WO2023280606A1 - A method for digital process monitoring in a slaughterhouse - Google Patents

A method for digital process monitoring in a slaughterhouse Download PDF

Info

Publication number
WO2023280606A1
WO2023280606A1 PCT/EP2022/067469 EP2022067469W WO2023280606A1 WO 2023280606 A1 WO2023280606 A1 WO 2023280606A1 EP 2022067469 W EP2022067469 W EP 2022067469W WO 2023280606 A1 WO2023280606 A1 WO 2023280606A1
Authority
WO
WIPO (PCT)
Prior art keywords
analysis
vision device
post
control
product
Prior art date
Application number
PCT/EP2022/067469
Other languages
French (fr)
Inventor
Dennis Brandborg NIELSEN
Paul Andreas Holger DIRAC
Jeppe Bo ANDERSEN
Original Assignee
Teknologisk Institut
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
Application filed by Teknologisk Institut filed Critical Teknologisk Institut
Priority to EP22741172.5A priority Critical patent/EP4367612A1/en
Publication of WO2023280606A1 publication Critical patent/WO2023280606A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion

Definitions

  • This invention relates to a method for performing process control in a slaughterhouse, which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-process, hereof, and which method is based on the use of a vision device, followed by an analysis of the obtained results.
  • EP1939811 discloses a method for associating source information for a source unit with a product converted therefrom, which method comprises the use of a computer system and imaging sensors that capture image data of a carcass, as it moves through a processing facility and is converted into individual food products.
  • EP2923305 discloses a method for scoring and controlling the quality of a plurality of moving food products, which method comprises image capturing of the incoming food products, and image analysis of the recorded data.
  • the present invention discloses a method for performing process control in a slaughterhouse, which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-, process hereof, using a vision device in communication/operation with a processing means.
  • the method of the invention offers solutions to various process challenges, and allows statistical treatment of the process in question, e.g., number of errors, error frequency, etc.
  • the present method also provides for a verification if the equipment is in order, and also allows for diagnosis of the process equipment and indicate on which part of the equipment it has gone wrong.
  • the method further offers the opportunity to check for errors associated with the raw material and allows for adjustment of the process based on input control, and an analysis of whether the raw material, e.g., the incoming pig, is suitable for being processed as planned, and the method offers feed-back to the process operator.
  • the method also allows for identification of human or manual errors.
  • the method of the invention also may prevent incorrect production, e.g., reduced yield, reduced quality, etc., and allows to correct errors associated with the choice of starting material and the intended processing of the raw material.
  • the method of the invention allows for equipment diagnosis and statistical process control, as well as check for manual processing errors, and enables feedback - to the database and/or to the process operator.
  • the method of the invention is based on image capturing and computation of the acquired image data using algorithms for control of manual or automatic processes or equipment.
  • Fig. 1 shows an example of a system used in the method of the invention: Starting product/incoming carcass ( 1A) ; Processed product/decapitated carcass (IB); Pre-process vision device/camera (2A); Post-process vision device/ camera (2B); Pre-process processor (3A); Post-process processor (3B); Processing equipment/head cutting tool (5).
  • IB Processed product/decapitated carcass
  • the present invention provides a method for performing process control in a slaughterhouse, processing animals for slaughter and meat items (1), which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-, process hereof, using a vision device (2) in communication/operation with one or more processing means (3).
  • the method of the invention may be characterised by comprising the subsequent steps of: i. subjecting a starting product/raw material (1A) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); ii. subjecting the processed product (IB) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); iii. using the results of the pre-process analyses obtained according to step i to determine whether the process should have been successful, and, using the results of the post-process analyses obtained according to step ii, to determine whether the process has actually been successful; and iv.
  • step ii comparing the occurrence of instances where the post process control performed according to step ii, has failed in instances where the product/raw material is analysed, according to step i, as being suitable for the process, with a statistical discriminator that determines when to consider the process as out of control.
  • the analysis may, in particular, be based on reference data obtained from a product specification, and this product specification should be accessible to the processing means (3).
  • step ii according to the method of the invention, the processed product is analysed for compliance with a product specification.
  • the method of the invention may be applied to the process of placing the incoming pig on the gambrel/hanger and to performing an analysis of correct placement of the carcass.
  • the method of the invention is applied to the process of bung handling/loosening of the rectum, and to performing an analysis of the drilling of the rectum.
  • the method of the invention is applied to the process of splitting the breast, and to performing an analysis of the splitting.
  • the method of the invention is applied to the process of cutting along the spine, and to performing an analysis of the cutting.
  • the method of the invention is applied to the process of cleaving the carcass, and to an analysis of the spinal canal, of the brain halves, and of the tail.
  • the method of the invention involves the identification of processes that are assumed to run smoothly, but still did not proceed as expected.
  • this analysis shall be based/associated with a statistical discriminator that determines when to consider the process as out of control.
  • Examples of statistical discriminators include any occurrence, even just one instance, where the process has failed, even though it should be able to proceed successfully.
  • statistical discriminators contemplated according to the invention include instances, e.g., X cases in a row (X being e.g., 2-8, 3-7, 4-6, etc.), or frequencies, e.g., Y out of 100 cases (Y being e.g., more than 5, more than 10, more than 20, more than 30, etc.), that should be able to run successfully, but did not go well.
  • statistical discriminators contemplated according to the invention include, e.g., changes in the error rate over time, or deviation or drift from a normal rate, e.g., from 10% to 12%, or the observation of greater variance.
  • Process control may be monitored using various Statistical Process Control (SPC) tools, that also can determine whether a process is in or out of control.
  • SPC Statistical Process Control
  • Out of control incidents may include instances where the process equipment is out of alignment or is broken, or, in case of a manual process, include instances where a process regulation has not been followed.
  • the starting product/raw material contemplated according to the invention may be any animal intended for slaughter, e.g., fattening pigs, broilers, beef cattle or other ruminants for human consumption, or it may be fish, and/or any products or sub products hereof.
  • the method of the invention may be applied to control of the method of removing tenderloin.
  • the method of the invention may be applied to control of the method of cutting of heads, toes, ears, and/or jaw removal.
  • inventions include three-splitting of the carcass, point-back sawing, middle splitting of chest and comb, and/or derinding.
  • the post-process analyses obtained according to step ii may include an analysis of the various cut surfaces.
  • Placement of the incoming pig on the gambrel/hanger Is the carcass placed correctly on the gambrel; Are the hinge joints and hooks intact; Is the stab in the hock made correctly.
  • Bung handling/loosening of the rectum Checking whether the right place has been drilled; Checking if drilling is correct.
  • Cutting along the spine Checking whether the breast is straight, and that the subsequent manual procedures up to the cutting are OK; Check that the cutting has been carried out correctly.
  • Cleaving the carcass Checking that the spinal canal is exposed along the entire length of the carcass; Checking that both brain halves remain in the head; Checking that the tail is not damaged.
  • the vision device The vision device
  • the vision device (2) for use according to the invention typically comprises a camera with a lens, an image sensor, a vision processing means, and communication means.
  • the vision system for use according to the invention also include lighting means.
  • the vision device (2) for use according to the invention shall be in communication with the processing means (3).
  • the cameras for use according to the invention may be any suitable camera/area- scan camera, e.g., a monochrome camera, a colour camera (RGB), multispectral camera (e.g., including both visible and infrared wavelengths), or a 3C/depth camera (e.g., a time-of-flight camera or a stereo camera system).
  • a monochrome camera e.g., a colour camera (RGB), multispectral camera (e.g., including both visible and infrared wavelengths), or a 3C/depth camera (e.g., a time-of-flight camera or a stereo camera system).
  • RGB colour camera
  • 3C/depth camera e.g., a time-of-flight camera or a stereo camera system
  • the method of the invention comprises steps wherein data obtained by use of the vision device (2) is transmitted or communicated to a means for storing information (4).
  • the means for storing information (4) for use according to the invention may be any media intended or suited for storage of digital information and may include the hard desk of the processing means (3) used according to the invention, or its memory (RAM), and/or, from an external hard desk, server, or central database.
  • the processing means includes
  • the method of the invention comprises the use of one or more processing means (3).
  • the processing means (3) for use according to the invention may be any available computation device (e.g., GPU, CPU, PLC, and/or PC), in operation with, and capable of receiving and processing data obtained from the vision device (2).
  • any available computation device e.g., GPU, CPU, PLC, and/or PC
  • the imaging devices (4) for use according to the invention shall be an adaptive imaging system, based on the use of artificial intelligence (AI).
  • AI artificial intelligence
  • the imaging system must be robust and capable of detecting e.g., meat products with a large biological variation. Robustness is gradually improved through self-learning.
  • an Artificial Intelligence (AI) application/algorithm covers machine learning and deep learning algorithms.
  • Machine learning is an application of artificial intelligence (AI) which use statistical techniques to perform automated decision-making, and optionally improve performance on specific tasks based on experience without being explicitly programmed.
  • AI artificial intelligence
  • the computer may be presented with example inputs and their desired outputs, as given by the supervisor, and the goal is to learn a general rule that maps inputs to outputs.
  • a supervised learning algorithm is trained to learn a general rule that maps inputs to outputs.
  • the precision and robustness of the system increases, but occasionally, e.g., caused by quality errors or recognition errors, manual assistance may be needed, for additional training of the system.
  • Carcasses and meat products are characterized by large variation in physical appearance. This variation comes from biological variation as well as machine and/or operator induced variations from previous stages in the processing.
  • the variation is characterized not only by differences between different types of products, but in particular by differences between products of the same type, e.g., in deformation, flexibility, colouring, shape, size, surface texture (e.g., wet, greasy, icy).
  • the vision system for use according to this invention may comprise both state- of-the-art and custom designed deep learning algorithms for detecting objects and positions in the images, combined in a way which meets the capacity requirements.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This invention relates to a method for performing process control in a slaughterhouse, which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-process, hereof, and which method is based on the use of a vision device, followed by analysis of the obtained results.

Description

A METHOD FOR DIGITAL PROCESS MONITORING IN A SLAUGHTERHOUSE
TECHNICAL FIELD
This invention relates to a method for performing process control in a slaughterhouse, which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-process, hereof, and which method is based on the use of a vision device, followed by an analysis of the obtained results.
BACKGROUND ART
Slaughterhouse processes are constantly challenged, making it essential to work agile. Faults and breakdowns at the slaughterhouse are the cause of reduced production capacity, quality defects and reduced yields. Fewer quality defects and better utilisation of the carcass result in more sustainable production and reduced climate footprint.
There are great demands for uptime and efficient utilisation of the production apparatus, at the same time as a need to be able to act agile based on production data. During the slaughter process, processes can fail because the equipment is out of control. However, it can also be due to previous process errors, or because the carcass is out of specification.
There is a need for ongoing system monitoring, so that the status and capability of the process or its elements can be proactively monitored.
EP1939811 discloses a method for associating source information for a source unit with a product converted therefrom, which method comprises the use of a computer system and imaging sensors that capture image data of a carcass, as it moves through a processing facility and is converted into individual food products.
EP2923305 discloses a method for scoring and controlling the quality of a plurality of moving food products, which method comprises image capturing of the incoming food products, and image analysis of the recorded data.
However, the method of the present invention for performing process control in a slaughterhouse has never been disclosed or suggested.
SUMMARY OF THE INVENTION
The present invention discloses a method for performing process control in a slaughterhouse, which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-, process hereof, using a vision device in communication/operation with a processing means.
The method of the invention offers solutions to various process challenges, and allows statistical treatment of the process in question, e.g., number of errors, error frequency, etc. The present method also provides for a verification if the equipment is in order, and also allows for diagnosis of the process equipment and indicate on which part of the equipment it has gone wrong.
The method further offers the opportunity to check for errors associated with the raw material and allows for adjustment of the process based on input control, and an analysis of whether the raw material, e.g., the incoming pig, is suitable for being processed as planned, and the method offers feed-back to the process operator.
The method also allows for identification of human or manual errors.
The method of the invention also may prevent incorrect production, e.g., reduced yield, reduced quality, etc., and allows to correct errors associated with the choice of starting material and the intended processing of the raw material.
Moreover, the method of the invention allows for equipment diagnosis and statistical process control, as well as check for manual processing errors, and enables feedback - to the database and/or to the process operator.
The method of the invention is based on image capturing and computation of the acquired image data using algorithms for control of manual or automatic processes or equipment.
Other objects of the invention will be apparent to the person skilled in the art from reading the following detailed description and accompanying drawings.
Any combination of two or more of the embodiments described herein is considered within the scope of the present invention.
BRIEF DESCRIPTION OF THE DRAWINGS
The present invention is further illustrated by reference to the accompanying drawing, in which,
Fig. 1 shows an example of a system used in the method of the invention: Starting product/incoming carcass ( 1A) ; Processed product/decapitated carcass (IB); Pre-process vision device/camera (2A); Post-process vision device/ camera (2B); Pre-process processor (3A); Post-process processor (3B); Processing equipment/head cutting tool (5). DETAILED DISCLOSURE OF THE INVENTION
The present invention provides a method for performing process control in a slaughterhouse, processing animals for slaughter and meat items (1), which method comprises a pre- and a post-process control with respect to an overall process, or to an integral, or sub-, process hereof, using a vision device (2) in communication/operation with one or more processing means (3).
The method of the invention may be characterised by comprising the subsequent steps of: i. subjecting a starting product/raw material (1A) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); ii. subjecting the processed product (IB) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); iii. using the results of the pre-process analyses obtained according to step i to determine whether the process should have been successful, and, using the results of the post-process analyses obtained according to step ii, to determine whether the process has actually been successful; and iv. comparing the occurrence of instances where the post process control performed according to step ii, has failed in instances where the product/raw material is analysed, according to step i, as being suitable for the process, with a statistical discriminator that determines when to consider the process as out of control.
When determining, according to the pre-process control step i, whether the process is predicted and expected to be able to run and be completed successfully, and, according to the post-process control step ii, whether the process has been successfully completed, the analysis may, in particular, be based on reference data obtained from a product specification, and this product specification should be accessible to the processing means (3).
In one embodiment, in step ii according to the method of the invention, the processed product is analysed for compliance with a product specification.
In another embodiment, the method of the invention may be applied to the process of placing the incoming pig on the gambrel/hanger and to performing an analysis of correct placement of the carcass.
In a third embodiment, the method of the invention is applied to the process of bung handling/loosening of the rectum, and to performing an analysis of the drilling of the rectum. In a fourth embodiment, the method of the invention is applied to the process of splitting the breast, and to performing an analysis of the splitting.
In a fifth embodiment, the method of the invention is applied to the process of cutting along the spine, and to performing an analysis of the cutting.
In a sixth embodiment, the method of the invention is applied to the process of cleaving the carcass, and to an analysis of the spinal canal, of the brain halves, and of the tail.
Statistical discriminators
The method of the invention involves the identification of processes that are assumed to run smoothly, but still did not proceed as expected.
When analysing the obtained results, and comparing, according to step iv, the occurrence of instances where the post process control performed according to step ii, has failed in instances where the product/raw material analysed, according to step i, as suitable for the process, this analysis shall be based/associated with a statistical discriminator that determines when to consider the process as out of control.
Examples of statistical discriminators include any occurrence, even just one instance, where the process has failed, even though it should be able to proceed successfully.
Alternatively, statistical discriminators contemplated according to the invention include instances, e.g., X cases in a row (X being e.g., 2-8, 3-7, 4-6, etc.), or frequencies, e.g., Y out of 100 cases (Y being e.g., more than 5, more than 10, more than 20, more than 30, etc.), that should be able to run successfully, but did not go well.
Moreover, statistical discriminators contemplated according to the invention include, e.g., changes in the error rate over time, or deviation or drift from a normal rate, e.g., from 10% to 12%, or the observation of greater variance.
Process control may be monitored using various Statistical Process Control (SPC) tools, that also can determine whether a process is in or out of control. When points on a control chart move outside the upper or lower control limit, the process is said to be "out of control." As long as the points are within control limits, the process is considered "in control."
Out of control incidents may include instances where the process equipment is out of alignment or is broken, or, in case of a manual process, include instances where a process regulation has not been followed.
The starting product/raw material
The starting product/raw material contemplated according to the invention may be any animal intended for slaughter, e.g., fattening pigs, broilers, beef cattle or other ruminants for human consumption, or it may be fish, and/or any products or sub products hereof.
In one embodiment, the method of the invention may be applied to control of the method of removing tenderloin.
In another embodiment, the method of the invention may be applied to control of the method of cutting of heads, toes, ears, and/or jaw removal.
Other embodiments of the method of the invention include three-splitting of the carcass, point-back sawing, middle splitting of chest and comb, and/or derinding.
When considering the process of three-splitting of the carcass, the post-process analyses obtained according to step ii, may include an analysis of the various cut surfaces.
Examples of process steps to become subject to analysis according to the invention include, e.g. :
Placement of the incoming pig on the gambrel/hanger: Is the carcass placed correctly on the gambrel; Are the hinge joints and hooks intact; Is the stab in the hock made correctly.
Bung handling/loosening of the rectum: Checking whether the right place has been drilled; Checking if drilling is correct.
Splitting of the breast: Checking that the start of the splitting is done in the right place; Check that the splitting has been carried out correctly.
Cutting along the spine: Checking whether the breast is straight, and that the subsequent manual procedures up to the cutting are OK; Check that the cutting has been carried out correctly.
Cleaving the carcass: Checking that the spinal canal is exposed along the entire length of the carcass; Checking that both brain halves remain in the head; Checking that the tail is not damaged.
The vision device
The vision device (2) for use according to the invention typically comprises a camera with a lens, an image sensor, a vision processing means, and communication means. Optionally the vision system for use according to the invention also include lighting means.
The vision device (2) for use according to the invention shall be in communication with the processing means (3).
The cameras for use according to the invention may be any suitable camera/area- scan camera, e.g., a monochrome camera, a colour camera (RGB), multispectral camera (e.g., including both visible and infrared wavelengths), or a 3C/depth camera (e.g., a time-of-flight camera or a stereo camera system). The means for storing information
The method of the invention comprises steps wherein data obtained by use of the vision device (2) is transmitted or communicated to a means for storing information (4).
The means for storing information (4) for use according to the invention may be any media intended or suited for storage of digital information and may include the hard desk of the processing means (3) used according to the invention, or its memory (RAM), and/or, from an external hard desk, server, or central database.
The processing means
For computing data obtained from the vision device (2), and, optionally, for communication with a means for storing information (4), the method of the invention comprises the use of one or more processing means (3).
The processing means (3) for use according to the invention may be any available computation device (e.g., GPU, CPU, PLC, and/or PC), in operation with, and capable of receiving and processing data obtained from the vision device (2).
Artificial Intelligence (AD applications/alaorithms
For performing the various analysis included in the method of the invention, different algorithms can be used, incl. self-learning algorithms and deep learning algorithms.
The imaging devices (4) for use according to the invention shall be an adaptive imaging system, based on the use of artificial intelligence (AI). The imaging system must be robust and capable of detecting e.g., meat products with a large biological variation. Robustness is gradually improved through self-learning.
In the context of this invention, and in accordance with established terminology, an Artificial Intelligence (AI) application/algorithm covers machine learning and deep learning algorithms.
Machine learning is an application of artificial intelligence (AI) which use statistical techniques to perform automated decision-making, and optionally improve performance on specific tasks based on experience without being explicitly programmed.
Several approaches to machine leaning exists, e.g., supervised learning, reinforced learning, imitation learning and un-supervised learning.
In supervised learning, the computer may be presented with example inputs and their desired outputs, as given by the supervisor, and the goal is to learn a general rule that maps inputs to outputs. Using large sets of reference data, covering different product types, along with the desired output for each element in the data sets, a supervised learning algorithm is trained to learn a general rule that maps inputs to outputs. As data is building up, the precision and robustness of the system increases, but occasionally, e.g., caused by quality errors or recognition errors, manual assistance may be needed, for additional training of the system.
Carcasses and meat products are characterized by large variation in physical appearance. This variation comes from biological variation as well as machine and/or operator induced variations from previous stages in the processing. The variation is characterized not only by differences between different types of products, but in particular by differences between products of the same type, e.g., in deformation, flexibility, colouring, shape, size, surface texture (e.g., wet, greasy, icy). The vision system for use according to this invention may comprise both state- of-the-art and custom designed deep learning algorithms for detecting objects and positions in the images, combined in a way which meets the capacity requirements.
List of reference signs This is a listing of various elements relating to the present invention and shown in the appended figures. Alternative/synonymous designations are separated by slashes.
1. Work piece/animal for slaughter/meat product
IA. Starting product
IB. Processed product 2. Vision device/imaging device/camera
2A. Pre-process vision device/camera
2B. Post-process vision device/camera
3. Processing means
3A. Pre-process processor 3B. Post-process processor
4. Means for storing information/hard desk/server/central database
5. Processing equipment (head cutting tool)

Claims

1. A method for performing process control in a slaughterhouse, processing animals for slaughter and meat items (1), which method comprises a pre- and a post process control with respect to an overall process, or to an integral, or sub-, process hereof, using a vision device (2) in communication/operation with one or more processing means (3), and which method comprises the subsequent steps of:
1. subjecting a starting product/raw material (1A) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); and ii. subjecting the processed product (IB) to analysis by use of the vision device (2), and transmitting/communicating the obtained results to a means for storing information (4); and which method is characterised by: iii. using the results of the pre-process analyses obtained according to step i to determine whether the process should have been successful, and, using the results of the post-process analyses obtained according to step ii, to determine whether the process has actually been successful; and iv. comparing the occurrence of instances where the post process control performed according to step ii, has failed in instances where the product/raw material is analysed, according to step i, as being suitable for the process, with a statistical discriminator that determines when to consider the process as out of control.
2. The method of claim 1, wherein, in step ii, the processed product is analysed for compliance with a product specification.
3. The method of claim 1, which method is applied to the process of placing the incoming pig on the gambrel/hanger and to performing an analysis of correct placement of the carcass.
4. The method of claim 1, which method is applied to the process of bung handling/loosening of the rectum, and to performing an analysis of the drilling of the rectum.
5. The method of claim 1, which method is applied to the process of splitting the breast, and to performing an analysis of the splitting.
6. The method of claim 1, which method is applied to the process of cutting along the spine, and to performing an analysis of the cutting.
7. The method of claim 1, which method is applied to the process of cleaving the carcass, and to an analysis of the spinal canal, of the brain halves, and of the tail.
PCT/EP2022/067469 2021-07-09 2022-06-27 A method for digital process monitoring in a slaughterhouse WO2023280606A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP22741172.5A EP4367612A1 (en) 2021-07-09 2022-06-27 A method for digital process monitoring in a slaughterhouse

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DKPA202100752A DK181011B1 (en) 2021-07-09 2021-07-09 Digital process monitoring
DKPA202100752 2021-07-09

Publications (1)

Publication Number Publication Date
WO2023280606A1 true WO2023280606A1 (en) 2023-01-12

Family

ID=82494084

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/067469 WO2023280606A1 (en) 2021-07-09 2022-06-27 A method for digital process monitoring in a slaughterhouse

Country Status (3)

Country Link
EP (1) EP4367612A1 (en)
DK (1) DK181011B1 (en)
WO (1) WO2023280606A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0879558A2 (en) * 1997-05-06 1998-11-25 Slagteriernes Forskningsinstitut Method and device for evisceration of carcasses
EP1939811A1 (en) 2006-12-18 2008-07-02 Cryovac, Inc. Method and system for associating source information for a source unit with a product converted therefrom
EP2923305A2 (en) 2012-11-26 2015-09-30 Frito-Lay North America, Inc. Method for scoring and controlling quality of food products in a dynamic production line
US20180153179A1 (en) * 2016-10-28 2018-06-07 Jarvis Products Corporation Beef splitting method and system
WO2020126890A1 (en) * 2018-12-17 2020-06-25 Teknologisk Institut Cellular meat production

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0879558A2 (en) * 1997-05-06 1998-11-25 Slagteriernes Forskningsinstitut Method and device for evisceration of carcasses
EP1939811A1 (en) 2006-12-18 2008-07-02 Cryovac, Inc. Method and system for associating source information for a source unit with a product converted therefrom
EP2923305A2 (en) 2012-11-26 2015-09-30 Frito-Lay North America, Inc. Method for scoring and controlling quality of food products in a dynamic production line
US20180153179A1 (en) * 2016-10-28 2018-06-07 Jarvis Products Corporation Beef splitting method and system
WO2020126890A1 (en) * 2018-12-17 2020-06-25 Teknologisk Institut Cellular meat production

Also Published As

Publication number Publication date
DK202100752A1 (en) 2022-09-21
EP4367612A1 (en) 2024-05-15
DK181011B1 (en) 2022-09-21

Similar Documents

Publication Publication Date Title
US9521829B2 (en) Livestock identification and monitoring
Wang et al. ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images
JP2019525786A (en) System and method for automatically detecting, locating, and semantic segmentation of anatomical objects
US6623348B1 (en) Method and apparatus for slaughtering and processing animals
JPH1084861A (en) Method and device for processing slaughtered animal or part of it in slaughterhouse
US10740940B2 (en) Automatic generation of fundus drawings
CN116935327B (en) Aquaculture monitoring method, device, equipment and storage medium based on AI vision
EP2651210B1 (en) System and a method for controlling an automatic milking system
JP7458623B2 (en) Work analysis device and work analysis method
CN111297367A (en) Animal state monitoring method and device, electronic equipment and storage medium
US9675091B1 (en) Automated monitoring in cutting up slaughtered animals
CN111948994A (en) Industrial production line closed-loop automatic quality control method based on data integration and correlation analysis
CN108596014A (en) Livestock behavior analysis method and device
CA3183341A1 (en) Autonomous livestock monitoring
DK181011B1 (en) Digital process monitoring
CN112288793A (en) Livestock individual backfat detection method and device, electronic equipment and storage medium
CN216931665U (en) Device for automatically cutting pig carcass
CN112131921A (en) Biological automatic measuring system based on stereoscopic vision and measuring method thereof
US11672255B2 (en) Method for evaluating a health state of an anatomical element, related evaluation device and related evaluation system
CN114494295A (en) Robot intelligent slaughter and segmentation method and device and storage medium
US20230342902A1 (en) Method and system for automated evaluation of animals
Bar et al. Towards robotic post-trimming of salmon fillets
KR102547735B1 (en) System and method for management of processing livestock products and computer program for the same
EP1174034A1 (en) Method for trimming pork bellies
JP2020183876A (en) Feature point recognition system and workpiece processing system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22741172

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022741172

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022741172

Country of ref document: EP

Effective date: 20240209