61 results about "Particle classification" patented technology

A method for collaborative source apportionment of volatile organic compounds (VOCs), a product, a medium, and a device are provided. The method includes: establishing a single particle classification model; training and optimizing the single particle classification model with a local pollution library, and analyzing pollution sources of single particle mass spectrometric data to be apportioned to obtain a time series of the pollution sources contributing to the particulate matter (PM); obtaining VOCs factors of the pollution sources and a time series thereof; performing correlation calculation on the time series of the pollution sources contributing to the PM and the time series of the VOCs factors to obtain a correlation coefficient; and attributing the PM and the VOCs factor having the correlation coefficient higher than a set threshold to a same pollution source, and identifying a common pollution source of the PM and the VOCs.

The embodiment of the invention discloses a biological aerosol real-time identification method and system based on ultraviolet laser induced multi-dimensional optical fingerprints. The method comprises the following steps: irradiating biological aerosol particles with ultraviolet laser with a set wavelength, scattering the ultraviolet laser under the action of the particles, and exciting the particles to generate fluorescence; mie scattering signals are collected in the first optical channel and used for measuring physical size information of particles; a broadband fluorescence signal is collected in a second optical channel and is used for determining chemical composition information of the particles; a fluorescence signal of a selected wavelength characteristic peak value is collected in a third optical channel and is used for determining microenvironment and conformation information of particles; the horizontal component intensity and the vertical component intensity of the fluorescence signal with the set wavelength are collected in a fourth optical channel and are used for determining the structural order information of the particles; based on the obtained physical size information, chemical composition information, microenvironment and conformation information and structural orderliness information, particle classification information in the biological aerosol is analyzed and determined.

The invention relates to an intelligent particle identification method for lunar soil particle screening, which comprises the following steps of: acquiring an optical signal, image data and a surface electrical signal of the same lunar soil sample particle to form a multi-modal feature set of each lunar soil sample particle; carrying out standardization processing on the multi-modal feature set; constructing a multi-modal deep learning neural network model based on a CNN + MLP + splicing fusion module structure; performing supervised learning training on the multi-modal deep learning neural network model to obtain a trained multi-modal deep learning neural network model; and inputting the standardized data into the trained multi-modal deep learning neural network model to realize particle classification. According to the method, an intelligent identification integrated deep learning model is adopted, the functions of particle shape distinguishing, component identification, particle size sorting and the like are carried out by utilizing an intelligent algorithm, automatic classification, clustering and attribute prediction can be realized, manual marking one by one is not needed, and the working efficiency is effectively improved.

The invention belongs to the technical field of screening equipment, and particularly relates to an abrasive particle classification screening device which comprises a box body, vibrators are evenly arranged at the four corners of the outer wall of the box body, a cover plate is installed at the top of the box body, and a feeding port is formed in the top of the cover plate; the sieve plates are symmetrically arranged on the inner wall of the box body up and down; the device comprises a box body and a sieve plate, the sieve plate is arranged in the box body, the buffer mechanism is installed on the inner wall of the box body, the bottom of the buffer mechanism makes contact with the top of the sieve plate, and the abrasive particle grading and screening device further comprises a steering mechanism arranged below the sieve plate. The sweeping brush can sweep the bottom of the box body and the sweeping rod can sweep the side face of the box body, the discharging speed of powdery grinding materials and fine grinding materials is increased, it is guaranteed that the bottom of the sweeping rod is always in contact with the bottom of the inner wall of the box body when the sweeping rod is put down, the discharging speed is kept, and the dust content in the box body is reduced; and dust adhered to the inner wall of the box body is cleaned.

The invention provides a tailing particle classification method based on multi-dimensional morphological feature compression and clustering, and belongs to the technical field of geotechnical engineering, mineral processing and particle classification, and the method comprises the following steps: S1-S6, obtaining an STL file database of tailing particles; s7, calculating and extracting morphological parameters to form an original parameter data set; s8-S10: obtaining a three-dimensional morphological parameter set which retains the original morphological feature information; s11-S12, determining an optimal clustering number by adopting an elbow rule, a contour coefficient and Gap statistics, and performing particle morphology clustering grouping on the three-dimensional morphology parameters by adopting a K-means algorithm; and S13, carrying out stacking test simulation on the clustered particle categories by using a discrete element method, analyzing the stacking density and the average coordination number of different categories of particles, and verifying the physical significance of a classification result. The tailing particle classification method can systematically and efficiently integrate particle multi-dimensional form information, can directly associate the information with macroscopic physical and mechanical properties, and is data-driven, clear in mechanism and explainable in result.

The invention relates to a particle micro-explosion combustion event detection and particle classification method based on multi-factor scoring, which takes a trajectory splitting event as a core, combines and analyzes a'termination trajectory 'and a'new trajectory' as a candidate condition of a primary micro-explosion combustion event, and converts a tracking problem from position tracking into identification and judgment of a physical process. Tracking errors caused by accidental factors in the particle tracking process can be reduced; through a two-step screening strategy of'deterministic screening 'and'probabilistic screening', the inherent'velocity attribute 'of the sub-particles can be effectively combined, a group determined as the sub-particles is firstly screened out, and the calculated amount of subsequent'probabilistic screening' is reduced; furthermore, a comprehensive scoring model is established, the micro-explosion characteristics of the mother particles are associated with the group characteristics of the child particles, a'probabilities screening 'strategy based on multi-dimensional associated information analysis is formed, the accuracy of particle classification is effectively improved, and high-precision and high-robustness recognition of the metal particle micro-explosion combustion event in the motion state is achieved.

The air inlet mechanism comprises an air inlet window and an annular shell body, the air inlet window comprises an upper ring body and a lower ring body, fan blades are arranged between the upper ring body and the lower ring body, fan blade gaps between the adjacent fan blades are gradually reduced from outside to inside, and the annular shell body is arranged in the annular shell body. The air inlet window is sleeved with the annular shell, an inner cavity of the annular shell is communicated with the fan blade gaps, an air inlet is formed in the annular shell, an air inlet pipe is installed at the air inlet, and the axis direction of the air inlet pipe is parallel to the tangential direction of the upper annular body. Tangential vortex air inlet is adopted, the cross sectional area of the inner cavity of the annular shell is reduced clockwise or anticlockwise from the air inlet, the air speed in the annular shell can be gradually increased, and therefore it is guaranteed that the air force in the air inlet window in the circumferential direction is the same, and the particle classification efficiency is improved.

The invention relates to the field of quantum machine learning and high-energy physics, in particular to a particle flow classification method based on a quantum complete graph self-attention network, and the method comprises the steps: obtaining particle features in a data set, screening out four representative particles with the maximum transverse momentum from each particle flow to replace the characteristics of the whole particle flow so as to form a complete graph; performing self-attention coefficient calculation and weighted summation on particle features in the complete graph by using a QGAT model constructed by a self-attention mechanism to complete updating of the particle features; and the updated quantum state of the particle features is subjected to dimension reduction representation through the quantum convolutional network and then is used as the input of a quantum classifier for result prediction, so that the particle classification precision and the model expression ability are greatly improved.

To provide a particle classification device and a particle classification method.SOLUTION: A particle classification device comprises: a supply chamber 51 which supplies a suspension solution 11 in which particles are dispersed; a filtration chamber 52 which allows fine particle components in the solution to pass therethrough by an electric-field filtration action and retains a concentrated liquid of coarse particle components; and a filtrate chamber 53 which discharges, to the outside, a filtrate including the fine particle components that have passed through. The filtration chamber 52 includes: a plate-shaped anode electrode 14 disposed on a supply chamber side and having through holes; and a cathode filter plate electrode 14 disposed on a filtrate chamber 53 side, including a diaphragm 13 having pores that block negatively-charged coarse particle components and having pores.SELECTED DRAWING: Figure 1

A system comprises a particle sensor for a vehicle comprising a light source that directs a beam to an interrogation region outside the vehicle; and an optical detector that receives scattered or reflected light from an aerosol particle in the interrogation region. A processor performs a method for particle classification comprising measuring an optical response from a single particle in the interrogation region by identifying an optical response peak for scattered or reflected light from the interrogation region; measuring an amplitude and duration of the optical response peak; correcting the duration of the optical response peak based on a vehicle airspeed; based on the measured amplitude of the optical response peak, generating an expected optical response duration for water droplet using a calibration table; analyzing the measured optical response duration and the expected optical response duration to determine particle classification; and generating classification probabilities for one or more particle types.

Aspects of the present disclosure include methods for adjusting a particle classification index in response to one or more saturated data signals based on detected light from particles in a fluid stream. Methods according to certain embodiments include detecting light from particles in a fluid stream, generating a plurality of data signals based on the detected light, identifying one or more saturated data signals, generating a saturation signal index corresponding to the identified saturated data signals, and applying the saturation signal index to a particle classification index to generate an adjusted particle classification index. In some embodiments, the methods include determining one or more parameters of a particle (e.g., for a particle sorting decision) by calculating an adjusted spectral unmixing matrix for fluorescence of the particle that excludes the one or more saturated data signals. Systems and integrated circuit devices (e.g., field programmable gate arrays) for implementing the subject methods are also provided. Non-transitory computer readable storage media are also described.

This invention provides a tailings particle classification method based on multi-dimensional morphological feature compression and clustering, belonging to the fields of geotechnical engineering, mineral processing, and particle classification technology. The method includes: S1-S6: acquiring an STL file database of tailings particles; S7: calculating and extracting morphological parameters to form an original parameter dataset; S8-S10: obtaining a three-dimensional morphological parameter set retaining the original morphological feature information; S11-S12: determining the optimal number of clusters using the elbow rule, silhouette coefficient, and Gap statistic, and using the K-means algorithm to cluster the three-dimensional morphological parameters into particle morphology groups; S13: using the discrete element method to conduct a stacking test simulation on the clustered particle categories, analyzing the stacking density and average coordination number of different particle categories, and verifying the physical meaning of the classification results. This tailings particle classification method can systematically and efficiently integrate multi-dimensional particle morphological information and directly correlate this information with macroscopic physical and mechanical properties. It is data-driven, has a clear mechanism, and the results are interpretable.

The invention discloses a cerium oxide grinding material as well as a preparation method and application thereof. According to the method, high-purity cerium carbonate is taken as a precursor, preliminary crushing is performed before calcination, and cerium oxide particles are prepared by adopting a two-step sintering method during calcination. And carrying out ball milling and particle grading to obtain the cerium oxide abrasive material. The prepared cerium oxide abrasive is used for a CMP STI process, the polishing speed is high and stable during polishing, and meanwhile, the wafer scratch is little.

"ENHANCEMENT APPLIED TO THE STATIC MACHINE ELEMENT DISCHARGE CHAMBER INTEGRATED INTO A DEVICE KNOWN AS A HYDROCYCLONE USED IN THE STAGE OF VERIFYING ORE PARTICLE SIZE QUALITY AFTER THE CRUSHING STAGE, AND ITS ASSEMBLY, COUPLING, AND DECOUPLING PROCESSES OF THE HYDROCYCLONE BODY" represented by an evolutionary solution in the industrial and commercial sector of particle classification / separation equipment for ores that have undergone concentration, desliming, solids recovery, and closed grinding circuit procedures, with particular application in equipment known as hydrocyclones (Eq), wherein, in order to solve problems of premature wear and complex maintenance of the static machine element discharge chamber, the invention is embodied in an enhancement to its constructive concept, such that it becomes composed of three components: a lower part (10), a male quick-coupling part (20), and a fixed base (30). A concept of quick engagement / disengagement of the operational lower part (10) is introduced for verification of the integrity of the cut diameter (H), being distinguished by the fact that it is sufficient to perform the quick disengagement / engagement of the assembly comprising the lower part (10) and the male quick-fit coupling part (20)."

The invention belongs to the related technical field of phase segmentation, and discloses a decoupling type phase segmentation method and system for a composite gel system microstructure, and the method comprises the steps: (1) forming a reusable particle database through particle images corresponding to each kind of target gel particles; (2) taking an artificially marked pure cement paste BSE image as a background image, inserting particles in a reusable particle database into a cement matrix area to obtain a stage 1 model training data set, and training a stage 1 universal segmentation model; (3) training the stage 2 particle classification model by adopting particles in the reusable particle database; (4) inputting the BSE image to be subjected to phase splitting into the stage 1 universal segmentation model to obtain a matrix, a pore and a particle mask; and stage 2, the classification model performs joint classification based on the particle masks and all particles in the BSE image to be subjected to phase splitting so as to obtain the specific phase category of each particle. According to the invention, the universality is improved.

The invention provides a correction device for a particle number measurement device, a correction program, a method for determining a particle size for correction, and a correction method for a particle number measurement device, which can reduce the influence of particle size change after classification and perform more accurate correction. A correction device (1) is provided with: a particle generation unit (10); an input unit (51); a particle classification unit (20); a particle detection unit (30); and a calculation unit (52) that, on the basis of a physical quantity factor that causes a change in the particle diameter in the particle detection unit (30) or the particle diameter distribution of the particles in the particle detection unit (30), determines the degree of change in the particle diameter of the particles reaching the particle detection unit (30) from the target particle diameter, and calculates the correction amount for the particle diameter extracted by the particle classification unit (20) on the basis of the degree of change. The particle diameter reaching the particle detection unit (30) becomes a target particle diameter. And a correction instruction unit (53) that instructs the particle classification unit (20) on the basis of the correction amount calculated by the calculation unit (52) so as to change the particle size of the particles extracted by the particle classification unit (20) to the particle size for correction.

To provide a method for singulating particles so that an action can be carried out on the particles such as for detecting parameters of particles in the stream.SOLUTION: Particles are sorted into paths based on a measurable parameter by forming them into a stream in at least one duct carried on a body rotating around an axis where the duct is shaped so that the particles are accelerated to cause the particles separated into the duct to be aligned one after another in a row in the duct. The parameter of the particles is measured in the aligned stream one after the other and the particles are directed into one of a plurality of paths as determined by the measurement. The body comprises a disk member having a front face facing a supply conduit and the duct lies in a radial plane of the disk member. In one arrangement the measurement of the parameter is carried out by one or more measurement devices either carried on the disk or outside the edge of the disk.SELECTED DRAWING: Figure 1

The invention discloses a mixed particle grading device and an operation method thereof, and relates to the technical field of particle material treatment.The mixed particle grading device comprises a first barrel extending in the vertical direction, the first barrel is provided with a flow guide component capable of enabling materials to spirally rotate, and an inlet and outlet is formed in the lower end of the first barrel and used for discharging coarse particles and introducing gas; the second barrel is arranged in the first barrel and located below the flow guide component, the upper portion of the second barrel extends in the vertical direction to form a first inlet, the lower portion of the second barrel extends out of the first barrel to form a first discharge port, an annular space is formed between the first barrel and the second barrel, and a turbulent flow assembly used for raising particles is arranged in the annular space; a second discharge port located above the turbulent flow assembly and below the upper end of the second barrel is formed in the side wall of the first barrel; the feeding pipeline and the air inlet pipeline are connected with the upper end of the first barrel. According to the grading device, large-difference mixed particles can be more sufficiently graded, so that the grading device has higher grading precision.

This invention discloses a visual recognition-based method and system for slag particle grading, relating to the field of industrial machine vision technology. The method includes constructing a doubling sequence based on an effective scale set, calculating a snapshot matrix and performing singular value decomposition to obtain a left singular vector matrix, calculating the projection residual, determining the fusion window length and extracting the window fusion diameter, calculating a consistency flag, setting the endpoints of the grading interval, calculating the fusion score by fitting the diameter and filtering it to obtain the output grade. By introducing a multi-channel adaptive subtraction mechanism based on background statistics, the interference of slag transport background and illumination fluctuations on particle boundary extraction is reduced, improving the reliability of particle size measurement. By constructing a multi-scale particle size fusion and consistency judgment mechanism constrained by imaging blur, stable estimation and fine grading of slag particle size are achieved, improving the continuity and controllability of the grading results within the critical particle size range.

The embodiment of the present application provides a particle classification device and system, which belongs to the field of optical metasurface technology. The device includes an optical driver and a screening channel; the optical driver includes a light source and an optical system; an optical window is provided on one side of the screening channel; a particle outlet is provided on the other side of the screening channel; wherein the optical window is opposite to the optical system, and the light generated by the light source is modulated by the optical system to form corresponding focal points at the particle outlets, so that the target particles in the screening channel perform a quasi-projectile motion under the drive of light force and then enter the particle outlet; and the length of the optical window is less than or equal to the length of the screening channel. The device and system improve the classification efficiency by forming a light trap at the particle outlet and using light force to drive the target particles to perform a quasi-projectile motion.

Aspects of the present disclosure include methods, systems, and non-transitory computer-readable storage media for classifying cytometry image data using images of single particles, e.g., single cells. A method for classifying cytometry image data according to certain embodiments includes receiving unclassified cytometry image data including a plurality of images corresponding to an image channel, adjusting aspects of at least one of the plurality of images of the cytometry image data, and applying a model to the adjusted cytometry image data to classify the cytometry image data, the model being trained to predict the presence of particles belonging to a first category of particles in the cytometry image data. Aspects of the present disclosure also include a method for training a model to classify cytometry image data, the method including receiving flow cytometry data including unclassified cytometry image data including a plurality of images, each instance of the cytometry image data corresponding to an image channel, classifying each instance of the cytometry image data of the flow cytometry data to establish ground truth data, and adjusting aspects of at least one of the plurality of images of each instance of the cytometry image data of the ground truth data to train the model to classify the cytometry image data as data including particles belonging to a first category of particles. A system for performing the subject methods is further provided.A non-transitory computer-readable storage medium is further described.

The invention discloses a live detection system and method for atmospheric water particles, the detection system is composed of a detection device, a balloon and a ground receiving system, and the detection device comprises a cylindrical shell, an inner cylinder, a Faraday ring, a photoelectric detection assembly, a signal processing unit, a data transmission unit and a power supply. Aqueous particles in the atmosphere penetrate through the inner cylinder, the Faraday ring detects the electric charge quantity, and the particle speed is inverted through the double rings. The photoelectric detection assembly captures particle images and obtains image textures. The signal processing unit integrates a cross-correlation algorithm, and a charge integration window dynamically adjusts an integration window delta t = L / v. A classification method based on fuzzy logic constructs a multi-parameter classification system through the speed (v), the particle size (d) and the scattering intensity (Z value), and establishes a particle classification model. And the data transmission unit transmits the collected charge signal waveform, particle image and environment temperature and humidity parameters by adopting a wireless data transmission transmitter and transmits the data back to a ground receiving system.

The utility model discloses magnetic density separation equipment for classifying electronic waste particles, which relates to the technical field of electronic waste treatment and comprises a bottom plate, and four supporting legs and two supporting plates are fixedly connected to the upper surface of the bottom plate. Superconducting magnets fixed to the supporting legs at the corresponding positions and a plurality of rotating rods rotationally connected with the supporting plates at the corresponding positions are arranged above the bottom plate. According to the device, various metals mixed in electronic wastes can be effectively separated at the same time through the paramagnetism of the magnetic fluid and the density difference of different metals, compared with other traditional schemes, the process steps are greatly shortened, and compared with a traditional method depending on chemical reagents or high-temperature smelting, physical separation does not need to use strong acid, cyanide or high temperature, and the cost is reduced. Separation is achieved only through physical fields such as a magnetic field and water flow, so that emission of toxic waste water and waste gas is remarkably reduced, the environmental protection treatment cost of enterprises is reduced, and meanwhile workers are prevented from making direct contact with heavy metal and harmful chemical substances.

The application discloses a method for identifying a leading particle in mud flow dynamic simulation and a method for querying a neighborhood particle. In view of the defect that the existing SPH model of mud flow cannot distinguish the leading particle, two schemes are provided under a single concept. The method for identifying the leading particle in mud flow dynamic simulation configures a 3D-CNN classification model in the SPH model to identify the leading particle and non-leading particle from the grid scale. The classification model is based on the frame data of the material model, defines a local aggregation space around the object particle, extracts a feature tensor, combines the object particle attribute, analyzes the particle attribute statistical index from the grid scale and the grid scale leading particle identification rule, generates a sample and trains the model. The method for querying the neighborhood particle in mud flow dynamic simulation is based on the leading particle identification technology, adopts tree storage for the leading particle, adopts hash storage for the opposite, obtains a global partition fusion hash table and optimizes the particle query. The application solves the problem of the leading particle of mud flow and global simulation, thereby reducing the operation complexity, optimizing the time and space cost, balancing the accuracy and efficiency of the numerical model.

The invention discloses a particle classification and size measurement method and device based on interference imaging and improved UNet + + +, and belongs to the field of particle measurement and image processing. The method comprises the following steps: acquiring a spherical particle interference fringe pattern and an irregular particle interference speckle pattern, and constructing a data set containing a mask pattern and a category label; dividing into a training set, a verification set and a test set; the training set is used for training a pre-constructed neural network model, the pre-constructed neural network model takes an original UNet + + + network as a basis, a space and channel attention module, a frequency domain dynamic convolution unit and a multi-axis Hadamard convolution attention module are introduced, and the network is trained to output a reconstructed image and a category label at the same time; and inputting a to-be-measured particle image into the trained network, outputting a particle category and a reconstructed image, and measuring the reconstructed image to obtain size information. According to the method, high-precision, real-time and end-to-end prediction of particle types and sizes is realized, and the method is suitable for a mixed scene of spherical droplets and irregular ice crystals in cloud.

A system comprises a particle sensor for a vehicle comprising a light source that directs a beam to an interrogation region outside the vehicle; and an optical detector that receives scattered or reflected light from an aerosol particle in the interrogation region. A processor performs a method for particle classification comprising measuring an optical response from a single particle in the interrogation region by identifying an optical response peak for scattered or reflected light from the interrogation region; measuring an amplitude and duration of the optical response peak; correcting the duration of the optical response peak based on a vehicle airspeed; based on the measured amplitude of the optical response peak, generating an expected optical response duration for water droplet using a calibration table; analyzing the measured optical response duration and the expected optical response duration to determine particle classification; and generating classification probabilities for one or more particle types.

The utility model discloses a graded collection device for particles discharged by a diesel engine, and belongs to the technical field of pollutant monitoring. According to the technical scheme, the device comprises a particle grading and collecting area, the particle grading and collecting area comprises an ionization area, a small particle area, a medium particle area and a large particle chamber, the small particle area comprises a small particle collecting chamber, and the small particle collecting chamber comprises a small particle positive plate, a small particle filter screen and a small particle negative plate from top to bottom; the middle particle area comprises a middle particle collecting chamber, and the middle particle collecting chamber comprises a middle particle positive plate, a middle particle filter screen and a middle particle negative plate from top to bottom. The utility model has the beneficial effects that the particle classification collection area realizes classification sampling of diesel engine particles through the design of multiple stages of collection areas, each collection area and the ionization chamber respectively form a circulation loop, and the sorting accuracy is improved through multiple times of sorting.

The application discloses a barley seed fine-grained classification method and system, electronic equipment and a storage medium, and belongs to the technical field of intelligent detection of agricultural seeds. The application constructs an LRSG-DenseNet classification model, takes DenseNet161 as a backbone, embeds a learnable radial spectrum gating module after a DenseBlock, maps spatial features to a frequency domain through two-dimensional real fast Fourier transform, constructs a pseudo-radial frequency index, realizes amplitude spectrum adaptive re-labeling by using a learnable spectrum parameter matrix, generates a channel attention vector by global average pooling and a multilayer perceptron, obtains spatial-frequency domain collaborative features by residual fusion, and completes fine-grained classification. The application only uses ordinary RGB images, does not need a hyperspectral device, can significantly improve the perception ability of subtle features such as seed coat texture and furrows, suppresses noise interference, improves the recognition accuracy and robustness of similar barley varieties, and is suitable for seed purity detection and high-throughput nondestructive sorting.

This utility model relates to the field of metallurgical auxiliary material production technology, specifically a particle classifier for metallurgical auxiliary material production. It includes a base plate, a classifying cylinder above the base plate, an upper screen plate and a lower screen plate installed on the inner wall of the classifying cylinder for particle classification, and two discharge troughs on the side wall of the classifying cylinder for unloading. It also includes a tilting mechanism, disposed on the top surface of the base plate, for tilting the classifying cylinder. The tilting mechanism includes a frame fixed to the top surface of the base plate, two rotating rollers fixed to the outer wall of the classifying cylinder and rotatably connected to two vertical ends of the frame, and a rotating rod coaxially fixed to the surface of one of the rotating rollers away from the classifying cylinder. This utility model solves the problem of inconvenient particle classification and unloading in metallurgical auxiliary materials by setting up a base plate, a classifying cylinder, a feed funnel, a discharge pipe, a solenoid valve, an upper screen plate, a lower screen plate, a tilting mechanism, and a shielding mechanism.

The present invention provides a classification model generation method, a particle classification method, a computer program, and an information processing device which are for classifying particles using, as training data, waveform data representing a specified morphological feature and waveform data representing an unspecified morphological feature.　The present invention generates a classification model that outputs determination information indicating whether or not particles have a specified morphological feature when waveform data is input, by learning using training data including: first waveform data representing a morphological feature of particles obtained by emitting light to particles which are included in a first sample and which have the specified morphological feature; information indicating that the first waveform data has been obtained from the particles which are included in the first sample; second waveform data representing a morphological feature of unspecified particles which are included in a second sample; information indicating that the second waveform data has been obtained from the particles which are included in the second sample; and the positive rate which is the proportion of particles having the specified morphological feature.