EP4196745A1 - Method and apparatus for online monitoring of foam quality during foam production process - Google Patents

Method and apparatus for online monitoring of foam quality during foam production process

Info

Publication number
EP4196745A1
EP4196745A1 EP21746058.3A EP21746058A EP4196745A1 EP 4196745 A1 EP4196745 A1 EP 4196745A1 EP 21746058 A EP21746058 A EP 21746058A EP 4196745 A1 EP4196745 A1 EP 4196745A1
Authority
EP
European Patent Office
Prior art keywords
foam
profile
topography map
cross
defects
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP21746058.3A
Other languages
German (de)
French (fr)
Inventor
Jianwu GAO
Jun Zhang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Covestro Deutschland AG
Original Assignee
Covestro Deutschland AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202010801935.5A external-priority patent/CN114076765A/en
Priority claimed from EP20207120.5A external-priority patent/EP4001834A1/en
Application filed by Covestro Deutschland AG filed Critical Covestro Deutschland AG
Publication of EP4196745A1 publication Critical patent/EP4196745A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
    • G01B11/2518—Projection by scanning of the object
    • G01B11/2522—Projection by scanning of the object the position of the object changing and being recorded
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/20—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles for articles of indefinite length
    • B29C44/28—Expanding the moulding material on continuous moving surfaces without restricting the upwards growth of the foam
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/34—Auxiliary operations
    • B29C44/36—Feeding the material to be shaped
    • B29C44/46—Feeding the material to be shaped into an open space or onto moving surfaces, i.e. to make articles of indefinite length
    • B29C44/467—Foam spreading or levelling devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/34—Auxiliary operations
    • B29C44/60—Measuring, controlling or regulating
    • C—CHEMISTRY; METALLURGY
    • C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
    • C08L—COMPOSITIONS OF MACROMOLECULAR COMPOUNDS
    • C08L75/00—Compositions of polyureas or polyurethanes; Compositions of derivatives of such polymers
    • C08L75/04—Polyurethanes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G01B11/245—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures using a plurality of fixed, simultaneously operating transducers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B17/00—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations
    • G01B17/06—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations for measuring contours or curvatures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8901—Optical details; Scanning details
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G01N29/041—Analysing solids on the surface of the material, e.g. using Lamb, Rayleigh or shear waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G01N29/06—Visualisation of the interior, e.g. acoustic microscopy
    • G01N29/0654—Imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/22—Details, e.g. general constructional or apparatus details
    • G01N29/26—Arrangements for orientation or scanning by relative movement of the head and the sensor
    • G01N29/265—Arrangements for orientation or scanning by relative movement of the head and the sensor by moving the sensor relative to a stationary material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/4481—Neural networks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29B—PREPARATION OR PRETREATMENT OF THE MATERIAL TO BE SHAPED; MAKING GRANULES OR PREFORMS; RECOVERY OF PLASTICS OR OTHER CONSTITUENTS OF WASTE MATERIAL CONTAINING PLASTICS
    • B29B7/00—Mixing; Kneading
    • B29B7/30—Mixing; Kneading continuous, with mechanical mixing or kneading devices
    • B29B7/58—Component parts, details or accessories; Auxiliary operations
    • B29B7/72—Measuring, controlling or regulating
    • B29B7/726—Measuring properties of mixture, e.g. temperature or density
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29B—PREPARATION OR PRETREATMENT OF THE MATERIAL TO BE SHAPED; MAKING GRANULES OR PREFORMS; RECOVERY OF PLASTICS OR OTHER CONSTITUENTS OF WASTE MATERIAL CONTAINING PLASTICS
    • B29B7/00—Mixing; Kneading
    • B29B7/74—Mixing; Kneading using other mixers or combinations of mixers, e.g. of dissimilar mixers ; Plant
    • B29B7/7404—Mixing devices specially adapted for foamable substances
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29B—PREPARATION OR PRETREATMENT OF THE MATERIAL TO BE SHAPED; MAKING GRANULES OR PREFORMS; RECOVERY OF PLASTICS OR OTHER CONSTITUENTS OF WASTE MATERIAL CONTAINING PLASTICS
    • B29B7/00—Mixing; Kneading
    • B29B7/80—Component parts, details or accessories; Auxiliary operations
    • B29B7/88—Adding charges, i.e. additives
    • B29B7/94—Liquid charges
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29K—INDEXING SCHEME ASSOCIATED WITH SUBCLASSES B29B, B29C OR B29D, RELATING TO MOULDING MATERIALS OR TO MATERIALS FOR MOULDS, REINFORCEMENTS, FILLERS OR PREFORMED PARTS, e.g. INSERTS
    • B29K2075/00—Use of PU, i.e. polyureas or polyurethanes or derivatives thereof, as moulding material
    • C—CHEMISTRY; METALLURGY
    • C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
    • C08G—MACROMOLECULAR COMPOUNDS OBTAINED OTHERWISE THAN BY REACTIONS ONLY INVOLVING UNSATURATED CARBON-TO-CARBON BONDS
    • C08G2110/00—Foam properties
    • C08G2110/0008—Foam properties flexible
    • C—CHEMISTRY; METALLURGY
    • C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
    • C08G—MACROMOLECULAR COMPOUNDS OBTAINED OTHERWISE THAN BY REACTIONS ONLY INVOLVING UNSATURATED CARBON-TO-CARBON BONDS
    • C08G2110/00—Foam properties
    • C08G2110/0083—Foam properties prepared using water as the sole blowing agent
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/845—Objects on a conveyor
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8901—Optical details; Scanning details
    • G01N2021/8908—Strip illuminator, e.g. light tube

Definitions

  • the present invention relates to a process and an apparatus for producing foam using a continuous foam block foaming method, and in particular to a method and an apparatus for online monitoring of foam quality during a foam production process.
  • the continuous foam block foaming method is a common production process for polyurethane foam, which is very suitable for large-scale industrial production.
  • polyols, isocyanates, water and auxiliary foaming agents, catalysts, stabilizers and other additives, as raw materials are pumped into the mixing nozzle with precise metering.
  • FIG. 1 is a view of a typical production apparatus using the continuous foam block foaming method. Referring to FIG. 1, these materials are spread on a slab 110 after being mixed by mechanical stirring or by other means, and the mixture is transported in the exhaust duct 120 by the slab.
  • the mixture undergoes chemical reactions and foams into a block 130 of a certain size (for example, with a maximum width of 220cm, a height of 120cm, and a length of no limitation).
  • a block 130 of a certain size for example, with a maximum width of 220cm, a height of 120cm, and a length of no limitation.
  • foam defect is an important quality control indicator, which is directly related to the physical properties of the foam and also determines the material cost of subsequent products.
  • the monitoring of quality performance indicators is the basis for data analysis and quality optimization.
  • An -objective of the present invention is to provide a method and an apparatus for online monitoring of foam quality during a foam production process, which has the advantages of being simple, convenient and efficient.
  • raw materials for foam production are injected onto a transporting slab of a conveyor via a mixing nozzle disposed at one end of the conveyor, the method comprising: continuously obtaining top profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and detecting foam defects based on the topography map for the surface of the foam.
  • the top profile data are obtained using laser sensors or ultrasonic sensors disposed above the foam at the cross section by means of line scan.
  • the top profile data comprise spatial position coordinates for respective points of top profiles of the foam
  • the topography map is obtained by assembling a plurality of top profiles
  • the defects of the foam are detected by: comparing a profile cut out from the topography map along a first direction with a first standard profile template, and comparing a profile cut out from the topography map along a second direction with a second standard profile template, wherein the first and second directions are perpendicular to a depth direction of the foam and are perpendicular to each other; and determining existence and categories of the defects based on the comparison results.
  • the first standard profile template and the second standard profile template are in the form of characteristic thresholds or standard profile curves determined based on -product quality specifications.
  • the top profile data comprise spatial position coordinates for respective points of top profiles of the foam
  • the topography map is in the form of point cloud including the spatial position coordinates for the respective points of the top profiles of the foam
  • the defects of the foam are detected by: searching for a target region with an abrupt change in depth in the point cloud; and determining existence and categories of the defects using a neural network model to identify the target region.
  • the categories of defects include surface crack, surface blistering and surface bulging.
  • the following step is further included: optimizing process parameters and/or formulations in the product manufacturing schemes by making comparisons among respective defect detection results for a plurality of product manufacturing schemes.
  • raw materials for foam production are injected onto the transporting slab of the conveyor via a mixing nozzle disposed at one end of the conveyor, the apparatus comprising: a top profile measuring unit configured to continuously obtain top profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and a calculating unit configured to detect the foam defects based on the topography map for the surface of the foam.
  • the top profile data for the cross sections are obtained by means of line scan, and a topography map is obtained by assembling the top profile data of a series of cross sections. Since the scan is performed only along a single straight line, there is no need to perform complex motion correction algorithms when generating the topography map, and there is no need to select sensors with a high response speed.
  • defects are detected by using a template comparison method, which simplifies criteria for defect determination, and provides a capability for customized and flexible configuration.
  • it is only necessary to scan the surface of the foam along a single straight line and the topography of the foam surface is relatively simple. This reduces the complexity of point cloud and facilitates the selection of simple recognition algorithms.
  • FIG. 1 is a view of a typical production apparatus using the continuous foam block method.
  • FIG. 2 is a side view of a typical production apparatus using the continuous foam block method.
  • FIG. 3 is a schematic diagram of obtaining a cross-sectional profile by scanning the top of the foam using laser sensors or ultrasonic sensors according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a top profile of a cross section of a foam product without surface defects obtained by being scanned by laser sensors or ultrasonic sensors.
  • FIGs.5A-5C are schematic diagrams of top profiles of cross sections of foam products with surface defects obtained by being scanned with laser sensors or ultrasonic sensors.
  • FIG. 6 exemplarily illustrates profile curves Cl and C2 cut out from a topography map along a first direction and a second direction, respectively.
  • FIG. 7 exemplarily illustrates a topography map of the foam surface, wherein the gray value of each point in the topography map represents the depth of the corresponding position on the foam surface.
  • FIG. 8 is a schematic block diagram of an apparatus for online monitoring of foam quality during a foam production process according to an embodiment of the present invention.
  • FIG. 9 is a flowchart of a method for online monitoring of foam quality during a foam production process according to another embodiment of the present invention.
  • FIG. 10 is a flowchart of a method for online monitoring of foam quality during foam production according to another embodiment of the present invention.
  • FIG. 2 is a side view of a typical production apparatus using the continuous foam block foaming method.
  • a production apparatus using the continuous foam block foaming method 20 includes a mixing nozzle 210, an exhaust duct (not shown), a conveyor 220 and a control system (not shown), where the mixing nozzle 210 is disposed at one end of the conveyor 220.
  • the conveyor 220 includes a transporting slab 221 and a power unit 222 for driving the transporting slab 221 to advance in the direction indicated by the arrow in the figure. Further referring to FIG.
  • the mixing nozzle 210 injects a mixture of raw materials such as polyols, isocyanates, water and auxiliary foaming agents, catalysts, stabilizers and other additives into the transporting slab 221 of the conveyor.
  • the mixture of these raw materials undergoes chemical reactions when being conveyed by the transporting slab 221 through the exhaust duct, thereby forming a block PF (such as a flexible polyurethane foam) of a certain size.
  • a control system performs real-time control and monitoring of the entire production process. For example, the control system controls the timing and flow rate of the mixture injection from the mixing nozzle 210 and the advancing speed of the transporting slab 221.
  • the defects of the foam are determined based on a topography map of the foam surface.
  • the topography map is a data set. Each point in the data set corresponds to one of the points on the foam surface, and the spatial position information of the corresponding point on the foam surface is represented by a three-dimensional array (x, y, z), where x, y and z are the spatial coordinate values of the corresponding point on the foam surface.
  • the categories of the defects described herein include, for example, but are not limited to surface crack, collapse, surface blistering, and surface bulging.
  • a location is selected on the advancing path of the transporting slab, and the cross-sectional profile data of the foam at the location are continuously obtained.
  • the topography map of the foam surface can be obtained by assembling the continuously obtained cross-sectional profiles.
  • the profile data described herein at least include the spatial position coordinates of each point of the profile.
  • the profile data for the cross section are top profile data for the cross section.
  • the top profile is only an example of the cross-sectional profile.
  • the cross-sectional profile data may also include side profile data.
  • a laser sensor or an ultrasonic sensor 30 can be disposed above the foam at the cross section as shown in FIG. 2.
  • the sensor is configured to perform a line scan on the foam in a direction perpendicular to the advancing direction of the transporting slab to obtain the top profile data of the cross section. Since the sensor scans the surface of the foam only along a single straight line, there is no need to perform complex motion correction algorithms when generating the topography map, and there is no need to select a sensor with a high response speed to meet the real-time monitoring requirements.
  • FIG. 3 is a schematic diagram of obtaining cross-sectional profile data by scanning the top of the foam using laser sensors or ultrasonic sensors according to an embodiment of the present invention.
  • a dual sensor arrangement is adopted, in which two laser sensors or ultrasonic sensors 30a, 30b are arranged side by side in a direction perpendicular to the advancing direction of the transporting slab, and perform a line scan or a line-by-line scan on the top surface of the foam in the direction of the side-by-side arrangement to obtain the top profile data of the cross section.
  • the areas scanned by the dual sensors may overlap, and the overlapping areas can be merged by image processing technology to obtain a complete top profile data of the cross section.
  • FIG. 4 is a schematic diagram of the cross- sectional top profile of a foam product without surface defects obtained by being scanned by laser sensors or ultrasonic sensors, where w in the figure represents the width of the transporting slab or the foam.
  • the top profile of the foam is not necessarily a flat surface, but is undulating as shown in FIG. 4.
  • FIGs.5A-5C are schematic diagrams of top profiles of cross sections of foam products with surface defects obtained by being scanned with laser sensors or ultrasonic sensors, wherein, FIG. 5A shows a top profile with the defect of surface crack, FIG. 5B shows a top profile with surface blistering, and FIG. 5C shows a top profile with surface bulging.
  • the top profile with the defect of surface crack has breaking points in some parts
  • the top profile with surface blistering has concaves in some parts
  • the top profile with surface bulging has convexes in some parts.
  • the top profiles of the cross sections are assembled in a time sequence to generate a topography map containing only the spatial position information of each of the points of the top profiles of the foam.
  • laser sensors or ultrasonic sensors can be used to scan the top of the foam at a certain time interval or sampling interval to obtain a series of cross-sectional top profiles with a certain time sequence.
  • the X axis of the spatial rectangular coordinate system is perpendicular to the advancing direction of the transporting slab and the depth or thickness direction of the foam
  • the Y axis is parallel to the advancing direction of the transporting slab
  • the Z axis is parallel to the depth or thickness direction of the foam.
  • the transporting slab can advance in a uniform speed or a variable speed.
  • the above-mentioned sampling interval At can be changed with the advancing speed v of the transporting slab, so as to ensure that adjacent top profiles are spaced equally along the advancing direction of the transporting slab, that is, to ensure that vxAt always remains unchanged.
  • a template comparison method can be used to detect the defects of the foam, which is described further below.
  • FIG. 6 it exemplarily illustrates profile curves Cl and C2 cut out from the topography map along a first direction and a second direction, respectively, where the first direction is, for example, the X axis direction, and the second direction is, for example, the Y axis direction, which are perpendicular to each other and at the same time perpendicular to the depth direction of the foam.
  • a series of profile curves cut out from the topography map along the first direction are compared with a first standard profile template (FIG. 6 exemplarily shows only one profile curve Cl cut out along the first direction), and on the other hand, a series of profile curves cut out from the topography map along the second direction are compared with a second standard profile template (FIG. 6 exemplarily shows only one profile curve C2 cut out along the second direction). Since the topography map is formed by assembling a plurality of cross-sectional top profiles, the profile curves cut out along the first direction here are namely the aforementioned top profiles of the cross sections.
  • the first standard profile template and the second standard profile template may be in the form of geometric characteristic thresholds determined based on production quality specifications. By comparing the geometric characteristics of the profile curves actually measured with the characteristic thresholds, it can be determined whether there are defects and the categories of the defects. For example, if the difference between the maximum height and the minimum height of the profile curve in a local range exceeds the corresponding threshold, it can be determined that there are blistering or bulging defects on the foam surface; or if the number of continuous breaking points of the profile curve exceeds the corresponding threshold, then it can be determined that there are crack defects on the foam surface.
  • the first standard profile template and the second standard profile template may also be in the form of standard profile curves determined based on production quality specifications (for example, the profile curves shown in FIG. 4).
  • the existence and categories of defects can be determined by calculating the matching degree (such as an overall deviation degree for the whole and the local deviation degree) and the deviation direction between the profile curves actually measured and the standard profile curves.
  • the above template comparison method simplifies criteria for defect determination, and provides a capability for customized and flexible configuration. For example, for different quality specifications, real-time monitoring of foam quality can be implemented using the corresponding standard profile curves or characteristic thresholds.
  • image recognition methods can also be used to detect foam defects, which will be described further below.
  • a topography map for the foam surface is exemplarily illustrated, where the gray scale value of each point in the topography map represents the depth of the corresponding position on the foam surface (also referred to as the spatial depth value), that is, the distance from the point to the slab.
  • the gray scale representation of the topography map can provide users with an intuitive illustration of the surface topography.
  • the topography map shown in FIG. 7 is in the form of a point cloud, with each point in the point cloud representing the spatial position coordinates for the respective points of the top profiles of the foam.
  • a target region with an abrupt change in depth is first searched for in the point cloud, and then the target region is identified based on a neural network model to determine the existence and categories of the defects.
  • the above-mentioned neural network model can be obtained by training using topography map samples tagged with defects.
  • the neural network model can be trained in the following manner.
  • a certain limit can be set to the physical dimensions of Lx W corresponding to the respective one of the samples, where L is the physical dimension of the respective sample along the advancing direction of the transporting slab, and W is the width of the foam.
  • L is the physical dimension of the respective sample along the advancing direction of the transporting slab
  • W is the width of the foam.
  • the physical dimension L can be set to be not less than 100mm.
  • a certain limit can be set to the physical dimensions of a single defect that is tagged.
  • the physical dimensions can be set to be not less than lOOmmx 100mm, or not less than 10 4 mm 2 .
  • [050] Third, it selects some samples from the plurality of samples of point cloud to obtain a training data set. Upon in-depth research, the inventor of the present invention has found that when those samples of point cloud tagged with defect categories occupy a large proportion in the training data set, the training difficulty and speed of the neural network model can be well balanced, especially when the proportion is greater than or equal to 10%. [051] Finally, train the neural network model using the training data set. The number of trainings can be one or more times.
  • the inventor of the present invention Upon in-depth research, the inventor of the present invention has found that when multiple trainings are performed, if 20% of the samples of point cloud samples in the training data set are retained for the next training upon completion of each training, not only the training speed can be increased, but also the accuracy of defect recognition by the model can also be improved.
  • the above-mentioned image recognition method has the advantages of easy implementation and high accuracy.
  • it is only necessary to scan the foam surface along a single straight line and the topography of the foam surface is relatively simple. This reduces the complexity of the point cloud, so simple recognition algorithms can be selected to generate the recognition results quickly.
  • FIG. 8 is a schematic block diagram of an apparatus for online monitoring of foam quality during a foam production process according to an embodiment of the present invention.
  • the apparatus 80 includes a profile measuring unit 810 and a calculating unit 820 coupled to the profile measuring unit 810.
  • the apparatus 80 further includes a storage unit 830 configured to store profile data, a display device 840 configured to display foam quality monitoring results, and a feedback unit 850.
  • the profile measuring unit 810 is configured to continuously obtain profile data for a cross section (such as top profile data) of the foam at a predetermined location to generate a topography map for a surface of the foam, which may be, for example, laser sensors or ultrasonic sensors disposed above the foam at the cross section as described above.
  • the calculating unit 820 is configured to detect defects of the foam based on the topography map of the foam surface. The specific method for defect detection has been described above, and will not be repeated here.
  • the feedback unit 850 is communicatively coupled to the calculating unit 820, the storage unit 830, and the production line control system (not shown), and is configured to send the defect detection results generated by the calculating unit 820 to the production line control system, or extract the defect detection results from the storage unit 830 and send the defect detection results to the production line control system.
  • the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes.
  • the expression "and/or" here means that both the process parameters and the formulations can be included at the same time, or one of the process parameters and the formulations can be included. Examples of process parameters include, for example, but are not limited to, the advancing speed of the transporting slab, and the temperature and injection speed of the raw materials injected.
  • the apparatus 80 of the embodiment shown in FIG. 8 can be one unit of the control system in the aforementioned production apparatus using the continuous foam block foaming method 20, or one independent of the control system in the production apparatus using the continuous foam block foaming method 20.
  • FIG. 9 is a flowchart of a method for online monitoring of foam quality during a foam production process according to another embodiment of the present invention.
  • the method of this embodiment is implemented with the aid of the apparatus shown in FIG. 8.
  • the implementation of the method in this embodiment is not limited to an apparatus with a specific structure.
  • step S910 the profile measuring unit 810 continuously obtains the profile data for the cross section (such as top profile data) of the foam at a predetermined location, and stores the profile data for the cross section obtained in the storage unit 830.
  • the profile data for the cross section can be used to generate a topography map of the foam surface, and the predetermined location is on the advancing path of the transporting slab.
  • step S920 the calculating unit 820 obtains the advancing speed of the transporting slab from the control system and acquires the cross-sectional profile data from the storage unit 830, thereby generating a topography map of the foam surface.
  • step S930 the calculating unit 820 compares a profile curve cut out from the topography map along a first direction with a first standard profile template, and compares a profile curve cut out from the topography map along a second direction with a second standard profile template.
  • step S940 the calculating unit 820 determines the existence and categories of the defects based on the comparison results.
  • the specific determination method has been described above, and will not be repeated here.
  • step S950 the calculating unit 820 outputs the determination results obtained in step S940 to the display unit 840.
  • step S960 the feedback unit 850 sends the defect detection results generated by the calculating unit 820 to the production line control system, or extracts the defect detection results from the storage unit 830 and sends the defect detection results to the production line control system, such that the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes.
  • FIG. 10 is a flowchart of a method for online monitoring of foam quality during foam production according to another embodiment of the present invention. Exemplarily, the method of this embodiment is implemented with the aid of the apparatus shown in FIG. 8. However, it should be pointed out that the implementation of the method in this embodiment is not limited to an apparatus with a specific structure.
  • step S1010 the profile measuring unit 810 continuously obtains the profile data for the cross section (such as top profile data) of the foam at a predetermined location, and stores the profile data for the cross section obtained in the storage unit 830.
  • the profile data for the cross section can be used to generate a topography map of the foam surface, and the predetermined location is on the advancing path of the transporting slab.
  • step S1020 the calculating unit 820 obtains the advancing speed of the transporting slab from the control system and acquires the top cross-sectional data from the storage unit 830, thereby generating a topography map in the form of a point cloud.
  • step S 1030 the calculating unit 820 searches for a target region with an abrupt change in depth in the point cloud.
  • step S 1040 the target region is identified based on a neural network model to determine the existence and categories of the defects.
  • the above-mentioned neural network model can be obtained by training using topography map samples tagged with defects.
  • step S1050 the calculating unit 820 outputs the determination results obtained in step S1040 to the display unit 840.
  • the feedback unit 850 sends the defect detection results generated by the calculating unit 820 to the production line control system, or extracts the defect detection results from the storage unit 830 and sends the defect detection results to the production line control system, such that the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Textile Engineering (AREA)
  • Polymers & Plastics (AREA)
  • Organic Chemistry (AREA)
  • Medicinal Chemistry (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Signal Processing (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The present invention relates to a process and an apparatus for producing foam using a continuous foam block foaming method, and in particular to a method and an apparatus for online monitoring of foam quality during a foam production process. In the method for online monitoring of foam quality in the foam production process according to the present invention, raw materials for foam production are injected onto a transporting slab of a conveyor via a mixing nozzle disposed at one end of the conveyor, the method comprising: continuously obtaining profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and detecting foam defects based on the topography map for the surface of the foam.

Description

METHOD AND APPARATUS FOR ONLINE MONITORING
OF FOAM QUALITY DURING FOAM PRODUCTION PROCESS
FIELD OF THE INVENTION
[001] The present invention relates to a process and an apparatus for producing foam using a continuous foam block foaming method, and in particular to a method and an apparatus for online monitoring of foam quality during a foam production process.
BACKGROUND OF THE INVENTION
[002] The continuous foam block foaming method is a common production process for polyurethane foam, which is very suitable for large-scale industrial production. In this process, polyols, isocyanates, water and auxiliary foaming agents, catalysts, stabilizers and other additives, as raw materials, are pumped into the mixing nozzle with precise metering. FIG. 1 is a view of a typical production apparatus using the continuous foam block foaming method. Referring to FIG. 1, these materials are spread on a slab 110 after being mixed by mechanical stirring or by other means, and the mixture is transported in the exhaust duct 120 by the slab. During the transportation process, the mixture undergoes chemical reactions and foams into a block 130 of a certain size (for example, with a maximum width of 220cm, a height of 120cm, and a length of no limitation). After the block (polyurethane foam) is made, it is cut into the required size and shape.
[003] In the production process using the continuous foam block foaming method, foam defect is an important quality control indicator, which is directly related to the physical properties of the foam and also determines the material cost of subsequent products. In intelligent manufacturing, the monitoring of quality performance indicators is the basis for data analysis and quality optimization. However, there is currently no method and apparatus capable of online monitoring foam quality in an accurate and efficient manner. SUMMARY OF THE INVENTION
[004] An -objective of the present invention is to provide a method and an apparatus for online monitoring of foam quality during a foam production process, which has the advantages of being simple, convenient and efficient.
[005] In the method for online monitoring of foam quality during a foam production process according to one aspect of the present invention, raw materials for foam production are injected onto a transporting slab of a conveyor via a mixing nozzle disposed at one end of the conveyor, the method comprising: continuously obtaining top profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and detecting foam defects based on the topography map for the surface of the foam.
[006] Optionally, in the above method, the top profile data are obtained using laser sensors or ultrasonic sensors disposed above the foam at the cross section by means of line scan.
[007] Optionally, in the above method, the top profile data comprise spatial position coordinates for respective points of top profiles of the foam, the topography map is obtained by assembling a plurality of top profiles, and the defects of the foam are detected by: comparing a profile cut out from the topography map along a first direction with a first standard profile template, and comparing a profile cut out from the topography map along a second direction with a second standard profile template, wherein the first and second directions are perpendicular to a depth direction of the foam and are perpendicular to each other; and determining existence and categories of the defects based on the comparison results. [008] Optionally, in the above method, the first standard profile template and the second standard profile template are in the form of characteristic thresholds or standard profile curves determined based on -product quality specifications.
[009] Optionally, in the above method, the top profile data comprise spatial position coordinates for respective points of top profiles of the foam, the topography map is in the form of point cloud including the spatial position coordinates for the respective points of the top profiles of the foam, and the defects of the foam are detected by: searching for a target region with an abrupt change in depth in the point cloud; and determining existence and categories of the defects using a neural network model to identify the target region.
[010] Optionally, in the above method, the categories of defects include surface crack, surface blistering and surface bulging.
[Oil] Optionally, in the above method, the following step is further included: optimizing process parameters and/or formulations in the product manufacturing schemes by making comparisons among respective defect detection results for a plurality of product manufacturing schemes.
[012] In the apparatus for online monitoring of foam quality during a foam production process according to another aspect of the present invention, raw materials for foam production are injected onto the transporting slab of the conveyor via a mixing nozzle disposed at one end of the conveyor, the apparatus comprising: a top profile measuring unit configured to continuously obtain top profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and a calculating unit configured to detect the foam defects based on the topography map for the surface of the foam. [013] According to the embodiments of the present invention, the top profile data for the cross sections are obtained by means of line scan, and a topography map is obtained by assembling the top profile data of a series of cross sections. Since the scan is performed only along a single straight line, there is no need to perform complex motion correction algorithms when generating the topography map, and there is no need to select sensors with a high response speed. In addition, according to the embodiments of the present invention, defects are detected by using a template comparison method, which simplifies criteria for defect determination, and provides a capability for customized and flexible configuration. Furthermore, in several embodiments of the present invention, it is only necessary to scan the surface of the foam along a single straight line and the topography of the foam surface is relatively simple. This reduces the complexity of point cloud and facilitates the selection of simple recognition algorithms.
BRIEF DESCRIPTION OF THE DRAWINGS
[014] FIG. 1 is a view of a typical production apparatus using the continuous foam block method.
[015] FIG. 2 is a side view of a typical production apparatus using the continuous foam block method.
[016] FIG. 3 is a schematic diagram of obtaining a cross-sectional profile by scanning the top of the foam using laser sensors or ultrasonic sensors according to an embodiment of the present invention.
[017] FIG. 4 is a schematic diagram of a top profile of a cross section of a foam product without surface defects obtained by being scanned by laser sensors or ultrasonic sensors.
[018] FIGs.5A-5C are schematic diagrams of top profiles of cross sections of foam products with surface defects obtained by being scanned with laser sensors or ultrasonic sensors. [019] FIG. 6 exemplarily illustrates profile curves Cl and C2 cut out from a topography map along a first direction and a second direction, respectively.
[020] FIG. 7 exemplarily illustrates a topography map of the foam surface, wherein the gray value of each point in the topography map represents the depth of the corresponding position on the foam surface.
[021] FIG. 8 is a schematic block diagram of an apparatus for online monitoring of foam quality during a foam production process according to an embodiment of the present invention.
[022] FIG. 9 is a flowchart of a method for online monitoring of foam quality during a foam production process according to another embodiment of the present invention.
[023] FIG. 10 is a flowchart of a method for online monitoring of foam quality during foam production according to another embodiment of the present invention.
DETAILED DESCRIPTION OF THE EMBODIMENT(S) OF THE INVENTION
[024] The present invention will be described in more detail below with reference to the accompanying drawings in which exemplary embodiments of the present invention are illustrated. However, the present invention can be implemented in different forms and should not be construed as being limited to the embodiments given herein. The above-mentioned embodiments are provided to make the disclosure herein comprehensive and complete, so as to convey the protection scope of the present invention to those skilled in the art in a more comprehensive manner.
[025] In the present specification, terms such as "comprising" and "including" mean that in addition to the units and steps that are directly and clearly stated in the specification and claims, the technical solution of the present invention may also include the scenarios including other units and steps that are not directly and clearly stated.
[026] Terms such as "first" and "second" do not indicate the order of the units in terms of time, space, size, etc., but merely serve to distinguish the units.
[027] FIG. 2 is a side view of a typical production apparatus using the continuous foam block foaming method. As shown in FIG. 2, a production apparatus using the continuous foam block foaming method 20 includes a mixing nozzle 210, an exhaust duct (not shown), a conveyor 220 and a control system (not shown), where the mixing nozzle 210 is disposed at one end of the conveyor 220. The conveyor 220 includes a transporting slab 221 and a power unit 222 for driving the transporting slab 221 to advance in the direction indicated by the arrow in the figure. Further referring to FIG. 2, the mixing nozzle 210 injects a mixture of raw materials such as polyols, isocyanates, water and auxiliary foaming agents, catalysts, stabilizers and other additives into the transporting slab 221 of the conveyor. The mixture of these raw materials undergoes chemical reactions when being conveyed by the transporting slab 221 through the exhaust duct, thereby forming a block PF (such as a flexible polyurethane foam) of a certain size. In the production apparatus shown in FIG. 2, a control system performs real-time control and monitoring of the entire production process. For example, the control system controls the timing and flow rate of the mixture injection from the mixing nozzle 210 and the advancing speed of the transporting slab 221.
[028] According to one aspect of the present invention, the defects of the foam are determined based on a topography map of the foam surface. In one or more embodiments of the present invention, the topography map is a data set. Each point in the data set corresponds to one of the points on the foam surface, and the spatial position information of the corresponding point on the foam surface is represented by a three-dimensional array (x, y, z), where x, y and z are the spatial coordinate values of the corresponding point on the foam surface. The categories of the defects described herein include, for example, but are not limited to surface crack, collapse, surface blistering, and surface bulging. [029] According to another aspect of the present invention, a location is selected on the advancing path of the transporting slab, and the cross-sectional profile data of the foam at the location are continuously obtained. The topography map of the foam surface can be obtained by assembling the continuously obtained cross-sectional profiles. The profile data described herein at least include the spatial position coordinates of each point of the profile.
[030] Optionally, in one or more embodiments of the present invention, the profile data for the cross section are top profile data for the cross section. However, it should be pointed out that the top profile is only an example of the cross-sectional profile. In other embodiments of the present invention, the cross-sectional profile data may also include side profile data. Although the following description of the embodiments of the present invention takes defect detection on the top surface of the foam as an example, those skilled in the art, after reading through the specification, will realize that the principle of the present invention embodied in the following description is also applicable to defect detection on other surfaces of the foam.
[031] In order to obtain the top profile data, according to an embodiment of the present invention, a laser sensor or an ultrasonic sensor 30 can be disposed above the foam at the cross section as shown in FIG. 2. The sensor is configured to perform a line scan on the foam in a direction perpendicular to the advancing direction of the transporting slab to obtain the top profile data of the cross section. Since the sensor scans the surface of the foam only along a single straight line, there is no need to perform complex motion correction algorithms when generating the topography map, and there is no need to select a sensor with a high response speed to meet the real-time monitoring requirements.
[032] FIG. 3 is a schematic diagram of obtaining cross-sectional profile data by scanning the top of the foam using laser sensors or ultrasonic sensors according to an embodiment of the present invention. In the embodiment shown in FIG. 3, a dual sensor arrangement is adopted, in which two laser sensors or ultrasonic sensors 30a, 30b are arranged side by side in a direction perpendicular to the advancing direction of the transporting slab, and perform a line scan or a line-by-line scan on the top surface of the foam in the direction of the side-by-side arrangement to obtain the top profile data of the cross section. The areas scanned by the dual sensors may overlap, and the overlapping areas can be merged by image processing technology to obtain a complete top profile data of the cross section.
[033] It should be pointed out that the number and arrangement of the aforementioned sensors are only illustrative. In practical applications, more sensors can be used according to the situation. FIG. 4 is a schematic diagram of the cross- sectional top profile of a foam product without surface defects obtained by being scanned by laser sensors or ultrasonic sensors, where w in the figure represents the width of the transporting slab or the foam. During the production process, the top profile of the foam is not necessarily a flat surface, but is undulating as shown in FIG. 4.
[034] FIGs.5A-5C are schematic diagrams of top profiles of cross sections of foam products with surface defects obtained by being scanned with laser sensors or ultrasonic sensors, wherein, FIG. 5A shows a top profile with the defect of surface crack, FIG. 5B shows a top profile with surface blistering, and FIG. 5C shows a top profile with surface bulging. As can be seen from FIGs.5A-5C, the top profile with the defect of surface crack has breaking points in some parts, the top profile with surface blistering has concaves in some parts, and the top profile with surface bulging has convexes in some parts.
[035] According to one or more embodiments of the present invention, the top profiles of the cross sections are assembled in a time sequence to generate a topography map containing only the spatial position information of each of the points of the top profiles of the foam. For example, laser sensors or ultrasonic sensors can be used to scan the top of the foam at a certain time interval or sampling interval to obtain a series of cross-sectional top profiles with a certain time sequence.
[036] Illustratively, it is supposed that the following spatial rectangular coordinate system is used to describe the spatial position of each point on the foam surface: the X axis of the spatial rectangular coordinate system is perpendicular to the advancing direction of the transporting slab and the depth or thickness direction of the foam, the Y axis is parallel to the advancing direction of the transporting slab, and the Z axis is parallel to the depth or thickness direction of the foam. For adjacent cross- sectional top profiles, there are pairs of points (x, y, z) and (x', y', z'), with their coordinate values along the X axis remaining unchanged (x=x'), y'=y+vxAt, where v is the advancing speed of the transporting slab, At is the set scan time interval (i.e., sampling interval), z and z' are the actual measured values. When the scan time interval is relatively large, the interpolation method can be used to insert the fitted cross- sectional top profile data between adjacent cross-sectional top profile data (between y and y' and between z and z') in terms of scan time.
[037] It should be pointed out that the transporting slab can advance in a uniform speed or a variable speed. Preferably, the above-mentioned sampling interval At can be changed with the advancing speed v of the transporting slab, so as to ensure that adjacent top profiles are spaced equally along the advancing direction of the transporting slab, that is, to ensure that vxAt always remains unchanged.
[038] For the topography map generated by assembling the cross-sectional top profiles, a template comparison method can be used to detect the defects of the foam, which is described further below.
[039] Referring to FIG. 6, it exemplarily illustrates profile curves Cl and C2 cut out from the topography map along a first direction and a second direction, respectively, where the first direction is, for example, the X axis direction, and the second direction is, for example, the Y axis direction, which are perpendicular to each other and at the same time perpendicular to the depth direction of the foam.
[040] When determining the defects, on the one hand, a series of profile curves cut out from the topography map along the first direction are compared with a first standard profile template (FIG. 6 exemplarily shows only one profile curve Cl cut out along the first direction), and on the other hand, a series of profile curves cut out from the topography map along the second direction are compared with a second standard profile template (FIG. 6 exemplarily shows only one profile curve C2 cut out along the second direction). Since the topography map is formed by assembling a plurality of cross-sectional top profiles, the profile curves cut out along the first direction here are namely the aforementioned top profiles of the cross sections. [041] Optionally, the first standard profile template and the second standard profile template may be in the form of geometric characteristic thresholds determined based on production quality specifications. By comparing the geometric characteristics of the profile curves actually measured with the characteristic thresholds, it can be determined whether there are defects and the categories of the defects. For example, if the difference between the maximum height and the minimum height of the profile curve in a local range exceeds the corresponding threshold, it can be determined that there are blistering or bulging defects on the foam surface; or if the number of continuous breaking points of the profile curve exceeds the corresponding threshold, then it can be determined that there are crack defects on the foam surface.
[042] Optionally, the first standard profile template and the second standard profile template may also be in the form of standard profile curves determined based on production quality specifications (for example, the profile curves shown in FIG. 4). The existence and categories of defects can be determined by calculating the matching degree (such as an overall deviation degree for the whole and the local deviation degree) and the deviation direction between the profile curves actually measured and the standard profile curves.
[043] The above template comparison method simplifies criteria for defect determination, and provides a capability for customized and flexible configuration. For example, for different quality specifications, real-time monitoring of foam quality can be implemented using the corresponding standard profile curves or characteristic thresholds.
[044] In addition to the above-mentioned template comparison method, image recognition methods can also be used to detect foam defects, which will be described further below.
[045] Referring to FIG. 7, a topography map for the foam surface is exemplarily illustrated, where the gray scale value of each point in the topography map represents the depth of the corresponding position on the foam surface (also referred to as the spatial depth value), that is, the distance from the point to the slab. The gray scale representation of the topography map can provide users with an intuitive illustration of the surface topography. Optionally, the topography map shown in FIG. 7 is in the form of a point cloud, with each point in the point cloud representing the spatial position coordinates for the respective points of the top profiles of the foam.
[046] It can be seen from the above that defects such as surface crack, collapse, surface blistering, and surface bulging will cause abrupt changes in local geometric characteristics. Therefore, in one or more embodiments of the present invention, a target region with an abrupt change in depth is first searched for in the point cloud, and then the target region is identified based on a neural network model to determine the existence and categories of the defects. The above-mentioned neural network model can be obtained by training using topography map samples tagged with defects.
[047] Exemplarily, in one or more embodiments of the present invention, the neural network model can be trained in the following manner.
[048] First, obtain a plurality of samples of point cloud. In order to balance the training difficulty and speed of the neural network model, a certain limit can be set to the physical dimensions of Lx W corresponding to the respective one of the samples, where L is the physical dimension of the respective sample along the advancing direction of the transporting slab, and W is the width of the foam. Preferably, the physical dimension L can be set to be not less than 100mm.
[049] Second, tag the obtained the samples of point cloud with defects according to predetermined quality standards. Likewise, in order to balance the training difficulty and speed of the neural network model, a certain limit can be set to the physical dimensions of a single defect that is tagged. Preferably, the physical dimensions can be set to be not less than lOOmmx 100mm, or not less than 104 mm2.
[050] Third, it selects some samples from the plurality of samples of point cloud to obtain a training data set. Upon in-depth research, the inventor of the present invention has found that when those samples of point cloud tagged with defect categories occupy a large proportion in the training data set, the training difficulty and speed of the neural network model can be well balanced, especially when the proportion is greater than or equal to 10%. [051] Finally, train the neural network model using the training data set. The number of trainings can be one or more times. Upon in-depth research, the inventor of the present invention has found that when multiple trainings are performed, if 20% of the samples of point cloud samples in the training data set are retained for the next training upon completion of each training, not only the training speed can be increased, but also the accuracy of defect recognition by the model can also be improved.
[052] The above-mentioned image recognition method has the advantages of easy implementation and high accuracy. In particular, in multiple embodiments of the present invention, it is only necessary to scan the foam surface along a single straight line and the topography of the foam surface is relatively simple. This reduces the complexity of the point cloud, so simple recognition algorithms can be selected to generate the recognition results quickly.
[053] FIG. 8 is a schematic block diagram of an apparatus for online monitoring of foam quality during a foam production process according to an embodiment of the present invention.
[054] As shown in FIG. 8, the apparatus 80 includes a profile measuring unit 810 and a calculating unit 820 coupled to the profile measuring unit 810. Optionally, the apparatus 80 further includes a storage unit 830 configured to store profile data, a display device 840 configured to display foam quality monitoring results, and a feedback unit 850.
[055] The profile measuring unit 810 is configured to continuously obtain profile data for a cross section (such as top profile data) of the foam at a predetermined location to generate a topography map for a surface of the foam, which may be, for example, laser sensors or ultrasonic sensors disposed above the foam at the cross section as described above. The calculating unit 820 is configured to detect defects of the foam based on the topography map of the foam surface. The specific method for defect detection has been described above, and will not be repeated here.
[056] The feedback unit 850 is communicatively coupled to the calculating unit 820, the storage unit 830, and the production line control system (not shown), and is configured to send the defect detection results generated by the calculating unit 820 to the production line control system, or extract the defect detection results from the storage unit 830 and send the defect detection results to the production line control system. Accordingly, the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes. It should be pointed out that the expression "and/or" here means that both the process parameters and the formulations can be included at the same time, or one of the process parameters and the formulations can be included. Examples of process parameters include, for example, but are not limited to, the advancing speed of the transporting slab, and the temperature and injection speed of the raw materials injected.
[057] It should be pointed out that the apparatus 80 of the embodiment shown in FIG. 8 can be one unit of the control system in the aforementioned production apparatus using the continuous foam block foaming method 20, or one independent of the control system in the production apparatus using the continuous foam block foaming method 20.
[058] FIG. 9 is a flowchart of a method for online monitoring of foam quality during a foam production process according to another embodiment of the present invention. For an illustrative purpose, the method of this embodiment is implemented with the aid of the apparatus shown in FIG. 8. However, it should be pointed out that the implementation of the method in this embodiment is not limited to an apparatus with a specific structure.
[059] As shown in FIG. 9, in step S910, the profile measuring unit 810 continuously obtains the profile data for the cross section (such as top profile data) of the foam at a predetermined location, and stores the profile data for the cross section obtained in the storage unit 830. The profile data for the cross section can be used to generate a topography map of the foam surface, and the predetermined location is on the advancing path of the transporting slab.
[060] Subsequently, in step S920, the calculating unit 820 obtains the advancing speed of the transporting slab from the control system and acquires the cross-sectional profile data from the storage unit 830, thereby generating a topography map of the foam surface.
[061] Then, in step S930, the calculating unit 820 compares a profile curve cut out from the topography map along a first direction with a first standard profile template, and compares a profile curve cut out from the topography map along a second direction with a second standard profile template.
[062] Subsequently, in step S940, the calculating unit 820 determines the existence and categories of the defects based on the comparison results. The specific determination method has been described above, and will not be repeated here.
[063] Next, in step S950, the calculating unit 820 outputs the determination results obtained in step S940 to the display unit 840.
[064] Optionally, in step S960, the feedback unit 850 sends the defect detection results generated by the calculating unit 820 to the production line control system, or extracts the defect detection results from the storage unit 830 and sends the defect detection results to the production line control system, such that the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes.
[065] FIG. 10 is a flowchart of a method for online monitoring of foam quality during foam production according to another embodiment of the present invention. Exemplarily, the method of this embodiment is implemented with the aid of the apparatus shown in FIG. 8. However, it should be pointed out that the implementation of the method in this embodiment is not limited to an apparatus with a specific structure.
[066] As shown in FIG. 10, in step S1010, the profile measuring unit 810 continuously obtains the profile data for the cross section (such as top profile data) of the foam at a predetermined location, and stores the profile data for the cross section obtained in the storage unit 830. The profile data for the cross section can be used to generate a topography map of the foam surface, and the predetermined location is on the advancing path of the transporting slab.
[067] Subsequently, in step S1020, the calculating unit 820 obtains the advancing speed of the transporting slab from the control system and acquires the top cross-sectional data from the storage unit 830, thereby generating a topography map in the form of a point cloud.
[068] Next, in step S 1030, the calculating unit 820 searches for a target region with an abrupt change in depth in the point cloud.
[069] Subsequently, in step S 1040, the target region is identified based on a neural network model to determine the existence and categories of the defects. The above-mentioned neural network model can be obtained by training using topography map samples tagged with defects.
[070] Next, in step S1050, the calculating unit 820 outputs the determination results obtained in step S1040 to the display unit 840.
[071] Optionally, in step S1060, the feedback unit 850 sends the defect detection results generated by the calculating unit 820 to the production line control system, or extracts the defect detection results from the storage unit 830 and sends the defect detection results to the production line control system, such that the production line control system can optimize the process parameters and/or formulations in the product manufacturing schemes by making comparison among respective defect detection results for the plurality of product manufacturing schemes.
[072] The principles and preferred embodiments of the present invention are described above. However, the present invention should not be construed as being limited to the specific embodiments discussed herein. The above-mentioned preferred embodiments should be considered as illustrative but not restrictive, and it should be understood that those skilled in the art can, without departing from the scope of the present invention defined by the appended claims, make changes to these embodiments.

Claims

Claims:
1. A method for online monitoring of foam quality during a foam production process, wherein raw materials for foam production are injected onto a transporting slab of a conveyor via a mixing nozzle disposed at one end of the conveyor, the method comprising: continuously obtaining profile data for a cross section of the foam at a predetermined location to generate a topography map for a surface of the foam, the predetermined location being one along an advancing path of the transporting slab; and detecting foam defects based on the topography map for the surface of the foam.
2. The method of claim 1, wherein the profile data for the cross section are top profile data for the cross section.
3. The method of claim 2, wherein the top profile data are obtained using laser sensors or ultrasonic sensors disposed above the foam at the cross section to perform a line scan on a top surface of the foam.
4. The method of claim 2 or 3, wherein the top profile data comprise spatial position coordinates for respective points of top profiles of the foam, the topography map is obtained by assembling a plurality of top profiles obtained at a sampling interval, the sampling interval changing with an advancing speed of the transporting slab so as to ensure that adjacent top profiles are spaced equally along the advancing direction of the transporting slab, wherein the defects of the foam are detected by: comparing a profile cut out from the topography map along a first direction with a first standard profile template, and comparing a profile cut out from the topography map along a second direction with a second standard profile template, wherein the first and second directions are perpendicular to a depth direction of the foam and are perpendicular to each other; and determining existence and categories of the defects based on the comparison results.
5. The method of claim 4, wherein the first standard profile template and the second standard profile template are in the form of characteristic thresholds or standard profile curves determined based on production quality specifications.
6. The method of claim 2 or 3, wherein the top profile data comprise spatial position coordinates for respective points of top profiles of the foam, the topography map is in the form of point cloud including the spatial position coordinates for the respective points of the top profiles of the foam, wherein the defects of the foam are detected by: searching for a target region with an abrupt change in depth in the point cloud; and determining existence and categories of the defects using a neural network model to identify the target region.
7. The method of claim 6, wherein the neural network model is trained by: obtaining a plurality of samples of point cloud, each of which has physical dimensions of LxW, where L corresponds to the physical dimension of the respective sample of point cloud along the advancing direction of the transporting slab and is not larger than a first threshold, and W corresponds to a width of the foam; tagging the samples of point cloud based on predetermined quality standards, wherein for a single defect that is tagged, its corresponding physical area is not larger than a second threshold; selecting a training data set from the samples of point cloud, wherein a proportion of the number of the samples of point cloud tagged with defect categories to the total number of the samples of point cloud of the training data set is not smaller than a first proportion; and iteratively training the neural network model using the training data set, wherein a second proportion of the samples of point cloud in the training data set are retained for the next training upon completion of each training. 18
8. The method of claim 4 or 6, wherein the categories of the defects include surface crack, collapse, surface blistering and surface bulging.
9. The method of claim 1 or 2, wherein the foam is flexible polyurethane (PUR) foam.
10. The method of claim 1 or 2, wherein the method further comprises: optimizing process parameters and/or formulations in the product manufacturing schemes by making comparisons among respective defect detection results for a plurality of product manufacturing schemes.
11. An apparatus for online monitoring of foam quality during a foam production process, wherein raw materials for foam production are injected onto a transporting slab of a conveyor via a mixing nozzel disposed at one end of the conveyor, the apparatus comprising: a profile measuring unit configured to continuously obtain profile data for a cross section of the foam at a predetermined location along an advancing path of the transporting slab; and a calculating unit configured to generate a topography map for a surface of the foam from the profile data for the cross section and detect foam defects based on the topography map for the surface of the foam.
12. The apparatus of claim 11, further comprising: a feedback unit communicatively coupled to a production line control system, configured to transmit defect detection results to the production line control system, so that the production line control system optimizes process parameters and/or formulations in the product manufacturing schemes by making comparisons among respective defect detection results for the plurality of product manufacturing schemes.
13. The apparatus of claim 11, wherein the profile data for the cross section are top profile data for the cross section. 19
14. The apparatus of claim 13, wherein the profile measuring unit comprises laser sensors or ultrasonic sensors disposed above the foam at the cross section configured to perform a line scan on a top surface of the foam to obtain the top profile data.
15. The apparatus of claim 13 or 14, wherein the top profile data comprise spatial position coordinates for respective points of top profiles of the foam, the topography map is obtained by assembling a plurality of top profiles obtained at a sampling interval, the sampling interval changing with an advancing speed of the transporting slab so as to ensure that adjacent top profiles are spaced equally along the advancing direction of the transporting slab, wherein the calculating unit is configured to detect the defects of the foam by: comparing a profile cut out from the topography map along a first direction with a first standard profile template, and comparing a profile cut out from the topography map along a second direction with a second standard profile template, the first standard profile template and the second standard profile template preferably being in the form of characteristic thresholds or standard profile curves determined based on production quality specifications, wherein the first and second directions are perpendicular to a depth direction of the foam and are perpendicular to each other; and determining existence and categories of the defects based on the comparison results.
EP21746058.3A 2020-08-11 2021-07-23 Method and apparatus for online monitoring of foam quality during foam production process Withdrawn EP4196745A1 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202010801935.5A CN114076765A (en) 2020-08-11 2020-08-11 Method and device for on-line monitoring of foam quality during foam production
EP20207120.5A EP4001834A1 (en) 2020-11-12 2020-11-12 Method and apparatus for online monitoring of foam quality during foam production process
PCT/EP2021/070647 WO2022033837A1 (en) 2020-08-11 2021-07-23 Method and apparatus for online monitoring of foam quality during foam production process

Publications (1)

Publication Number Publication Date
EP4196745A1 true EP4196745A1 (en) 2023-06-21

Family

ID=77051057

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21746058.3A Withdrawn EP4196745A1 (en) 2020-08-11 2021-07-23 Method and apparatus for online monitoring of foam quality during foam production process

Country Status (2)

Country Link
EP (1) EP4196745A1 (en)
WO (1) WO2022033837A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118835120B (en) * 2024-07-24 2025-02-18 南京航空航天大学 An intelligent monitoring continuous production line for lightweight foam aluminum in aerospace

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020223594A2 (en) * 2019-05-02 2020-11-05 Kodak Alaris, Inc Automated 360-degree dense point object inspection

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10237005A1 (en) * 2002-08-13 2004-02-26 Bayer Ag Soft foam is produced by determining the height of the foam along an advancing line, comparing it to a reference value, and using the difference to control any adjustment
DE102005003341A1 (en) * 2005-01-25 2006-07-27 Bayer Materialscience Ag Process and plant for the optimized production of foam in a continuous block foam process

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020223594A2 (en) * 2019-05-02 2020-11-05 Kodak Alaris, Inc Automated 360-degree dense point object inspection

Also Published As

Publication number Publication date
WO2022033837A1 (en) 2022-02-17

Similar Documents

Publication Publication Date Title
EP4001834A1 (en) Method and apparatus for online monitoring of foam quality during foam production process
CN112504184B (en) Rapid online quality inspection system for three-dimensional size of steel plate
Zhao et al. Artificial intelligence powered real-time quality monitoring for additive manufacturing in construction
EP4196745A1 (en) Method and apparatus for online monitoring of foam quality during foam production process
CN114994061A (en) Machine vision-based steel rail intelligent detection method and system
CN112988815B (en) A method and system for online anomaly detection of large-scale high-dimensional high-speed streaming data
CN112991368B (en) Target object detection method and device, storage medium and electronic device
CN113295001A (en) System, method and device for detecting material layer thickness of sintering machine trolley
CN119624930B (en) Device and method for detecting process parameters of parts
CN117368943A (en) Slope monitoring and early warning method and system based on laser radar
US20230354833A1 (en) Methods and systems for intelligent processing of aquatic products
Momot et al. Deep Learning Automated System for Thermal Defectometry of Multilayer Materials
CN114076765A (en) Method and device for on-line monitoring of foam quality during foam production
CN119057859B (en) Multi-point collaborative optimization insulation board cutting method and device
AU645123B2 (en) Automatic windowing for article recognition
CN119618056A (en) Novel laser measuring process
CN109948979B (en) Inventory detection method, equipment and storage medium
JP7575664B2 (en) Image generating device, quality judgement device, image generating method, quality judgement method and program
EP3875242A1 (en) Method and apparatus for online determining foam density during foam production process
JP5975295B2 (en) Inspection apparatus and program
CN115854897A (en) Rubber roller laser intelligent detection method, device, equipment and medium
CN117372380A (en) Industrial ultrasonic non-destructive inspection image data enhancement method based on generative adversarial network
CN119126106B (en) An underground inspection robot with a radar system
CN119871416B (en) Sampling robot and control method thereof, and medium
CN113899785A (en) Detection method for lithium battery based on ultrasonic and infrared flaw detection

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20230313

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Free format text: PREVIOUS MAIN CLASS: G01B0011250000

Ipc: G01B0011245000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: B29B 7/94 20060101ALN20250122BHEP

Ipc: B29B 7/74 20060101ALN20250122BHEP

Ipc: B29B 7/72 20060101ALN20250122BHEP

Ipc: G01N 29/44 20060101ALI20250122BHEP

Ipc: G01N 29/265 20060101ALI20250122BHEP

Ipc: G01N 29/06 20060101ALI20250122BHEP

Ipc: G01N 29/04 20060101ALI20250122BHEP

Ipc: G01N 21/89 20060101ALI20250122BHEP

Ipc: C08L 75/04 20060101ALI20250122BHEP

Ipc: B29C 44/60 20060101ALI20250122BHEP

Ipc: B29C 44/46 20060101ALI20250122BHEP

Ipc: B29C 44/28 20060101ALI20250122BHEP

Ipc: G01B 17/06 20060101ALI20250122BHEP

Ipc: G01B 11/25 20060101ALI20250122BHEP

Ipc: G01B 11/245 20060101AFI20250122BHEP

RIC1 Information provided on ipc code assigned before grant

Ipc: B29B 7/94 20060101ALN20250128BHEP

Ipc: B29B 7/74 20060101ALN20250128BHEP

Ipc: B29B 7/72 20060101ALN20250128BHEP

Ipc: G01N 29/44 20060101ALI20250128BHEP

Ipc: G01N 29/265 20060101ALI20250128BHEP

Ipc: G01N 29/06 20060101ALI20250128BHEP

Ipc: G01N 29/04 20060101ALI20250128BHEP

Ipc: G01N 21/89 20060101ALI20250128BHEP

Ipc: C08L 75/04 20060101ALI20250128BHEP

Ipc: B29C 44/60 20060101ALI20250128BHEP

Ipc: B29C 44/46 20060101ALI20250128BHEP

Ipc: B29C 44/28 20060101ALI20250128BHEP

Ipc: G01B 17/06 20060101ALI20250128BHEP

Ipc: G01B 11/25 20060101ALI20250128BHEP

Ipc: G01B 11/245 20060101AFI20250128BHEP

INTG Intention to grant announced

Effective date: 20250211

RIC1 Information provided on ipc code assigned before grant

Ipc: B29B 7/94 20060101ALN20250203BHEP

Ipc: B29B 7/74 20060101ALN20250203BHEP

Ipc: B29B 7/72 20060101ALN20250203BHEP

Ipc: G01N 29/44 20060101ALI20250203BHEP

Ipc: G01N 29/265 20060101ALI20250203BHEP

Ipc: G01N 29/06 20060101ALI20250203BHEP

Ipc: G01N 29/04 20060101ALI20250203BHEP

Ipc: G01N 21/89 20060101ALI20250203BHEP

Ipc: C08L 75/04 20060101ALI20250203BHEP

Ipc: B29C 44/60 20060101ALI20250203BHEP

Ipc: B29C 44/46 20060101ALI20250203BHEP

Ipc: B29C 44/28 20060101ALI20250203BHEP

Ipc: G01B 17/06 20060101ALI20250203BHEP

Ipc: G01B 11/25 20060101ALI20250203BHEP

Ipc: G01B 11/245 20060101AFI20250203BHEP

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20250612