47results about How to "Improve exploration ability" patented technology

The invention discloses an electrical automatic control method and system. The method comprises the following steps: acquiring temperature data and load current data in an electrical cabinet; denoising the temperature data by adopting a wavelet transform algorithm; filtering the load current data by adopting a Kalman filtering algorithm; establishing a temperature rise compensation model based on a long short-term memory (LSTM) neural network, wherein the output of the temperature rise compensation model is a temperature rise predicted value in the electrical cabinet; setting a multi-objective function of temperature rise control in the electrical cabinet; solving by adopting a multi-target ant colony algorithm to obtain an optimal control strategy of the cooling fan; and starting, stopping and speed adjustment of the cooling fan are controlled according to the optimal control strategy of the cooling fan. Aiming at frequent starting and stopping of a cooling fan of an electrical cabinet in the prior art, a temperature rise compensation model is established based on a long short-term memory (LSTM) neural network, a multi-objective optimization function including temperature rise deviation and starting and stopping times of the cooling fan is set, an improved multi-objective ant colony algorithm is adopted for solving, and starting and stopping of the cooling fan are reduced.

The invention relates to the technical field of fault detection for a wireless communication network, and discloses a fault detection method for the wireless communication network. By collecting data of base station signal strength, network delay, data packet loss rate and user equipment signal quality, the problem of insufficient fault detection caused by a single index is solved. Through multi-dimensional data acquisition, the system can comprehensively evaluate network performance, the fault detection accuracy is improved, and different fault types can be effectively identified especially in a complex fault mode. By storing the data according to the time sequence, the problem of time sequence chaos is avoided, and accurate detection of time-varying faults is ensured. The comprehensive data vector generated by each time of sampling comprises a plurality of network performance indexes, so that the fault detection and positioning capability is improved. Abnormal values are eliminated through data preprocessing, the data quality is ensured, an accurate basis is provided for subsequent analysis, and the reliability of a detection result is ensured.

The invention discloses an unmanned ship multi-path optimization method for large-scale dynamic search and rescue tasks, and belongs to the technical field of unmanned ship path planning. According to the method, a multi-track optimization framework combined with a deep reinforcement learning algorithm is introduced, so that the efficiency and accuracy of path planning are effectively improved. Through a multi-trajectory sampling technology, the problem of trajectory data sampling deviation in a traditional method is solved, and the robustness and adaptability of an algorithm in a dynamic rescue environment are enhanced. Meanwhile, an encoder-decoder structure is designed, path exploration of the unmanned ship is optimized by utilizing reinforcement learning, and the exploration capability of the model to a complex solution space is greatly improved. According to the method, the optimal searching path can be quickly found, and the unmanned ship is prevented from falling into a local optimal solution. According to the invention, the unmanned ship can intelligently adapt to a large-scale emergency rescue scene, the search time is greatly shortened, the task success rate is improved, and key technical support is provided for the application of the unmanned ship in emergency rescue.

The invention relates to a data calibration method suitable for an atmospheric pollutant sensor deployed in an embedded terminal. The method comprises the following steps: acquiring original response data of different sensors with different concentrations in different atmospheric environments after temperature compensation, and corresponding temperature, humidity, air pressure data and sampling time; collecting real concentration values of detection objects corresponding to different sensors at corresponding moments given by a national control station or a provincial control station; preprocessing the obtained data to obtain a final data set; a random forest algorithm is used as a teacher model, a gradient elevator algorithm is used as a student model, and hyper-parameters of the gradient elevator algorithm and the random forest algorithm are optimized by using a hedera helix algorithm; substituting a hyper-parameter optimal solution found by optimization into a corresponding algorithm, and retraining the teacher model and the student model by using hyper-parameter combinations; and deploying, updating and displaying the model in the embedded equipment. And the model size is reduced to realize the deployment of the embedded end on the premise of ensuring the accuracy.

The invention provides a mold surface repairing method and system based on laser cladding, and relates to the technical field of laser cladding, the method comprises the following steps: selecting a matrix material with a proper size, and pretreating the surface of the matrix material; according to the actual process requirements, the value range of laser cladding process parameters is determined, and a response curved surface model of the microhardness and the dilution rate is established; optimizing the response curved surface model, and obtaining an optimized process parameter combination by taking maximization of microhardness and minimization of dilution rate as targets; according to the optimized technological parameter combination, the laser cladding process is carried out, and a cladding layer is formed on the pretreated base material; and performing performance detection on the formed cladding layer, and adjusting process parameters according to a performance detection result until an optimal process parameter combination is determined. By means of the method, it can be guaranteed that the hardness of the cladding layer is stabilized within the ideal range, the mold repairing quality is remarkably improved, and the service life of the mold is remarkably prolonged.

The invention discloses a line path planning scheme generation method and system based on deep reinforcement learning, and the method comprises the steps: firstly constructing a grid map and an evaluation index system of a planning region, determining the index weight based on a Critic method to construct a grid comprehensive cost evaluation model, and then constructing a path planning model with the minimum total cost as a target, the method comprises the following steps of: firstly, extracting an optimal power transmission line planning path, describing the optimal power transmission line planning path as a Markov decision process, then introducing mixed noise and an epsilon-greedy strategy into a depth deterministic strategy gradient algorithm, improving a priority experience playback mechanism to obtain an improved depth deterministic strategy gradient algorithm, and finally training an intelligent agent based on the algorithm and outputting an optimal power transmission line planning path. According to the method, mixed noise is added, the exploring ability of the intelligent agent is improved, a greedy strategy is introduced to accelerate the learning efficiency of the initial stage of the algorithm and reduce the exploring frequency so as to reduce unnecessary trial and error, and finally, an instant reward value is fused into a priority experience playback mechanism to help the intelligent agent to accurately distinguish the importance of different experiences and accelerate the learning efficiency of the intelligent agent.

The invention discloses an evaporation cooling air conditioner energy-saving optimization control method and system based on a mechanism model, and relates to the technical field of evaporation cooling air conditioner control, and the method comprises the steps: carrying out preliminary partitioning according to the distribution condition of evaporation cooling air conditioners in a warehouse, and obtaining cold supply partitions; equipment operation states, personnel activities and lighting systems in the warehouse are monitored in real time, and heat source distribution values of all subareas in the cold supply subarea are obtained; setting a regional heat source prediction algorithm, and predicting a heat source distribution prediction value in the partition in combination with the goods density; and setting a self-adaptive evaporation cooling air conditioner parameter adjusting strategy, and dynamically adjusting the cooling water temperature, the air inlet amount, the air supply temperature and the air supply direction according to the heat source distribution predicted value and the monitored humidity level. The problems that under the conditions of high humidity and high goods density, an air conditioning system is insufficient in robustness and high in energy consumption are solved, and it is ensured that efficient and stable operation can still be achieved when the load changes.

An automatic generation method for a digital construction scheme of a power transmission line project comprises the steps that the digital construction scheme of the power transmission line project is decomposed, an automatic generation model of the digital construction scheme of the power transmission line project is constructed, and the automatic generation model comprises a state space, an action space, an intelligent agent and a reward function; the intelligent agent comprises a strategy network and a value network, the strategy network is used for outputting action probability distribution, the value network is used for outputting a state value, and the reward function comprises an efficiency reward, a quality reward and a security penalty; training the intelligent agent by using a PPO algorithm, and optimizing parameters of the strategy network by minimizing a loss function; and then obtaining an optimal digital construction scheme of the power transmission line project based on the trained automatic generation model. According to the method, deep reinforcement learning and automatic generation of the digital construction scheme of the power transmission line project are combined, and the obtained optimal scheme can improve the construction efficiency, improve the project quality and ensure the construction safety.

The invention discloses a weapon-target allocation optimization method based on an improved golden sine algorithm. The method comprises the following steps: establishing a weapon-target damage probability matrix; aiming at a weapon-target allocation problem, establishing a mathematical model comprising a weapon allocation matrix, a target function and a constraint function; generating an original population satisfying the constraint; and optimizing the population by adopting an improved golden sine algorithm, optimizing the population by updating a golden section coefficient and an individual position and using a dynamic random reverse learning strategy, and searching a better individual until iteration is ended. Compared with the prior art, the method provided by the invention avoids falling into a local optimal solution in the WTA problem optimization process by improving the position updating formula of the golden sine algorithm, and meanwhile, the population diversity is improved by fusing the dynamic random reverse learning strategy, and the algorithm is prevented from premature convergence, so that the algorithm has relatively strong global search capability, and the algorithm is more suitable for being popularized and used. And meanwhile, the method has relatively high capability of jumping out of a local optimal solution.

The invention requests to protect a reinforcement learning mixing method applied to assembly sequence planning, the assembly sequence planning can be essentially understood as a sorting of product parts, the excellent assembly sequence can shorten the production cycle of products, and the production cost is reduced. In the invention, a reinforcement learning algorithm, i.e., a Greedy-QS algorithm, which combines a Q-learning algorithm and a Sarsa algorithm is provided to solve the problem of assembly sequence planning. In the work of the method, firstly, the to-be-assembled product is reasonably abstracted into a mathematical model expressed by several Boolean matrixes, the complexity of the assembly model is reduced, the operability of the algorithm for the assembly sequence planning problem is improved, and then the optimal solution is solved by using the Greedy-QS algorithm. Experiments prove that compared with a Q-learning algorithm, a Sarsa algorithm and a Q-SARSA algorithm, the Greedy-QS algorithm has a faster convergence speed in the assembly sequence planning problem, the obtained reward value of the optimal assembly sequence is higher, and the advantages of the Q-learning algorithm and the Sarsa algorithm are both achieved.

The invention discloses a cold-chain logistics vehicle planning system. The system comprises the following steps of initial population creation, explosion and spark generation, evaluation and selection, genetic manipulation, pheromone updating, termination judgment and optimal solution output. According to the method, a dynamic pheromone updating and path reward and punishment mechanism is introduced through improvement of pheromone updating, so that the convergence speed of the algorithm is accelerated, and the quality of a solution is improved; the exploration depth of a solution space is increased by improving the crossover operation and considering the length and quality of an introduced path; improvement of mutation operation depends on a self-adaptive mutation strategy, the exploration capability of the algorithm is enhanced, multi-objective optimization is introduced into path planning through the improved firework algorithm to consider transportation cost, temperature control and energy consumption management at the same time, and a dynamic adjustment mechanism is combined to cope with frequently changing terrain and climate conditions in the karst landform, so that the development of the karst landform is facilitated. Therefore, the adaptability of the algorithm in a complex environment is improved.

The invention discloses an unmanned aerial vehicle communication system strategy optimization method based on deep reinforcement learning, and the method comprises the steps: building an unmanned aerial vehicle communication system model which comprises an unmanned aerial vehicle, an RIS and a plurality of ground receiving users, carrying out the optimization of a maximum rate C through an improved TD3 algorithm improvement-TD3 by employing the deep reinforcement learning (DRL) technology under the condition of giving specific channel state information (CSI), and carrying out the optimization of the maximum rate C through the improved TD3 algorithm improvement-TD3. And solving an optimal beam forming matrix and an optimal phase shift matrix. According to the method, entropy regularization is introduced into an existing TD3 algorithm, so that exploratory performance is enhanced, an intelligent agent is promoted to explore more environments, the relation between exploration and utilization is balanced, finally, an optimal transmitting beam forming matrix and RIS phase shift are obtained, falling into a local optimal solution is avoided, and learning robustness and generalization ability are improved.

A self-adaptive multi-objective evolution method for optimizing the capacity of an off-grid wind and light hydrogen production and energy storage system comprises the following steps: firstly, according to an energy storage system model, taking unit hydrogen production cost, wind and light abandoning penalty and load shedding penalty as minimization objectives; secondly, the capacity of each component of the wind-solar power generation unit, the power storage unit and the hydrogen and oxygen storage unit is used as a decision variable, and the system is set to conform to the actual constraint; thirdly, initializing a population; individuals in the population are initialized according to the constructed search space, so that the individuals meet constraint conditions; then adaptively selecting a search strategy; the strategy adaptive network selects a proper search strategy based on individual decision variables and objective function values, and evolves a new sub-population; and fusing the parent population and the child population to calculate the non-dominated level and the congestion degree of all individuals, determining parameters of the reward updating strategy adaptive network according to the non-dominated level, and screening out a new population. According to the method, the randomness and blindness of algorithm search can be reduced, and the search efficiency of the algorithm is enhanced.

The invention belongs to the field of ecological system carbon circulation, particularly relates to a time sequence-oriented carbon release scene dynamic forward modeling method and system, and aims to solve the problems that detail changes cannot be grasped, mixed release of multiple carbon sources cannot be recognized and the forward modeling frequency is limited during existing carbon release scene forward modeling. The method comprises the following steps: selecting a target curve and determining a potential carbon source; identifying potential fluctuation of the target curve and dividing stages; generating a carbon release mode in each stage based on a random sampling method, and inputting the carbon release mode into the carbon cycle model for simulation; and calculating an error and screening an optimal carbon release mode. According to the method, multiple carbon release modes can be efficiently generated, the coverage range of extreme conditions and complex carbon release scenes can be expanded, high-precision simulation can be realized, and the dynamic evolution process of the complex carbon release scenes can be further optimized.

The invention discloses a deep reinforcement learning manipulator grasping method for sparse rewards, comprising: firstly analyzing the characteristics of the manipulator grasping task, modeling it as a Markov decision problem, designing a binary sparse reward, reducing the complexity of the reward function design, and reducing the design cost; secondly, taking the DDPG algorithm as the main deep reinforcement learning training algorithm framework, building an Actor-Critic structure network, and processing the continuous state action space; then, designing a post-experience playback mechanism, using the G-HGG algorithm for auxiliary target generation, using a pre-trained action network for action screening and adding exploration noise and energy functions to process the accumulated experience pool, enhancing the experience utilization rate, and improving the training efficiency and grasping success rate; finally, building a manipulator model and scene information, using interactive data for optimization training, and realizing manipulator target grasping. The method can solve the grasping learning problem of the manipulator under sparse rewards.

This invention discloses an intelligent path planning method for heavy-duty robotic arms used in the dismantling of decommissioned photovoltaic (PV) modules. The method involves modeling and training the dismantling task of decommissioned PV modules using an actor-critic algorithm, followed by intelligent path planning for the heavy-duty robotic arm based on the constructed model, generating locally optimal work trajectories. Heavy-duty robotic arms face scenarios with few obstacles in the dismantling of decommissioned PV modules, and their path planning problem can be reduced to an optimization task for a single robotic arm. This solution employs an actor-critic algorithm to achieve efficient and stable path generation, supporting automated dismantling. Furthermore, it introduces the concept of entropy to enhance exploratory capabilities, avoid local optima, and ensure the robotic arm can adapt to the irregular shapes of the modules and dynamic environmental changes.

The application discloses a trajectory coverage sensor layout method based on layered deep reinforcement learning, comprising the following steps: constructing a trajectory dataset of a target area and a sensor deployment constraint model, including a deployable area, a minimum spacing constraint and a coverage criterion; decomposing a global layout task into two levels of hotspot center selection and local offset optimization: in the high-level strategy, the global trajectory density is analyzed based on environment observation, and a soft actor-critic algorithm is used to generate hotspot center instructions; in the low-level strategy, a continuous action optimization method with a mixed density network and a Gumbel-Softmax selector is used to solve the multi-modal of the sensor offset in each hotspot. The application introduces a random network distillation module at the high and low levels, and through a cross-layer reward injection mechanism, the high-level strategy can be adaptively updated according to the actual coverage gain of the low level, so as to improve the coordination and convergence efficiency of the overall layout.

The application provides a kind of motion optimization method and system of mechanical arm based on improved sparrow algorithm, based on the kinematic model of mechanical arm, the trajectory of mechanical arm is planned using polynomial interpolation method, and the joint motion trajectory is obtained;Based on the joint trajectory, the objective function and the constraint condition of the mechanical arm are constructed;The sine-cosine mapping, improved elite reverse learning strategy and Cauchy Gaussian variation principle are integrated into the sparrow algorithm to obtain the improved sparrow algorithm;Based on the objective function and the constraint condition, the improved sparrow algorithm is applied to the trajectory planning of the mechanical arm, and the motion of the mechanical arm is optimized.The application integrates the sine-cosine mapping, improved elite reverse learning strategy and Cauchy Gaussian variation strategy into the sparrow algorithm to form the improved sparrow algorithm, improves the diversity of population, avoids falling into local optimum, and can effectively find the global optimal solution.The improved sparrow algorithm is applied to the mechanical arm, which improves the running efficiency and running accuracy of the mechanical arm.

The application discloses an aircraft cluster cooperative non-cooperative target capturing method driven by entropy regularization, applies the entropy regularization thought to reinforcement learning, optimizes the updating method of the parameters of an evaluation network and a policy network, so that a UAV can obtain a more optimal maneuvering strategy, and the UAV performs actions according to the maneuvering strategy, and realizes the interception of an attacking aircraft. The aircraft cluster cooperative non-cooperative target capturing method driven by entropy regularization can not rely on a deterministic strategy in the interception process of multiple UAVs, but adopts a random strategy, avoids the training from falling into a local optimal point, and the actions of the aircraft are randomized as much as possible while the aircraft completes the task, so that the exploratory and robustness can be practically improved.

The present invention discloses an adaptive steering driving assistance method based on a high-precision map, comprising the following steps: when a positioning device detects that the distance between the vehicle and the designated road ahead is less than or equal to a preset distance, a vehicle-mounted radar detects whether there is a vehicle ahead on the designated road ahead; when the detection result is that there is a vehicle ahead, the vehicle-mounted radar measurement angle is maintained; when the detection result is that there is no vehicle ahead, the vehicle-mounted radar measurement angle is continuously adjusted according to the road conditions of the designated road; until the detection result changes to the presence of the vehicle ahead, the vehicle-mounted radar measurement angle is maintained at this time; if the vehicle ahead is adjusted to a preset upper limit angle and the detection result is still that there is no vehicle ahead, the vehicle-mounted radar is adjusted back to the initial angle; when the vehicle leaves the designated road, the vehicle-mounted radar is adjusted back to the initial angle. The present invention timely uses mechanical driving to calculate and rotate the radar in the horizontal and pitch directions to increase the field of view angle corresponding to the road conditions to accurately detect the road conditions of the vehicle ahead, and enhances the radar's exploration performance of the vehicle conditions ahead of the lane.

The invention discloses a cloud large model and marginal small model collaborative terminal device with a body and a control method of the cloud large model and marginal small model collaborative terminal device. The body terminal device comprises a cloud large model intelligent training module which is used for training and optimizing a TD3 strategy model through an immune algorithm so as to improve the exploration capability and the control precision. The edge reasoning and control module is used for deploying a lightweight TD3 model, sensing the environment in real time under the conditions of low power consumption and low delay and outputting a control action; the communication and cooperation module is used for synchronizing data and control strategies between the cloud and the edge; and the execution and feedback module is used for converting the control action into actual flight operation and returning information such as position, speed and attitude so as to support continuous updating and control.

This invention discloses a reinforcement learning simulation step size control method based on closed-loop adaptive noise injection and entropy increase optimization strategy, belonging to integrated circuit computer-aided design technology. Specifically, the method involves: first, inputting the circuit netlist and interacting with the simulator using file read / write; next, establishing two new network output layers to convert the deterministic actions of the policy network's output into a probability distribution; then, obtaining the entropy regularization term based on the probability density function and weight coefficients, and adding it to the policy loss function; next, generating Gaussian-distributed exploration noise and adjusting the standard deviation of the noise at each step using a PID controller; finally, adjusting the policy network parameters using a gradient update method and injecting the exploration noise into the output actions to obtain the final time step. Using this invention helps enhance the simulation stability of pseudo-transient analysis, improves simulation efficiency, and provides a new method for DC analysis.

The invention discloses a power distribution network voltage reactive power optimization method fusing a graph neural network and reinforcement learning, and relates to the crossing field of power system automation and deep reinforcement learning, and the method comprises the steps: 1, extracting the topological information of a power distribution network through the graph neural network GNN, taking the minimum line loss as an objective function, building a continuous reactive power optimization model of the power distribution network, and obtaining a continuous reactive power optimization model of the power distribution network; meanwhile, constraints of safe operation of the power distribution network are added; 2, describing a reactive power optimization problem of the power distribution network as a Markov decision process according to the model constructed in the step 1; 3, the GNN is embedded into the deep Q network, and a unique network is constructed to solve the constructed Markov decision process; and training the constructed model by using historical operation data of the power grid. The main innovation point of the method is that the dependence on an accurate physical model is eliminated, the rapid reactive power optimization of the power distribution network can be realized, and meanwhile, the trained model has relatively strong generalization capability and can be solved in real time, so that the calculation burden is greatly reduced.

The invention provides a surface mine transportation scheduling method and device, and relates to the technical field of transportation scheduling, and the method can obtain engineering data of a target mining area, and employs a global search algorithm based on a gradient optimizer according to the engineering data and a target function constructed with the lowest total transportation cost as a target. And carrying out iterative optimization on the number of transportation times of each transportation route in the target mining area to obtain a target number of transportation times scheme, and further determining a vehicle scheduling scheme of the target mining area. Therefore, when the vehicle scheduling scheme of the target mining area is determined, a global search algorithm based on a gradient optimizer is adopted, and the problems of low operation efficiency and easy premature convergence of a particle swarm type method for a multi-dimensional optimization problem can be avoided through a gradient search rule and a local escape operator; the early-stage exploration capability and the later-stage development capability can be better balanced, and the optimal scheduling scheme can be quickly and accurately obtained.

The present application belongs to the field of intelligent driving technology, and specifically relates to a multi-objective human-vehicle sharing control method based on hierarchical deep reinforcement learning, including step 1: obtaining the observation states of each environment in the driving simulation environment; step 2: establishing the overall environment state space based on the observation states of each environment, and establishing the driving right allocation coefficient action space based on the driving right allocation strategy; step 3: based on step 2, it is divided into the first layer of lane keeping model training objectives and the second layer of left and right lane changing model training objectives; step 4: establishing a basic reward function, integrating the driving of the fully automatic driving system, the full driver model and the human-machine co-driving to obtain the fusion reward function of the lane keeping model and the left and right lane changing model; step 5: hierarchical training of the fusion reward function until the optimal human-machine shared driving system driving right allocation strategy is obtained and the allocation weight is output. The present application simplifies the process of allocating driving control rights in the human-machine shared driving system, and improves the efficiency and accuracy of training.

The invention belongs to the technical field of cantilever beam design, and particularly relates to an optimal design method of a cantilever beam, which comprises the following steps of: firstly, establishing a mathematical model aiming at the problem of cantilever beam design; secondly, the algorithm is introduced into an arithmetic optimization algorithm (RAOA) of Q-learning; a random elite pool strategy is introduced to further optimize the algorithm; and finally, carrying out iterative solution through an improved arithmetic optimization algorithm. According to the method, the exploration capability and the convergence speed of the algorithm are enhanced, search strategies with different capabilities are integrated, so that the search effectiveness is improved, a better solution can be obtained in a short time in practical application, and meanwhile, the search strategies can be dynamically adjusted according to different optimization problems to ensure the maximum income.

The invention discloses an urban traffic path planning method based on multi-modal multi-target differential evolution. The urban traffic path planning method is specifically implemented according to the following steps: step 1, preprocessing address data and simulating according to the address data to obtain an urban map; 2, determining an optimization target according to a map; and step 3, obtaining an optimal path by using a multi-modal multi-target differential evolution algorithm with the purpose of minimizing an optimization target. According to the method, the problem that a plurality of optimal paths cannot be found in urban traffic path planning through a multi-objective evolutionary algorithm in the prior art is solved.

The present application relates to cloud computing and distributed computing scheduling technical field, specifically belong to a kind of serverless MapReduce multi-objective scheduling optimization method, including: constructing directed acyclic graph, resource allocation decision is encoded as the solution from source node to target node, initial population is generated using hybrid initialization strategy, fitness evaluation, the crowded distance of solution in each non-dominated front is calculated, in turn execute tournament selection, adaptive crossover strategy, topological repair mutation strategy, periodically execute heuristic search guided solution injection strategy, crowded distance selection is carried out, the global Pareto optimal solution set is updated, the global Pareto optimal solution set of current time output is achieved, otherwise return iteration. The present application has the positive effect of balancing the execution cost and execution time of MapReduce job, improving the global Pareto optimal solution set quality of multi-objective scheduling scheme, enhancing the convergence speed and robustness of algorithm.

An automated industrial malt manufacturing device (11) and an agent- and digital twin-based malt manufacturing system (1) are proposed for the automated operation of the industrial malt manufacturing device (11) of the agent- and digital twin-based malt manufacturing system (1). The malt manufacturing device (11) converts supplied grains (2, 21, 21i) into output malt (3). The malt manufacturing device (11) includes: a soaking device (111) for wetting the supplied grains (2, 21, 21i) until the moisture content of the supplied grains (2, 21, 21i) reaches a certain level (111). 1) Reaching a defined moisture content level (1112); a germination device (112) configured to receive moistened grains (22) after being moistened by a soaking device (111), for germinating the moistened grains (22) by activating enzymes in the moistened grains (22) and converting the moistened grains (22) into germinated green malt (23); and a drying kiln (113) configured to receive germinated grains (23) after being germinated by the germination device (112), for drying the germinated green malt (23) to a defined moisture content level (1131). The system (1) based on intelligent agents and digital twins includes a digital twin structure (12) providing a virtual digital representation of the physical malt manufacturing equipment (11). In addition, it includes sensors and / or measuring devices (13) associated with the physical malt manufacturing equipment (11), which transmit measured sensory parameter values ​​(131), wherein the system (1) dynamically monitors the transmitted sensory parameter values ​​(131) and updates the digital twin (12) based on the parameter values.

The present invention relates to an optimization method based on a chaotic multi-strategy fusion improved whale algorithm, and belongs to the field of mechanical engineering technology. First, a tension / compression spring design problem model is constructed, and then a plurality of improvement strategies are integrated to improve the whale optimization algorithm, and then the improved whale optimization algorithm is used to optimize the mathematical model, and finally, the optimal variable combination and optimal target value of the tension / compression spring model are output. The present invention integrates a plurality of improvement strategies to improve the initial population quality and population diversity of the whale optimization algorithm, improve the convergence speed and exploration ability, avoid the tension / compression spring design method from falling into the local optimum, and make the algorithm have better optimization accuracy when solving the tension / compression spring design problem.