Surface Integrity Cutting Fluids Machining and Monitoring Strategies_10 potx

These problems arise in performing the monitoring and service functions that are usually seen by the operator, who would normally undertake the: monitoring of the cutting tool’s condi-ti

over 1°C The hydraulic and electronic cabinets were

temperature – controlled to ± 1°C The ‘refractive index

of the air’ had to be corrected – based upon a

modifi-cation to the Edlen (1966) equation, as the laser path

positional monitoring system would otherwise be

af-fected, with a correction factor being entered into the

CNC controller

The ‘T-shaped base’ of the Nanocentre was

sup-ported on three pneumatic mounts that were ‘tuned’ to

eliminate floor-borne vibrations of ≥ 2.5 Hz Two types

of vibrational sources occur, namely forced- and

self-excited, with the forced vibrations originating from

external sources – through the foundations, while the

self-excited vibrations normally being the result of

in-ternal sources A ‘floor vibration audit’ on the

vibra-tional influences was conducted, to establish whether

the overall enclosure was sufficiently vibration

absor-bent The floor vibration spectra gave typical

vibra-tional readings of 1 nm (rms) at frequencies of 25 Hz,

during the tests, with the external air compressors

emitting a floor borne 25 Hz frequency component,

which had to be subsequently nullified Further testing

procedures were undertaken, including ‘modal

analy-sis’ and ‘thermal imaging’ of the machine’s structure,

together with a full calibration of the machine tool’s

kinematics

Once all of these tests and various others had been

completed and compensated for, then a machining

testing program could then be undertaken A

typi-cal test piece is illustrated in Fig 257b, where an

al-uminium 6061-T6 part was heat treated and then

stabilised, of φ250 mm copper-plated (200 µm depth

coating) part These testpieces were faced-off with a

monolithic diamond tool – taking very shallow DOC’s

of just a few micrometres, producing for example, a

face-turned surface texture averaging ≈ 2.8 nm Ra

Later, profiling tests were also conducted, prior to

fi-nal operatiofi-nal acceptance by AWE, from the machine

tool builder

Prior to completing this summation of the just

some of the rigorous testing procedures carried out to

ensure that the Nanocentre machine tool could

oper-ate within the nanometric range of ultra-high

machin-ing operation, it is worth makmachin-ing an unusual point

concerning human intervention at this exacting-level

of machining It was found that when several

person-nel were within the machine tool enclosure while

machining took place, then the thermal output from

these people, influenced the part’s dimensional size

– without actually contacting the machine, by simply

acting as a heat-emitting source Moreover, it was also found that when diamond-turning by facing-off

a very ductile testpiece similar to that depicted in Fig 257b, when these people were in conversation during

the nanometric cutting of the part, their ‘voice signa-tures’ – in the form of air-borne vibrations were ‘ma-chined’ into the surface – in a similar manner to that of

an acrylic recording of a record in the past! Therefore,

in order to ensure that both the human thermal effects and the vibrational perturbations (i.e by air-borne vi-brations – talking), the personnel had to be removed while any ultra-precision machining operations were

in progress

Ultra-precision machining at these nano-metric levels of operation, severely stretches today’s levels

of technological challenges for: machine tools, me-trology, plant and equipment, as we approach that of atomic-levels of precisional uncertainties It is not just the case of purchasing an extremely accurate and

 ‘Human body – as a heat source’ The average body – in a

‘sedentary state’ , will emit ≈100 W of heat So, here in this case, when there are two people present in the machine tool enclosure, they will radiate ≈200 W of heat – influencing

the machine’s and hence, the workpiece’s thermal expansion – when machining at nanometric levels of accuracy and preci-sion (Internet source: Burruss, R.A.P., Virtual People, 2005)

 ‘Monolithic diamond’ , has some of the following

characteris-tics: hardness of ≈8,000 Hv; Density (ρ) of 3,515 kg m–; com-pressive strength of 7,000 MPa; and a Young’s modulus (E) of

930 GPa.(Source: Cardarelli et al., 2000)

 ‘Atomic radius’ , for example, for some typical elements, ranges

from that of: carbon, having an atomic radius of ≈0.071 nm (i.e its atomic ≈φ0.142 nm)*, iron’s atomic radius is ≈0.124 nm (i.e ≈φ0.248 nm, or ≈¼ nm)*, Aluminium’s atomic radius is

≈0.143 nm (i.e ≈φ0.286 nm, or >¼ nm), Cesium’s atomic radius

is ≈0.265 nm (i.e ≈φ0.530 nm, or >½ nm).(Source: Callister, Jr

et al., 2003)*Slight digression here, may help explain why these atomic radii are important, when certain elements are alloyed together, such as iron and carbon, these being the main con-stituents of plain carbon steel.When an allotropic change oc-curs to the iron’s atomic lattice structure (i.e BCC→FCC @

≈910°C), then the carbon being somewhat smaller, can fit into these (now) larger interstitial sites – voids – within the FCC iron lattice – distorting the adjacent iron atoms Upon rapid cooling (e.g by water quenching), some of the carbon is

‘trapped’ and severely distorts the structure as it attempts to transform back to the original BCC form Hence, this dis-torted structure of iron-carbon – termed martensite, is both

a very hard, but brittle structure, requiring tempering: if it is

to act as a hardened and tempered workpiece material This is the basis (i.e somewhat simplified), behind this iron-carbon heat-treatment process

precise machine tool (Fig 257a), and hoping to utilise

it to machine when approaching nano-metric

resolu-tion levels There are many often interrelated factors

that have to be considered and then dealt with, if one

is to successfully operate at this ultra-precision level of

machining operations

9.11 Machine Tool

Monitoring Techniques

Introduction

One of the most fundamental requirements for

increas-ing productivity of CNC machine tools, is the ability

to operate them ideally, in an untended manner, but

at the very least, minimally-manned – whether they

are ‘stand-alone’ machines, or part of a flexible

manu-facturing cell, or system (FMC/S) So, if an untended

operation has been decided upon, then the absence

of an operator will create a considerable number of

problems that must be overcome, if the machining

op-erations are to be satisfactory These problems arise in

performing the monitoring and service functions that

are usually seen by the operator, who would normally

undertake the: monitoring of the cutting tool’s

condi-tion and its performance; replacing worn, or defective

tooling by interrupting the cutting cycle; assessing the

workpiece quality during machining; changing speeds

and feeds – if required; plus responding to unusual

conditions that are either seen, or heard, during the

cutting operation While, in an unmanned

machin-ing environment, the associated monitormachin-ing systems

must provide the ‘artificial intelligence’ (AI), necessary

to ‘mirror’ the experience gained by a fully-skilled

op-erator and their instinctive reactions and, to provide

the type of expertise usually associated with human

involvement To cope with these every-day

human-intelligence activities and their subsequent

interven-tion during any machining operainterven-tions, a considerable

number of monitoring systems have been developed

In general, monitoring systems can be classified as:

process-monitoring; workpiece-monitoring; machine

tool monitoring; and tool-monitoring systems Typical

applications of these monitoring systems for untended

operation on machine tools, include:

• Monitoring the correct loading of the workpiece,

correcting any set-up misalignments, or datum

off-sets, while checking the quality of the workpiece,

• Checking that the correct tools are available, by identifying both the tools and their setting offsets, monitoring for tool wear and breakage and, initiat-ing tool replacements – as necessary,

• Adjusting speed and feed as appropriate and, com-pensating for such effects as tool wear, thermal de-formation and chip congestion,

• Monitoring of machine elements, including the CNC controller and taking any necessary correc-tive action in response to: program failure; diag-nostic error messages; etc

Whatever the function that is to be monitored, there

is a need for some form of sensor to be incorporated into the system – to detect any problems as they arise,

so that action can be appropriately taken, if necessary Thus, a sensor’s output – triggered by an error mes-sage, must be processed to obtain the correct informa-tion, allowing decision(s ) to be made The machine’s control unit, will then receive this ‘sensed’ result and initiate controlled actions to either correct, or re-cover the situation Various types of monitoring and sensing systems are currently available for machine tools Although, because this subject matter is so vast and sophisticated, only several of these monitoring techniques and sensing systems will now be consid-ered

9.11.1 Cutting Tool Condition

Monitoring

Introduction

Whenever an operator is present during a machining operation, one of their major functions is to monitor the tool’s condition while the cutting continues, where they continually assure themselves that a tool in-cut

is performing productively The tool-related monitor-ing functions performed by an operator durmonitor-ing any component’s manufacture, may be classified into four groups, briefly these are:

1 Tool identification – this ensures that the correct

tool will be used for a specific operation, with a va-riety of techniques being employed to achieve this crucial tooling activity Techniques include the use of: touch-trigger probes (Fig 133); non-contacting probing methods (Fig 134); ‘tagged’ tooling of the contact (Figs 116 and 117), or non-contact variet-ies (not depicted),

2 Tool-offset measurement – of the cutting edge’s

po-sition is necessary, in relation to that of the part’s

datum point This can be accomplished by the

‘probing-techniques’ and tool identification

meth-ods mentioned above,

3 Tool life monitoring – is necessary to estimate the

extent of a worn tool’s condition, which must be

replaced prior to tool failure The are a range of

sensing devices available and they can be classified

into two main groups: ‘Direct sensing’ – include:

radioactive techniques; measurement of electrical

resistance; optical observation of the wear zone;

measurement of workpiece dimensional changes;

or the distance between the workpiece and the

tool post, ‘Indirect sensing’ – based upon either:

temperature; sound; vibration; acoustic emission

and force This latter method can be measured

and monitored either directly, by dynamometry

(Figs 178–180, 237 and 244), or indirectly via

mea-surements of power, current, or torque – some of

these techniques will shortly be discussed,

4 Tool breakage detection – can be monitored to

en-sure that the cutting edge does not fail in-cut, as

damage to both the tooling assembly and the

work-piece may occur as a result Once again, a variety

of commercially-available techniques based upon

force-related signals are available, including: those

methods that use a dynamometer, either situated

on the tool block, or in say, a turning operation

be-low the tooling turret (Fig 179); thrust-/feed-force

sensors (Fig 258); spindle-bearing/motor-current

monitoring (not shown); power-/torque

monitor-ing (Fig 259a) This latter technique (Fig 259a),

is often known as: ‘Torque-controlled machining’

(TCM)

NB In order to fully appreciate the complexity and

sophistication of any tool- condition monitoring,

on CNC machine tools, the following section has

been included

Tool-Condition Monitoring –

With Feed-Force Sensors

Modern microprocessor-designed tool-monitoring

systems can be utilised for a variety of reasons, for

example, to monitor the tool’s condition, or to reduce

machining value-added costs The advantages of using

monitoring detection, are

• Tool wear is monitored and tool changes initiated when necessary, so avoiding damage to the ma-chine, or workpiece,

• If breakage occurs, a signal will be immediately produced to stop the machine tool – usually within milliseconds,

• The system detects if a tool, or workpiece is miss-ing, thus eliminating wasted machine time and the likelihood of unpredictable crashes

While the cost advantages of using tool monitoring are:

• Tool life can be optimised, meaning that the tools need to be only changed when they are worn – to a specified amount (Figs 174 and 176) and so reduce the tool costs (Fig 177e),

• Down-time (i.e here, it is normally associated with unanticipated wear rates, or tool crashes) is re-duced, which increases the machine’s output and as

a result, improving cycle-time and costs per part,

• Repairs to the machine tool and cutting tools may

be reduced to a minimum, so the maintenance costs are lower,

• The machining operation is automatically moni-tored, limiting any costly labour rates by subse-quent operator involvement

The above listed advantages for tool-condition moni-toring are quite an impressive recommendation, but how does it achieve consistent and accurate tool moni-toring, while simultaneously controlling the cutting process? These questions will now be considered, deal-ing in the first instance, with how the system monitors the tool’s performance during machining

A well known fact is that a tool will produce rela-tively high loads during a cutting operation, as it

begins to wear For effective ‘process monitoring’ it

is important that the signal utilised should vary in a progressive manner as the tool wears and, not just at

the time that it actually breaks It has been shown (Fig 258b) that during a machining operation, the axial force component (FA) provides a better indication of the cutting edge’s condition as a function of tool wear, than the torque value (M) Thus, the increase in the axial force is more clearly defined – in both cases, from that of a sharp tool (Fig 258b – left) to that of a worn tool (Fig 258b – right) This change in the force gener-ated whilst cutting is instantly detected by a feed force sensor (Fig 258a) The sensor transforms the force change into an electrical signal which is transmitted

Figure 258 Tool-condition monitoring on a turning centre [Courtesy of Sandvik Coromant]

.

to the signal-processing device Once the signal is

re-ceived, the processing device can immediately initiate

action by the machine’s CNC controller, if the tool is

either: worn, broken, or not in-cut This situation is

all very well, but when should tool monitoring take

place and, what action should result? In Fig 258a (i.e

the inset diagram), the graphical depiction shows how

continuous monitoring of the axial force can be used

to triggered several alarm-states:

• Level I – can be utilised to monitor whether a tool is

in-cut, or not-in-cut, as the situation arises,

mean-ing that either the tool, or component, or indeed

both, are missing,

• Level II – can be used to detect tool wear, with the

alarm signal being used to initiate a tool change (i.e

to a ‘sister tool’) on completion of the operation,

• Level III – can be utilised for tool breakage, with

the signal being used to immediately stop the

‘feed-ing-function’ of the machine tool, when breakage is

detected,

• Tool crashes – a further level can also be employed

for crash protection, which acts in a similar

man-ner to ‘Level III’ , but this alarm immediately stops

all motions and in so doing, protects the machine

tool

In Fig 258c, the schematic diagram illustrates

typi-cal monitoring positions on a two-axis turning centre,

showing potential sites to place the sensors, such as on

the ball-screw nuts of the recirculating ballscrew

as-semblies, for both the X- and Z-axes Not shown here,

but normally also fitted is a current sensor Thus, these

signals are continuously monitored by either a single-

or multi-channel control unit, as will be the control

signals from the machine tool’s CNC controller Any

alarm signals triggered, being passed back through a

closed-loop to the machine’s control unit for

appropri-ate action to be taken, or indeed if any The function of

a typical commercially-available multi-channel signal

processing unit, might be to:

• Sense – then process tool-cutting information from

signals at the various sensors and sites for the

mul-tiple channels of the unit,

 ‘Tool breakage detection times’ , it is possible to vary the

reac-tion time, which is usually between: 0.1 to 1 second, but for

any form of tool breakage a shorter reaction time is desirable,

typically ranging from: 1 to 10 milliseconds

• Learn – by automatically memorising the signal

values obtained from the sharp cutting tools, whilst

in this ‘learn-mode’ ,

• Stores data – for a significant number of cutting

operations per channel in its memory for each cut-ting operation, as well as automatically setcut-ting the appropriate levels for each alarm signal from its memory,

• Reacts – by sending alarms to the machine’s control

unit, informing it if the tool is either: worn; broken;

or not-in-cut,

• Coordinates – automatically, machining and

moni-toring on commands from the machine’s control unit,

• Adapts – to the particular machine and its cutting

environment: once installed and programmed to suit the machine tool, with the setup parameters being modified to adapt to any further machining requirements,

• Communicates – between the operator and the

machine via the control panel, informing the oper-ating personnel about cutting tool conditions and providing an interface for control of all functions

In Fig 258c, this line-diagram depicts a typical turn-ing centre application of tool condition monitorturn-ing The machine is controlled on two axes, with sensors

on the feed-drive bearings of both the X- and Z-axes

A representative nominal force for these sensors is 40

kN, but this rating will depend upon the end-user’s re-quirements The sensors can be designed for tapered,

or angular contact bearings, or for a combined axial and radial bearing application – suiting the particular machine tool When tool monitoring is needed for a four-axis turning centre, two tool monitoring units are usually needed, since each turret (i.e to and bottom) can be operated both independently The key elements

in any tool condition monitoring situation are the sensor’s position and its design For universal instal-lation on a variety of machine tool configurations, the positioning of the sensing devices is usually on the re-circulating ballscrew nut assembly

 ‘System-learning’ , in the past this was somewhat a basic of

functional performance, but with the advent of ‘artificial neural networks’ , they have an ‘AI-ability’* to ‘mimic’ human involve-ment and react to their environinvolve-ment – once ‘trained’ More will be said on this ‘AI-topic’ in the final section of this book.

* ‘AI’ is a term that is normally utilised when some form of ‘artifi-cial Intelligence’ is employed in the decision-making process.

Much more could be said concerning the

informa-tion on their: operainforma-tional setup; range; and

adaptabil-ity; for these tool condition monitoring systems In

the interests of brevity, the reader should look to the

manufacturers of such equipment, or the references

and available literature for more specific depth

in-formation

9.11.2 Adaptive Control and Machine

Tool Optimisation

Adaptive Control

Adaptive control systems have been utilised since their

introduction in the 1960’s, where their operational

performance and reliability was somewhat dubious,

because of the type of sensors utilised, the speed of

signal-data processing and their installation on the

machine tool Many of these early systems attempted

to undertake many functions simultaneously and were

often termed; ‘adaptive control optimisation’ (ACO),

but due to the problems mentioned above, they were

somewhat unreliable and as such, fell out of favour

Later, a more pragmatic approach to adaptive control

constraint (ACC) was introduced called:

‘torque-con-trolled machining’ (TCM), which offered a simpler

termed: ‘feed-only system’ – with a typical system

be-ing depicted in Fig 259a Thus, the operation of a TCM

system, involves unique sensory circuitry and

compu-tation methods that measure the net cutting torque,

then compares this value obtained, to that of the preset

torque limits – these previously being established for

the cutting tool and workpiece combination utilised

The appropriate control actions, namely, a feedrate

reduction is then automatically taken, whilst keeping

within the maximum torque and power limits of the

spindle motor If a condition arises where the feedrate

falls below a preset limit, a new tool (i.e sister tool) is

called-up to complete the machining operation This

feedback-loop in which continuous monitoring by the

sensors and updating the machine control unit – using

adaptive control, produces optimal cutting conditions

for the tool and workpiece combination

Adaptive control via TCM (Fig 259a), basically

op-erates in the following manner Prior to its activation

and if for example, a variation of stock was present for

roughing operation with a large face-mill The

unpre-dictability of the height of this stock if a TCM system

was not activated, might otherwise over-load the

cut-ting edges, possibly causing damage to the: cutter

as-sembly; workpiece; or even the machine tool Once the TCM has been correctly activated and preset to a torque limit, then if the DOC is large, the control sys-tem senses a torque increase and simultaneously the feedrate over-ride is initiated This over-riding of the programmed feedrate decreases the feed for this large

DOC, it will then increase as the DOC lessens, or rapidly move over an ‘air-cut’ , thus producing optimal cutting tool protection and efficiency as the chip-load is more uniform, regardless of the variable DOC’s Even if there

is no discernible difference in the relative height of the

DOC taken, but the bulk hardness of the part may vary

by up to 300% in some cases, machining with the TCM activated will protect the tooling So to mention the some benefits to be gained from TCM, they include: extended tool life; optimised feedrates – without the risk of tool damage; higher throughput of machined parts; tool breakage minimised; quicker setup times; and reduced operator intervention Obviously very small diameter tooling, may not respond to the torque demands so readily, but for most machining opera-tions and tool/workpiece combinaopera-tions the system has distinct benefits to the overall machining production process

To summarise the principal benefits of utilising some form of adaptive control system, they are:

• Main spindle motor is protected from overload,

• Damage to the cutter and to the expensive value-added workpiece are protected,

• Optimal stock removal rates are possible, under steady-state machining conditions,

• Using a constant: cutting power; cutting force; and feed force; optimises tool life,

• If unpredictable air-gaps occur – whilst cutting, the fastest tool travel is utilised,

• Where workpiece hardness significantly varies, tool edges are protected by adjustments of the loads,

• Where an operator’s experience, or the program’s efficiency may differ for varying cutting operations, the adaptive control system eliminates this ‘techni-cal gap’ ,

• There is no over-shooting of the permitted cutting power during re-entry into the workpiece material whilst machining the part under regular condi-tions

Costs vary the for ‘post-installation’ of adaptive con-trol systems to CNC machine tools, but at today’s prices they range from: $ 9,000 to $ 15,000 (US) How-ever, once installed they last the life of the machine

Figure 259 Either use: adaptive control or CNC program optimisation – for variable tool path trajectories

.

tool, giving a superb pay-back on the original

invest-ment, when one considers the major benefits listed

above

Machine Tool Optimisation

If a company has significant numbers of CNC machine

tools in their manufacturing facility, then it may not

be feasible to introduce an ‘adaptive control’ system

across all of these machines – despite the positive

merits described above, simply on financial grounds

alone Under such circumstances, perhaps a

‘software-approach’ by simulating the cutting operations to the

problem of machining optimisation, may be the way

forward? Some companies offer CNC programming

optimisation packages that are based upon literally

thousands of ‘man-hours’ of development and

refine-ment (i.e Fig 259b, shows a very sophisticated version

of such a tool verification and simulation system)

These simulation systems are often part of a larger:

op-timisation; verification and analysis product that can

be ‘tailored’ to suit a machining company’s product

range and manufacturing output These

‘knowledge-based’ systems of the machining process, via previous

simulation, know the exact: DOC; width of cut; and

angle of cut (i.e for cutter orientation, when

profil-ing); for the machining process under consideration

Further, the system also knows how much material

is to be removed by each cutting edge, as such, the

system also has information on the tooling available

from the magazine, therefore it selects correct tool and

assigns to it the optimum feedrate Moreover, once

this information has been established for the new tool,

it outputs the tool path – which was identical to say,

that of the original tool, but now having significantly

improved feedrates, although the system does not alter

its trajectory

While setting up the system, it is usual for such

software (Fig 259b) to prompt the user for cutter

set-tings as the part simulation occurs, by in essence,

add-ing the user’s intelligence to that of the cutter’s

opera-tion With these systems it is usual to have all cutter

settings stored in an optimisation library, thus the user

only has to define the setting once While, the more

sophisticated systems find the maximum volume

re-moval rate and chip thickness for each tool, then it

employs them to determine the optimisation settings

for that tool

In optimised roughing-out, the objective here is

ob-viously to remove as much stock material as possible

in the fastest time Conversely, for finish-machining,

chip-loads may vary considerably, as the tool profiles through the workpiece material that was left behind during previous roughing cuts over the contours

– to near-net shape By optimising the tool’s path, the software adjusts the feedrates to maintain a constant chip-load (Fig 259b) This cutter optimisation will

improve the tool life and give an enhanced machined surface finish to the component This fact is especially critical when ‘tip-cutting’ , with either a ball-nosed end mill (Fig 247b), or contouring over a surface with a small step-over, such as when semi-finishing, or fin-ishing a steel mould cavity (Fig 249b)

Summarising the advantages of utilising a simu-lated optimisation cutter-path software package, such

as the one in Fig 259b which only illustrates some ba-sic and simple tool paths Thus, cutter-path optimisa-tion offers the user the ability to:

• Machine more efficiently – cutting more parts in

the same amount of time, by significantly reducing the machined component’s cycle-time,

• Reducing part cost thereby saving money –

increas-ing productivity by reducincreas-ing the time it takes to cut parts, will become a significant saving per annum,

• Improving part quality – by minimising the

con-stant cutting pressure, thus reducing cutter deflec-tion, with finished corners, edges and blend areas, needing less subsequent hand-finishing,

• Cutter life improved – because of optimised

cut-ting conditions are used, which prolongs tool life Moreover, with shorter in-cut time, this results in less tool wear, also having the benefit of reducing down-time to change inserts, or tooling,

• Reduction in machine tool wear – as a more

con-stant cutting pressure between the machine tool and the workpiece reduces variable forces on the axis motors, giving smoother machine operation,

• Utilises time available more effectively – allowing

machinists to operate several CNC machine tools,

or setup the following job, etc., as they do not have

to be constantly ready to reduce/increase the ma-chine’s feedrate over-ride

By investing in suitable simulation and optimisation software of the tool’s path, enables a company that is currently involved in a considerable amount of

ma- ‘Constant chip-loads’ , are normally recommended by cutting

tool manufacturers, as they reduce the effect of ‘chip-thinning’ somewhat.

chining activities to become very cost-effective and

efficient when compared to their direct competition,

both nationally and internationally One could

cer-tainly ask the question, under these circumstances

just mentioned: ‘Can a company afford not to be using

such software, if their main competition – both here and

abroad have it available now?’

9.11.3 Artificial Intelligence:

AI and Neural Network

Integration

Introduction

Over the past decade and a half, some significant

ad-vances in machining materials have occurred, while

complementary progress has also been made in the

machine tool’s CNC controllers, coupled to their faster

micro-processor speed and additional technological

refinements Many of these machine tools are

inte-grated into fully-automated systems machining lines

– for volume part production purposes, or into

flex-ible manufacturing cells/systems (FMC/S) – allowing

scope for mixing batch sizes and perhaps employing

a ‘Group Technology’ (GT) approach (i.e see Footnote

24, Chapter 6) So that the full potential of these

ma-chine tools can be exploited, it is exceedingly

impor-tant that production processes are both monitored and

controlled in an ‘intelligent manner’

Previously, when little cutting data and minimal

tooling-related behaviour had been established for a

new production run, it was necessary to instigate some

form of tool measurement procedure So, after

operat-ing a cuttoperat-ing tool for an extended time-period in-cut,

so that the tool’s wear pattern (Fig 174) had begun to

reach the end of its productive life (Fig 176), it was

necessary to exchange it for a new tool This arbitrary

tool-changing strategy was at the discretion of the

op-erator, therefore it relied upon their past machining

experience to decide when it was advisable to instigate

the necessary down-time – for this tooling-related

ac-tivity An alternative approach, was to employ some

form of condition monitoring procedure, by utilising

off-line direct measurements to ascertain the amount

of wear that had occurred so far This assessment

ac-tivity entails a certain degree of operator competence

in a variety of disciplines, because the cutting tool’s

inspection required microscopical analysis by

metro-logical/metallographical techniques to determine the

current status of the tool’s cutting edge(s) This

tool-ing investigation necessitated that the tool be at rest and out-of-cut, so that its life could be correctly estab-lished, which can be a costly and time-consuming pro-cess, diminishing the cost-effectiveness of the overall production process

One machining strategy that can be used to over-come most production deficiencies, is to have some form of on-line, indirect system, which has the ad-vantages of being beneficial in terms of: improved running costs; enhanced component quality; and effi-ciency in production performance In order to achieve such beneficial tooling-related and part production enhancements, it is necessary to utilise some form of

‘on-line tool condition monitoring’ So that this tool

monitoring objective can be successful, a number of hard- and soft-ware activities must be undertaken, then integrated into a usable ‘workshop-hardened’ instrumental package In the early-to-mid 1990’s a novel approach to this problem, but also included the

some distinct refinements by: ‘on-line tool condition monitoring – using neural networks’ was developed by

Littlefair et al (1995) This fundamental and applied research work was fully-supported by a range of in-dustrial companies, it was later also installed at sev-eral widely-differing manufacturing companies In or-der to comprehend the complexity of such an on-line tooling related activities, the following case-study has been included (Littlefair, et al., 1995), as it succinctly describes the hard- and soft-ware issues that had to be overcome

9.11.4 Tool Monitoring Techniques –

a ‘Case-Study’

The technique of tool wear monitoring can be classi-fied in two distinct manners, these are by either:

• Direct monitoring – produce accurate results, but

they are difficult to fully-implement in a shop-floor environment,

• Indirect monitoring – considers various parameters

which change as a result of increasing tool wear The latter tool monitoring strategy was utilised in a single-point turning operation on a CNC turning cen-tre, by incorporating: tool force; vibration; and acous-tic emission; by being integrated into a neural network; and this theme will now be mentioned Each of these monitoring systems will be briefly described, plus the neural network – appropriate for complete sensor-fu-sion, will then be described

Tool – Force Monitoring

In single-point turning, if one ignores the orthogonal

cutting condition, then for oblique cutting three

re-actionary forces are experienced by the tool, termed:

tangential; axial; and radial force components (Fig

19a) The tangential force is generated due to the

workpiece’s rotation, this being by far the greatest of

the three forces An axial force component is the

re-sult of the applied feed force, while the radial force is

a function of, in the main, the inclination of the

ap-proach angle and to a lesser extent influenced by that

of the tool nose radius – this radial component being

the smallest of the forces Each of these component

forces in oblique cutting are influenced by a range of

factors, such as: workpiece material and its condition;

DOC; tool cutting insert geometry; and cutting data

utilised – speed and feed In this case, a

special-pur-pose holder for a platform-based dynamometer was

manufactured (Fig 261a)

Tool – Vibration Monitoring

In machining processes, the onset and subsequent

development of vibration orginates from the overall

dynamic behaviour of the tool-workpiece-machine

system The anticipated vibrational causes can be both

cyclic in nature – resulting from changes due to

com-pression and sliding of the workpiece material in the

shear zone, and, changes in the frictional conditions in

the contact zones – between the tool and workpiece

So that vibrational influences during continuous

cut-ting could be monitored, accelerometers tend to be

utilised Normally, accelerometers are situated as close

to the cutting edge as possible, usually at a convenient

position on the toolholder The vibration parameters

monitored are usually related to either the toolholder’s

natural frequency, or the frequency of chip

segmenta-tion Moreover, it is also possible to effectively utilise

that of a dynamometer’s ‘force signal’ for indirect

vi-bration monitoring

Tool – Acoustic Emission Monitoring

Acoustic emissions (AE) are those high-frequency

stress waves generated due to the spontaneous energy

release in materials undergoing: deformation; fracture;

phase transformations; etc Thus, AE signatures can be

divided into two distinct types: continuous –

contain-ing low-amplitude and high-frequency signals (i.e in

the range: 100 to 400 kHz); burst – containing higher

amplitude and lower frequency signals (i.e in the range: 100 to 150 kHz) By the application of Fourier transforms coupled to that of statistical analysis-based techniques, it is possible to utilise both of them for the analysis of AE signals The root-mean-square (rms) value has been shown to produce an increasing trend with increased amounts of tool flank wear, further, the combination of both skew and kurtosis of the AE signal will also indicate a correlation with flank wear rates

Tool – Sensor Fusion and Multi-sensor Integration

The application of multiple sensors can be effectively-employed in a complex tool-wear monitoring system for machining environments, to obtain harmonizing information about the turning production process This multi-sensor monitoring acts to reaffirm the ‘con-fidence factor’ , when dealing with the prospective di-agnostics from the single-point turning process How-ever, the exercise of utilising multiple sensors, entails integration and fusion of the sensory information, to extract the essential features from the data, by remov-ing the ‘redundancy’ present in this data In this re-gard, the application of artificial neural networks, can provide the solution to the sensor-fusion and auto-matic decision-making processes for this tool-condi-tion monitoring system

Artificial Neural Networks (ANN)

Artificial neural networks (Fig 260a), are composed of many simple processing nodes which operate simulta-neously These ANN’s mimic the functional behaviour

of biological neural network systems, allowing them

to be utilised to integrate and fuse information from multiple-sensor sources The functional behaviour

of the overall system is primarily determined by the pattern of connectivity of the nodes (Fig 260a) As a system, ANN’s are capable of performing some high-level functions, such as: adaptation; generalisation and target-learning These capabilities are particularly rel-evant for any form of tool-wear monitoring applica-tions The advantages of employing ANN’s to integrate and fuse data, are their inherent capabilities to: adapt

to instructed environments; robustness to noise; fault tolerance; simultaneous processing; and feasibility of on-line realisation (i.e via hardware implementation) Possibly the most widely used ANN and the one

reported in this section, is that of the ‘multi-layer per-ceptron’ type, which uses an ‘error-back-propagation