Non-Destructive Techniques Based on Eddy Current Testing

2.1. Electromagnetic Induction and Eddy Current Inspection

Every coil is characterized by the impedance parameter Z₀, which is a complex number defined as in Equation (1) and which represents the voltage-current ratio (V₀/I₀) for a single frequency sinusoidal excitation f. Impedance Z₀ has a magnitude |Z| and a phase φ:

When an alternating current energizes a coil, it creates a time-varying magnetic field. The magnetic lines of flux tend to be concentrated at the center of the coil. Eddy current inspection is based on Faraday’s electromagnetic induction law as demonstrated in Equation (2). Faraday discovered that a time-varying magnetic induction flux density induces currents in an electrical conductor. The electromotive force ε is proportional to the time-rate change of the magnetic induction flux density Φ_B:

When an alternating energized coil of impedance Z₀ approaches an electrically conductive non-ferromagnetic material, the primary alternating magnetic field penetrates the material and generates continuous and circular eddy currents. The induced currents flowing within the test piece generate a secondary magnetic field that tends to oppose the primary magnetic field, as shown in Figure 1. This opposing magnetic field, coming from the conductive material, has a weakening effect on the primary magnetic field. In effect, the new imaginary part of the coil impedance decreases proportionally when the eddy current intensity in the test piece increases [12]. Eddy currents also contribute to the increasing of the power dissipation of energy that changes the real part of coil impedance. Measuring this coil impedance variation from Z₀ to Z_c, by monitoring either the voltage or the current signal, can reveal specific information such as conductivity and chemical composition of the test piece [13].

2.2. Complex Impedance Plane

This subsection describes the coil impedance changes that occur when a coil probe interacts with materials and presents the normalized impedance plane. When there is no test piece close to the coil sensor, its impedance Z₀ is a complex value, as Equation (3) shows:

When a conductive test material approaches the energized coil probe, eddy currents appear on the test piece. Eddy currents create a secondary field that interacts with the primary field. As a result, the new impedance is Z_c as Equation (4) demonstrates:

Coil impedance is a two-dimensional variable, and the real and imaginary parts can be represented on an impedance plane. The X-axis plots the real part of impedance, and the Y-axis represents the imaginary part. Real and imaginary impedance parts of Z_c can be redefined as R_cn and X_cn to obtain the normalized impedance as Figure 2(a) shows [12,15]. Equation (5) indicates the transformation:

The normalized real part of the new impedance R_cn is 0 when there is no change in the real part of the impedance. R_cn is divided by the imaginary part of the impedance X₀ when there is no metal near the sensor. X_cn represents the number of times that the new imaginary part of Z_c is bigger or smaller than the imaginary part when there is no target X₀. To summarize, this transformation means that when there is no test piece near the coil the new impedance values become R_cn = 0 and X_cn = 1. This point is called “air point” P₀.

2.3. Eddy Current Transformer Model

The transformer model of Figure 4 presents a diagram of the basic probe-flaw interaction. Some authors such as Placko et al. and Peng et al. have proposed this model to explain what occurs when the space between a coil probe and a test piece varies [12,16]. The primary circuit, whose impedance is the ratio $Z_c=\frac{U}{I}$, represents the coil sensor. The secondary circuit represents the test piece. The real impedance R_e represents the resistance of the loops described by the flow of eddy currents. The resistor R_e is consequently proportional to the resistivity of the test piece. The imaginary term jI_m represents the leakage inductance of the circuit. Finally, the coupling coefficient k is linked to the distance between the sensor and the test piece. The coefficient k decreases when the distance increases.

The following Equations (6) and (7) are obtained from Kirchhoff’s Voltage Law to describe the transformer in Figure 4:

When there is no test piece near the coil sensor, the coupling factor k is zero and the measured impedance is Z₀ of the primary circuit as presented in Equation (1). When a conductive test piece is approached, the complex impedance of the primary circuit becomes Z_c as formulated in Equation (8):

The inductance and resistivity of the primary circuit can be identified from Equation (8) as demonstrated in Equations (9) and (10) respectively. The equivalent inductance L decreases due to the induced eddy currents. In contrast, the resistivity increases:

From Equation (8) the normalized real and imaginary parts of impedance R_cn and X_cn are presented in Equations (11) and (12) [12,16]:

Assuming that I_m, R_e and L₁ do not depend on the distance between the sensor and the target, the lift-off line for a fixed frequency in the normalized impedance plane can be plotted when the coupling factor k changes.

2.4. Magnetic Field Sensors for Eddy Current Testing

These non-destructive techniques need to pick up the magnetic flux from eddy currents. Many important developments have been made in magnetic sensors during the past 60 years [17]. Novkovski has researched the recent progress of state-of-the-art magnetic field sensors such as inductive coils, fluxgate magnetometers, proton precession magnetometers, superconducting quantum interference devices SQUID, Hall effect devices and magnetoresistors [17]. Nowadays, the trend in magnetometer development is toward miniaturization, and researchers are looking for new ways to reduce the size of these sensors. Section 4 reviews the most common, state-of-the-art sensors used in eddy current testing.

The magnetic field is the result of distributed currents and the distribution of ferromagnetic materials around the sensor [17]. In regions where no currents flow, the induction field is the gradient of a potential V that satisfies Laplace’s Equation (13) [18]:

Some authors such as Backus consider a two-dimensional vector field B defined in some open subset V = V(z) = V(x, y) of the Euclidean plane where z = x + iy [19]. The field B has real and imaginary components, as Equation (14) demonstrates:

Determining the real and imaginary components of B has several applications. For instance, by measuring the field on a grid of points, it is possible to reconstruct the currents [17]. This is an inverse problem which is solved in many non-destructive tests [17].

2.5. Elements of a Basic Inspection System

Figure 5 presents a block diagram of analog eddy current equipment. It includes a single tone generator which energizes the test coil sensor. Phase, frequency and amplitude can be adjusted to optimum parameters for the test pieces. When a crack occurs, the coil impedance experiences a change. The defect signal modulates the tone from the oscillator. A quadrature amplitude demodulator extracts the defect signal caused by the impedance variation. The demodulator outputs are X-axis and Y-axis signals. Each component represents the real and imaginary parts of the impedance respectively. These signals can be filtered and analyzed.

The voltage signals, which represent the impedance changes in the inspection coil, can be displayed on a XY plot. Figure 6 illustrates a typical loop of an impedance plane on a XY plot when a flawed tube is inspected using a differential coil probe. Most eddy current systems permit configuring of alarms on an XY plot to distinguish between flawed or unflawed test pieces. Alarm events can activate analog or digital outputs. In addition, modern eddy current equipment usually has digital inputs such as test piece presence or encoder connectors to start testing or to measure the speed of inspected bars or tubes respectively.

3.1. Electrical Conductivity of the Test piece

Materials have a characteristic resistance to the flow of electricity which is characterized with the magnitude electrical conductivity σ or its inverse resistivity $\rho =\frac{1}{\sigma }$. Conductivity is crucial in eddy current inspection.

Highly conductive materials such as cooper and aluminum create intense eddy currents and have two advantages over less conductive materials. First, cracks generate higher signal levels, as the impedance plane in Figure 2(a) illustrates. In addition to that, the phase lag between the flaws and lift-off line is larger when highly conductive materials are tested, that is φ₁ > φ₂ as Figure 2(a) shows. The disadvantage of highly conductive materials is that the standard penetration depth is lower at a fixed frequency than in lower conductive materials such as steel and stainless steel. Factors that exert an influence in conductivity are the temperature of the test piece, the alloy composition and the residual stress, which is related to the atomic structure.

Many authors have measured residual stress using eddy current techniques. Coils can detect very small stress variations in ferromagnetic steels due to the magneto-elastic effect [20]. Stress can be measured based on the changes in the impedance of an electromagnetic coil as Figure 7(a,b) shows [21]. The impedance change occurs due to variations in the electrical conductivity and the magnetic permeability of the test piece.

Heat treatments cause variations of hardness, which are related to conductivity, as Figure 8 illustrates. Eddy currents can detect when pieces have received a heat treatment as well as the severity of the treatment. The eddy current testing can also characterize grain size changes after thermal treatment based on conductivity and magnetic permeability changes [22]. As Figure 9 shows, the hardness is inversely proportional to the grain size [22].

Some authors have published papers related to the conductivity of the test piece, as it is one of the most important variables in eddy current testing. Shao et al. presented a method for the reconstruction of conductivity profiles from eddy current impedance change data [24]. This is an inverse problem which solves the conductivity profile of the material from the electrical signal obtained in the eddy current inspection. On the other hand, other authors such as Uzal et al. have published numerical and analytical methods for computing the coil impedance when arbitrary radial conductivity changes occur in the test piece [25].

3.2. Magnetic Permeability

Magnetic permeability μ is a number that quantifies the degree of magnetic induction B of materials when a magnetic field H is applied, as shown in Equation (15):

Magnetic permeability μ is a scalar in isotropic mediums. Free space has a characteristic permeability constant μ₀. In many instances, the permeability of materials is expressed as relative permeability μ_r in respect of free space μ₀ as Equation (16) shows:

Materials can be classified by their magnetic properties which strongly affect the eddy current testing. The most common classification of materials depending on their magnetic response is presented below:

• Firstly, paramagnetic materials, such as aluminum, are softly attracted to magnetic fields and, hence, have a relative magnetic permeability slightly greater than one, μ_r ≥ 1.

• Secondly, diamagnetic materials like copper and lead create a magnetic field in opposition to an externally applied magnetic field, thus causing a softly repulsive effect. Magnetic permeability is less than μ₀; therefore, the relative permeability is a bit less than one, μ_r ≤ 1.

• The third group of this classification is formed by ferromagnetic materials such as iron, nickel, cobalt and some of their alloys. These materials are strongly attracted by magnetic fields and concentrate the flux of magnetic fields. Their relative permeability is much greater than one μ_r ≫ 1. One hundred or two hundred are typical values of relative permeability.

Figure 10 shows two magnetization curves of unannealed and annealed steel and plots the relation between B and H fields [26]. The relationship between H and B is not linear and presents hysteresis in ferromagnetic materials. The curve may be divided into two parts divided by the knee of the curve. The first part of the curve has the greater slope, and the second part has the smaller slope [27]. Saturation state is reached when the increase of H causes very little increase in B, as Figure 10 indicates.

High magnetic permeability makes the standard penetration depth decrease. In order to compensate for this effect and explore the material internally, ferromagnetic materials are inspected at lower frequencies than non-ferromagnetic ones.

Ferromagnetic materials have a characteristic property, which is a high permeability variation that presents particular difficulties when testing eddy current flow [28]. The following subsection explains this phenomenon.

3.3. Lift-Off

The lift-off is the impedance change that occurs when there is variation in the distance between the inspection coil probe and the test piece. The lift-off variations can be caused by varying coating thicknesses, irregular sample surfaces or the operator’s movements [31]. The magnetic field is stronger close to the coil, so lift-off is stronger near the probe. In many applications, eddy current measurements are adversely affected by lift-off [32]. Lift-off is considered a noise source and it is undesirable in defect detection. Lift-off could occur in the same direction as the crack, thereby concealing the crack response. Therefore, the distance between the probe and metal must be as constant as possible in order to avoid lift-off.

At the normalized impedance plane of Figure 11, the lift-off curves start at the air point (0,0), when there is no test piece. In this case, air point is (0,0) instead of (0,1) as discussed in the previous section because a different transformation in the Y-axis has been used as shown in Equation (17). Air point corresponds to X_c = X₀ and therefore the normalized imaginary part is null X_cn = 0:

Figure 11 plots lift-off lines in steps of 0.1 mm. The impedance values are plotted using triangles. In some cases, when measuring the thickness of non-conductive coatings over metal, lift-off is employed as a useful property. Figure 11 demonstrates that when the test piece is closely adjacent to the coil probe, the triangle separation is larger than when the test piece is further away. This means that the resolution to measure non-conductive coatings is greater for thin coatings [33].

Lift-off is explained using a coil whose axis is normal to the test piece. However, lift-off also occurs when the test is conducted using encircling probes. The vibration of the rod or the tube inside the probe generates noise which presents difficulties in conducting inspections. Some authors including Theodoulidis et al. were conscious of lift-off testing tubes. They presented an analytical model of wobble in heat exchanger tube inspection with bobbin coils [34]. Figure 12 illustrates the offset position of the tube inside the bobbin coils.

There are methods for lift-off compensation when eddy currents are used in order to detect cracks and lift-off becomes an undesired variable. For instance, Yin et al. researched dual excitation frequencies and coil design to minimize the lift-off effect [32]. Research into processing data is also conducted, with a view to minimizing the lift-off effect. Lopez et al. proposed the use of wavelets to remove eddy current probe wobble noise from steam generator tubes [35]. Reduction of the lift-off effect has also been attempted by optimizing the coil design [36] and sensor array.

Authors such as Gui Yun et al. have researched the reduction of lift-off effects via normalization techniques [31]. The technique can be applied to the measurement of metal thickness beneath non-conductive coatings and to the measurement of microstructure and strain/stress, where the output is highly sensitive to the lift-off effect. They proposed an approach using two reference signals calculated in two stages as Figure 13 shows.

The first stage was aimed to reduce the lift-off effect and used the first reference signal y_air (n) obtained when the probe was in the air. By doing so, they created a newly derived defect signal $y_x^{\prime }(n)$ that was relatively free of lift-off variation as Equation (18) shows:

The second stage was to work out the crack information. They used a second reference signal y_ref (n), which was obtained from a good sample part. They also derived the normalized reference signal ${y^{\prime }}_{\mathit{ref}}(n)$ as Equation (19) shows:

Finally, a new differential signal was worked out as Equation (20) indicates. The authors obtained a significant lift-off reduction:

3.4. Fill Factor

Fill factor is a number which measures how well the test piece fills the coil in external encircling probes. It can be calculated as Equation (21) demonstrates:

Fill factor is the ratio of the cross sectional area of the test piece and area of the coil section. It is necessary that the coil wires be as close as possible to the test piece, in order to have a greater response potential to cracks. In other words, it is desirable for the fill factor to be as near as possible to unity. For the internal inspection of tubes, a probe is introduced using a guidance system. The fill factor is redefined as follows in Equation (22) where it also demonstrates the desire that is nearer to one:

3.5. Edge Effect

Edge effect is a phenomenon that occurs when an inspection coil is at the end of the test piece. In these instances, eddy current flow is distorted as currents cannot flow at the edge. So, in order to avoid the confusion with flaws, inspection is limited near edges. The distance where the edge effect is present is from approximately one to three times the diameter of the inspection coil in the case of encircling probes. So a reduction in coil size reduces the edge effect, although there is a limit, as the diameter of external encircling coils must be higher than that of the inspected materials.

Some authors have specifically addressed the edge effect in their research. For instance, Theodoulidis et al. proposed a model to calculate the quasi-static electromagnetic field of a cylindrical coil in the vicinity of the edge of a metal block [37]. The authors obtained some analytical expressions of fields that provided a better understanding of the edge effect and formed the basis of a procedure for solving a whole class of edge related problems.

3.6. Frequency and Skin Effect

Frequency inspection in eddy current testing is crucial to detecting flaws. When fixing a frequency, the initial coil impedance Z₀ is adjusted. When inspection frequency f is increased, the imaginary part of the impedance is increased as Equation (23) demonstrates:

Eddy current flow is not uniformly distributed throughout the entire volume of test pieces. Current flow is stronger at the surface, decreasing exponentially by increments in relation to the distance from the surface. Assuming that the current density flowing along X axis, Equation (24) represents this current flux:

Standard penetration depth depends on electrical conductivity, the magnetic permeability of the test material and on the eddy current frequency. Standard penetration depth is lower as conductivity, permeability or inspection frequency increase. The penetration depth can be calculated as Equation (27) expresses [38]:

Equation (27) demonstrates that low frequency tests increase the standard depth of penetration and are more suitable for inspecting subsurface flaws. Some authors have researched the detection of subsurface defects, including Ramos et al. regarding the characterization of depth profiles of subsurface defects in aluminum plates [38].

Skin effect is also a limiting factor of increasing frequency as desired. The thickness of the inspected material must be two or three times the standard depth of penetration to prevent the eddy current flow from appearing on the other side of the test piece.

Typical inspection frequencies in eddy current testing are in the range of 100 Hz–10 MHz. Most authors such as Ditchburn et al. [39] and Thollon et al. [15] use this range. However, a few authors such as Owston use higher frequencies. Owston described a high frequency eddy-current apparatus working at 25 MHz for detecting surface defects and thin metallic coatings [40].

Low frequency tests are commonly used in the inspection of ferromagnetic materials to compensate for their high permeability and penetrate into the test piece. On the other hand, the inspection of small discontinuities occurring in the near-surface region is recommended at high frequency to maximize eddy current flow at the surface.

Skin effect and other parameters such as the crack morphology and crack position with respect to the surface determine a band of operating frequencies where the cracks are detectable. At the optimum frequency of testing, the crack sensitivity reaches the maximum.

3.7. The Phase Lag

The phase lag is the parameter that permits the user to obtain information regarding the depth of a defect within a material. The phase lag is represented by the term $\phi =-\frac{z}{\delta }$ in Equation (29) [38].

The phase lag represents the shift in phase between the defects on the surface and defects at z distance from the surface:

The phase lag depends linearly with depth z. When the defect is at one standard depth of penetration z = δ, the phase lag φ is φ = 1 radian ≈ 57°. When it is at two standard depths of penetration z = 2δ, the lag occurs at φ = 2radian ≈ 114° with respect to surface cracks. As a result, the phase lag can be used to determine the depth of subsurface defects. Using the complex impedance plane, the lift-off line can be taken as a reference phase as it occurs on the surface. Flaw direction can be measured with respect to the lift-off phase. It is desirable to have phase resolution between the lift-off line and cracks.

3.8. Signal-to-Noise Ratio

The signal-to-noise ratio (SNR) is a parameter that quantifies the number of times that the signal amplitude from the response to a crack is greater than the signal amplitude of the background noise. Noise sources limit eddy current testing. Some of the main noise sources in eddy current testing are temperature variations, lift-off, changes in the electromagnetic properties of the material such as conductivity or magnetic permeability and changes in test speed. Some methods for maximizing the SNR are listed below.

The simplest way to increase the SNR is to amplify the signal level. However, amplifiers increase the noise level and introduce their own noise. Therefore, there is a limit to the number of amplification stages that can be applied.

Another way to minimize noise is filtering. Filtering is possible if the perturbation is not in the pass band of the desired signal. Also, if there is phase difference between defects and the noise source, then phase discrimination techniques can be applied.

In addition, some types of coil probes are less influenced than others by some noise sources. For instance, self-compensated differential coil probes are less sensitive to small variations in diameter, conductivity or magnetic permeability than absolute coil probes. In some instances, copper shields cover the probes to decrease the pick-up noise from external sources; therefore, they increase the signal to noise ratio.

Coil size is also crucial in order to obtain a high-level signal for crack detection. It is crucial that the fill-factor is close to one in the case of encircling coil probes, and it is also crucial that the coil size is similar to the crack size. Some authors such as Grimberg et al. [54] take the coil size into account.

Another technique used to maximize the SNR is magnetization. As explained in the previous section, direct current magnetization minimizes the effect of permeability variations in ferromagnetic materials.

The last proposed method to improve the SNR is the selection of the most suitable sensor, as every sensor has limitations in sensitivity and noise level. In some applications, the magnetic field levels are so low that standard coil probes cannot be used to detect them. In these instances special magnetometers such as superconducting quantum interference devices (SQUID) are sensitive to extremely low field levels. SQUIDs have been used in eddy current testing for 30 years [55]. However, the disadvantage of SQUIDs is that they require a cryostat to maintain them at very low temperatures.

3.9. Equivalence Model of Eddy Current Coil Sensors for Applications

This subsection presents a review of the equivalence model of eddy current sensors and its relation to applications. Eddy current testing uses the electromagnetic properties of materials that depend on their composition, microstructure and the applied and residual stresses [22]. These properties are measured via the impedance Z_c described in Section 2, which is a function of lift-off, target conductivity σ, target magnetic permeability μ and the eddy current frequency f as Equation (31) shows:

Some authors such as Tian et al. have researched the influence of the heterogeneity of the test piece in eddy current sensors [28]. When measuring one of these variables, such as lift-off, in Equation (30), conductivity σ and permeability variations of the test piece are noise sources that influence the test. When frequency f is high enough, the approximation shown in Equation (31) can be done [28]:

Increasing the excitation frequency can suppress the influence of the non-equalization of the conductivity of the test piece R_e as R_e ≪ ωL₁. The heterogeneity in non-ferromagnetic metals such as aluminum and copper due to conductivity variations is much lower than that in ferromagnetic metals, since the conductivity for aluminum and copper is much smaller than those of steel and cast iron which allow the approximation of R_e ≪ ωL₁ to be more true.

The effect of magnetic permeability heterogeneity in non-ferromagnetic targets is much less than the heterogeneity of ferromagnetic targets. The measuring accuracy of non-ferromagnetic targets can be higher than that of ferromagnetic targets.

With regard to microstructure, Mercier et al. used eddy currents to evaluate steel decarburizing in the austenitization process [8]. Decarburizing can change the microstructure and the mechanical properties of steel. Changes in electrical conductivity and magnetic permeability occur in the decarburized surface.

Zergoug et al. analyzed the relation between mechanical micro-hardness and impedance variations in eddy current testing [22]. The characterization of the microstructure modifications due to heat treatment and corrosion by eddy currents permitted the measuring of mechanical and metallurgical parameters of materials.

In ferromagnetic materials, the use of a low frequency provides a good impedance resolution. The most significant result in the case of ferromagnetic materials characterization is the relationship between the electric and magnetic parameters and the hardness and the grain size. The hardness is inversely proportional to the grain size.

Schoenekess et al. detected tensile stress alterations in prestressing steel using eddy current testing [56]. Changes in mechanical stress shift the electrical conductivity and magnetic permeability of the material and are always very small, typically less than 1% [57]. Temperature compensation of the entire measurement system was absolutely necessary to minimize measurement errors.

4.1. Coil Probes

Coil probes are the most widely used sensors in eddy current inspection. This subsection presents a discussion regarding different coil probe types, the most important parameters in coil probes and the circuitry used to pick up signals.

4.2. Magnetoresistive Sensors

Magnetoresistive sensors are magnetic field transducers that exhibit a linear change in electrical resistance under an external magnetic field [67]. Magnetoresistive sensors are highly sensitive and accurate, but the main disadvantage of them is the high temperature coefficient [17]. Germano et al. presented transference curves for two types of magnetoresistive sensors: spin-valve (SV) and magnetic tunnel junction (MTJ) sensors [67].

SV magnetometers are spin-valve transistors used as magnetic field sensors and have a ferromagnet–semiconductor hybrid structure [17]. The magnetic tunnel junctions are based on a spin dependent tunneling effect [17]. Two transfer curves of these magnetoresistive sensors are shown in Figure 27, which demonstrates that resistance decreases when the field strength increases.

Magnetoresistive sensors can be used in non-destructive evaluation to detect the secondary field from eddy currents. Some researchers such as Ramos et al. [38]. and Yamada et al. [68] use these types of sensors Yamada et al. used an SV-GMR sensor whose operating range of magnetic field density was from nT to mT. The sensor provided high sensitivity over frequencies up to 100 MHz and high spatial resolution due to the minizaturation [68].

4.3. Hall-effect Sensors

Hall-effect sensors can detect magnetic fields from eddy currents and can be used in eddy current testing. Hall voltage is proportional to the current flowing through the conductive rectangle and the magnetic induction perpendicular to the conductor as Figure 28 shows. The Hall devices are used mainly in the mT range and can be easily miniaturized and integrated within microelectronic circuits [17]. Their disadvantages are their limited sensitivity to silicon, the high level of 1/f noise and the relatively large offset [17].

Some authors such as Jongwoo et al have researched eddy current testing using Hall-effect sensors. They presented a quantitative eddy current evaluation of cracks on austenite stainless steel using a Hall-effect sensor array [69].

Other researchers such as He et al. tested the use of a differential hall probe to detect defects in the riveted structures of aircrafts [50]. The hall response signals were disturbed by noise, which leads to inaccuracy in detecting the defects. They used an averaging method and wavelet de-noise method to process the Hall responses [50].

Paasi et al. presented a three-axis Hall sensor magnetometer for the testing of superconductor homogeneity to measure the three components of the magnetic fields from eddy current flow [70]. The three-axis Hall sensor provides increased sensitivity when compared to classical Hall sensor techniques that measuring only one (usually vertical) component of the field.

4.4. SQUID Devices

Superconducting quantum interference devices (SQUIDs) are very sensitive magnetometers designed to measure extremely weak magnetic fields. SQUIDs are based on superconducting loops that contain Josephson junctions [17]. SQUIDs are sensors that can measure extremely low magnetic induction levels. The disadvantage of these types of sensors is the need for cryogenic refrigeration in order to decrease noise levels to the range of $\text{fT}/\sqrt{\text{Hz}}$ that limit their use in many applications.

SQUIDs have been used in eddy current testing since the 1980s [55]. In conventional eddy-current systems, where the magnetic field produced by the eddy currents is detected by means of an induction coil, the typical field noise is about $1 \text{nT}/\sqrt{\text{Hz}}$ at eddy current frequencies of about 100 kHz. In some cases, this field noise is too high for certain applications such as the detection of tiny oxide particles, especially if the test materials are highly conductive, such as copper or aluminum. In these instances, SQUID magnetometers must be used instead of coil probes.

Some authors have researched eddy current testing using SQUIDs. For instance, Muck et al. tested various materials and obtained a much higher sensitivity than conventional eddy current evaluation and ultrasonic testing [71]. Others such as Ruosi et al. presented their experimental and numerical detection results of surface and subsurface artificial features in Al-Ti planar structures [72].

The combination of high sensitivity, even in unshielded environments, high spatial resolution and flat frequency response up to 1 MHz offered by SQUIDs mean that they are powerful sensors for eddy current evaluation [72].

4.5. Comparison of Different Probe Structure and Magnetic Sensors

There are some parameters, including the magnetic field range, the operating frequency band and sensor dimensions that permit the selection of the most suitable sensor type for eddy current testing [68]. In this subsection, a comparison of different probe structures and magnetic sensors is presented.

Coil probes provide high sensitivity to defects when the flaw size is comparable with the coil transducer [54]. Short and small diameter encircling coil probes provide higher sensitivity to small cracks than long and big diameter probes. Grimberg et al. took this relationship between coil size and sensitivity into account and proposed a method for reconstructing the flaw in order to determine the crack’s depth [54]. The disadvantage is that the coil sizes must adapt to the size of the tubes or bars being produced.

Coil probes provide high sensitivity to defects when eddy current flow is drastically changed. This means that encircling coils are optimized for detecting short discontinuities parallel to the axis of the inspected tubes or bars. Differential encircling probes only detect discontinuities when a long crack that is parallel to the major axis enters and leaves the probe.

To detect long discontinuities over their full length, pancake-type rotating probes are designed. They are able to detect as small as 50 μm. Pancake-type probes scan smaller areas than encircling coils which means the pancake-type probes are more sensitive [73].

Automatic scanning is widely used in production lines. Automatic inspection using pancake-type probes is complex, because they require rotating systems. The automatic scanning using encircling probes is simpler than using pancake-type probes because they are static. Encircling probes provide more control over production quality at very high speeds up to 150 m/s.

Segment coil probes are specifically designed for controlling the weld seam of welded pipes [59]. The sensitivity of segment probes is higher than encircling probes as they limit the scanning surface to the weld area, whereas encircling probes can scan 360 degrees.

Horseshoe-shaped coils are useful in the detection of laminar flaws that pancake-type coils cannot detect. Spiral coils provide high sensitivity and arrays of coils permit high-speed inspection and obtain high space resolution, reducing the coil size [62].

In general, the advantages of using coils as sensors for the eddy currents are the simplicity of their construction, the huge dynamic range and the possibility of focusing the sensor [48]. Some disadvantages are the high induction voltage at the start of the signal [48] and the fact that they are difficult to make smaller [17].

Other magnetometers can be used instead of pick-up coils. Hall sensors are magnetic-field sensors whose dynamic range is not large enough for some applications [48]. SQUIDs are difficult and expensive [48], although they provide very low field noise to the range of $\text{fT}/\sqrt{\text{Hz}}$ when compared to induction coils that have field noise of about $1 \text{nT}/\sqrt{\text{Hz}}$ [55]. Many authors find the structure and characteristics of magnetoresistive sensor attractive for non-destructive evaluation because of their micro size, high frequency operation and high sensitivity [68].