99results about How to "Adapt quickly" patented technology

The invention belongs to the field of power distribution network low-carbon economic optimization scheduling, and provides a power distribution network source network load storage low-carbon optimization scheduling increment reinforcement learning method and system, and the method comprises the steps: carrying out the intelligent agent division of a power grid, obtaining a plurality of intelligent agent regions, and collecting the observation data of each intelligent agent region; on the basis of the observation data, constructing a low-carbon economic dispatching model of source-grid-load-storage cooperation by taking the operation cost and carbon emission of each agent regional power grid as objective functions; designing the source-network-load-storage coordinated low-carbon economic dispatching model into a reinforcement learning model in a multi-agent environment according to a state space, an action space, an environment and a reward function; and solving the reinforcement learning model in the multi-agent environment to obtain an optimal scheduling solution. According to the incremental optimization method, the environment can help the intelligent agent to detect environment changes in training, excessive exploration risks are avoided, the training time is shortened, and meanwhile the flexibility of the system is improved.

The invention relates to the technical field of geological disaster monitoring, and discloses a debris flow monitoring and early warning system based on Internet of Things, comprising a multi-source data acquisition module used for acquiring environmental data related to debris flow; the data transmission module is used for transmitting the environment data to a data center or a cloud end from a collection point; the data preprocessing module is used for carrying out abnormal value cleaning, time synchronization and normalization processing on the environment data; the deep learning analysis module is used for analyzing the preprocessed data so as to predict the occurrence risk of debris flow; and the dynamic early warning and publishing module is used for generating a multi-stage early warning signal according to an output result of the deep learning analysis module and publishing early warning information to a user in multiple modes. The accuracy, the real-time performance and the adaptability of the debris flow early warning system are improved through multi-source data fusion, edge calculation and a dynamic learning mechanism so as to cope with debris flow disasters in a complex geological environment.

The invention discloses an automatic model tuning system based on an AI training intelligent workbench, and relates to the technical field of artificial intelligence, and the system comprises the steps: setting a data collection instrument and an environment monitoring point, collecting model real-time data in a model training process, and carrying out the preprocessing; performing model performance analysis according to the model real-time data and the model original data to obtain final parameter configuration; and performing model training by utilizing the final parameter configuration, dividing the model training process into different stages, dynamically adjusting an intelligent control strategy based on model performance requirements, and performing optimization on the different stages of the model. According to the method, through multi-dimensional performance evaluation, parameter configuration is optimized, and the robustness and generalization ability of the model are improved. Through dynamic adjustment of an intelligent control strategy, fine management of a training process is realized, efficiency and resource utilization are improved, model convergence is accelerated, and finally an efficient, stable and high-adaptability model training effect is achieved.

The invention relates to a big data and deep learning-based public opinion analysis method and apparatus, and a medium. The method comprises the steps of collecting text, image and video multi-modal public opinion data of multiple cities; performing cleaning, duplicate removal, word segmentation and stop word filtering preprocessing operation on the collected public opinion data; respectively extracting text features and image or video features by using a natural language processing technology and a computer vision technology, and fusing the features through a multi-modal fusion algorithm; by adopting a distributed system and a distributed task scheduling algorithm, cross-platform and cross-language efficient data acquisition is realized, resource allocation can be dynamically adjusted according to public opinion popularity of each city, the real-time performance and comprehensiveness of key city data are ensured, and meanwhile, through a method of combining a TF-IDF algorithm, an emotion dictionary and deep learning, the real-time performance of the city is improved. The data quality is effectively improved, and a reliable basis is provided for subsequent analysis.

The invention relates to the technical field of air conditioner control, and discloses an air conditioner load data control method and system.The method comprises the steps that firstly, meteorological parameters and load parameters of an air conditioner are collected, and data cleaning, timestamp definition and standardization processing are conducted; then, defining a feature vector according to the processed data, generating a feature data set, and constructing a load prediction model by using a neural network algorithm; and pre-training the model by using the source domain data set through a transfer learning strategy, and enhancing the target domain data to generate a new sample. Next, parameters of the pre-training model are migrated to the new task model, and partial network layer parameters are frozen to form an initialized reinforcement learning model; and finally, training unfrozen layer parameters by using the target domain data set, and finely adjusting the model to realize real-time and accurate optimal setting of the air conditioner temperature, thereby achieving the purpose of load optimization control. Through combination of transfer learning and reinforcement learning, the generalization ability, robustness and adaptability of the model are effectively improved.

The invention relates to the technical field of director and picture synthesis methods, in particular to an intelligent director and picture synthesis method of a panoramic live broadcast system, which comprises the following steps: acquiring panoramic video data shot by a panoramic camera; obtaining user feedback data; based on the panoramic video data, generating a shot selection strategy by using a deep reinforcement learning algorithm; detecting a live broadcast key event in real time by using a target detection and tracking algorithm based on the panoramic video data; generating a picture shooting plan sequence according to the shot selection strategy and the live broadcast key event; performing intelligent editing and synthesis on the panoramic video data based on the picture shooting plan sequence; and outputting the synthesized live video. And updating parameters of the deep reinforcement learning algorithm based on the user feedback data, thereby realizing full automation of the program directing process, greatly improving the efficiency, and enabling the system to continuously learn from live broadcast experience through the deep reinforcement learning algorithm and gradually improve the decision-making ability of the system.

The invention discloses an automatic driving federal reinforcement learning method based on meta learning and empirical vectors. The method comprises the following steps: constructing an automatic driving heterogeneous environment; constructing an Actor network, and updating Actor network parameters through a deterministic strategy gradient; constructing a Critic network, updating Critic network parameters through a meta learning algorithm and an error back propagation algorithm, adding experience vector integration in a training process, and updating learning experience of each automatic driving vehicle so as to optimize performance of a global strategy; in the training process, all automatic driving vehicles regularly send local Critic network parameters, Actor network parameters and local experience vectors to the central server for aggregation. According to the method, the adaptive capacity of the automatic driving vehicle to the environmental heterogeneity is improved, the problems that in existing federal reinforcement learning, the convergence speed is reduced and the strategy generalization capacity is reduced due to the dynamic change of the environment and the fluctuation of the strategy performance are solved, and therefore the training efficiency and the strategy robustness are improved.

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

The invention discloses a lithium ion battery state-of-charge estimation method and device based on transfer learning, and belongs to the technical field of battery management systems, and the method comprises the steps: obtaining current, voltage and temperature original data, and carrying out the normalization processing of the current, voltage and temperature original data, and constructing time sequence data; sequentially performing convolution processing and pooling processing on the time sequence data, and substituting the time sequence data into an LSTM network to extract time sequence features; carrying out transfer learning processing on the time sequence characteristics to obtain an SOC value of primary version prediction; and the SOC value after Kalman filtering correction is obtained from the SOC value predicted by the primary edition through a Kalman filter.

A multi-scene adaptive pedestrian trajectory prediction method based on an attention mechanism realizes trajectory prediction in multiple scenes by constructing an adaptive pedestrian trajectory prediction model, and the model design comprises the steps of extracting historical trajectory features by using a multi-head attention mechanism, and capturing interaction among pedestrians by a social attention module by using a graph convolutional network. The track alignment module further compares and aligns track characteristics in different scenes; and finally, through a sample weighted enhanced training strategy, the learning ability of the model to the complex trajectory is optimized. According to the method, the accuracy of pedestrian trajectory prediction can be remarkably improved, and the overall prediction performance and robustness are improved.

The invention relates to a heterogeneous GPU (Graphics Processing Unit) resource scheduling method and system based on the combination of meta learning and reinforcement learning, and aims to improve the utilization efficiency of computing resources in large model training and reasoning and improve the adaptive capacity of tasks and the response speed of the system. According to the method, efficient scheduling of GPU resources is achieved through the five steps of task feature extraction, meta-learning strategy initialization, reinforcement learning scheduling optimization, task scheduling execution and dynamic strategy adjustment. Wherein the meta-learning module generates an initial scheduling strategy by utilizing knowledge accumulated by historical tasks, so that the exploration time is shortened; and the reinforcement learning module continuously optimizes a scheduling strategy through environment feedback to realize efficient distribution of tasks. The system can adaptively adjust strategies according to different task requirements and dynamic changes of GPU hardware resources, and therefore higher resource utilization rate and overall performance optimization are achieved.

The invention relates to a digital factory production management method and system, and the method comprises the steps: predicting a future initial order demand based on a data analysis tool and historical sales data, and adjusting the initial order demand based on a current market trend and a current market strategy corresponding to a target peer, and obtaining a target order demand; obtaining the required production capacity and the equipment utilization rate corresponding to each piece of production equipment based on the target order demand; acquiring real-time operation data corresponding to each piece of production equipment, and predicting maintenance requirements corresponding to the real-time operation data, the required production capacity and the equipment utilization rate based on the trained deep learning model; and making a maintenance plan of each production device in advance based on the maintenance demand and the maintenance priority corresponding to each production device. The production equipment is subjected to preventive maintenance, the reliability and stability of the production equipment are improved, the use of maintenance resources is optimized, and the maintenance efficiency and quality are improved.

The invention relates to the technical field of marine monitoring, in particular to a Transform-based marine organism population anomaly monitoring method and system. The method comprises the following steps: acquiring marine organism population data of different monitoring points, including remote sensing satellite image data, time sequence measurement data of an underwater sensor network and high-resolution image data acquired by an unmanned aerial vehicle; preprocessing the acquired marine organism population data; performing feature screening on the marine organism data based on a gate control mechanism; carrying out anomaly detection on the screened features on the basis of a Transform model; and outputting an anomaly detection result and feeding back the anomaly detection result to the Transform model for retraining. According to the self-adaptive feature screening method based on the gate control mechanism, the features most relevant to the marine organism population change can be automatically recognized and screened out, and therefore interference of data redundancy and noise is reduced.

The invention relates to the technical field of legal information processing, and discloses a legal instrument intelligent supervision and verification method, which comprises the following steps: receiving a legal instrument uploaded by a user, the legal instrument comprising text content, image data and audio information; extracting the text content of the legal document through an optical character recognition technology, and generating a corresponding text feature vector; the invention also discloses an intelligent supervision and verification system for the legal instruments, and the system comprises a data storage module which is used for storing the legal instruments uploaded by the user, and the extracted text feature vectors, image feature vectors and audio feature vectors. Dynamic rule optimization is realized through an intelligent self-learning check engine, and manual intervention is reduced; intelligent rule generation improves efficiency and accuracy; a multi-modal feature fusion technology is used for comprehensively analyzing legal documents and providing accurate compliance analysis; a real-time risk assessment mechanism ensures instant feedback, and legal risks are effectively reduced.

The invention provides an index system construction method and system for electricity market operation, and the method comprises the steps: integrating data from different sources of an electricity market, and carrying out the preprocessing of the data; pre-processed data are obtained, and self-supervised data extraction is carried out on the data from the pre-processed data; constructing a power market multi-task meta-learning optimization model; a real-time operation index system of the electricity market is constructed and dynamically adjusted; a multi-target strategy optimization algorithm is constructed, and an optimal market strategy is designed according to the market indexes adjusted in real time; and carrying out system learning and system adaptive updating according to the optimal market strategy, and keeping the optimal performance. By combining meta-learning and self-supervised learning technologies, the system can quickly adapt to different market environments and scenes, automatically mine and generate key operation indexes from large-scale unmarked power market data, and realize real-time updating and optimization of the index system.

The invention provides a high-precision attitude estimation method for processing limited data based on a pre-training diffusion model, and the method comprises the steps: carrying out the preprocessing of an input image, and calling a function to combine with noise to generate a key point prompt; mapping the input image through an encoder to obtain a potential code, and increasing Gaussian noise of different amplitudes on the potential code to obtain a noise image; performing attention mechanism processing on the noise image to obtain a semantic corresponding point between the input image and the reference image; training the image pair, integrating training results of the basic class image and the new class image, and inputting an integration result into an Adam optimizer for optimization to obtain an optimization result; evaluating the image pair; according to the method, the key points of the unlabeled image data can be learned in a cross-category mode, a good attitude estimation effect is achieved under the condition that the data is limited, and the actual application value of attitude estimation is improved.

The invention relates to the field of Wenchang chicken breeding methods, in particular to a Wenchang chicken breeding method capable of achieving multi-stage accurate feeding and disease early warning. The method comprises the following steps: S1, breeding in a chick transition stage: establishing a Wenchang chick transition room, S2, breeding in a growing period stage: adopting a mixed mode of free-range breeding and artificial feeding, and S3, breeding in an optimization period: selecting chickens for cage breeding; in the Wenchang chicken breeding process, the Wenchang chickens are bred in a multi-stage precise feeding mode, when chicks are introduced in the initial stage, a transition chamber is established, a nutritional agent containing rhizoma atractylodis macrocephalae, radix astragali, multivitamin powder and probiotics is added into feed, feeding is conducted in the Wenchang chicken breeding stage, the mixed mode of free-ranging and artificial feeding is adopted, and the breeding efficiency of the Wenchang chickens is improved. Nutritional agents containing multivitamin powder, probiotics, hawthorn fruit powder and medicated leaven are added in fixed-point feeding, good chickens are selected for cage culture in the optimization period of Wenchang chickens, traditional Chinese medicine agents are added, disease prevention and early warning can be conducted on the Wenchang chickens, and the Wenchang chickens are natural, small in toxic and side effect and easy to metabolize.

The invention discloses a multi-energy complementary power distribution control method, belongs to the technical field of electric power system control, and aims to solve the problems that an existing multi-energy system control method based on periodic instruction issuing is heavy in communication burden, response lags when sudden disturbance is dealt with in two scheduling intervals, and the power distribution efficiency is poor. And the operation economy and the dynamic stability are difficult to consider at the same time. The method comprises the steps that an upper-layer optimization controller generates virtual impedance potential field function parameters and key topological characteristics and issues the virtual impedance potential field function parameters and the key topological characteristics to a local controller; the local controller executes power control based on the potential field gradient and monitors the topological position of the operation point; when a topology crossing event is detected, an asynchronous event triggering signal is sent upwards, and an upper-layer controller is triggered to carry out aperiodic re-planning. According to the method, decoupling of economic optimization and dynamic control is realized, the robustness and the adaptive capacity of the system under disturbance are improved, meanwhile, the communication burden is reduced, and the method is suitable for a system containing a large amount of distributed energy.

The invention relates to the technical field of micro-grid load prediction, and discloses a multi-factor efficient fusion micro-grid load short-term prediction model optimization method. According to the method, micro-grid load historical data and multi-source factor data including information such as meteorology and electricity price are collected, and one-hot coding and normalization processing are carried out. Load data is decomposed into high-frequency and low-frequency components by using a variational mode decomposition technology, and prediction is carried out by respectively adopting a long-short-term memory network integrated with an attention mechanism and a linear regression model. And by calculating the difference between the source domain data and the target domain data in the model hidden layer feature space, the domain adaptive capacity of the model is enhanced, and accurate short-term prediction of the microgrid load is realized.

The invention discloses a fast slew rate enhancement system of an operational amplifier, which comprises a current identification circuit for monitoring the current of a load tube current mirror structure in the operational amplifier; the comparator is used for comparing the current monitored by the current identification circuit or a signal related to the current with a threshold value, judging the size of the monitored current, taking a comparison result of the comparator as a basis for judging that the slew rate is limited, and starting an enable signal of the corresponding slew rate enhancement circuit; and the slew rate enhancing circuit is used for enhancing the slew rate of the operational amplifier by utilizing the slew rate enhancing enable signal identified by the comparator. Whether the operational amplifier is in the slew rate limited state or not is judged according to the chip internal current signal change of the load current mirror tube in the operational amplifier, and interference of off-chip noise signals is effectively prevented; and meanwhile, the influence of the operational amplifier input imbalance on the slew rate triggering system is reduced because the operational amplifier input imbalance is irrelevant to the operational amplifier differential input pair transistor imbalance.

The high-strength three-way welding connection structure for the hydrogen conveying pipeline belongs to the field of three-way welding and comprises a base, two sliding grooves are formed in the upper surface of the base, first motors are fixed to the left side and the right side of the base correspondingly, and output shafts of the first motors penetrate into the sliding grooves and are fixedly connected with first screw rods; vertical frames are in threaded connection with the outer surfaces of the first screws, second motors are fixed to the opposite sides of the two vertical frames, and the opposite ends of output shafts of the two second motors penetrate to the opposite sides of the two vertical frames correspondingly. Supporting is provided from the inner wall of the three-way pipe through the supporting rollers, the transverse pipe positioning mechanism applies clamping force from the outer wall through the clamping blocks, a double-positioning structure of inner supporting and outer clamping is formed, it is ensured that three ports of the three-way pipe are strictly coaxial, and welding deflection is avoided; the clamping force can be automatically adjusted according to the small difference of the pipe diameters of the three-way pipes, the three-way pipes of different specifications can be rapidly matched through linear driving of the sliding frame and the air cylinder, and the universality is remarkably improved.

A control method for a vehicle steering system and a controller are disclosed. The method comprises the following steps: acquiring a first steering wheel angle and a first yaw velocity of a target vehicle during operation; determining a theoretical system response value based on a system transfer function of the target vehicle and the first steering wheel angle, and fusing the first yaw velocity and the theoretical system response value into a second yaw velocity; determining an error value based on the target yaw velocity and the second yaw velocity, and inputting the error value into a position closed-loop PID controller to obtain a rotation angle increment; whether a steering wheel motor of the target vehicle supports a speed closed-loop PID controller or not is judged, if not, the rotation angle increment is output to the steering wheel motor, if yes, the rotation angle increment is output to the speed closed-loop PID controller, a rotation speed instruction is obtained, and the rotation speed instruction is output to the steering wheel motor. In addition, parameters in the closed-loop PID controller can be automatically calibrated. The debugging efficiency and the performance of the vehicle steering system can be improved through the method.

The invention provides a wine brewing wastewater treatment device, and belongs to the technical field of wine brewing wastewater mushroom dregs. Comprising a fermentation reaction bin, the top of the fermentation reaction bin is provided with a feeding pipe bin, one side of the feeding pipe bin is provided with an auxiliary agent bin, the top of the fermentation reaction bin is provided with a biological agent bin, and the side of the fermentation reaction bin is provided with a control center. By arranging the sprinkling adjusting assembly and the stirring and mixing assembly, a microbial agent and an auxiliary agent are fully contacted and mixed, the activity of the microbial agent is improved, the degradation process of the fermented glutinous rice wastewater is accelerated, the treatment efficiency is improved, meanwhile, the microbial agent is more uniformly distributed in the fermented glutinous rice wastewater through stirring, the consistent reaction effect of each area is ensured, and the treatment effect is improved. The phenomenon of insufficient local treatment is avoided, blockage is avoided, it is guaranteed that the microbial inoculum content concentration and the fermentation speed of all areas are equal, damage caused by device pressure drop during blockage is avoided, the service life of equipment is prolonged, and the production cost is reduced.

The invention relates to a rapid charge supply device for spacecraft pulse charge emission, and belongs to the field of space charging and discharging. The bottom plate is of a plate-shaped structure which is horizontally arranged in the axial direction; the cathode is of a cylindrical structure; the cathodes are in coaxial butt joint; the anode is of a cylinder structure; the anode is coaxially arranged in the inner cavity of the cathode; the root of the anode is butted with the bottom plate; the working medium sleeves the outer wall of the middle part of the anode and is filled between the cathode and the anode; the spring is sleeved on the outer wall of the anode root; one end of the spring is contacted with the bottom plate; one end of the spring contacts with the working medium end face; the insulating assembly is arranged at the opening of the axial head end of the cathode; two poles of the energy compression module are respectively connected with the cathode and the anode; the power supply is connected with the energy compression module to charge the energy compression module; a charge self-consistent cavity is formed on the outer side of the opening of the axial head end of the cathode; when the device is used for spacecraft pulse charge beam output, rapid supply in the pulse is achieved, and the spacecraft is kept electrically neutral in real time.

The invention provides a passive active field self-adaptive polyp semi-supervised segmentation and classification system and a passive active field self-adaptive polyp semi-supervised segmentation and classification method. The segmentation and classification system comprises a data collection module, a data preprocessing module, a source domain sample screening module, a target domain sample screening module, a data labeling module, a polyp segmentation and classification model construction module and a polyp segmentation and classification model semi-supervised training module. According to the method, a certain number of representative samples are screened out through a source domain sample screening module, and a certain number of representative samples, inter-domain similar samples with relatively high similarity with source domain features and inter-domain difference samples with relatively low similarity with the source domain features are screened out through a target domain sample screening module; and marking the screened samples, and subsequently training a polyp segmentation and classification model through a cross pseudo-supervision consistency strategy to obtain final model parameters. According to the method, the dependence of the polyp segmentation and classification model on the labeled data volume can be greatly improved, and the method has good cross-medical center robustness.

The application discloses a three-level coordinated production line body intelligent control method and system, and belongs to the technical field of intelligent manufacturing. The method comprises the following steps: establishing a global task planning layer, performing semantic analysis and logical disintegration at a first preset frequency, and generating an atomic action sequence; establishing a local space perception layer, receiving the atomic action sequence at a second preset frequency, constructing a dynamic local map by using sensor data, determining a workpiece pose by point cloud registration, and mapping the atomic action sequence into a continuous motion trajectory flow; establishing a real-time action execution layer, receiving an instantaneous target pose at a third preset frequency, calculating a theoretical driving torque by combining a Lagrange dynamics equation, switching to an impedance control mode at a contact moment, and driving an execution mechanism to complete work; and establishing an asynchronous coordination layer, realizing three-layer asynchronous communication through an industrial network, and controlling the three-layer frequencies to be distributed in a ladder type in an increasing manner. The application has the effects of improving the flexibility, precision and safety of a production line.

The invention provides a zero-shot SAR image recognition method based on a dual-branch autoencoder, which belongs to the technical field of image processing. The method comprises: constructing a dual-branch generation network G‑Net to extract semantic features and visual features of images in a training set; inputting fused features into a classification network C‑Net and a conversion network T‑Net, wherein the classification network C‑Net outputs target classification of the SAR image, and the conversion network T‑Net outputs a reconstructed image of the SAR image, and the positions of all known targets in a feature space are obtained; and back-propagation gradient optimization is performed on the network by calculating known target classification and image reconstruction losses to predict the positions of unknown targets in the feature space. The invention realizes accurate recognition of known targets and effective distinction of unknown targets, and solves the problem of distribution concentration in zero-shot SAR image recognition tasks.

The invention discloses a public security event identification method based on small sample learning and a knowledge graph, which comprises the following steps: generating a virtual scene similar to a real event scene through the combination of small sample data and the knowledge graph, and dynamically activating nodes related to the event through a knowledge activation threshold value, freezing and storing the unrelated nodes, and dynamically releasing frozen nodes; identifying dynamic evolution of the event by monitoring node relation fluctuation in the knowledge graph; a multidimensional event analysis result is generated through mutual reinforcement of a graph fission mechanism and an interactive training mechanism; generating a risk path identification result through the event aggregation trigger point; the scheme has the characteristics of realizing efficient learning of small samples, enhancing semantic understanding ability, dynamically adapting to diversified scenes, improving event identification flexibility and constructing a global risk assessment framework.

The utility model relates to the technical field of metal processing auxiliary equipment, and discloses an aligning and positioning tool for laminated processing of metal plates, which comprises a square guide rail, a sliding guide rail and a positioning component. A protruding block is arranged on the inner side of the square guide rail and connected with the two sliding guide rails in a sliding mode, a vertically-sliding positioning piece is arranged in each sliding guide rail, each positioning piece is composed of a sliding part and a rotating part, and the rotating parts are in rolling contact with the plate through the limiting holes. An elastic telescopic rod is arranged between the sliding guide rails to achieve self-adaptive adjustment, and the square guide rails drive the sliding guide rails to move oppositely through electric push rods. The working panel is provided with a guide groove and a slidable positioning sleeve, and plates are diagonally fixed through bolts. According to the tool, the electric push rod drives the positioning piece to conduct multi-direction linkage, the elastic telescopic rod and the rolling contact structure are combined, four-direction automatic positioning of the plate is achieved, the problems that a traditional tool is low in positioning efficiency and poor in precision are effectively solved, and the tool has the advantages of being capable of rapidly adapting to plates of different sizes, stable in multiple angles, capable of preventing deviation and capable of improving the machining precision.