Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

446results about How to "Address limitations" patented technology

Intelligent customer service method for adaptively adjusting interaction strategy by using reinforcement learning

The invention discloses an intelligent customer service method for adaptively adjusting an interaction strategy by using reinforcement learning, and the method comprises the following steps: S1, obtaining a natural language text inputted by a user, and generating a multi-dimensional state vector; s2, grouping the users by using a real-time dynamic clustering algorithm, and updating a clustering result; s3, generating an action space in a specific state, and enriching the action space in combination with a rule-based strategy and a learning-based strategy; s4, aggregating neighbor node features through a graph convolutional network, and extracting local features; s5, weighting adjacent node features by using a graph attention network, and dynamically allocating attention weights; s6, carrying out interaction strategy optimization by adopting a spiral ladder type deep exploration network, and optimizing action selection; and S7, combining online learning with an experience playback mechanism, continuously updating an interaction strategy, and making a quick response to dynamically changing user demands. According to the method, reinforcement learning, the graph neural network and the sentiment analysis technology are combined, and intelligent customer service interaction strategy self-adaptive adjustment and optimization are achieved.
Owner:KEXUN JIALIAN INFORMATION TECH CO LTD +1

Evaluation method and system for targeted medication scheme

The invention relates to the technical field of intelligent medical treatment, in particular to an evaluation method and system for a targeted medication regimen, and the method comprises the steps: building a comprehensive database which comprises basic information, gene expression data, protein interaction information and integrated treatment data of a patient; obtaining a targeted medication scheme of the current patient; analyzing gene expression data of the targeted medication scheme, evaluating the curative effect of the targeted medication scheme, and forming a curative effect dimension; constructing a protein interaction network, combining gene expression data with a protein network, analyzing molecular characteristics of a tumor of a patient, identifying and confirming a target spot of a drug, and forming an individual adaptability dimension; and establishing a multi-dimensional evaluation space, taking the curative effect dimension and the individual adaptability dimension as independent dimension input, and comprehensively generating a multi-dimensional evaluation result according to the safety dimension and the economical efficiency dimension of the targeted medication scheme, the curative effect dimension and the individual adaptability dimension, and outputting the multi-dimensional evaluation result. The problems that an existing targeted medication evaluation method is single and limited are effectively solved.
Owner:CHANGZHOU BERGER MEDICAL LAB CO LTD

Code peculiar smell detection method and system based on AST code measurement and code semantics

The invention provides a code peculiar smell detection method and system based on AST code measurement and code semantics. The method comprises the following steps of: firstly, constructing a FA-AST (Flow-Augmented Abstraction Syntax Tree) by analyzing a code snippet, and extracting three types of AST-based code metrics, namely a structure metric, a syntactic metric and a semantic metric from the FA-AST; then, a deep learning model is used for capturing contextual information and a dependency relationship of the code from the source code so as to extract code semantics; and finally, by fusing AST-based code measurement and code semantics, inputting a classification model to carry out training and testing so as to identify the peculiar smell in the code and evaluate the severity of the peculiar smell. Compared with software code measurement extracted by a traditional static code analysis tool, the AST-based code measurement provided by the invention is more comprehensive and easier to extract, and has obvious advantages in the aspect of improving the code odor detection precision and efficiency.
Owner:HANGZHOU DIANZI UNIV +1

Zero sample reference image segmentation method based on hierarchical prompt and directional clue

The invention discloses a zero sample reference image segmentation method based on hierarchical prompt and directional clues. The method comprises the following steps: firstly, acquiring masks of all object instances in an input image through a hierarchical prompt mask generation network; and extracting and fusing the comprehensive visual feature and the focus visual feature based on a directional clue to obtain a comprehensive-focus visual feature. Then, generating a title text and a negative expression text by using a pre-training model BLIP2, and extracting text features by using a CLIP text encoder; and for the input text T, extracting and fusing the comprehensive text feature and the focus text feature to obtain a comprehensive-focus text feature. Finally, the cosine similarity between the image I and the text T is calculated through a pre-training model CLIP, the mask center serves as position information through a space rectifier, and the mask with the highest matching score is selected. According to the method, accurate instance masks can be generated in sheltered and complex scenes, the problem that CLIP is insensitive to spatial position information is solved, and excellent performance is shown.
Owner:ZHEJIANG UNIV

Photovoltaic bracket

The present application provides a photovoltaic bracket, including: a load-bearing module for fixedly connecting to a wall; a support module for installing a photovoltaic panel, and the support module has at least three connecting parts; a transfer module, including a first connecting member and a second connecting member; the first connecting member includes a rotating rod, one end of the rotating rod is rotatably connected to the load-bearing module, and the other end of the rotating rod is rotatably connected to the first connecting part; the second connecting member is fixedly connected to the load-bearing module, and the second connecting member can be detachably connected to the second connecting part or the third connecting part; when the second connecting member is detachably connected to the second connecting part, the distance between the first connecting part and the load-bearing module is the first distance, and when the second connecting member is detachably connected to the third connecting part, the distance between the first connecting part and the load-bearing module is the second distance, and the first distance is greater than the second distance. Based on the photovoltaic bracket provided by the present application, the problems of limited application scenarios and inconvenient maintenance of photovoltaic brackets existing in related technologies can be solved.
Owner:HOYMILES POWER ELECTRONICS INC +1

Visual data platform full-link data flow tracing method, system, device and medium

The invention relates to the technical field of big data management and data analysis, and discloses a visual data platform full-link data flow traceability method, system and device and a medium, and the method comprises the steps: monitoring a job scheduling process submission event, analyzing the input and output configuration information of each job node, converting the information into a data flow model, and storing the data flow model in a traceability database; static analysis is conducted on node scripts and codes, and analysis results are stored in a traceability database; generating a unique identifier for each data record, and recording related information in a data circulation process; and writing the data flow relationship into a graph database Neo4j through a Kafka asynchronous message, and performing data traceability query by a user through a visual interface. The method has the beneficial effects that the data quality and safety are improved, and the limitation and complexity of a mainstream open source tool in the aspect of a data blood relationship analysis function are solved.
Owner:LUCULENT SMART TECHNOLOGIES CO LTD

Bearing fault diagnosis method and device

The invention discloses a bearing fault diagnosis method and device, and relates to the technical field of bearing fault diagnosis, and the method comprises a model training step, a model integration step and a fault diagnosis step, and the model training step provides a trained diagnosis model for the model integration step. The anomaly detection model output in the model integration step is used as the model algorithm input in the fault diagnosis step, and the model integration step is used for integrating a plurality of models to improve the diagnosis accuracy and the system robustness; the model integration step comprises the steps of multi-model integration, dynamic model selection and anomaly detection. According to the bearing fault diagnosis method, the model integration step is designed, the advantage integration function of multiple models is achieved, the limitation problem when a single model processes complex and changeable fault modes is solved, fault diagnosis is difficult to comprehensively and accurately conduct, the accuracy and robustness of a bearing fault diagnosis system are improved, and the fault diagnosis efficiency is improved. Fault detection under complex working conditions can be better handled, and the probability of false alarm and missing alarm is reduced.
Owner:YANCHENG SHURONGZHISHENG TECH CO LTD +1

GIS combined electric appliance operation monitoring and state evaluation system based on multi-feature fusion

The invention discloses a GIS combined electric appliance operation monitoring and state evaluation system based on multi-feature fusion, and relates to the technical field of electric appliance monitoring. When the system operates, comprehensive monitoring and accurate evaluation are carried out on the operation state of an electric appliance, multiple types of sensors and Internet of Things equipment are deployed inside and outside GIS equipment, and the operation state parameters of the equipment are collected in real time; the feature fusion module is used for establishing a multi-modal data fusion model by using a data fusion algorithm, acquiring a comprehensive evaluation index Pgzs, matching the comprehensive evaluation index Pgzs with a preset equipment operation state evaluation threshold P, generating an electric appliance operation state evaluation scheme, and performing data fusion on the electric appliance operation state evaluation scheme; and then, display and notification are carried out in various modes, so that subtle changes of various parameters in the operation process of the electric appliance can be captured and analyzed in real time, the accuracy and comprehensiveness of evaluation are improved through multi-modal data fusion, and early warning of abnormal conditions is carried out in time.
Owner:LIAOYUAN POWER SUPPLY COMPANY STATE GRID JILIN ELECTRIC POWER +1

Emotion recognition method and system based on electroencephalogram signals, storage medium and electronic equipment

PendingCN119128709ASolve the problem of weakened memorySpeed ​​up the training convergence processInput/output for user-computer interactionBiological modelsData setSignal on
The invention provides an emotion recognition method and system based on electroencephalogram signals, a storage medium and electronic equipment. The method comprises the following steps that the electroencephalogram signals and corresponding label information are obtained; the electroencephalogram signals are preprocessed based on the electrode positions of the electroencephalogram signals, and a three-dimensional brain feature map is obtained; forming an electroencephalogram signal data set based on the three-dimensional brain feature map and the label information; and training an emotion recognition depth model based on the electroencephalogram data set so as to realize emotion recognition based on the trained emotion recognition depth model. According to the emotion recognition method and system based on the electroencephalogram signals, the storage medium and the electronic equipment, accurate emotion recognition is achieved through the electroencephalogram signals on the basis of a mixed structure of the convolutional neural network and the Transform.
Owner:SHANGHAI UNIV +1

Multi-modal data fusion method and system, readable storage medium and computer equipment

The invention provides a multi-modal data fusion method and system, a readable storage medium and computer equipment, and the method comprises the steps: obtaining modal data corresponding to each equipment node, the modal data comprising text data, image data, video data and audio data, and each equipment node corresponding to one modal data; performing gradient learning on the initial local model on each equipment node according to the modal data to obtain a final local model on each equipment node; and fusing the final local models on the equipment nodes by adopting a weighted average algorithm to obtain an initial fusion model, and carrying out iterative convergence on the initial fusion model to obtain a final fusion model. According to the method, multi-modal and cross-modal federated learning can be realized, so that correlation information among different modals can be better captured, the performance and generalization ability of the model are improved, and more comprehensive data understanding and application are realized.
Owner:GUANGZHOU UNIVERSITY

Basin ecological safety monitoring method and system based on big data

The invention discloses a drainage basin ecological safety monitoring method and system based on big data. The method comprises the steps of data acquisition, data preprocessing, drainage basin ecological environment monitoring, drainage basin ecological system monitoring, hyper-parameter optimization and drainage basin ecological comprehensive monitoring. The invention belongs to the technical field of ecological safety information processing, and particularly relates to a drainage basin ecological safety monitoring method and system based on big data, according to the scheme, ecological environment monitoring and ecological system monitoring are creatively and deeply fused, and the comprehensiveness and accuracy of drainage basin ecological safety monitoring are improved; adjacent domain similarity, a standard deviation adjustment distance and a distribution coefficient are introduced, a selection process of a clustering center is optimized, and the technical problem that a watershed ecosystem monitoring result is not accurate enough is solved. The algorithm for obtaining the optimal parameters of the monitoring model is improved by adopting the dynamic adaptation factors, the opposite individuals and the individual symbiotic update, the optimal parameter combination is obtained, the accuracy of the model output result is improved, and the drainage basin ecological environment monitoring result is more accurate.
Owner:CHONGQING UNIV +1

Thermal generator set load prediction system based on machine learning

The invention discloses a thermal generator set load prediction system based on machine learning, and the system overcomes the defects of a conventional load prediction method through an end-to-end solution composed of a comprehensive data collection module, a multi-level feature engineering module, a multi-model integration module, a self-adaptive optimization module and the like. The system collects multi-dimensional data from a thermal generator set control system, an environment monitoring system, a fuel detection system and a historical database, wherein the multi-dimensional data comprises load data, environment data, fuel characteristics and equipment operation data. According to the multi-dimensional data integration mode, the model not only depends on single historical load data, but combines multiple influence factors such as environment, fuel and equipment states, the problem that a traditional method depends on a single data source is solved, the load prediction precision is effectively improved, and the load prediction efficiency is improved. And the adaptive capacity of the prediction model to different environment conditions and equipment states is stronger.
Owner:HUANENG JILIN POWER GENERATION CO LTD CHANGCHUN THERMAL POWER PLANT

Configuration method and system of sensing signal

The invention discloses a sensing signal configuration method and system. The method comprises the following steps: calculating a target distance which can be sensed by adopting a target sensing signal according to parameters of a base station, the target sensing signal comprising a continuous wave sensing signal or a pulse sensing signal; determining a target sensing distance range according to the target sensing scene; and determining a target sensing signal configured for the base station according to the size relationship between the target distance and the boundary value of the target sensing distance range.
Owner:ZTE CORP

Typical fault simulation test platform and test method for real-type power distribution network in low-voltage transformer area

The invention discloses a typical fault simulation test platform for a real-type power distribution network of a low-voltage transformer area, as shown in Figure 1, comprising a low-voltage transformer area simulation structure which is connected with a transformer area fusion terminal in a wireless mode. The low-voltage transformer area simulation structure is further connected with a low-voltage fault simulation device and low-voltage intelligent equipment through wiring terminals in a circuit, and the low-voltage fault simulation device and the low-voltage intelligent equipment are connected with the low-voltage transformer area simulation structure in a wireless mode. The low-voltage intelligent device is also connected with the low-voltage fault simulation device and the transformer area fusion terminal in a wireless mode. The invention also discloses a method for testing by using the typical fault simulation test platform for the real-type power distribution network of the low-voltage transformer area. According to the typical fault simulation test platform for the real-type power distribution network in the low-voltage transformer area, the running state of the power distribution network in the low-voltage transformer area can be truly simulated, various typical faults of the low-voltage power distribution network can be reproduced, and the problem that an existing test platform cannot achieve a real test effect is solved.
Owner:POWER RES INST OF STATE GRID SHAANXI ELECTRIC POWER CO LTD

Drilling rig for geological prospecting

The invention belongs to the field of drilling equipment, and discloses a drilling device for geological prospecting, which comprises a chassis, a triangular vertical frame is fixed at the top end of the chassis, a triangular table is fixed at one end in the triangular vertical frame, and a drill spindle body is arranged at the center position in the triangular table. The bottom end of the triangular table is provided with a side gear reduction driving unit used for driving the drill spindle body to rotate and running the drill spindle body to conduct Z-axis sliding. And the bracket is arranged at the other end in the triangular vertical frame. Through the design of the Z-axis lead screw type drilling feeding assembly, the drilling depth can be flexibly adjusted under the condition that equipment is not replaced and does not need to be lifted, the limitation of traditional drilling equipment on the depth and efficiency is solved, more geological information can be obtained, a more reliable foundation is provided for resource development, and the drilling efficiency is improved. And the drill rod body is connected through the shaft rod sliding connection structure, so that the drilling period is shortened, and the construction cost is reduced.
Owner:THE EIGHTH GEOLOGICAL BRIGADE OF SHANDONG PROVINCIAL BUREAU OF GEOLOGICAL & MINERAL EXPLORATION & DEV (SHANDONG PROVINCIAL EIGHTH GEOLOGICAL & MINERAL EXPLORATION INST)

Anti-locking fixing device for secondary cable construction

The invention relates to the field of cable construction devices, in particular to an anti-locking fixing device for secondary cable construction. Comprising a support adjusting mechanism, a wire dragging mechanism and / or a corner mechanism, the support adjusting mechanism comprises a central column, an adjusting mounting seat, a telescopic column, a support base and a driven rotating rod; the adjusting mounting seat is arranged on the central column in a sleeving manner; the telescopic column is arranged on the outer side of the central column, and the upper end of the telescopic column is rotationally connected with the adjusting mounting seat; the middle of the telescopic column is rotationally connected with the driven rotating rod and rotationally connected with the lower portion of the center column through the driven rotating rod. The interior of the central column is hollow and is used for mounting a wire dragging mechanism and / or a corner mechanism; the wire dragging mechanism comprises a wire dragging frame and a wire dragging guide wheel. The wire dragging frame is composed of a wire dragging fixing rod and a U-shaped frame fixed to the wire dragging fixing rod. The corner mechanism comprises a corner frame, a corner guide wheel and a guide wheel upper plate; the corner bracket comprises a guide wheel lower plate, a corner fixing rod fixedly connected to the lower portion of the guide wheel lower plate, and a guide wheel column installed on the upper portion of the guide wheel lower plate.
Owner:SUQIAN POWER SUPPLY COMPANY OF JIANGSU PROVINCE POWER +2

Battery SOC estimation method and device based on Kalman filtering, electron and medium

The invention belongs to the technical field of battery parameter estimation, and particularly relates to a battery SOC estimation method and device based on Kalman filtering, equipment and a medium. According to the scheme provided by the invention, aiming at the problems of small error and large influence caused by the voltage plateau period of the battery when SOC estimation is carried out on the lithium iron phosphate battery by a traditional Kalman filtering method, on the basis of a Kalman filtering algorithm, the improved formula is introduced, and the value of the gain G in the voltage plateau period in the improved formula is determined, so that the SOC estimation accuracy of the lithium iron phosphate battery is improved. The SOC estimation precision of the lithium iron phosphate battery is effectively improved, the maximum effectiveness of the battery can be ensured through accurate SOC estimation, the cost is reduced, and resource waste is prevented.
Owner:JINAN UNIVERSITY +1

Charged particle identification method, charged particle identification system based on screen grid ionization chamber, computer equipment and storage medium

The invention discloses a charged particle identification method, a charged particle identification system based on a screen grid ionization chamber, computer equipment and a storage medium, and belongs to the technical field of radiation detection. The charged particle identification method comprises the following steps: acquiring signals generated by charged particles at a cathode and an anode of a detector and generating characteristic quantities; constructing particle identification parameters by using the obtained characteristic quantity; generating a two-dimensional spectrogram according to the identification parameters and observing distribution characteristics of different particle events; and identifying different particles according to the distribution characteristics of different particle events in the two-dimensional spectrogram. Particle energy is associated with an ionization range during identification, the problem of limitation of a traditional particle identification technology in a high event rate and complex particle product environment is solved, especially the capability of processing a tritium nuclear event superposition phenomenon in a resonance energy region is improved, and therefore the problem that due to the fact that the energy resolution is low, the probability of tritium nuclear event superposition is low can be solved. And the defect problem in the prior art that the detection range is limited due to the fact that complex particle types cannot be accurately identified is solved.
Owner:XI AN JIAOTONG UNIV

Super-resolution image processing method and device based on artificial intelligence

The invention relates to the technical field of artificial intelligence and image processing, in particular to a super-resolution image processing method and device based on artificial intelligence, and the method comprises the steps: obtaining a first target image meeting a first preset resolution condition, segmenting the first target image, and obtaining a second target image meeting a preset pixel condition; aligning pixels of the second target image by using the extracted depth features of the second target image to obtain a third target image; and performing feature fusion processing on the third target image by using a preset target neural network, and obtaining an RGB image meeting a second preset resolution condition from the first target image according to the fused image. Therefore, the problem of limitation of an image super-resolution processing mode in related technologies is solved, the applicability of the image super-resolution method is improved, the complexity of image super-resolution operation is reduced, and the efficiency of image super-resolution processing is improved.
Owner:TSINGHUA UNIVERSITY

Voltage transformer DC bias test device for photovoltaic power generation and control method thereof

The invention discloses a voltage transformer direct current bias test device for photovoltaic power generation and a control method thereof in the field of electrical measurement. The device and the control method thereof comprise a first voltage regulator, an alternating current booster, a direct current voltage source and a voltage divider for monitoring. The components form a direct current bias voltage source which is connected with a primary coil of a voltage transformer for photovoltaic power generation in parallel and applies direct current bias power frequency test voltage, a second alternating current voltage source is connected with a standard voltage transformer in parallel and applies processing frequency alternating current test voltage, and a voltage divider for monitoring monitors voltage output by the direct current bias voltage source. Secondary coil output voltages of a tested mutual inductor and a standard mutual inductor, a voltage of a primary current flowing through a sampling resistor and an output voltage of a voltage divider are measured and input to a voltage transformer direct current bias performance measurement unit; and obtaining an error of the tested voltage transformer for photovoltaic power generation under a direct current bias condition, a primary current waveform, and a power frequency alternating current component and a direct current bias component of output voltage of a direct current bias voltage source.
Owner:ZHEJIANG HORIZON INSTR TRANSFORMERS

Drug production process supervision platform

The invention discloses a medicine production process supervision platform, and relates to the technical field of traditional Chinese medicine decoction production process supervision, and the platform comprises a data acquisition module, a basic data analysis unit and a harmful data analysis unit of a data analysis module, an abnormity analysis module, and an abnormity processing module. By analyzing the basic data and the harmful data of the traditional Chinese medicine decoction and then analyzing the abnormal conditions of the basic data and the harmful data of the traditional Chinese medicine decoction, the problem of limitation existing in the current abnormal analysis process of the traditional Chinese medicine decoction is solved, and when the basic data or the harmful data of the traditional Chinese medicine decoction is abnormal, the abnormal condition of the traditional Chinese medicine decoction is analyzed. The data of the raw materials are analyzed, and if the raw materials are not abnormal, abnormal conditions of the production process of the traditional Chinese medicine decoction are analyzed and judged, so that comprehensive and objective analysis of the traditional Chinese medicine decoction is realized, and the reliability and authenticity of abnormal condition analysis results of the traditional Chinese medicine decoction are guaranteed.
Owner:SHANDONG YANGDU JIANHUA PHARM CO LTD

Display module, display device, handwriting pen, interaction system and interaction method

The invention discloses a display module, a display device, a handwriting pen, an interaction system and an interaction method.According to one embodiment, the display module comprises a light-emitting device layer and a coding position layer which are arranged on a substrate, and the light-emitting device layer comprises a plurality of pixel units arranged in an array; the plurality of pixel units at least comprise a plurality of pixel groups which are arranged in an array according to a preset touch identification unit; the coding position layer comprises a coding pattern layer and an auxiliary pattern layer, and the coding pattern layer comprises coding patterns which correspond to the pixel groups, are used for identifying position information and absorb light with a preset wavelength; the auxiliary pattern layer comprises auxiliary patterns which correspond to the pixel groups, are used for at least forming optical display effect complementation with the coding patterns of the pixel groups and penetrate through the light with the preset wavelength, and orthographic projections of the auxiliary patterns and the coding patterns and the patterns on the substrate fall into orthographic projections of the pixel units of the pixel groups on the substrate. According to the embodiment, the display effect of the display module is effectively improved.
Owner:BOE TECHNOLOGY GROUP CO LTD

Electric energy metering misalignment evaluation method and system considering multi-source measurement data fusion

The invention provides an electric energy metering misalignment evaluation method and system considering multi-source measurement data fusion, and relates to the technical field of electric power metering evaluation, and the method comprises the steps: obtaining multi-source electric energy metering data, and carrying out the preprocessing of the multi-source electric energy metering data as an initial sample set; extracting sample feature data based on the initial sample set, and constructing a sample feature distribution representation learning model based on the sample feature data; setting a grouping similarity threshold, grouping the sample feature data, and calculating grouping category mean value sample feature data; constructing a complementary distance metric function; obtaining normal sample feature data based on the sample feature distribution representation learning model; inputting the normal sample feature data into a region-oriented mean grouping category feature extractor to obtain sample features; calculating a complementary distance metric value based on a complementary distance metric function, and inputting a softmax function to output a recognition sample category; and comparing the identified sample category with an actual user sample category, and judging whether the electric energy metering data are misaligned or not.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO MARKETING SERVICE CENT (MEASURING CENT) +1

Multi-camera background schlieren arbitrary coplanar view field splicing method

The invention discloses a multi-camera background schlieren arbitrary coplanar field-of-view splicing method, which comprises the following steps of: synchronously acquiring background images and experimental images of different areas of a complex geometric structure flow field by adopting a plurality of cameras under the conditions of still air and fluid flow; taking a view field delimited according to an actual complex flow field structure as a spliced view field to obtain a full-view contour, and drawing an unstructured grid for the full-view contour; on the basis of the sub-displacement fields shot by the cameras respectively, displacement on each grid point is obtained through interpolation according to the regional position corresponding relation, and full-field displacement distribution after splicing is obtained; and calculating the density information of the flow field by solving a Poisson equation according to the spliced full-field displacement distribution. The problem of limitation of a single camera system in large-view-field complex flow field measurement is solved, high-precision measurement of a complex geometric structure and a large-scale flow field is achieved, the application range of the BOS technology is expanded, and the measurement precision and flexibility are improved.
Owner:TIANMUSHAN LABORATORY

Multi-agent cluster three-dimensional path planning and re-planning method and system

The invention provides a multi-agent cluster three-dimensional path planning and re-planning method and a multi-agent cluster three-dimensional path planning and re-planning system. A multi-agent cluster three-dimensional path planning and re-planning method comprises the following steps: S1, constructing a map environment, and constructing a three-dimensional environment model through sensor data or map data; s2, aiming at the three-dimensional environment model, designing a particle swarm algorithm to carry out overall path planning so as to obtain a global three-dimensional path; s3, aiming at the three-dimensional environment model, designing a depth Q network to re-plan a global three-dimensional path to obtain an optimal three-dimensional path; and S4, converting the obtained optimal three-dimensional path into a motion instruction of the intelligent agent to obtain an actual execution path of the intelligent agent. Particle swarm algorithm global planning and DQN algorithm re-planning are adopted to carry out intelligent agent path planning, on one hand, the problem of limitation of an existing single-class algorithm on path planning is solved, and on the other hand, the problem that the existing algorithm is poor in performance in a dynamically changing scene is solved.
Owner:杭州智元研究院有限公司

An intelligent monitoring and early warning system for sewage treatment

The present invention discloses an intelligent monitoring and early warning system for sewage treatment, and relates to the field of intelligent treatment technology. The present invention comprises a data acquisition and analysis module, an unqualified sewage treatment module, an equipment data acquisition and analysis module, an abnormal equipment analysis module, and an early warning terminal. The clean water data in each level of treatment of each sewage treatment line is analyzed, and then each unqualified level of treatment of each unqualified sewage treatment line is obtained, and the clean water therein is transmitted to the level of treatment corresponding to the idle sewage treatment line, and an early warning is issued, thereby solving the limitation problem existing in the feasibility analysis process of the current intelligent monitoring and early warning development of sewage treatment, and then the data of each equipment in each unqualified treatment level is analyzed, and then each abnormal equipment is obtained, and an early warning is issued, thereby updating the replacement and cleaning interval period of each abnormal equipment, ensuring the normal operation of each equipment, and realizing the intelligent monitoring and early warning of sewage treatment.
Owner:ANKANG HAOYI TECH CO LTD

Three-way valve

The invention discloses a three-way valve, which belongs to the technical field of three-way valves and comprises a three-way pipe fitting, three groups of butterfly valves, three groups of transmission mechanisms and a driving box, the three groups of butterfly valves are fixedly mounted at three ports of the three-way pipe fitting respectively; the butterfly valve comprises a valve body and a valve clack, a valve rod is fixedly mounted on the valve clack, and the valve clack is rotatably mounted in the valve body through the valve rod; a second groove is formed in the arc face of the valve clack, and an expansion and shrinkage piece is fixedly installed in the second groove. The three-way valve with a three-way switch function is formed by combining the three-way pipe fitting and the three butterfly valves, the three-way valve can adapt to control switching of the flow direction of a medium in a large-diameter pipeline, and the problem of limitation of a ball valve tee joint on the diameter size is solved; according to the three-way valve, airtight protection is additionally arranged on the three sets of butterfly valves, so that the butterfly valves have good airtightness, leakage is not prone to occurring when the butterfly valves face large calibers and high pressure, the safety of the three-way valve is greatly improved, and the three-way valve can stably run for a long time.
Owner:SHANGHAI HUAQI YUTAI ENG MATERIALS CO LTD

Integrated system and method for flow channel leakage detection and flow resistance detection in liquid cooling shell

The invention discloses an integrated system and method for flow channel leakage detection and flow resistance detection in a liquid cooling shell. The integrated system comprises a waterway system. The waterway system comprises a pressure test pump, a first electric ball valve, a first flow sensor, a differential pressure sensing module, a second electric ball valve and a water tank which are connected in sequence; the multi-stage centrifugal pump is connected with the pressure test pump in parallel; two ends of the first electric ball valve and the first flow sensor are connected in parallel with a third electric ball valve and a second flow sensor; the third electric ball valve is connected in series with the second flow sensor; two ends of the differential pressure sensing module are connected with a liquid cooling shell part to be detected; the differential pressure sensing module comprises a differential pressure sensor group. According to the invention, an automatic detection mode is adopted, and pressure and flow resistance detection of the flow channel in the shell part is automatically carried out by comprehensively using the pressure difference sensor, the pressure sensor, the flow sensor and the like, so that the limitation and complexity of manual detection are solved, meanwhile, the traceability of data is realized, and the detection scheme is efficient and reliable.
Owner:NANJING RES INST OF ELECTRONICS TECH

Method for detecting welding edge of thick-wall workpiece welding seam under high-temperature environment based on low-frequency far-field eddy current

The invention relates to a low-frequency far-field eddy current-based method for detecting a welding edge of a thick-wall workpiece welding seam in a high-temperature environment, and belongs to the field of thick-wall workpiece welding seam detection. A far-field eddy current probe of the far-field eddy current flaw detection system is placed on the surface of a weld joint of a workpiece to be detected, the probe is started to move along the weld joint, signals transmitted from a receiving coil are monitored in real time, and the received signals are processed and analyzed to identify defects in the weld joint. The device has the advantages that the adopted far-field eddy current probe comprises the exciting coil and the receiving coil, signals collected by the probe are processed and analyzed in real time, the accuracy and reliability of a detection result are ensured, the detection efficiency of the welding seam of the thick-wall workpiece is improved, the risk of missing detection is reduced, and a powerful guarantee is provided for industrial safety production; the detection sensitivity and depth can be improved, online detection can be achieved, namely, defect detection is conducted synchronously in the welding process, and the production efficiency and safety are greatly improved.
Owner:JILIN ELECTRIC POWER RES INST LTD +1

Complex inner hole rapid detection method based on laser scanning

PendingCN121829354Aavoid scratchesAvoid probe wear problemsUsing optical meansTriangulationLaser scanning
The invention relates to the technical field of precision measurement and optical detection, and discloses a complex inner hole rapid detection method based on laser scanning. According to the method, full-automatic three-dimensional reconstruction of the special-shaped inner hole with the high depth-diameter ratio is achieved through cooperative movement of a rotating platform and an axial feeding laser measuring head in combination with triangulation method laser displacement sensing, multi-source data fusion and an environment compensation mechanism. According to the invention, a traditional contact type measuring means is abandoned, and a non-contact laser scanning technology is adopted, so that the problem of workpiece surface scratch or measuring head wear caused by physical contact is avoided; through cooperative movement of the rotating platform and the linear feeding mechanism, full-circumferential and full-depth coverage scanning of a complex inner hole is achieved, and the limitation that only discrete points or local information can be obtained through an existing method is solved.
Owner:NANYANG NORMAL UNIV