21 results about "Material classification" patented technology

This utility model relates to the field of auxiliary equipment for construction engineering, and discloses a portable material classification, storage, and transportation box for construction engineering. The box includes a storage box with two fixed plates fixedly connected to its bottom inner wall. A motor is fixedly connected to the inner wall of one of the fixed plates, and a gear is fixedly connected to the drive end of the motor. Connecting rods are rotatably connected inside both fixed plates, and a gear is fixedly connected to the outer wall of one of the connecting rods. Transmission plates are fixedly connected to the outer walls of both connecting rods, and connecting rods are fixedly connected to the inner walls of both transmission plates. This utility model reduces the corrosion of the box material by rainwater and acidic or alkaline liquids such as construction site concrete slurry, prevents aluminum alloy oxidation and steel plate rusting, maintains structural strength, and the sealed structure reduces the leakage of volatile gases while preventing the intrusion of external corrosive gases, ensuring the chemical stability of the materials.

This application discloses a method and apparatus for material classification, a machine-readable storage medium, and an electronic device. The classification method includes: traversing model files to establish a first dataset, a second dataset, a third dataset, a fourth dataset, a fifth dataset, a sixth dataset, and a seventh dataset; for each object in each of the third, fourth, fifth, and sixth datasets, using an AI large language model, determining the corresponding recommended material type, and assigning the determined recommended material type to the object's material classification attribute. This achieves automated material classification.

The present application relates to the technical field of industrial vision detection and intelligent manufacturing, and in particular provides a papermaking wood grading evaluation method based on 3D vision and high-resolution imaging fusion. The method comprises raw material feeding and pre-screening, and collecting front and back multi-modal information to realize heterogeneous data archiving, establish an initial digital archive of the target physical form; camera alignment and foreground segmentation are performed, and material categories and associated metadata are identified to obtain offline grading evaluation. Through hardware synchronization and algorithm cooperation, the method realizes automatic collection of front and back of wood, calculation of three-dimensional geometric parameters, material classification and grading evaluation, significantly improving detection accuracy, reviewability and automation level.

This invention discloses a method, apparatus, system, and storage medium for simulating modulation TOF camera correction. First, a light intensity threshold is calculated as the depth error classification standard. The light intensity threshold with the largest standard deviation of the depth error is selected as the depth error oscillation critical point. A light intensity-distance lookup table is established based on the light intensity-distance dataset to correct high-intensity depth data. A light intensity-depth random forest nonlinear model is established, and the hyperparameters of the model are optimized using a particle swarm optimization algorithm for low-intensity depth data. Next, a material correction classification model is constructed. For light scattering errors caused by materials in the measurement scene, the LDA algorithm is used to extract effective features and establish a material-depth distortion dataset. Finally, during real-time acquisition, the trained material correction classification model is used to classify the materials of the acquired objects. Based on the material classification results, the depth data is corrected using the material-depth distortion dataset to obtain a high-quality depth image.

The application discloses a kind of supercritical foaming material classification inventory management method for electrical protection, belong to material intelligent warehousing technical field, specifically include: first, obtain the antistatic index of the supercritical foaming material to be handled, flame-retardant grade, compressive yield strength and thermal decomposition temperature four basic attribute parameters;Then the parameters are constructed as multidimensional feature tensor, mapped to the preset attribute space coordinate system, according to the coordinate distribution to generate target warehouse classification label, the tensor, label and material storage coordinates are associated and stored in the inventory database;Subsequently, receive target electrical component protection task instruction, extract the demand attribute threshold of antistatic, flame-retardant, compression and thermal stability, generate dimension-matched demand feature tensor and place in the coordinate system;Then calculate the space euclidean distance and the included angle cosine similarity of both;Finally, according to double-threshold comparison, the target multidimensional feature tensor is screened out, the corresponding discharge matching scheduling instruction is generated and sent to the inventory control terminal.

The application provides an industrial material hierarchical classification method fusing retrieval enhancement and explicit hierarchical constraint, belongs to the field of industrial material classification, and comprises the following steps: vectorizing and coding historical industrial material data to obtain a standard material vector knowledge base; according to a to-be-classified industrial material, standard material samples are retrieved in the standard material vector knowledge base based on similarity, and a composite input text is obtained by splicing; historical industrial material classification samples are acquired, a fine-tuning dataset is constructed based on random undersampling of head categories and generative enhancement of tail categories, a large language model is fine-tuned and trained, and an industrial material classification model is obtained; according to an enterprise standard classification system, a legal word element classification prefix tree is constructed, the industrial material classification model is constrained to sample only from legal word elements, and an industrial material classification result conforming to the enterprise standard classification system is obtained. The application solves the problem of inaccurate industrial material classification caused by a large label space and significant long-tail distribution in industrial material classification.

The application discloses a kind of automatic ceramic tube airtight detection welding integrated machine, including rack and be located on it take material mechanism, transfer material mechanism, airtight test unit, transfer material classification unit, appearance detection unit, material moving mechanism, pipe body supply unit, wire supply unit, wire welding unit and controller, take material mechanism and send ceramic tube to airtight test unit detection by transfer material mechanism;Transfer material classification unit is rejected according to detection result unqualified product;Material moving mechanism is sent to pre-soldering tin area by pipe body supply unit after the ceramic tube of detection qualified, and is removed to wire welding unit by multi-axis mechanical arm after pre-soldering tin;Wire supply unit realizes the automatic fixed-length cutting of wire, peeling and wire core pre-tin by linear guide rail, first wire clamp, wire cutting module and micro-motion module;Wire welding unit takes wire from wire supply unit and completes welding with multi-axis mechanical arm cooperation.The application integrates airtight detection, appearance detection and automatic wire welding, realizes fully automated production.

The application belongs to the field of underwater target recognition by sonar, and particularly relates to a target material classification method based on a time-frequency dual-path attention fusion network, which comprises a data acquisition module, an original echo data acquisition module based on an image sonar system; a preprocessing module, which pre-processes the original echo data; and a TF-CTAM-InceptionTime model, which outputs after processing the input pre-processed data. The application applies time-domain multi-scale convolution and frequency-domain FFT feature extraction to sonar target classification, fully utilizes the complementary information of time-domain waveform details and frequency-domain spectral structure, adopts a double attention mechanism to adaptively focus on the key frequency components and important moments of sonar echoes, enhances the distinguishing ability of target materials, introduces residual connection and bottleneck structure on the basis of InceptionTime to improve the stability of deep network training and accelerate convergence, avoids information loss caused by image-level processing, retains complete amplitude and phase information, and realizes efficient recognition and classification of target shape and material.

This utility model relates to the field of combined sieve technology and discloses a multifunctional combined sieve, including a support frame and a sieve frame. A vibrator is fixedly installed at the connection end between the support frame and the sieve frame. A support column is fixedly installed on the inner wall of the sieve frame. A sieve plate mounting assembly is provided along the inner edge of the sieve frame. A vibration adjustment assembly is fixedly installed on the sieve frame through the sieve plate mounting assembly. The sieve plate mounting assembly includes a mounting frame and a limiting frame. A mounting seat is fixedly installed at the end of the mounting frame away from the limiting frame, and a limiting groove is formed at the end of the limiting frame away from the mounting frame. This multifunctional combined sieve, through the design of sieve plates with three different mesh sizes, can form a three-level layered screening. The combination of different mesh sizes can complete the classification of multiple particle sizes of materials in one go, eliminating the need for multiple screenings, improving work efficiency, and meeting diverse material classification needs. This facilitates the improvement of the versatility and practicality of the overall combined sieve and makes it easy to promote its use.

The application belongs to the technical field of cloth identification, and discloses a cloth material quality identification method and system based on label relations, which comprises the following steps: obtaining a sample set to be measured, semantic features, original classification scores, a label vector of cloth, and constructing an initial relation graph; inputting the initial relation graph into a first graph attention network to obtain shallow relation representation; connecting the semantic features with the shallow relation representation to obtain joint features of each node; inputting the joint features into a second graph attention network to form label encoding; using the label encoding to map the original classification scores into material classification scores corresponding to the sample material quality; inputting the shallow relation representation into a third graph attention network to obtain deep relation representation, and extracting a label compensation vector; using the label compensation vector to compensate the material classification scores to obtain target classification scores, and comparing the target classification scores with positive and negative sample thresholds to determine material information. The application considers the connectivity between different cloths, and significantly improves the identification accuracy of cloth material quality.

This invention discloses a material hierarchy perception, underwater degradation adaptation, and long-tail category optimization method and system for marine debris detection, belonging to the fields of computer vision and intelligent marine environmental monitoring. The method constructs a material category system, calculates image color shift, contrast reduction, blurring degree, and scattering intensity to obtain an underwater degradation score, and adaptively fuses branch features from the original and enhanced images. The detection network outputs the location, category, and material probability of debris targets, applying consistency constraints based on the hierarchical mapping between fine-grained and material categories. To address the long-tail distribution problem, category weights and resampling factors are constructed, and a long-tail loss function is introduced to enhance tail category recognition capabilities. Finally, multi-frame video results are temporally fused to output stable material classification and pollution statistics. This invention effectively improves the accuracy and statistical reliability of debris detection in complex underwater environments and is applicable to scenarios such as marine monitoring, environmental assessment, and intelligent cleanup assistance.

The utility model provides a kind of FFC sheet detection equipment, including cabinet and feeding mechanism, material pulling mechanism, CCD photographing detection mechanism, material discharging mechanism and material receiving mechanism installed in cabinet from right to left in proper order;Feeding mechanism includes material box and material taking manipulator;Material box is used to place stacked FFC sheet;Material taking manipulator is used to suck the left end of FFC sheet from material box and carry to material pulling mechanism;Material pulling mechanism is used to control FFC sheet to left conveying;Material pulling mechanism includes pulling component and transparent detection platform;Pulling component is used to control FFC sheet to right conveying;Transparent detection platform is docked in the left side of pulling component, for positioning FFC sheet and detecting by CCD photographing detection mechanism;Material discharging mechanism is docked in the left side of material pulling mechanism, for receiving FFC sheet sent out by material pulling mechanism and controlling FFC sheet to left conveying;Material receiving mechanism is used to receive FFC sheet sent out by material discharging mechanism and collect according to OK material and NG material classification;The design can efficiently and accurately complete the detection of FFC sheet.

This utility model relates to a material grading and conveying device; it includes a first feeding hopper, a first discharge port at the bottom of the first feeding hopper corresponding to the low end of a first belt conveyor, a first deflecting roller between the first discharge port and the low end of the first belt conveyor, a second feeding hopper directly below the high end of the first belt conveyor corresponding to the second feeding hopper, a second discharge port at the bottom of the second feeding hopper corresponding to the low end of the second belt conveyor, a second deflecting roller between the second discharge port and the low end of the second belt conveyor, a first inlet at the bottom of a first material pipe located on one side of a first spool separator directly below the high end of the second belt conveyor, a first material pipe connected to the top of a first cyclone unloader, a first impurity outlet at the bottom of the first material pipe, and a first airlock fan at the bottom of the first cyclone unloader; it has the advantages of reasonable structural design, labor-saving conveying, and effective screening of impurities in moxa wool.

This utility model relates to the field of air classifiers, and more particularly to a high-efficiency and energy-saving vibrating screen recycling device, comprising a mounting frame one, a conveyor belt one, a mounting frame two, and a screen plate. The first mounting frame one houses the first conveyor belt, and the second mounting frame is located at the lower end of one side. The second mounting frame two houses the second conveyor belt, and the first mounting frame one has a slot inside, with the screen plate inside the slot. Guide wheels are located on both outer walls of the first mounting frame one, and a connecting rod is rotatably mounted between one of the guide wheels and the screen plate. This device achieves rapid material classification and screening through the coordinated action of a single motor driving the first conveyor belt and the screen plate, improving separation efficiency, enhancing screening effect, and ensuring precise separation of coarse and fine materials. It solves the problem of insufficient screening of feed powder in existing V-type air classifiers, which leads to excessive power consumption and energy waste.

This invention discloses a furniture processing scrap sorting and collection device, relating to the field of furniture processing technology. It includes: a modular dynamic sorting platform and a feeding frame located in the middle of the modular dynamic sorting platform; the feeding frame includes a feeding bin, a wave-shaped progressive screening rack, and a spiral conveyor cylinder arranged sequentially from top to bottom; the wave-shaped progressive screening rack is located between the feeding bin and the spiral conveyor cylinder and is used for sorting scraps; the modular dynamic sorting platform includes a platform frame and multiple lifting units evenly distributed in a matrix on the platform frame and connected one-to-one with the control circuit modules. This invention integrates graded sorting, dynamic flexible guidance, and path planning into one unit. By independently controlling each lifting unit to rise and fall as needed, a dynamically changing guide channel is constructed on the platform surface, which can flexibly adapt to various material classification needs without changing physical tooling.

The application discloses a supercritical foaming material classification inventory management method for electric appliance protection, and belongs to the technical field of material intelligent storage, and specifically comprises the following steps: first, obtaining four basic attribute parameters of the supercritical foaming material to be processed, namely, the antistatic index, the flame-retardant grade, the compressive yield strength and the thermal decomposition temperature; then, constructing the parameters into a multi-dimensional feature tensor, mapping the multi-dimensional feature tensor to a preset attribute space coordinate system, generating a target warehouse entry classification label according to the coordinate distribution, and storing the tensor, the label and the material storage coordinates into an inventory database in association; subsequently, receiving a target electric appliance component protection task instruction, extracting the demand attribute threshold values of antistatic, flame-retardant, compression and thermal stability, generating a demand feature tensor matched in dimension and placing the demand feature tensor in the coordinate system; then, calculating the spatial Euclidean distance and the included angle cosine similarity of the two; finally, screening out the target multi-dimensional feature tensor according to double-threshold comparison, generating a corresponding warehouse exit matching scheduling instruction and sending the warehouse exit matching scheduling instruction to an inventory control terminal.

The utility model relates to a kind of waste alloy material classification device based on LIBS technology, belong to waste alloy classification technical field, including conveying system, the end of conveying system includes multiple parallelly arranged transmission channel corresponding to different alloy categories;Conveying system is sequentially provided with cleaning system, LIBS detection system and classification system along transmission path, and the classification system is electrically connected with LIBS detection system.The classification system is set downstream in the end of the conveying system, and the classified material after identification is classified and transported to the corresponding channel, specifically including mechanical arm and the classification execution mechanism connected with the mechanical arm.The utility model is washed to the surface of waste alloy material before classification, improve the accuracy of detection;By setting LIBS detection system, reduce the detection time, ensure the accuracy and operating efficiency of classification system.