Search
Use the search bar or filters below to find any TAPPI product or publication.
Filters
Content Type
Publications
Level of Knowledge
Committees
Event Type
Collections
Journal articles
Predictive advisory solutions for chemistry management, control, and optimization, TAPPI Journal March 2025
ABSTRACT: Process runnability and end-product quality in paper and board making are often connected to chemistry. Typically, monitoring of the chemistry status is based on a few laboratory measurements and a limited number of online specific chemistry-related measurements. Therefore, mill personnel do not have real-time transparency of the chemistry related phenomena, which can cause production instability, including deposition, higher chemical consumption, quality issues in the end-product and runnability problems. Machine learning techniques have been used to establish soft sensor models and to detect abnormalities. Furthermore, these soft sensors prove to be most useful when combined with expert-driven interpretation. This study is aimed at utilizing a hybrid solution comprising chemistry and physics models and machine learning models for stabilizing chemistry-related processes in paper and board production. The principal idea is to combine chemistry/physics models and machine learning models in a fashion close to white box modeling. A cornerstone in the approach is to formulate explanations of the findings from the models; that is, to explain in plain text what the findings mean and how operational changes can mitigate the identified risks. The approach has been demonstrated for several different applications, including deposit control in the wet end, both raw water treatment and usage, and wastewater treatment. This approach provides mill personnel with knowledge of identified phenomena and recommendations on how to stabilize chemistry-related processes. Instead of using close to black box machine learning models, a hybrid solution including chemistry/physics models can enhance the performance of artificial intelligence (AI) deployed systems. A successful way of gaining the trust from mill personnel is by creating a plain text explanation of the findings from the hybrid models. The correlation between the likelihood of a phenomena and disturbance and the explanations are derived and validated by application and chemistry and physics experts.
Journal articles
Colloidal silica and its effects during formation of paper sheets in the presence of nanofibrillated cellulose, cationic starch, and cationic acrylamide copolymer, TAPPI Journal May 2025
ABSTRACT: This work considered effects of colloidal silica addition during laboratory preparation of paper sheets containing nanofibrillated cellulose (NFC) that had been pretreated with cationic starch. The emphasis was on process performance issues, including dewatering rates, fine particle retention, and the extent of fiber flocculation. In addition, micrographs were obtained to show what was happening to the NFC upon treatments with cationic starch and subsequent application of hydrodynamic shear. Contrasting results were obtained, depending on the charge density of the cationic starch. Pretreatment of the NFC with a high charge density cationic starch (degree of substitution 0.2) resulted in strong interactions with the colloidal silica, enhancing the dewatering rate and contributing to fine-particle retention. The medium charge cationic starch pretreatment led to effects suggesting a bridging mechanism of action, and subsequent colloidal silica had no significant effect on dewatering. Treatment of that system with a high level of colloidal silica (0.2%) resulted in lower retention. In general, the final colloidal silica treatments tended to decrease the level of flocculation in the suspensions, giving more uniform handsheets. Mechanisms, some of them related to the clustering and dispersion of cationic starch-treated NFC, were proposed to account for the observed effects.