the whole life cycle is realized.

The invention relates to the technical field of wind power prediction, and particularly discloses a gradient synergy and double alignment fused small sample wind power prediction method, which comprises the following steps: designing a Fourier enhanced Transform shared feature extractor to extract general feature representation with periodic perception from wind power time sequence data of a multi-source domain and a target domain; then, constructing a hybrid domain adaptive module, and realizing implicit and explicit dual alignment of feature distribution of a source domain and a target domain through a plurality of adversarial domain classifiers arranged in parallel and multi-core maximum mean difference measurement; and finally, introducing a gradient projection algorithm, carrying out collaborative optimization on conflict gradients of the prediction task and the domain adaptation task in a back propagation process, and eliminating gradient conflicts in multi-task learning. The method effectively improves the feature extraction capability, domain adaptability and optimization stability of the model in a small sample scene, and remarkably improves the prediction precision and robustness in a cross-domain wind power prediction task.

This invention discloses a method and system for constructing a physically guided diffusion model for robust optimization, belonging to the technical field of power system optimization and scheduling. The method includes: constructing a wind farm topology information map and a topology-aware variational autoencoder (VAE). The VAE includes an encoder and a decoder. The encoder encodes the input wind power operation data into latent variables, and the decoder restores the latent variables to the wind power scenario. A diffusion model is constructed. The gradient of the predefined power system operating cost function onto the wind power scenario is projected onto the tangent space of the latent manifold to obtain a gradient-guided operator, which is then introduced into the diffusion model in the next round of solution. This method achieves dimensionality reduction mapping of high-dimensional wind power scenarios by constructing a topology-aware VAE that integrates wind farm topology information and introduces a gradient-guided diffusion process based on the power system operating cost gradient, thus solving the technical problem of low efficiency in solving traditional robust optimization subproblems.

The invention belongs to the technical field of load identification for structural health monitoring, and provides a concentrated load positioning method based on principal stress constraint and strain gradient trajectory identification, which comprises the following steps: arranging a strain sensor in a plane structure plate monitoring area and collecting strain data of a measuring point; and constructing a strain field inversion function based on a radial basis function, establishing an error optimization function containing a fitting error term and a smooth constraint, introducing a principal stress direction constraint and a gradient projection smooth constraint to form a comprehensive error function, and solving to obtain optimal strain field distribution. And further calculating a strain gradient vector of each grid node, tracking a gradient trajectory through a gradient descent method, finally carrying out iterative clustering analysis based on distance statistics on a trajectory end point, and outputting a cluster center as a concentrated load application position identification result. According to the method, the concentrated load positioning precision can be improved, the anti-noise capability is enhanced, and rapid and stable load position identification without a large number of training samples is realized.

The invention relates to the technical field of electric data processing and intelligent algorithms, in particular to an image processing projection scaling optimization method and system based on the symplectic manifold acceleration technology. The method comprises the following steps: for a constraint minimization problem corresponding to an image deblurring or binary classification scene, solving the constraint minimization problem by adopting a zoom gradient projection algorithm to obtain an image deblurring result or a classification result; and a second-order symplectic integrator is introduced to perform position updating and momentum updating in the process of solving the constraint minimization problem by adopting the zoom gradient projection algorithm, so that the convergence efficiency of solving the constraint minimization problem by adopting the zoom gradient projection algorithm is improved.

The embodiment of the application provides a high under-actuated space manipulator trajectory optimization method, comprising the following steps: constructing a high under-actuated space manipulator direction dynamics operability and dynamics condition number index according to a coupling relationship between a high under-actuated space manipulator active joint torque and end acceleration; constructing a high under-actuated space manipulator trajectory optimization objective function according to the high under-actuated space manipulator direction dynamics operability and dynamics condition number index; and performing trajectory optimization on the high under-actuated space manipulator by using a gradient projection method according to a high under-actuated space manipulator kinematic coupling relationship and the high under-actuated space manipulator trajectory optimization objective function.

The invention relates to the technical field of regional heat supply control, and discloses a heat supply network multi-time scale regulation and control system and method based on digital twinning, and the system comprises a long time scale optimizer module which is configured to generate a preliminary economic dispatching plan; the space-time feasible domain dynamic constraint agent module is configured to receive the preliminary economic dispatching plan and call a digital twinborn body to carry out prospective simulation deduction and is used for identifying and generating a dynamic constraint set; and the feasible region gradient projection module is configured to receive the dynamic constraint set and calculate the gradient of each constraint in the dynamic constraint set relative to a control variable in the preliminary economic dispatching plan based on the digital twin so as to generate a gradient vector set. Prospective simulation is carried out through digital twinning so as to predict and avoid physical safety risks in an economic dispatching plan, and gradient information is utilized to guide secondary optimization so as to efficiently generate a final scheme, so that cooperation of heat supply network operation safety and economical efficiency is realized.

The invention relates to the technical field of artificial intelligence, and discloses a tunnel emergency evacuation guiding system based on artificial intelligence, which is constructed under an industrial-grade edge cloud cooperative computing architecture. The system integrates multi-sensor perception, edge intelligent analysis and reinforcement learning decision, and realizes dynamic risk assessment and adaptive evacuation control under tunnel emergencies. The edge calculation unit adopts an improved GUM-CNN model to carry out fusion and risk prediction on multi-source emergency data, and the stability and calculation efficiency of the model are improved through low-rank gradient projection, random sampling for deviation removal and a spectrum orthogonal constraint mechanism. And the central intelligent guide server generates an optimal evacuation scheme based on a reinforcement learning algorithm, and realizes dynamic guide of crowds and vehicles through guide lamps, variable information signs and emergency broadcast. The intelligent level and safety of tunnel emergency evacuation are effectively improved.

A microgrid multi-resource collaborative autonomous optimization method and system based on coupling constraint relaxation abstracts each physical unit with power regulation capability within the microgrid as an identical regulation agent. The minimum sum of the local objective functions of all regulation agents is used as the global objective function. Relaxation variables are introduced to correct the total power balance constraint satisfied by the global objective function. A global penalty term common to all regulation agents is constructed based on the relaxation variables and penalty coefficients, and this global penalty term is superimposed on the global objective function to obtain the collaborative autonomous optimization objective. Based on the collaborative autonomous optimization objective, a distributed gradient projection method is used to iteratively predict the output of each regulation agent. When the iterative convergence criterion is met, the iteration stops and the predicted output of each regulation agent is output as the result of the microgrid multi-resource collaborative autonomous optimization. This forms a microgrid internal collaborative optimization system that is decoupled from resource types, has no external dependencies, and possesses adaptive capabilities, realizing autonomous collaboration among multiple units under the constraint of coupling.

The application discloses a minimum harmonic optimization overmodulation method of a permanent magnet synchronous motor, and comprises the following steps: S1, a mathematical model of a double three-phase permanent magnet synchronous motor is established, and a deadbeat prediction control model is designed; motor winding variable signals are mapped, and a discretization model of the double three-phase permanent magnet synchronous motor is established; a deadbeat prediction control model of the system is constructed, and a state expansion observer is introduced to estimate and compensate harmonic currents; S2, overmodulation optimization control based on a gradient projection algorithm; a cost function taking the error between a reference modulation signal and a feasible modulation signal as an objective is constructed, and is converted into a quadratic programming problem containing linear equation constraints and boundary constraints; an optimal duty cycle is solved by online iteration through the gradient projection algorithm, the collaborative optimization of fundamental wave voltage synthesis and harmonic voltage minimization is realized, and the utilization rate of a direct current bus voltage and the dynamic performance of the system are improved. The modulation strategy has excellent steady-state performance and dynamic response capability under different working conditions.

The invention belongs to the related technical field of edge computing, and discloses an edge end participating in cloud-edge federated learning, a control method, a cloud-edge federated learning system and an edge end control processing method. In the edge end control processing method, if the edge end participates in the federated learning of this round, a global model and a global estimation gradient are obtained and trained to obtain a local model g; uploading the local model g and the local estimation gradient to a central server, and resetting the local estimation gradient; if the new samples do not participate in the federated learning of the round, the gradient of each new sample on the local model g is calculated, and the sample with the minimum gradient projection in the data set is put into a to-be-recycled area on the basis of updating the local estimation gradient; and when the sample data of the to-be-recycled area reaches a preset upper limit, deleting the sample with the lowest importance degree from the local, and putting the to-be-recycled sample with the increased data importance degree into the data set again. On the basis of the method, the storage pressure of the edge end equipment can be relieved in the cloud edge fusion architecture, and meanwhile data forgetting is avoided.

This invention discloses a multi-objective optimization method and system for real-time adaptive combustion and control of generating units, comprising: acquiring unit operating and decision parameters; constructing a system with net power as the objective function; employing an online hybrid Gaussian process regression and uncertainty quantification network (OH-GPR-UQN) to identify the dynamic relationship between the decision parameters and the net power objective function online, estimating the gradient and quantifying its uncertainty; based on the gradient and its uncertainty, employing a Bayesian optimization-guided adaptive exploration and utilization constraint hill-climbing algorithm (BOA-CEHC) to determine the adjustment step size and direction disturbance of the decision parameters by maximizing an acquisition function that simultaneously considers "utilizing" the gradient and "exploring" uncertainty, and combining gradient projection and penalty functions to process operating constraints to obtain optimized parameters; the optimized parameters are used for closed-loop control, and operating data is fed back to update OH-GPR-UQN online. This invention can accurately identify, intelligently optimize, and robustly handle constraints, significantly improving the overall efficiency of the generating unit.

The present application relates to the technical field of disaster detection, in particular to a geological disaster detection method and system based on image processing, comprising the following steps: collecting multi-temporal topographic images and dividing them into blocks, constructing a main boundary angle difference value array, calculating the included angle change to screen image blocks and combining fault regions, extracting crack contours to calculate the opening angle and construct the offset sequence, generating an enhanced feature map based on gradient projection texture field interpolation, constructing a residual data field to divide grid points, and determining abnormal regions. In the present application, the main boundary angle difference value array of the blocks is constructed and affine aggregation is performed in combination with the consistency of the edge gray gradient, so that the precise reconstruction and continuity recovery of the cross-scale nonlinear fault structure in the topographic image are realized, the gradient derivative quantity is generated by using the crack endpoint opening angle offset sequence and the texture vector field is expanded, which can sensitively capture the weak morphological changes of the local topography in the time evolution process, and solve the problem that the small disaster precursor features are difficult to identify in a complex background.

The invention provides a pump frequency model prediction regulation and control method for a membrane bioreactor, and aims to solve the problems of prediction misalignment, energy consumption increase and inaccurate regulation and control caused by the phenomena of sudden flow change and severe pump frequency fluctuation of pump station regulation and control in a membrane bioreactor system of an urban sewage plant. The method comprises the steps that firstly, a flow prediction model based on self-adaptive state perception is established, the length of a prediction domain is adjusted through a nonlinear modulation function, and rapid perception and response of a pump station to sudden working conditions are achieved; and secondly, designing an intelligent model prediction controller, and carrying out online solving on the composite objective function by using a gradient projection method under engineering constraints. And finally, in combination with real-time operation data and an intelligent controller, optimal regulation and control of the frequency combination of the lifting pump are realized. Results show that the method can quickly adjust the frequency of the lift pump under the sudden working condition caused by flow abrupt change, flow tracking and energy consumption suppression are considered at the same time, and the stability and energy efficiency of a pump station are remarkably improved.

The invention discloses a gradient correction federated fine-tuning method and system based on disturbance reasoning, which effectively reduce the memory overhead of fine-tuning a large model by edge equipment and shorten the model convergence time on the premise of ensuring the precision of the large model through forward disturbance reasoning and conflict gradient correction mechanisms. The edge equipment generates a plurality of disturbance models according to random seeds issued by the cloud, and efficiently obtains a large number of forward gradients through disturbance reasoning, thereby avoiding high computing power consumption caused by back propagation. And then, the cloud server performs conflict detection on the forward gradients uploaded by the edge-end devices, eliminates conflicts through gradient projection, calculates weights in combination with historical gradient information of the edge-end devices, and weights the gradients, thereby weakening the adverse effects of different data distributions on the convergence and precision of the model. And finally, the cloud server updates the global model through federal aggregation to obtain a fine-tuned target large model.