124results about How to "Efficient screening" patented technology

This application provides a method, system, medium, and equipment for detecting thermal hazards in tunnels, relating to the field of tunnel safety detection. The method includes: acquiring geological feature data of the target tunnel; identifying a group of thermal hazard parameters with a correlation greater than a set threshold; setting a quantitative scoring range based on this; using the analytic hierarchy process (AHP) to assign weights and calculate hazard scores; then, combining relevant data to establish a dataset and training a lightweight gradient boosting model; finally, inputting data from an unexcavated tunnel section into the model to output the thermal hazard level. This application, by acquiring geological feature data, can accurately understand the environment, screen key parameters to eliminate redundancy, quantify parameters, and rationally allocate weights to ensure objective and accurate scores. It enables tunnel thermal hazard detection and early warning, providing guidance for prevention and control, reducing impact, and is of great significance to tunnel engineering.

The invention discloses a swelling microneedle patch and a preparation method thereof. The swelling microneedle patch comprises a backing and a swelling microneedle array adhered to the backing, the swelling microneedle array comprises a plurality of microneedles; the microneedle is in the shape of a cone or a rectangular pyramid; the height of the microneedle is 100 to 1000 [mu] m; the diameter of the tip end of the microneedle is 5-30 microns; the diameter of the bottom of the microneedle is 50-500 [mu] m; and the center-to-center distance between every two adjacent microneedles is 50-2000 microns. The swelling microneedle patch provided by the invention can overcome the barrier action of cuticle to penetrate subcutaneously and absorb subcutaneous tissue interstitial fluid, and is simple in preparation process, low in cost and high in universality. The patch is combined with a colloidal gold lateral chromatography test strip, so that the limitations that in-vitro diagnosis of infectious diseases depends on a blood sample, professional medical personnel are needed for operation, the subject compliance is poor and the like can be solved, and the patch is suitable for rapid screening and diagnosis of the infectious diseases.

The utility model discloses a rice polishing machine which comprises a working table and a polishing machine body, two supporting frames are fixedly connected to the upper side of the working table, a vibrating screen mechanism is arranged at the top ends of the two supporting frames, two symmetrical cleaning mechanisms are arranged on the upper side of the working table, and a feeding hopper is connected to the top end of the polishing machine body. The vibrating screen mechanism comprises four mounting seats, the four mounting seats are connected to the two ends of the tops of the two supporting frames through bolts correspondingly, springs are fixedly connected to the upper sides of the four mounting seats correspondingly, and dampers are connected to the inner sides of the four springs correspondingly. Compared with the prior art, the rice polishing machine has the advantages that the rice polishing machine can prevent the screen holes from being blocked and has a cleaning function.

The invention discloses a depression detection method based on EEG channel selection and multi-dimensional feature fusion, which avoids the problem of sensitivity of k-means to the clustering number and initial clustering centers, improves the k-means, determines the number of clustering centers by adopting a Karlinski-Halabass criterion, calculates the PageRank value of an EEG channel based on maximum and minimum similarity, and finally determines the number of the clustering centers by adopting the Karlinski-Halabass criterion and the PageRank value of the EEG channel based on the maximum and minimum similarity. Selecting the first k channels as initial clustering centers, designing a self-adaptive threshold model, and selecting channels with distances smaller than a threshold as key EEG channels; constructing a brain function network and a super-brain function network by using the key EEG channel, and extracting low-dimensional time domain features of the key EEG channel, low-dimensional spatial domain features of the brain function network and high-dimensional spatial domain features of the super-brain function network; and designing a multi-dimensional feature fusion strategy based on standard deviation, and fusing low-dimensional time domain features, low-dimensional spatial domain features and high-dimensional spatial domain features to realize depression detection with high accuracy.

This application discloses a block asphalt crushing and impurity removal device, comprising: a feeding frame, a crushing mechanism installed on the upper side of the feeding frame to crush the incoming block asphalt, and a connecting discharge mechanism on the lower side of the crushing mechanism to receive the crushed particles; a discharge frame connected to one side of the feeding frame, and a filter cylinder installed on the inner side of the discharge frame; a first discharge port on the lower side of the discharge frame, and a second discharge port on the lower side of the filter cylinder, located at the lower end of the discharge frame, to discharge small asphalt particles. This application has at least the following advantages: the tilt angle adjustment mechanism can dynamically adjust the tilt angle of the filter cylinder, thereby controlling the material flow rate, adapting to different feed rates and screening requirements, and ensuring stable screening results; by optimizing the combined design of the crushing mechanism and the filter cylinder, rapid crushing of block asphalt and efficient removal of impurities are achieved, improving overall processing efficiency.

This utility model relates to the field of solder wire production technology and discloses a solder wire production waste recycling device, including a main body. A controller is fixedly installed on the left side of the main body, and a feeding trough is fixedly installed on the top of the main body. Mounting seats are fixedly installed on the left and right sides of the inner side of the main body, and a drive seat is fixedly installed on the mounting seat. A crushing gear is fixedly installed at the transmission end of the drive seat. A screening plate is movably installed on the inner side of the main body. A drive motor is installed on the lower right side of the screening plate, and an impact plate is fixedly installed at the transmission end of the drive motor. A water tank is fixedly installed below the screening plate. This solder wire production waste recycling device achieves efficient crushing and precise screening of waste by setting up intermeshing crushing gears and an eccentric vibrating screening plate. The combination of preliminary water washing in the water tank and secondary sorting by a gravity separator significantly improves the purity of the recycled solder.

The utility model provides a kind of industrial silicon powder granulating device, comprising: granulator body, the screening device of being equipped in the discharge port below of granulator body, the conveying plate of being fixed in the discharge port below of screening device, the powder elevator of being equipped in granulator body, conveying plate side, the inlet of powder elevator of being equipped in the lower end of conveying plate, the discharge port of powder elevator being equipped in the above of granulator body;Through above-mentioned scheme, screening device can promptly, effectively screen the particle produced by granulator, effectively separate qualified particle meeting granularity requirement and unqualified particle or powder, powder recycling is realized by powder elevator, avoid the waste of powder, reduce the consumption of raw material, reduce the raw material procurement cost of enterprise.

The invention discloses a marketing content generation method based on multi-agent cooperation and related equipment, and the method comprises the steps: determining a target business scene according to content generation demand information and content generation reference information, and obtaining a corresponding target scene data package from a marketing scene library; determining a target agent list and a task list according to the target scene data packet, generating a task directed acyclic graph in combination with the material information and the constraint information, and further generating an arrangement plan; and calling a target agent plug-in to execute a generation task according to the target agent list and the arrangement plan, obtaining a stage content generation result, and performing acceptance check to obtain a final content generation result. According to the embodiment of the invention, full-process automation from scene recognition, task disassembly, task arrangement, multi-agent task generation execution to content acceptance can be realized, and the marketing content generation efficiency, quality and stability can be effectively improved. The method can be widely applied to the technical field of generative artificial intelligence.

The utility model belongs to the technical field of curing treatment, and particularly relates to a gravel slurry curing treatment device. The device comprises a machine frame, a filtering mechanism, an extruding mechanism and a control system, the filtering mechanism, the extruding mechanism and the control system are located on the machine frame, a feeding mechanism is arranged on one side of the machine frame and comprises a feeding pump, a feeding pipeline and a pre-screening device, a flow control valve and a pressure sensor are arranged on the feeding pipeline, and the pre-screening device is arranged on the feeding pipeline. The flow control valve is used for adjusting the feeding flow, the pressure sensor is used for monitoring the feeding pressure in real time and transmitting a pressure signal to the control system, and the pre-screening device is arranged at the front end of the feeding pipeline. According to the utility model, the pre-screening device is arranged to pre-treat gravel slurry and screen gravel particles with different particle sizes, so that the problem that the gravel particles block filter cloth and a feeding channel of the filter press is effectively avoided, the filter pressing efficiency is improved, and the maintenance cost of equipment is reduced.

The utility model discloses a bamboo shoot bubbling bath boiling device which comprises a bath boiling box, a driving motor is fixedly installed on one side of the top face of the bath boiling box, the output end of the driving motor drives a spiral blade installed in the bath boiling box to rotate through a synchronous belt wheel set, and through holes and installation cavities are formed in the bath boiling box at intervals. A bamboo shoot collecting plate is arranged below the through hole, a blow-off pipe is fixedly mounted on the bottom surface of the bamboo shoot collecting plate, and a bubbling pipe is mounted in the mounting cavity. According to the utility model, the helical blade is arranged in the bath boiling box, under the driving of the driving motor and the synchronous belt wheel group, the helical blade conveys bamboo shoots and moves from the bamboo shoot inlet to the bamboo shoot outlet while the impurities are screened out through the through holes, and in the conveying process, the impurities on the surfaces of the bamboo shoots, such as chippings and soil, are removed through the through holes. The bamboo shoots can fall to the bottom of the bath boiling box through the through holes and then are discharged through the blow-off pipe, efficient impurity screening in the material conveying process is achieved, and the cleanliness of the bamboo shoots is guaranteed.

This utility model discloses a vibrating screen for nicotinamide production, comprising a support frame, four fixed seats (first type) fixed to the support frame, springs fixed to the fixed seats (first type), and fixed seats (second type) fixed to the springs. A vibrating screen body is fixed between the four fixed seats (second type). A dual-shaft motor is fixed to the lower side of the vibrating screen body. Eccentric wheels are fixed to the output shafts of the dual-shaft motors. Fixed columns are fixed to the output shafts of the dual-shaft motors. Connecting shells are fixed to the fixed columns. Sealing covers are fixed to the connecting shells. Connecting pipes are embedded within the fixed columns and communicate with the connecting shells. Through its control structure, this utility model allows the device to dynamically adjust the amplitude of the vibrating screen body according to screening requirements. When a water pump is started to inject water into the connecting shells, the centrifugal force of the connecting shells increases, causing the dual-shaft motors to drive the vibrating screen to produce a larger amplitude, suitable for processing materials that are difficult to screen. Conversely, pumping water reduces the amplitude, suitable for fine screening.

The application relates to the technical field of artificial intelligence, and discloses a data processing method, device, equipment and storage medium to improve blacklist processing capability. The method part comprises the following steps: receiving a loan approval request sent by a target business system, the loan approval request carrying loan approval data, the loan approval data comprising a system type of the target business system and attribute information of an applicant; calling a blacklist interface corresponding to the system type to obtain a system blacklist; judging whether the applicant is a user in the system blacklist according to the attribute information of the applicant; when the applicant is not a user in the system blacklist, a platform blacklist of an automatic approval platform is called; judging whether the applicant is a user in the platform blacklist according to the attribute information of the applicant; when the applicant is a user in the platform blacklist, a loan service corresponding to the loan approval request is rejected, and rejection result information is generated and fed back to the target business system.

The utility model relates to the field of shot blasting treatment especially relates to a kind of shot blasting and sand blasting collection device, including mounting seat, the mounting seat is rotatably connected with screening bucket, the mounting seat is equipped with driving motor, the output shaft of driving motor is connected with the screening bucket, the mounting seat is slidably connected with collection arc-shaped plate, the collection arc-shaped plate is located the downside of the screening bucket, for collecting the material screened by the screening bucket.The utility model is rotated by driving motor and drives screening bucket, utilizes the joint action of centrifugal force and gravity to make material fully move in screening bucket, accelerate the material meeting the size requirement to pass through sieve hole, compared with artificial screening or fixed sieve plate screening, high-efficiency screening can be realized without manual intervention, greatly reduce labor intensity, simultaneously adapt to the material processing demand of large-scale shot blasting and sand blasting operation, shorten material processing cycle.

The application discloses a KASP molecular marker combination related to soybean salt tolerance and application thereof. Through soybean natural population salt tolerance phenotype identification and genome-wide association analysis (GWAS), three SNP sites extremely significantly associated with soybean salt tolerance traits are obtained, four salt tolerance candidate genes for regulating stress response and signal transduction of soybean are mined out; further based on the genomic sequence characteristics of the three SNP sites and the four candidate genes, seven molecular markers with high stability, good polymorphism and closely linked to salt tolerance traits are designed and verified to be developed. The application simultaneously provides a molecular marker development process, a soybean salt tolerance molecular identification method and application in germplasm screening and molecular assisted breeding. The application provides complete KASP primer combinations and molecular detection methods, which can provide efficient tools for accurate identification and screening of salt-tolerant soybean resources and molecular marker assisted breeding, and has a wide application prospect.

The utility model belongs to the technical field of silica gel cat litter production, and discloses screening equipment for silica gel cat litter production, which comprises a rack, a screening box, a screen, a collecting frame and a driving device, the screening box is obliquely arranged on the rack, the screen is arranged in the screening box, the collecting frame is arranged on one side of the screening box and used for collecting silica gel cat litter with different particle sizes, and the driving device is connected with the bottom of the screening box and used for driving the screening box to vibrate; the screening net comprises an upper screening net, a middle screening net and a lower screening net, the upper screening net, the middle screening net and the lower screening net are sequentially arranged at equal intervals from top to bottom along the height of the screening box, the inclination angle of the screening box is 5-15 degrees, and a feeding opening used for feeding is formed in the top of the screening box; discharging ports used for discharging are formed in one side of the screening box, and the discharging ports are arranged at equal intervals in the height direction of the screening box. The silica gel cat litter screening device is simple in structure, convenient to operate and capable of effectively screening silica gel cat litter with different particle sizes so as to improve production efficiency.

The utility model relates to the technical field of kitchen waste treatment, in particular to modularized skid-mounted kitchen waste front-end pretreatment equipment. Comprising a shell with openings in one side and the bottom, a mounting frame is fixedly arranged on the lower side wall of the shell, and a guide hopper is fixedly arranged on the lower side wall of the mounting frame. According to the kitchen waste screening device, after a transport vehicle throws kitchen waste into the screening disc, the overturning mechanism drives the screening disc to do small-amplitude reciprocating rotation, so that large sundries and fiber impurities in the kitchen waste can be rapidly separated by the screening disc, and the situation that the large sundries affect draining treatment of the draining mechanism on the fiber impurities is avoided; after a worker treats the kitchen waste, the turnover mechanism drives the screening disc to rotate upwards, the screening disc is moved to the upper side of the mounting frame, and large sundries in the screening disc can be poured out of the shell, so that the workload of manually treating the large sundries by the worker is avoided, and the worker can conveniently treat the kitchen waste.

This invention belongs to the field of wheat breeding, specifically relating to a wheat Fusarium head blight resistance locus and molecular breeding method. This invention identified five stable Fusarium head blight resistance-associated loci, Qfhb.jaas-2D, Qfhb.jaas-3A, Qfhb.jaas-3B.1, Qfhb.jaas-5A.2, and Qfhb.jaas-6D, on chromosomes 2A, 2D, 3A, 5A, and 6D. For the identified resistance loci, this invention designed KASP molecular markers. These markers have high specificity and sensitivity, enabling accurate and rapid detection of resistance genotypes in wheat materials, providing a powerful tool for marker-assisted selection (MAS). This invention verified the effectiveness of the screened resistance loci. The results showed that the above five loci were significantly associated with Fusarium head blight resistance, providing a reliable basis for the breeding of resistant varieties.

The invention discloses a method for detecting potential electric leakage defects of an LED device, and relates to the technical field of semiconductor photoelectric device detection. Aiming at the technical pain point that recessive microdefects (such as a metal migration channel caused by a V-shaped pit and dislocation) cannot be identified by the existing single spectroscopic detection, the invention provides a detection logic of reference parameter acquisition, defect stress excitation, parameter acquisition after excitation and differential analysis and judgment. Specific stress is applied to primarily screened qualified products, ion migration at potential defects is excited in an oriented mode, and hidden electric leakage is dominated. Potential defective products are accurately rejected by calculating parameter drift distances (VFL, IR) before and after stress. The method is not only suitable for interactive screens, but also suitable for high-reliability scenes such as vehicle-mounted display and high-end illumination, and can effectively intercept hidden lamp beads causing'caterpillar 'failure or early light attenuation, thereby remarkably improving the product yield and the terminal reliability.

The application belongs to the technical field of quartz sand processing, in particular to a fine crushing and multi-stage purification process for preparing ultra-high-purity quartz sand, which comprises a machine body, a fixed frame is fixedly connected to the upper surface of the machine body, a feeding port is formed in the fixed frame, a first motor is arranged below the machine body, a crushing roller is drivingly connected to the output end of the first motor, auxiliary plates are fixedly connected to the inner wall of the feeding port on both sides, tooth gears are fixedly connected to one side of the auxiliary plates and staggered with the tooth gears on the circumferential surface of the crushing roller, the auxiliary plates are used for assisting the crushing roller to crush quartz sand, a purification cavity is fixedly connected to the middle of the machine body, and a sieve plate is elastically connected in the purification cavity, through the hooking assembly and the blockage cleaning assembly, the problem that the existing screening is blocked and the screening efficiency is reduced is solved, and the problem that the falling is slow during the screening process is solved.

The invention belongs to the technical field of biology, and particularly relates to a promoter responding to pentanediamine, a pentanediamine biosensor and application of the pentanediamine biosensor. The original PpyrF promoter can respond to the concentration of pentamethylene diamine and regulate and control the expression of report protein GFP, the promoter PpyrF-D40 or PpyrF-F5 is obtained by truncation or mutation optimization of the promoter PpyrF, and the dynamic range and sensitivity of the pentamethylene diamine biosensor are improved. The pentane diamine biosensor further constructed on the basis of the promoter PpyrF-D40 or PpyrF-F5 has no responsiveness to a pentane diamine synthesis precursor lysine, so that the biosensor has good specificity when being applied to screening of pentane diamine production strains. The fluorescence intensity value of the pentane diamine biosensor obtained through screening shows an excellent linear response relationship with the concentration of pentane diamine, and the pentane diamine biosensor can be used for efficiently breeding a pentane diamine high-yield strain by being combined with a high-throughput screening system and the like, and has the advantages of high detection efficiency, high sensitivity and the like.

The invention discloses a wind power blade defect intelligent identification method based on machine vision, and relates to the technical field of wind power generation equipment state monitoring. According to the method, an interference item feature library and a defect feature library exclusive to a wind power blade are constructed, and a double-branch feature decoupling network is designed; the defect feature decoupling branch and the interference item feature decoupling branch are utilized to intensify the defect essential features and the interference item features in a targeted mode, and the feature decoupling process guided by a loss function is adopted in the training stage, so that two sets of independent feature representation systems are formed in the model. In the face of a leaf image containing cracks and water spots at the same time, the network can spontaneously cause linear textures and shadow changes to defect branches, and cause flowing forms and color diffusion to interference term branches, so that preliminary separation is achieved in the stage of outputting a probability heat map, and the probability heat map is obtained. The fundamental problem that a large number of invalid alarms are generated due to feature confusion is solved.

The invention relates to the technical field of electric power energy storage, and discloses a GIS-based mountain compressed air energy storage power station site selection method and system, and the method comprises the steps: obtaining first-stage data, second-stage data and third-stage data in a target mountain region; obtaining an alternative region based on the first-level data; obtaining a geological available area based on the secondary data; screening out mountains meeting conditions based on the secondary data, and constructing contours and main ridge lines of the mountains meeting the requirements; determining a mountain reference region, and calculating the area of the reference region; solving an optimal internal rectangle of the mountain reference area, judging whether the mountain reference area meets the requirements of the optimal internal rectangle or not, and determining a target available mountain; the score of the target available mountain is determined by integrating the second-level data and the third-level data, and the area with the high score is used as the final site selection; according to the method, the problems of insufficient accuracy, low timeliness and poor visualization of an existing site selection method are solved.

This utility model provides an automated vibratory screening device for quartz sand, relating to the field of quartz sand screening technology. It includes a mounting frame with a mounting ring welded to the bottom inner side of the top of the mounting frame. A splicing screening assembly is provided on the upper side of the mounting ring frame. The splicing screening assembly includes a support ring frame mounted on the top of a support ring frame, a splicing frame above the support ring frame, and a splicing top frame above the splicing frame. A vibration connecting block is welded to the upper inner wall of the splicing top frame. By setting up an electrically controlled lifting rod, a connecting top plate, a servo motor, and a vibrating pressure plate, the servo motor drives the vibrating pressure plate to reciprocate. The vibrating pressure plate corresponds one-to-one with the vibrating connecting block, causing the entire splicing screening assembly to vibrate, thereby achieving effective screening of quartz sand. Simultaneously, the bottom support spring reduces the outward transmission of vibration, preventing significant shaking of the entire device and reducing overall vibration and noise generation.

The invention is suitable for the technical field of deep learning, and provides a nucleic acid aptamer generation and screening method and device, electronic equipment and a program product. The method comprises the following steps: inputting a target protein into a protein structure encoder, and extracting a first protein feature of the target protein; inputting the guiding condition and the guiding intensity coefficient into a condition diffusion model to generate at least one candidate nucleic acid aptamer; inputting each candidate nucleic acid aptamer into a nucleic acid encoder, and extracting a first nucleic acid sequence feature of each candidate nucleic acid aptamer; inputting each first nucleic acid sequence feature and the first protein feature into a semantic space alignment module, and calculating a prediction score of each candidate nucleic acid aptamer; adding each candidate nucleic acid aptamer and the predicted score thereof into a nucleic acid candidate pool; and determining the candidate nucleic acid aptamer with the highest predicted score in the nucleic acid candidate pool as the nucleic acid aptamer with the optimal binding capacity with the target protein. According to the invention, efficient generation and screening of the high-affinity nucleic acid aptamer can be realized.

This invention belongs to the field of road defect identification technology, specifically disclosing an intelligent road defect identification method based on multimodal perception. It acquires multispectral images and three-dimensional laser point clouds of the same road surface location, divides the area into oil-dominated marking zones and crack candidate marking zones based on the pixel brightness ratio between multispectral bands, and then projects the oil-dominated marking zones inversely into three-dimensional space. A local dynamic elevation baseline is constructed using the point cloud of the clean road surface outside the oil-contaminated boundary. Relative elevation difference analysis is performed within the oil-dominated marking zones, and the elevation change of the point cloud is used as a physical verification method to check the spectral marking results. This enables proactive collaboration between the multispectral image and the three-dimensional point cloud, effectively identifying hidden cracks under oil contamination. It goes beyond simply distinguishing between oil contamination and defects on the surface; instead, it uses the physical indicator of structural subsidence to confirm whether cracks are hidden beneath the oil contamination, significantly reducing the risk of missed crack detection in oil-covered scenarios.

The application provides a multi-model cooperative detection method and system for traffic abnormal events, and relates to the technical field of intelligent transportation.The method comprises the following steps: constructing a multi-source perception system covering a target traffic area, and obtaining a multi-source traffic data set; performing semantic division based on road structure and traffic operation characteristics, obtaining a plurality of traffic state units, continuously encoding the states, and generating a plurality of time-series traffic state representations; performing traffic state abnormality preliminary screening, and constructing a candidate abnormal traffic event set; inputting a multi-model cooperative analysis framework, performing multi-model joint reasoning, and outputting abnormal traffic event identification results; and combining traffic network propagation characteristics to generate abnormal traffic event response strategies.The application solves the technical problem that the traffic abnormality detection in the prior art often uses a single model to analyze data, which cannot capture multi-dimensional information of complex traffic events, thereby affecting the accurate identification of traffic abnormal events.

The invention provides a pathogenic factor for neurodegenerative diseases and application of the pathogenic factor. The pathogenic factor for the neurodegenerative diseases is a PASP-GPR37-IL-6 signal axis. According to the application, the action mechanism of the PASP-GPR37-IL-6 signal axis serving as a neurodegenerative disease (especially Parkinson's disease) pathogenic factor is defined for the first time, the molecular path of neuroinflammation and neurodegenerative diseases regulated and controlled by the oligodendroglia through the signal axis is disclosed, and the research blank of participation of the oligodendroglia in PD pathogenesis in the prior art is filled.

The utility model discloses a pugging de-ironing separator, which comprises a rotating plate, a bottom frame, a primary screening mechanism, a magnet clamping mechanism and a clamping auxiliary mechanism, the primary screening mechanism comprises a driving motor and a screening box, the magnet clamping mechanism comprises a bottom fixing pipe and a clamping rod, and the clamping auxiliary mechanism comprises an outer rotating sleeve and a positioning ring. The eccentric wheel is driven by the driving motor to rotate, rotary motion is converted into reciprocating motion of the screening box through the push-pull rod, efficient screening of pug is achieved, large waste materials can be effectively separated from the pug, and the problem that in a traditional device, large waste materials are difficult to screen is solved. The magnet clamping mechanism adopts the combined design of a bottom fixing pipe, a clamping pipe and a clamping rod, and through the rotary clamping mode of an inner supporting frame and an embedded rotating block and the continuous pressure provided by a compression spring, rapid mounting and dismounting of a magnet plate are achieved.

This invention discloses a method and system for distribution network fault identification based on adaptive visual graphs and multi-source fusion. The method includes the following steps: S1: Acquire multi-source electrical analog data of the distribution network and preprocess it to obtain preprocessed multi-source signals; S2: Dynamically weight and fuse the preprocessed multi-source signals using a correlation variance contribution algorithm to obtain a fused signal; S3: Map the fused signal into a graph structure using an adaptive convergent visual graph algorithm; S4: Input the graph structure into a pre-constructed graph neural network model to obtain a global graph feature vector; S5: Input the global graph feature vector into a fully connected layer and output the fault probability distribution through a Softmax classifier. This invention constructs a feature space that can objectively characterize the essential differences between normal operating conditions and fault states in terms of physical correlation and topological structure, thereby achieving accurate identification of known faults and effective identification and elimination of unknown benign disturbances.

The utility model belongs to the technical field of resin processing, and particularly relates to a heating and uniform stirring device for producing chlorinated polypropylene resin, which comprises a mixing bin body, a feeding pipe, a discharging pipe, a stirring mechanism, a heating mechanism, a discharging pipe, a stirring mechanism, a heating mechanism and a heating mechanism, the bottom end of the feeding pipe is fixedly communicated with the top of the mixing bin body; the bottom end of the filter pipe is detachably inserted into the feeding pipe, and a filter screen is mounted in the filter pipe; the vibration assembly comprises two moving rods, a sliding seat, two telescopic rods, two connecting rods and two vibration motors, vibration discharging of a filter pipe and a filter screen is achieved through a simple structure, the fluidity of resin raw materials can be improved, discharging is promoted, the filter screen is prevented from being blocked, meanwhile, the filter screen is convenient to disassemble, assemble and maintain, and the service life of the filter screen is prolonged. Operation is convenient, time and labor are saved, and practicability is high.