[go: up one dir, main page]

SE2230287A1 - Method of facilitating applying a desired clamp force by a tightening tool - Google Patents

Method of facilitating applying a desired clamp force by a tightening tool

Info

Publication number
SE2230287A1
SE2230287A1 SE2230287A SE2230287A SE2230287A1 SE 2230287 A1 SE2230287 A1 SE 2230287A1 SE 2230287 A SE2230287 A SE 2230287A SE 2230287 A SE2230287 A SE 2230287A SE 2230287 A1 SE2230287 A1 SE 2230287A1
Authority
SE
Sweden
Prior art keywords
ultrasonic signal
reflected ultrasonic
quality
recorded
tightening
Prior art date
Application number
SE2230287A
Other languages
Swedish (sv)
Other versions
SE546313C2 (en
Inventor
Fabian Revilla
Mazen Bahy
Original Assignee
Atlas Copco Ind Technique Ab
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 Atlas Copco Ind Technique Ab filed Critical Atlas Copco Ind Technique Ab
Priority to SE2230287A priority Critical patent/SE546313C2/en
Priority to DE102023124319.5A priority patent/DE102023124319A1/en
Priority to CN202311175142.7A priority patent/CN117705329A/en
Publication of SE2230287A1 publication Critical patent/SE2230287A1/en
Publication of SE546313C2 publication Critical patent/SE546313C2/en

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25B—TOOLS OR BENCH DEVICES NOT OTHERWISE PROVIDED FOR, FOR FASTENING, CONNECTING, DISENGAGING OR HOLDING
    • B25B23/00—Details of, or accessories for, spanners, wrenches, screwdrivers
    • B25B23/14—Arrangement of torque limiters or torque indicators in wrenches or screwdrivers
    • 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
    • G01N29/07—Analysing solids by measuring propagation velocity or propagation time of acoustic waves
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25B—TOOLS OR BENCH DEVICES NOT OTHERWISE PROVIDED FOR, FOR FASTENING, CONNECTING, DISENGAGING OR HOLDING
    • B25B21/00—Portable power-driven screw or nut setting or loosening tools; Attachments for drilling apparatus serving the same purpose
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25B—TOOLS OR BENCH DEVICES NOT OTHERWISE PROVIDED FOR, FOR FASTENING, CONNECTING, DISENGAGING OR HOLDING
    • B25B23/00—Details of, or accessories for, spanners, wrenches, screwdrivers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25B—TOOLS OR BENCH DEVICES NOT OTHERWISE PROVIDED FOR, FOR FASTENING, CONNECTING, DISENGAGING OR HOLDING
    • B25B23/00—Details of, or accessories for, spanners, wrenches, screwdrivers
    • B25B23/14—Arrangement of torque limiters or torque indicators in wrenches or screwdrivers
    • B25B23/147—Arrangement of torque limiters or torque indicators in wrenches or screwdrivers specially adapted for electrically operated wrenches or screwdrivers
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/25—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons
    • G01L1/255—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons using acoustic waves, or acoustic emission
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/24—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for determining value of torque or twisting moment for tightening a nut or other member which is similarly stressed
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/24—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for determining value of torque or twisting moment for tightening a nut or other member which is similarly stressed
    • G01L5/246—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for determining value of torque or twisting moment for tightening a nut or other member which is similarly stressed using acoustic 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
    • G01N29/34—Generating the ultrasonic, sonic or infrasonic waves, e.g. electronic circuits specially adapted therefor
    • G01N29/348—Generating the ultrasonic, sonic or infrasonic waves, e.g. electronic circuits specially adapted therefor with frequency characteristics, e.g. single frequency signals, chirp signals
    • 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
    • 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
    • G01N29/50—Processing the detected response signal, e.g. electronic circuits specially adapted therefor using auto-correlation techniques or cross-correlation techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2291/00—Indexing codes associated with group G01N29/00
    • G01N2291/02—Indexing codes associated with the analysed material
    • G01N2291/028—Material parameters
    • G01N2291/02827—Elastic parameters, strength or force
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2291/00—Indexing codes associated with group G01N29/00
    • G01N2291/04—Wave modes and trajectories
    • G01N2291/044—Internal reflections (echoes), e.g. on walls or defects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Mechanical Engineering (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Toxicology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Force Measurement Appropriate To Specific Purposes (AREA)

Abstract

The present disclosure relates to a method of a device (10, 30) of controlling applying a clamp force by a tightening tool (10) to a fastener (20), which is determined based on a measured time of flight of an ultrasonic signal being transmitted via a proximal end of the fastener (20) and reflected against a distal end section of the fastener (20). The method is based on a machine-learning method to select an adequate frequency for the ultrasonic signal being transmitted.

Description

TECHNICAL FIELD id="p-1" id="p-1" id="p-1" id="p-1" id="p-1" id="p-1" id="p-1" id="p-1" id="p-1"
[0001] The present disclosure relates to a method of a device of facilitating applying a desired clamp force by a tightening tool to a fastener for tightening a joint, the applied clamp force being determined based on a measured time of flight of an ultrasonic signal being transmitted via a proximal end of the fastener and reflected against a distal end section ofthe fastener when tightening the joint, and a device performing the method. id="p-2" id="p-2" id="p-2" id="p-2" id="p-2" id="p-2" id="p-2" id="p-2" id="p-2"
[0002] Further, a computer program is provided comprising computer-executable instructions for causing the device to perform steps of the method when the computer- executable instructions are executed on a processing unit included in the device. id="p-3" id="p-3" id="p-3" id="p-3" id="p-3" id="p-3" id="p-3" id="p-3" id="p-3"
[0003] Moreover, a computer program product is provided comprising a computer readable medium, the computer readable medium having the computer program embodied thereon.
BACKGROUND id="p-4" id="p-4" id="p-4" id="p-4" id="p-4" id="p-4" id="p-4" id="p-4" id="p-4"
[0004] ln industrial applications, various types of tools are utilized for facilitating and aiding work. For instance, automated tightening tools are employed for tightening structural joints using fasteners such as e.g. bolts and nuts or screws. ln such environment, these tools are an absolute necessity for providing sufficiently high quality and tightening force in the tightening process. id="p-5" id="p-5" id="p-5" id="p-5" id="p-5" id="p-5" id="p-5" id="p-5" id="p-5"
[0005] When tightening a joint, it is crucial to control the tightening operation provided by the tool. This may be undertaken in many ways, e.g. with torque control, angle control, or by measuring the elongation ofthe bolt during the tightening process, also known as clamp force control. id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6"
[0006] A problem occurring during the tightening process is that there are several undesired tightening results that may occur for the bolt or screw being tightened, such as e.g. a bolt being incorrectly tightened resulting in a slightly too great or slightly too small clamp force at the joint. This problem occurs both upon an operator manually handling the tightening tool as well as in applications here the tightening process is fully automated.
SUMMARY id="p-7" id="p-7" id="p-7" id="p-7" id="p-7" id="p-7" id="p-7" id="p-7" id="p-7"
[0007] One objective is to solve, or at least mitigate, this problem in the art and thus to provide an improved method of facilitating applying a desired clamp force by a tightening tool. id="p-8" id="p-8" id="p-8" id="p-8" id="p-8" id="p-8" id="p-8" id="p-8" id="p-8"
[0008] This objective is attained in a first aspect by a method of a device of controlling applying of a clamp force by a tightening tool to a fastener for tightening a joint, the applied clamp force being determined based on a measured time offlight of an ultrasonic signal being transmitted via a proximal end of the fastener and reflected against a distal end of the fastener when tightening the joint. The method comprising recording, for each different frequency of the ultrasonic signal being transmitted at a plurality of different frequencies, a reflected ultrasonic signal, assigning, to each recorded reflected ultrasonic signal, a quality metric representing a degree of resemblance of each reflected ultrasonic signal with the corresponding transmitted ultrasonic signal, training a machine-learning model by supplying each recorded reflected ultrasonic signal and the assigned quality metric to the machine-learning model to learn the quality of each recorded reflected ultrasonic signal, and supplying the trained machine-learning model with at least one further recorded reflected ultrasonic signal, wherein the trained machine-learning model determines whether or not the supplied at least one further recorded reflected ultrasonic signal complies with a quality criteria and if so indicates that a selected frequency of the transmitted ultrasonic signal for which the at least one further reflected ultrasonic signal was recorded may be utilized for determining the applied clamp force upon the tightening tool applying a clamp force to the fastener. id="p-9" id="p-9" id="p-9" id="p-9" id="p-9" id="p-9" id="p-9" id="p-9" id="p-9"
[0009] This objective is attained in a second aspect by a device configured to control applying of a clamp force by a tightening tool to a fastener for tightening a joint, the applied clamp force being determined based on a measured time of flight of an ultrasonic signal being transmitted via a proximal end of the fastener and reflected against a distal end of the fastener when tightening the joint, the device comprising a processing unit and a memory, said memory containing instructions executable by said processing unit, whereby the device is operative to record, for each different frequency of the ultrasonic signal being transmitted at a plurality of different frequencies, a reflected ultrasonic signal, assign, to each recorded reflected ultrasonic signal, a quality metric representing a degree of resemblance of each reflected ultrasonic signal with the corresponding transmitted ultrasonic signal, train a machine-learning model by supplying each recorded reflected ultrasonic signal and the assigned quality metric to the machine-learning model to learn the quality of each recorded reflected ultrasonic signal, and supply the trained machine-learning model with at least one further recorded reflected ultrasonic signal, wherein the trained machine-learning model determines whether or not the supplied at least one further recorded reflected ultrasonic signal complies with a quality criteria and if so indicates that a selected frequency of the transmitted ultrasonic signal for which the at least one further reflected ultrasonic signal was recorded may be utilized for determining the applied clamp force upon the tightening tool applying a clamp force to the fastener. id="p-10" id="p-10" id="p-10" id="p-10" id="p-10" id="p-10" id="p-10" id="p-10" id="p-10"
[0010] As previously mentioned, when using a tightening tool it is important that the resulting clamp force, i.e. the force that holds a bolted joint together, is accurate. id="p-11" id="p-11" id="p-11" id="p-11" id="p-11" id="p-11" id="p-11" id="p-11" id="p-11"
[0011] There are typically four different methods of controlling the tightening of screw joints to achieve the required clamp force: torque control, angle control, gradient control, and clamp force or elongation control. id="p-12" id="p-12" id="p-12" id="p-12" id="p-12" id="p-12" id="p-12" id="p-12" id="p-12"
[0012] Of the four methods, clamp force control using ultrasonic technique provides a more accurate and non-expensive solution since it requires access to just one bolt end and is friction independent. The ultrasonic method is based on measuring bolt elongation by using signal-echo techniques. id="p-13" id="p-13" id="p-13" id="p-13" id="p-13" id="p-13" id="p-13" id="p-13" id="p-13"
[0013] However, the quality ofthe measurements are partly based on the quality of the echo signal, which in its turn is dependent on the frequency of the ultrasonic signal being transmitted through the fastener. id="p-14" id="p-14" id="p-14" id="p-14" id="p-14" id="p-14" id="p-14" id="p-14" id="p-14"
[0014] Advantageously, in an embodiment, the determining of the quality of a recorded echo signal only needs to be performed in a training phase ofa machine- learning model; once in the execution phase the trained machine-learning model will be utilized to determine whether or not a recorded echo signal complies with a quality criteria or not before performing the tightening operation, which is far less processing- heavy as compared to determining the quality from scratch each time a joint is tightened. 4 id="p-15" id="p-15" id="p-15" id="p-15" id="p-15" id="p-15" id="p-15" id="p-15" id="p-15"
[0015] ln an embodiment, the trained machine-learning model is supplied with the quality criteria to be complied with. id="p-16" id="p-16" id="p-16" id="p-16" id="p-16" id="p-16" id="p-16" id="p-16" id="p-16"
[0016] ln an embodiment, the machine-learning model to be trained is supplied with the quality criteria to be complied with. id="p-17" id="p-17" id="p-17" id="p-17" id="p-17" id="p-17" id="p-17" id="p-17" id="p-17"
[0017] ln an embodiment, cross-correlation is performed to find a correlation between the transmitted ultrasonic signal and recorded reflected ultrasonic signal for each frequency. id="p-18" id="p-18" id="p-18" id="p-18" id="p-18" id="p-18" id="p-18" id="p-18" id="p-18"
[0018] ln an embodiment, the quality criteria is considered to be complied with if the quality metric exceeds a quality threshold value. id="p-19" id="p-19" id="p-19" id="p-19" id="p-19" id="p-19" id="p-19" id="p-19" id="p-19"
[0019] ln an embodiment, the machine learning is based on one or more of neural networks, random forest-based classification and regression analysis. id="p-20" id="p-20" id="p-20" id="p-20" id="p-20" id="p-20" id="p-20" id="p-20" id="p-20"
[0020] ln an embodiment, an alert is provided as to whether or not the supplied at least one further recorded reflected ultrasonic signal complies with the quality criteria. [0021] ln an embodiment, the alert indicates a recommended frequency. id="p-22" id="p-22" id="p-22" id="p-22" id="p-22" id="p-22" id="p-22" id="p-22" id="p-22"
[0022] ln an embodiment, the alert is provided to an operator ofthe tightening tool, to the tightening tool itself, to a supervision control room or to a remote cloud function. id="p-23" id="p-23" id="p-23" id="p-23" id="p-23" id="p-23" id="p-23" id="p-23" id="p-23"
[0023] ln an embodiment, the tightening tool is controlled to provide an audible and/or visual alert to the operator of the tool. id="p-24" id="p-24" id="p-24" id="p-24" id="p-24" id="p-24" id="p-24" id="p-24" id="p-24"
[0024] ln a third aspect, a computer program is provided comprising computer- executable instructions for causing the device to perform steps recited in the method of the first aspect when the computer-executable instructions are executed on a processing unit included in the device. [002 5] ln a fourth aspect, a computer program product is provided comprising a computer readable medium, the computer readable medium having the computer program according to the third aspect embodied thereon. id="p-26" id="p-26" id="p-26" id="p-26" id="p-26" id="p-26" id="p-26" id="p-26" id="p-26"
[0026] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the element, apparatus, component, means, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
BRIEF DESCRIPTION OF THE DRAWINGS [002 7] Aspects and embodiments are now described, by way of example, with refer- ence to the accompanying drawings, in which: id="p-28" id="p-28" id="p-28" id="p-28" id="p-28" id="p-28" id="p-28" id="p-28" id="p-28"
[0028] Figure 1 illustrates an industrial tool in the form of a tightening tool, for which tool embodiments may be implemented; id="p-29" id="p-29" id="p-29" id="p-29" id="p-29" id="p-29" id="p-29" id="p-29" id="p-29"
[0029] Figure 2 illustrates a joint being tightened using a fastener in the form of a bolt and a nut utilizing ultrasonic clamp force control; id="p-30" id="p-30" id="p-30" id="p-30" id="p-30" id="p-30" id="p-30" id="p-30" id="p-30"
[0030] Figures 3a-c illustrate quality of a reflected signal in relation to a transmitted signal; id="p-31" id="p-31" id="p-31" id="p-31" id="p-31" id="p-31" id="p-31" id="p-31" id="p-31"
[0031] Figure 4 shows a flowchart of a method of facilitating applying a desired clamp force by a tightening tool to a fastener for tightening a joint according to an embodiment; id="p-32" id="p-32" id="p-32" id="p-32" id="p-32" id="p-32" id="p-32" id="p-32" id="p-32"
[0032] Figure 5 illustrates training of a machine-learning model according to an embodiment; [003 3] Figure 6 illustrates utilizing the trained machine-learning model in an embodiment; and id="p-34" id="p-34" id="p-34" id="p-34" id="p-34" id="p-34" id="p-34" id="p-34" id="p-34"
[0034] Figure 7 illustrates a device in which the method according to embodiments may be implemented.
DETAILED DESCRIPTION [003 5] The aspects of the present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments of the invention are shown. id="p-36" id="p-36" id="p-36" id="p-36" id="p-36" id="p-36" id="p-36" id="p-36" id="p-36"
[0036] These aspects may, however, be embodied in many different forms and should not be construed as limiting; rather, these embodiments are provided by way of example so that this disclosure will be thorough and complete, and to fully convey the scope of all aspects ofinvention to those skilled in the art. Like numbers refer to like elements throughout the description. id="p-37" id="p-37" id="p-37" id="p-37" id="p-37" id="p-37" id="p-37" id="p-37" id="p-37"
[0037] Figure 1 illustrates an industrial tool in the form of a tightening tool 10 configured to apply a torque to a fastener such as a bolt 20 for tightening a joint, for which tool embodiments may be implemented. id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38"
[0038] The tightening tool 10 may be cordless or electrically powered via a cord and has a main body 11 and a tool head 12. The tool head 12 has an output shaft 13 with a socket (not shown) configured to be rotatably driven by an electric motor arranged inside the main body 11 to apply the torque to the bolt 20. id="p-39" id="p-39" id="p-39" id="p-39" id="p-39" id="p-39" id="p-39" id="p-39" id="p-39"
[0039] The tightening tool 10 may be arranged with a display 14 via which an operator ofthe tool 10 may be presented with information relating to operation ofthe tool 10, and an interface 15 via which the operator may input data to the tool 10. id="p-40" id="p-40" id="p-40" id="p-40" id="p-40" id="p-40" id="p-40" id="p-40" id="p-40"
[0040] The tightening tool 10 may further be arranged with communicating capability in the form of a radio transmitter/receiver 16 for wirelessly transmitting operational data, such as applied torque, to a remotely located controller such as a cloud server 30. Alternatively, communication between the tool 10 and the controller 30 may be undertaken via a wired connection. id="p-41" id="p-41" id="p-41" id="p-41" id="p-41" id="p-41" id="p-41" id="p-41" id="p-41"
[0041] Thus, the tool 10 may for instance communicate measured operational data to the controller 30 for further evaluation while the controller 30 e.g. may send operational settings to be applied by the tool 10 or instructions to be displayed to the operator via the display 14. id="p-42" id="p-42" id="p-42" id="p-42" id="p-42" id="p-42" id="p-42" id="p-42" id="p-42"
[0042] As previously mentioned, when using a tightening tool 10 it is important that the resulting clamp force, i.e. the force that holds a bolted joint together, is accurate. id="p-43" id="p-43" id="p-43" id="p-43" id="p-43" id="p-43" id="p-43" id="p-43" id="p-43"
[0043] There are typically four different methods of controlling the tightening of threaded joints to achieve the required clamp force: torque control, angle control, gradient control, and clamp force or elongation control. id="p-44" id="p-44" id="p-44" id="p-44" id="p-44" id="p-44" id="p-44" id="p-44" id="p-44"
[0044] The method applied in the following will be clamp force/elongation control (both terms will be used in the following). Clamp force control using ultrasonic technique provides a more accurate and non-expensive solution since it requires access to just one bolt end and is friction independent. id="p-45" id="p-45" id="p-45" id="p-45" id="p-45" id="p-45" id="p-45" id="p-45" id="p-45"
[0045] Figure 2 illustrates a joint 22 being tightened using a fastener in the form of a bolt 20 and a nut 21. Ultrasonic clamp force control requires an ultrasonic sensor 23 to be applied to the bolt head. The ultrasonic method is based on measuring bolt elongation by using signal-echo techniques. id="p-46" id="p-46" id="p-46" id="p-46" id="p-46" id="p-46" id="p-46" id="p-46" id="p-46"
[0046] The sensor 23 transmits an ultrasonic signal of a specific frequency into a proximal end the bolt 20, which signal travels through the bolt 20 and reflects against a distal end 24 of the bolt 20 and is subsequently received by the sensor 23 (referred to as an echo). The time of flight (TOF), i.e. the time elapsing between the transmission and the reception ofthe ultrasonic signal by the sensor 23, is measured for the bolt 20 in an untightened state as well as for a tightened bolt. The difference between the tvvo TOF measurements is referred to as delta TOF (ATOF). id="p-47" id="p-47" id="p-47" id="p-47" id="p-47" id="p-47" id="p-47" id="p-47" id="p-47"
[0047] The difference in bolt length before and after tightening is referred to as elongation. ln other words, the bolt 20 will stretch with the degree oftightening. For instance, assuming that the bolt length is 100 mm in the untightened state, while being 102 mm upon being tightened to provide a desired clamping force in the joint 22, the elongation required for providing the desired clamp force in the joint 22 is thus 2 mm. As is understood, when the bolt 20 is elongated during tightening, the TOF increases, and vice versa. [0048] The clamp force applied to joint 22 by the bolt 20 may be estimated as: Fd = CIATOF (1) where C1 is a constant that depends on the measurement chain and the material properties ofthe bolt. Roughly one-third of the TOF is determined by the elongation of the bolt 20, while two-thirds are determined by the stress acting on the bolt 20. This is known as the acoustoelastic effect. id="p-49" id="p-49" id="p-49" id="p-49" id="p-49" id="p-49" id="p-49" id="p-49" id="p-49"
[0049] Now, in order to accurately measure TOF, the signal reflected against the distal end 24 of the bolt 20 needs to be of a sufficiently high quality. lf not, the measured TOF will be inaccurate and consequently the applied claim force Fu as estimated using equation (1) will also be inaccurate. id="p-50" id="p-50" id="p-50" id="p-50" id="p-50" id="p-50" id="p-50" id="p-50" id="p-50"
[0050] Hence, in a practical scenario, the tightening tool 10 may apply a clamp force which seemingly is correct based on the measured TOF according to equation (1), but which in fact is not since the estimation relies on a poorly measured TOF as a consequence of a low-quality echo signal. This may in worst case lead to hazardous consequences (or at least incorrectly tightened bolts). id="p-51" id="p-51" id="p-51" id="p-51" id="p-51" id="p-51" id="p-51" id="p-51" id="p-51"
[0051] The quality of the reflected ultrasonic signal being utilized to measure the TOF is highly dependent on the frequency of the ultrasonic signal transmitted by the sensor 23. id="p-52" id="p-52" id="p-52" id="p-52" id="p-52" id="p-52" id="p-52" id="p-52" id="p-52"
[0052] When measuring TOF, one of two common methods are typically utilized; the first method utilizes the time difference between the transmitted signal and its first echo, while the second method uses the time difference between the first and second echo. Embodiments described herein are equally applicable to both these methods. id="p-53" id="p-53" id="p-53" id="p-53" id="p-53" id="p-53" id="p-53" id="p-53" id="p-53"
[0053] Ultrasonic signals transmitted at different frequencies will result in varying quality of the reflected signals, and there is thus an "optimal" frequency with which the ultrasonic signal is to be transmitted for attaining a highest-quality reflected signal. The optimal transmission frequency depends on factors such as material, dimensions and temperature ofthe bolt, the size and shape of the distal end of the bolt, stress in the bolt, GtC. id="p-54" id="p-54" id="p-54" id="p-54" id="p-54" id="p-54" id="p-54" id="p-54" id="p-54"
[0054] An illustration of three different transmitted and reflected ultrasonic signals in the setup of Figure 2 is shown throughout Figures 3a-3c. When measuring clamp force using the clamp force/elongation control method, commonly used transmitted ultrasonic signals are so-called barker signals or chirp signals. Figures 3a-c illustrate barker coded signals. [005 5] lf e.g. chirp signals are utilized rather than barker signals, further signal parameters may be monitored, such as burst length. ln such a scenario, embodiments described herein may be implemented using burst length as a parameter in addition or alternative to frequency. id="p-56" id="p-56" id="p-56" id="p-56" id="p-56" id="p-56" id="p-56" id="p-56" id="p-56"
[0056] ln Figure 3a, the quality ofthe reflected signal (bottom graph) is poor and thus the reflected signal does not resemble the transmitted signal (top graph). As a consequence, the accuracy ofthe measured TOF will thus likely be poor. [005 7] ln Figure 3b, the quality is slightly higher (i.e. medium quality) and the reflected signal hence has some resemblance with the transmitted signal. As a consequence, the accuracy of the measured TOF will thus be higher than in Figure 3a, but not necessarily acceptable in a high-precision scenario. id="p-58" id="p-58" id="p-58" id="p-58" id="p-58" id="p-58" id="p-58" id="p-58" id="p-58"
[0058] ln Figure 3c, the quality of the reflected signal is high and resembles the transmitted signal to a high extent. As a consequence, the accuracy of the measured TOF 9 is likely high and the applied clamp force estimated based on equation (1) is most likely aCCllfate. id="p-59" id="p-59" id="p-59" id="p-59" id="p-59" id="p-59" id="p-59" id="p-59" id="p-59"
[0059] As can be concluded from the illustrations of Figures 3a-c, it is important that the quality of the reflected ultrasonic signal is sufficiently high and given that the quality is highly dependent on the frequency of the transmitted ultrasonic signal, the frequency must be carefully selected. id="p-60" id="p-60" id="p-60" id="p-60" id="p-60" id="p-60" id="p-60" id="p-60" id="p-60"
[0060] Hence, for each specific bolt tightening condition affected by the factors discussed hereinabove, one or more optimal frequencies exist for the ultrasonic signal transmitted by the sensor 23 that results in the highest-quality reflected signal and most accurate measurement ofthe TOF and thus the applied clamp force, in order to enable the tightening tool 10 to accurately apply a desired clamp force for a specific joint. id="p-61" id="p-61" id="p-61" id="p-61" id="p-61" id="p-61" id="p-61" id="p-61" id="p-61"
[0061] Given that the optimal frequency of the transmitted ultrasonic signal will vary with different tightening conditions, the optimal frequency - or at least a frequency resulting in a reflected signal having a sufficiently high quality - must be found for each tightening. This is both computation-heavy and time-consuming. id="p-62" id="p-62" id="p-62" id="p-62" id="p-62" id="p-62" id="p-62" id="p-62" id="p-62"
[0062] As will be described in the following, by applying machine learning (ML) for training a tightening model to which a great number of recorded echo signals are provided, i.e. ultrasonic signals at different frequencies being transmitted through the bolt 20 by the sensor 23 and reflected against the distal end 24 ofthe bolt 20, along with a quality metric being assigned to each reflected signal, it will subsequently be possible to determine whether or not a reflected signal supplied to the trained ML model is of a sufficiently hight quality, and that an applied clamp force estimated using equation (1) thus may be relied upon. id="p-63" id="p-63" id="p-63" id="p-63" id="p-63" id="p-63" id="p-63" id="p-63" id="p-63"
[0063] When collecting measurement data in a training phase, a torque is applied to the bolt 20 in order to tighten the joint 22. The torque may be applied by hand and the bolt 20 is typically only lightly tightened in the training phase. id="p-64" id="p-64" id="p-64" id="p-64" id="p-64" id="p-64" id="p-64" id="p-64" id="p-64"
[0064] Figure 4 shows a flowchart of a method of facilitating applying a desired clamp force by a tightening tool to a fastener for tightening a joint according to an embodiment. id="p-65" id="p-65" id="p-65" id="p-65" id="p-65" id="p-65" id="p-65" id="p-65" id="p-65"
[0065] As has been described hereinabove in detail with reference to Figure 2, the clamp force control approach (also referred to as elongation control) will be utilized 1O where the applied clamp force is determined based on a measured TOF of an ultrasonic signal being transmitted via a proximal end of the bolt 20 and reflected against a distal end 24 of the bolt 20 when tightening the joint 22. id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66"
[0066] Thus, in a first step S101, the sensor 23 is controlled to transmit the ultrasonic signal at a plurality of different frequencies and for each different frequency of the transmitted ultrasonic signal, a reflected ultrasonic signal is recorded. id="p-67" id="p-67" id="p-67" id="p-67" id="p-67" id="p-67" id="p-67" id="p-67" id="p-67"
[0067] As previously discussed, it is important that the quality of the reflected signal being recorded in step S101 for each selected frequency of the transmitted ultrasonic signal is sufficiently high, such that the TOF may be accurately measured in order to subsequently estimate the applied clamp force according to equation (1). id="p-68" id="p-68" id="p-68" id="p-68" id="p-68" id="p-68" id="p-68" id="p-68" id="p-68"
[0068] Therefore, in step S102, a quality metric is assigned to each recorded reflected ultrasonic signal which represents degree of resemblance of each reflected ultrasonic signal with the corresponding transmitted ultrasonic signal. ln other words, the better the resemblance, the higher the quality. id="p-69" id="p-69" id="p-69" id="p-69" id="p-69" id="p-69" id="p-69" id="p-69" id="p-69"
[0069] ln an example, data processing in the form of cross-correlation is performed to find the correlation between a transmitted signal and recorded reflection of that signal. ln an example, if there is full resemblance between the two, the cross-correlation may be 1 while if there is no resemblance, the cross-correlation may be 0. id="p-70" id="p-70" id="p-70" id="p-70" id="p-70" id="p-70" id="p-70" id="p-70" id="p-70"
[0070] With reference to Table 1 below, for a particular frequency fof the transmitted ultrasonic signal, the recorded reflected signal will be assigned a quality metric q based on the resemblance (e.g. cross-correlation) between the transmitted signal and its recorded reflection.
Frequency of transmitted signal Quality of reflected signal f1 q1 f2 q2 f3 q3 fn qn 11 Table 1. Quality metric q specifying quality of the reflected signal for each selected frequency fof the transmitted signal. id="p-71" id="p-71" id="p-71" id="p-71" id="p-71" id="p-71" id="p-71" id="p-71" id="p-71"
[0071] ln Table 1, each reflected signal at frequencies fl-fn is assigned an individual quality metric q1-qn. id="p-72" id="p-72" id="p-72" id="p-72" id="p-72" id="p-72" id="p-72" id="p-72" id="p-72"
[0072] As is understood, tens or even hundreds of frequencies may be sent through the bolt during the training phase and a quality metric may be derived and associated with each frequency. lt may then be concluded that the best quality metric out of all quality metrics indicates the optimal frequency to be selected for the ultrasonic signal. id="p-73" id="p-73" id="p-73" id="p-73" id="p-73" id="p-73" id="p-73" id="p-73" id="p-73"
[0073] ln practice, it is typically not a matter of finding the optimal frequency but to find one out of potentially many transmitted frequencies which results in a sufficiently high quality for the echo signal. id="p-74" id="p-74" id="p-74" id="p-74" id="p-74" id="p-74" id="p-74" id="p-74" id="p-74"
[0074] As is understood, during normal everyday operation ofthe tightening tool 10, it is not practically feasible to perform such data processing each time a bolt is to be tightened since performing cross-correlation for each tightening operation is processing heavy and time-consuming. This problem is resolved by training an ML model. id="p-75" id="p-75" id="p-75" id="p-75" id="p-75" id="p-75" id="p-75" id="p-75" id="p-75"
[0075] ln step S103, an ML model is trained by supplying each recorded reflected ultrasonic signal and the assigned quality metric to the ML model. The ML model is thus trained to learn which frequencies will result in an echo signal of sufficiently high quality. id="p-76" id="p-76" id="p-76" id="p-76" id="p-76" id="p-76" id="p-76" id="p-76" id="p-76"
[0076] Step S103 marks the end ofthe training phase, after which the execution phase commences where the trained ML model is employed to determine whether or not a selected frequency of the transmitted ultrasonic signal results in a reflected signal of sufficiently high quality. id="p-77" id="p-77" id="p-77" id="p-77" id="p-77" id="p-77" id="p-77" id="p-77" id="p-77"
[0077] Thus, in step S104, during normal operation ofthe tightening tool 10, the trained ML model is supplied with at least one further recorded reflected ultrasonic signal recorded before tightening a joint. id="p-78" id="p-78" id="p-78" id="p-78" id="p-78" id="p-78" id="p-78" id="p-78" id="p-78"
[0078] The trained ML model determines whether or not the supplied further recorded reflected ultrasonic signal complies with the predetermined quality criteria. id="p-79" id="p-79" id="p-79" id="p-79" id="p-79" id="p-79" id="p-79" id="p-79" id="p-79"
[0079] lf so, an output of the ML model indicates that a selected frequency ofthe transmitted ultrasonic signal for which the reflected signal was recorded may be utilized 12 for determining the applied clamp force upon the tightening tool 10 applying a desired clamp force to the bolt. id="p-80" id="p-80" id="p-80" id="p-80" id="p-80" id="p-80" id="p-80" id="p-80" id="p-80"
[0080] Figure 5 illustrates the training of the ML model according to an embodiment, while Figure 6 illustrates utilizing the trained ML model in an embodiment. id="p-81" id="p-81" id="p-81" id="p-81" id="p-81" id="p-81" id="p-81" id="p-81" id="p-81"
[0081] Thus, during a training phase, reflected signals ofthe ultrasonic signal transmitted through the bolt 20 by the sensor 23 at different frequencies are recorded and a quality metric is assigned to each reflected signal as previously described through steps S101 and S102 in Figure 4. id="p-82" id="p-82" id="p-82" id="p-82" id="p-82" id="p-82" id="p-82" id="p-82" id="p-82"
[0082] For instance, assuming that ten echo signals are recorded (in practice far more signals will be recorded in the training phase) and supplied to the ML model as a training set, as illustrated in Table 2.
Frequency of transmitted signal Quality of reflected signal fl, f2, f3, f4 q1 f5, f6, f7, f8 q2 f9, f10 q3 Table 2. Quality metric q associated with each frequency fof the recorded echoes. id="p-83" id="p-83" id="p-83" id="p-83" id="p-83" id="p-83" id="p-83" id="p-83" id="p-83"
[0083] ln this particular example, the frequencies are divided into classes where the assigned quality metric serves as a label for each class. id="p-84" id="p-84" id="p-84" id="p-84" id="p-84" id="p-84" id="p-84" id="p-84" id="p-84"
[0084] Hence, q1 indicates that the cross-correlation between the transmitted signal and the corresponding echo for the frequency class comprising frequencies f1-f4 is in the range 0.7-0.79, q2 indicates that the cross-correlation is in the range 0.6-0.69 for frequencies f5-f8, while q3 indicates that the cross-correlation is in the range 0.5-0.59 for frequencies f9 and f10. id="p-85" id="p-85" id="p-85" id="p-85" id="p-85" id="p-85" id="p-85" id="p-85" id="p-85"
[0085] This data is used to train the ML model such that the ML model subsequently can take a decision in the execution phase whether or not a supplied echo signal has a sufficiently high quality. id="p-86" id="p-86" id="p-86" id="p-86" id="p-86" id="p-86" id="p-86" id="p-86" id="p-86"
[0086] Any appropriate machine learning-approach may be utilized for training the ML model according to embodiments, such as for instance various types of neural 13 networks: deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs), or random forest-based classification, regression analysis, etc. id="p-87" id="p-87" id="p-87" id="p-87" id="p-87" id="p-87" id="p-87" id="p-87" id="p-87"
[0087] As illustrated in Figure 6, after the training set has been supplied to the ML model for adequate training, the execution phase may commence. id="p-88" id="p-88" id="p-88" id="p-88" id="p-88" id="p-88" id="p-88" id="p-88" id="p-88"
[0088] ln the execution phase, when the tightening tool 10 is to tighten a bolt 20, a frequency is selected for the ultrasonic signal to be transmitted by the sensor 23 through the bolt 20 during the tightening operation. id="p-89" id="p-89" id="p-89" id="p-89" id="p-89" id="p-89" id="p-89" id="p-89" id="p-89"
[0089] As a result, the TOF may be accurately measured in order to estimate the desired clamp force to be applied to the joint 22 based on equation (1), given that the selected frequency results in an echo signal of sufficiently high quality. That is, the bolt 20 will be tightened by the tool 10 until a ATOF is reached representing the desired clamp force upon utilizing the selected frequency. id="p-90" id="p-90" id="p-90" id="p-90" id="p-90" id="p-90" id="p-90" id="p-90" id="p-90"
[0090] Now, with reference to Table 2, assuming that the predetermined quality criteria stipulates that q 2 0.7 for the quality criteria to be complied with and the tightening tool 10 selects a frequency f5 for the transmitted ultrasonic signal, the trained ML model will conclude that the reflected signal being a result ofthe signal transmitted at frequency f5 will not be of sufficiently high quality since the assigned quality metric does not comply with the predetermined quality criteria stipulating that q 2 0.7 (for the class of frequencies comprising frequencies f5-f8, the quality matric is 0.69 at best). id="p-91" id="p-91" id="p-91" id="p-91" id="p-91" id="p-91" id="p-91" id="p-91" id="p-91"
[0091] The trained ML model will thus accordingly output an indication that the quality criteria is not complied with for frequency f5 (in practice typically outputting either "1" or "0"). id="p-92" id="p-92" id="p-92" id="p-92" id="p-92" id="p-92" id="p-92" id="p-92" id="p-92"
[0092] As illustrated in Figure 6, the predetermined quality criteria may optionally be supplied to the trained ML model in the execution phase along with the recorded reflected signal to indicate to the trained ML model the quality requirements for the reflected signal, since the requirements may vary for different applications. id="p-93" id="p-93" id="p-93" id="p-93" id="p-93" id="p-93" id="p-93" id="p-93" id="p-93"
[0093] Alternatively, the quality requirement may be supplied to the ML model during the training phase to indicate to the ML model the quality an echo signal must present in order to comply with the quality requirements. 14 id="p-94" id="p-94" id="p-94" id="p-94" id="p-94" id="p-94" id="p-94" id="p-94" id="p-94"
[0094] As a consequence of the quality criteria not being complied with, the tightening tool 10 will not use frequency f5 for measuring TOF (and thus indirectly clamp force), but rather select a new frequency - say f4 - for the transmitted ultrasonic signal and supply the corresponding recorded echo signal to the trained ML model. id="p-95" id="p-95" id="p-95" id="p-95" id="p-95" id="p-95" id="p-95" id="p-95" id="p-95"
[0095] Again, the trained ML model determines whether or not the new echo signal complies with the quality criteria q 2 0.7. Turning to Table 2, any signal in the class comprising frequencies f1-f4 is assigned with a quality metric q1 of at least 0.7, and the ML model outputs an indication that the quality criteria is complied with. id="p-96" id="p-96" id="p-96" id="p-96" id="p-96" id="p-96" id="p-96" id="p-96" id="p-96"
[0096] The tightening tool 10 will as a result transmit an ultrasonic signal at frequency f4 and measure the TOF to apply the desired clamp force in line with equation (1) upon tightening the joint 22. id="p-97" id="p-97" id="p-97" id="p-97" id="p-97" id="p-97" id="p-97" id="p-97" id="p-97"
[0097] ln another example, assuming that the bolt 20 is to be tightened in a scenario where the quality requirements are lower, say q 2 0.6, the selected transmission frequency of f5 would indeed result in a recorded echo signal complying with the quality criteria (all frequencies f5-f8 are indicated to have a quality metric q2 of at least 0.6), and the trained ML model would output an indication accordingly. id="p-98" id="p-98" id="p-98" id="p-98" id="p-98" id="p-98" id="p-98" id="p-98" id="p-98"
[0098] Advantageously, the determining of the quality of a recorded echo signal only needs to be performed in the training phase; once in the execution phase the trained ML model will be utilized to determine whether or not a recorded echo signal complies with a quality criteria or not before performing the tightening operation, which is far less processing-heavy. id="p-99" id="p-99" id="p-99" id="p-99" id="p-99" id="p-99" id="p-99" id="p-99" id="p-99"
[0099] ln an embodiment, an alert ofthe result ofthe output ofthe trained ML model in the execution phase is provided, indicating whether or not the quality of an echo signal complies with the quality criteria. id="p-100" id="p-100" id="p-100" id="p-100" id="p-100" id="p-100" id="p-100" id="p-100" id="p-100"
[00100] ln a further embodiment, the determined optimal frequency (or frequencies) are presented. Thus, in case many frequencies are tested, it may be preferred to only provide an alert for the one(s) considered best. id="p-101" id="p-101" id="p-101" id="p-101" id="p-101" id="p-101" id="p-101" id="p-101" id="p-101"
[00101] The alert may be provided to an operator of the tightening tool 10, to the tightening tool 10 itself, to a supervision control room or to the remote controller 30. id="p-102" id="p-102" id="p-102" id="p-102" id="p-102" id="p-102" id="p-102" id="p-102" id="p-102"
[00102] ln the case ofthe tightening tool 10 alerting an operator ofthe tool 10, the alert may be provided audibly and/or visually, e.g. via the tool display 14. id="p-103" id="p-103" id="p-103" id="p-103" id="p-103" id="p-103" id="p-103" id="p-103" id="p-103"
[00103] Advantageously, if the alert indicates that a selected frequency oftentimes appear to result in an echo signal of high quality, then the sensor 23 can be initialized to utilize that frequency. id="p-104" id="p-104" id="p-104" id="p-104" id="p-104" id="p-104" id="p-104" id="p-104" id="p-104"
[00104] ln contrast, should a selected frequency oftentimes be unsuccessful, than such frequency may be disregarded. id="p-105" id="p-105" id="p-105" id="p-105" id="p-105" id="p-105" id="p-105" id="p-105" id="p-105"
[00105] Even though the training phase may be performed locally in the tightening tool 10, the training of the ML model will typically take place at a device with high- capacity processing capabilities, such as the controller 30. Thus, the controller 30 will be in communication with the sensor 23 (or a device controlling the sensor 23) for controlling the sensor 23 to transmit an ultrasonic signal at multiple frequencies and subsequently supply the recorded echo signals to the controller 30. id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106"
[00106] The controller 30 being aware ofthe appearance ofthe ultrasonic signal transmitted by the sensor 23 will thereafter determine and assign a quality metric to each recorded echo signal (e.g. performing cross-correlation) and train the ML model. id="p-107" id="p-107" id="p-107" id="p-107" id="p-107" id="p-107" id="p-107" id="p-107" id="p-107"
[00107] Subsequently in the execution phase, the trained ML model will be supplied with further recorded echo signals for which a quality assessment is to be performed. This may again be performed at the controller 30, but it may alternatively be envisaged that the trained ML model is provided to and stored at the tightening tool such that computations during the execution phase is performed locally at the tightening tool 10, since such computations are far less computationally demanding as compared to those undertaken during the training phase. id="p-108" id="p-108" id="p-108" id="p-108" id="p-108" id="p-108" id="p-108" id="p-108" id="p-108"
[00108] Thus, with reference to Figure 7, the steps ofthe method described herein may be performed either at the tightening tool 10, at the controller 30 or in cooperation between the tool 10 and the controller 30. Either way the tightening tool 10 as well as the controller 30 may perform one or more ofthese steps utilizing a processing unit 41 embodied in the form of one or more microprocessors (CPU) arranged to execute a computer program 42 (SW) downloaded to a storage medium 43 (MEM) associated with the microprocessor, such as a Random Access Memory (RAM), a Flash memory or a hard disk drive. The processing unit 41 is arranged to cause the tool/controller to carry out the method according to embodiments when the appropriate computer program 42 comprising computer-executable instructions is downloaded to the storage medium 43 16 and executed by the processing unit 41. The storage medium 43 may also be a computer program product comprising the computer program 42. Alternatively, the computer program 42 may be transferred to the storage medium 43 by means ofa suitable computer program product, such as a Digital Versatile Disc (DVD) or a memory stick. As a further alternative, the computer program 42 may be downloaded to the storage medium 43 over a network. The processing unit 41 may alternatively be embodied in the form of a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), etc. Further, a communication interface 44 (INT) may be provided for allowing wired or wireless communication of data. id="p-109" id="p-109" id="p-109" id="p-109" id="p-109" id="p-109" id="p-109" id="p-109" id="p-109"
[00109] The aspects ofthe present disclosure have mainly been described above with reference to a few embodiments and examples thereof. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope ofthe invention, as defined by the appended patent claims. id="p-110" id="p-110" id="p-110" id="p-110" id="p-110" id="p-110" id="p-110" id="p-110" id="p-110"
[00110] Thus, while various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Claims (13)

Claims
1. A method of a device (10, 30) for controlling applying of a clamp force by a tightening tool (10) to a fastener (20) for tightening a joint (22), the applied clamp force being determined based on a measured time of flight of an ultrasonic signal being transmitted via a proximal end of the fastener (20) and reflected against a distal end (24) ofthe fastener (20) when tightening the joint (22), the method comprising: recording (S101), for each different frequency ofthe ultrasonic signal being transmitted at a plurality of different frequencies, a reflected ultrasonic signal; assigning (S102), to each recorded reflected ultrasonic signal, a quality metric representing a degree of resemblance of each reflected ultrasonic signal with the corresponding transmitted ultrasonic signal; training (S103) a machine-learning model by supplying each recorded reflected ultrasonic signal and the assigned quality metric to the machine-learning model to learn the quality of each recorded reflected ultrasonic signal; and supplying (S104) the trained machine-learning model with at least one further recorded reflected ultrasonic signal, wherein the trained machine-learning model determines whether or not the supplied at least one further recorded reflected ultrasonic signal complies with a quality criteria and if so indicates that a selected frequency of the transmitted ultrasonic signal for which the at least one further reflected ultrasonic signal was recorded may be utilized for determining the applied clamp force upon the tightening tool (10) applying a clamp force to the fastener (20).
2. The method of claim 1, the supplying (S104) of the trained machine-learning model with at least one further recorded reflected ultrasonic signal further comprises: supplying the trained machine-learning model with the quality criteria to be complied with.
3. The method of claim 1, the training (S103) ofthe machine-learning model further comprising: supplying the machine-learning model with the quality criteria to be complied With.
4. The method according to any one of the preceding claims, the assigning (S102) of a quality metric to each recorded reflected ultrasonic signal further comprising:performing cross-correlation to find a correlation between the transmitted ultrasonic signal and recorded reflected ultrasonic signal for each frequency.
5. The method according to any one of the preceding claims, the quality criteria being considered to be complied with if the quality metric exceeds a quality threshold value.
6. The method of any one of the preceding claims, wherein the machine learning is based on one or more of neural networks, random forest-based classification and regression analysis.
7. The method of any one of the preceding claims, further comprising: providing an alert as to whether or not the supplied at least one further recorded reflected ultrasonic signal complies with the quality criteria.
8. The method according to claim 7, the alert indicating a recommended frequency.
9. The method according to claims 7 or 8, wherein the alert is provided to an operator ofthe tightening tool (10), to the tightening tool (10) itself, to a supervision control room and/or to a remote cloud function (30).
10. The method according to claim 9, wherein the tightening tool (10) is controlled to provide an audible and/or visual alert to the operator ofthe tool (10).
11. A computer program (42) comprising computer-executable instructions for causing the device (10, 30) to perform steps recited in any one of claims 1-10 when the computer-executable instructions are executed on a processing unit (41) included in the device (10, 30).
12. A computer program product comprising a computer readable medium (43), the computer readable medium having the computer program (42) according to claimembodied thereon.
13. A device (10, 30) configured to control applying of a clamp force by a tightening tool (10) to a fastener (20) for tightening a joint (22), the applied clamp force being determined based on a measured time of flight of an ultrasonic signal being transmitted via a proximal end of the fastener (20) and reflected against a distal end (24) of the fastener (20) when tightening the joint (22), the device (10, 30) comprising a processing unit (41) and a memory (43), said memory containing instructions (42) executable by said processing unit (41), whereby the device (10, 30) is operative to:record, for each different frequency of the ultrasonic signal being transmitted at a plurality of different frequencies, a reflected ultrasonic signal; assign, to each recorded reflected ultrasonic signal, a quality metric representing a degree of resemblance of each reflected ultrasonic signal with the corresponding transmitted ultrasonic signal; train a machine-learning model by supplying each recorded reflected ultrasonic signal and the assigned quality metric to the machine-learning model to learn the quality of each recorded reflected ultrasonic signal; and supply the trained machine-learning model with at least one further recorded reflected ultrasonic signal, wherein the trained machine-learning model determines whether or not the supplied at least one further recorded reflected ultrasonic signal complies with a quality criteria and if so indicates that a selected frequency of the transmitted ultrasonic signal for which the at least one further reflected ultrasonic signal was recorded may be utilized for determining the applied clamp force upon the tightening tool (10) applying a clamp force to the fastener (20).
SE2230287A 2022-09-14 2022-09-14 Machine learning method of facilitating applying a desired clamp force by a tightening tool SE546313C2 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
SE2230287A SE546313C2 (en) 2022-09-14 2022-09-14 Machine learning method of facilitating applying a desired clamp force by a tightening tool
DE102023124319.5A DE102023124319A1 (en) 2022-09-14 2023-09-08 Method for facilitating the application of a desired clamping force by a tightening tool
CN202311175142.7A CN117705329A (en) 2022-09-14 2023-09-12 Method for facilitating application of a desired clamping force by tightening a tool

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
SE2230287A SE546313C2 (en) 2022-09-14 2022-09-14 Machine learning method of facilitating applying a desired clamp force by a tightening tool

Publications (2)

Publication Number Publication Date
SE2230287A1 true SE2230287A1 (en) 2024-03-15
SE546313C2 SE546313C2 (en) 2024-10-01

Family

ID=90054644

Family Applications (1)

Application Number Title Priority Date Filing Date
SE2230287A SE546313C2 (en) 2022-09-14 2022-09-14 Machine learning method of facilitating applying a desired clamp force by a tightening tool

Country Status (3)

Country Link
CN (1) CN117705329A (en)
DE (1) DE102023124319A1 (en)
SE (1) SE546313C2 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118586784B (en) * 2024-08-06 2024-12-06 济南轨道交通集团有限公司 Data-driven intelligent evaluation method and system for geotechnical slope reinforcement quality

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2411780A1 (en) * 2009-03-27 2012-02-01 Atlas Copco Tools AB Method and device for ultrasonic measurements
JP2016522414A (en) * 2013-06-12 2016-07-28 アトラス・コプコ・インダストリアル・テクニーク・アクチボラグ Method for ultrasonically measuring fastener elongation performed with a power tool and power tool
US20180328797A1 (en) * 2017-05-15 2018-11-15 Hyundai Motor Company Method for measuring axial force of bolt
JP2019128193A (en) * 2018-01-23 2019-08-01 正文 金友 Method for inspecting fastening state
US20200009696A1 (en) * 2018-07-03 2020-01-09 Toyota Jidosha Kabushiki Kaisha Inspection system
US20200173963A1 (en) * 2018-12-04 2020-06-04 Intellifast Gmbh Method and Device for Determining the Prestress Force of a Connection Component
KR20220087078A (en) * 2020-12-17 2022-06-24 한국생산기술연구원 Method for monitoring of joining quality for self piercing rivet, process for joining of self piercing rivet, and apparatus system for the same

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2411780A1 (en) * 2009-03-27 2012-02-01 Atlas Copco Tools AB Method and device for ultrasonic measurements
JP2016522414A (en) * 2013-06-12 2016-07-28 アトラス・コプコ・インダストリアル・テクニーク・アクチボラグ Method for ultrasonically measuring fastener elongation performed with a power tool and power tool
US20180328797A1 (en) * 2017-05-15 2018-11-15 Hyundai Motor Company Method for measuring axial force of bolt
JP2019128193A (en) * 2018-01-23 2019-08-01 正文 金友 Method for inspecting fastening state
US20200009696A1 (en) * 2018-07-03 2020-01-09 Toyota Jidosha Kabushiki Kaisha Inspection system
US20200173963A1 (en) * 2018-12-04 2020-06-04 Intellifast Gmbh Method and Device for Determining the Prestress Force of a Connection Component
KR20220087078A (en) * 2020-12-17 2022-06-24 한국생산기술연구원 Method for monitoring of joining quality for self piercing rivet, process for joining of self piercing rivet, and apparatus system for the same

Also Published As

Publication number Publication date
DE102023124319A1 (en) 2024-03-14
SE546313C2 (en) 2024-10-01
CN117705329A (en) 2024-03-15

Similar Documents

Publication Publication Date Title
SE2230287A1 (en) Method of facilitating applying a desired clamp force by a tightening tool
Das et al. A combined wavelet packet and Hilbert-Huang transform for defect detection and modelling of weld strength in friction stir welding process
IL305052A (en) Systems and methods for semiconductor adaptive testing using inline defect part average testing
JP7035178B2 (en) Diagnostic equipment and diagnostic methods for rolling equipment
JP6100720B2 (en) Welded part inspection device and welded part inspection method
IL274911B1 (en) A device and method for calibrating a robotic cell
CN105424798A (en) Method for actively detecting defects in metal thin-walled structure part
SE2130370A1 (en) Determining tightening class of a tightening tool
SE2330201A1 (en) Method and device for enabling ml estimation of tightening class utilizing normalization
KR101315391B1 (en) A nondestructive welding quality total inspection system and a inspection method thereof using an electromagnetic induction sensor
SE2330200A1 (en) Ml estimation of tightening classes
SE2330199A1 (en) Determining correctness of estimated tightening classes
SE546511C2 (en) Configuration of tightening tool
IES87509Y1 (en) Uav-based concrete ultrasonic flaw detection device and method
CN113466331B (en) Pulse eddy current thermal imaging dynamic detection device and method for tread crack of train wheel
JP5955797B2 (en) Welded part inspection method and welded part inspection apparatus
JP6154770B2 (en) Welded part inspection device and welded part inspection method
IL305110B1 (en) Systems and methods for semiconductor defect-guided burn-in and system level tests
KR102157337B1 (en) Apparatus for auto examination using ultrasonics wave and image
KR101936367B1 (en) A fatigue degree inspection apparatus and an inspection method thereof using an electromagnetic induction sensor
CN104807891A (en) Device for identifying continuity of specially-shaped part by utilizing acoustic spectral analysis
Jyothisree et al. Railway track crack detection using robot
US20190143610A1 (en) Method And Apparatus For Detection Of Loose Stack Joints And Cracked Components Of Ultrasonic Stacks
JPH03246472A (en) Winding abnormality detecting device for winding coil for motor
CN115824646A (en) Self-test circuit and method for checking the integrity of a signal passing through a signal path