7 DISCUSSION

It is important to note that all of the samples tested for tensile strength, with the exception of two samples prepared with HMG B-72 adhesive, failed within the marble structure and not within or at the adhesive bond line. The two anomalies can be assumed to represent errors in the coupon preparation, though other factors yet unidentified may be at work including the lower viscosity of the commercial B-72 mixture or possible inconsistency of the solvent/copolymer ratio within the tube. All eight adhesive categories failed within the stress range of 4,317-4,688 kPa (626-80 psi) in tension, with the exception of the B-72 HMG adhesive group, which failed at higher stress (an average stress of 5,027 kPa (729 psi) if the two anomalies, which failed at the adhesive line, are dropped from the calculation). This latter set of results warrants further investigation, since the largest variation in results was within the two groups using commercially prepared B-72.

7.1 SHEAR AND TENSILE STRENGTH OF B-72

From the shear data, the B-72–acetone adhesive mixture appears unsuitable for marble-to-marble bonds where large shear forces might be present. On the other hand, the B-72–acetone barriers in shear and the B-72–acetone and B-72–toluene in tensile appear to function quite well. Clearly the B-72 marble-to-marble bonds, by themselves, are stronger under tensile loading conditions than the marble. The strength difference between the coated barrier bonds compared to those bonds formed by traditional structural adhesives is insignificant. This finding suggests that for tensile bond strengths there is little or no difference between the use of a structural adhesive (with or without a barrier coat) and B-72 used as an adhesive.

It is likely that the discrepancy between the shear strength of the B-72 as an adhesive and the shear strength of the bonds where B-72 was used as a barrier is not due to any interaction between either the epoxy or the polyester and the B-72 but rather results from the degree to which the B-72 layer had dried prior to the test. Solvent loss from the B-72 will be significantly slower within an adhesive joint compared to the same mixture when applied as a thinner coating and dried with the entire substrate surfaces exposed before bonding. The more solvent that remains in the B-72, the softer the material will be and the more “elastic in nature” it will appear since the solvent acts as a “plasticizer” and adds to the free volume of the polymer, resulting in a weaker bond line. We know, for example, that the choice of solvent, and certainly the retention of that solvent (based on factors such as volatility and rate of diffusion through the free volume of the polymer), can significantly lower the glass transition temperature (Tg) of a polymer compared with the bulk polymer (Horie 1987; Schilling 1989; Hansen 1994). For example, Selwitz (n.d.) reports that films cast from acetone have a higher Tg than those cast from a number of other solvents. Above some critical solvent content, the B-72 layer will cause the barrier or the bond line to act as a weak elastomer, stretching and eventually losing cohesive strength (Down 1984; Down et al. 1996).

An important point for the conservator to remember is that numerous variables come into play when preparing a real bond on a real sculpture. The tensile test coupons represented a 12.7 mm (0.5 in.) diameter bond surface, approximately 1.38 sq. cm (0.23 sq. in.), on low-porosity, relatively consistent marble types. Different substrates can have dramatic effects upon the bond strength as well as the reversibility. Higher open porosity of the bonded surfaces will lead to more absorption of either the solvent or the solvent-adhesive-barrier combination, which may change the strength of the bond. A larger bond area and a bond area with a more complex surface (such as a fractured marble surface) will impede the loss of solvent and dramatically increase the time needed to form a good, strong bond. In any case, it would be difficult and impractical, given the variety of sizes, complexities, and configurations of bonds, to determine with accuracy the point at which sufficient solvent loss has occurred and the bond has reached full strength. Although the authors intend to further test these variables, one suggestion does come forward. Given the evident tensile bond strength of B-72 with this particular type of marble, it may make good sense to coat both sides of the joint with B-72 and then, after sufficient drying time, to adhere the joint with an optional, non-solvent-based adhesive such as epoxy or polyester. The advantage of this method is that it ensures a full or sufficient loss of solvent from the B-72 barrier coatings while the joint substrates are fully exposed before the introduction of the second structural adhesive and before the mating or closing of the joint. Additionally, the 100% solid adhesive (such as epoxy) would assure the filling of any voids that might result from a less-than-intimate match of the two substrates to be bonded. A higher degree of reversibility is, in any case, maintained because of the barrier layer. Conservators should bear in mind that B-72 is a thermoplastic resin with the relatively low glass transition temperature range of 37-41�C (98.6-105.8�F) (Schilling 1989), and it may creep or cold-flow over time when the adhesive bond is under continual stress since creep is both temperature and stress dependent.5 This characteristic may be a concern even at midrange temperatures (18-24�C [65-75�F]) when the stress is maintained over decades.

7.2 CREEP AND COLD FLOW

All solids are elastic to some degree under stress. When that stress is high and/or when it is applied for extended periods of time, in the range of decades, some materials will break while others will become plastic. Materials presenting such plasticity may creep—that is, deform slowly under constant stress. When creep occurs at room temperature, it is normally called “cold-flow” (Skeist 1977, 101). Equally, all thermoplastic amorphous polymers or the amorphous parts of semicrystalline thermoplastic polymers (which can range from 40% to 70% of the polymer structure) are susceptible to creep under the influence of temperature (particularly rising above the polymer's Tg range) or stress (particularly over long time frames). Although it is commonly assumed that B-72 will not creep or cold-flow, very little verifiable testing of the copolymer has been done in this area, particularly looking at the copolymer as an adhesive and under continual stress levels expected of an adhesive. Most polymers are viscoelastic to some degree, however, and most viscoelastic solids show time-dependent deformation even at low stresses and temperatures below their Tg. Recent research has shown that some polymers, such as polymethyl-methacrylate, undergo strain hardening, which increases the polymer's resistance to plastic deformation (creep) after the initial yield (Crist 1993). However, no direct measurements of B-72 have been done to evaluate the contribution of these phenomena to its resistance or susceptibility to creep. Applications of Plexiglas in commercial glazing recognize design limits to avoid permanent deformation (creep) over a long time due to the weight of the Plexiglas sheet (Luskin 1983-84).

Susceptibility to creep is determined by a number of factors including the polymer's Tg. The lower the Tg, the more likely the polymer is to deform under normal conditions (serviceable loads at room temperature over a time frame of years or decades). The closer a polymer comes to its Tg, the more elastic it becomes. The softening of a polymer at its Tg is due to long-range segmental motions of the polymer chain, twisting and repositioning to accommodate stress, which in turn is dependent upon the stiffness of the polymer backbone as well as the presence and nature of pendant groups. In this second-order transition there is an increase in the polymer free volume, the ratio of which is normally around 0.025 at the Tg, but this ratio can also be greatly influenced by plasticizers or the presence of solvents. Over time, polymer chains can also reorder, leading to a change in the polymer's Tg as well as its strength and susceptibility to creep. Helical jumps in the polymer chain have been reported over time that can lead to mechanical relaxation which, in turn, can lead to chain diffusion between crystalline and amorphous regions, ultimately resulting in creep (Schmidt-Rohr and Richert 1999). To avoid these various movements and increases in elasticity, adhesives used for structural joints are often chosen for their high Tgs, which are considerably higher than room temperature. This characteristic also avoids differences in the linear coefficient of thermal expansion between the polymer (as it reaches its Tg) and the substrate. Araldite AY 103 with 956 hardener has a Tg of 83�C (181�F), and Akemi polyester has a Tg of 68-76�C (156-70�F). By comparison, B-72 has a Tg of 37-41�C (98.6-105.8�F). Although some epoxies such as Hxtal NYL, Araldite 2020, and Fynebond have Tgs closer to B-72 (40-45�C, 40-46�C, and 44-48�C, respectively), these are not commonly used in the conservation of large-scale sculpture, and some, such as Araldite 2020, are not commercially available in the United States.