System and method of dynamic corrective enzyme selection and formulation for pulp and paper production
Systems and methods as disclosed herein automatically provide real-time dosing corrections for an industrial process wherein enzyme blends are applied to natural fibers for pulp/paper production. An initial enzyme blend (e.g., enzymes and supporting formulation components, as relevant) and respective dose rates are selected to be applied based on expected fiber surface substrate characterization, expected fiber quality characterization, the physical conditions of the system being treated, respective characteristics of the initially selected enzyme blend components, etc. Upon application of the initial enzyme blend, online sensors provide real-time feedback data corresponding to measured actual values for the fiber surface substrate characterization and fiber quality characterization. A replacement enzyme blend (enzymes and supporting formulation components) and respective dose rates thereof is dynamically selected based on the feedback data. The enzyme dosing stage can be optimized responsive to product changes and/or variations in fiber sources/blend and/or physical conditions, substantially in real time.
1. A method of automatically providing real-time dosing corrections for an industrial process wherein one or more enzymatic compositions are applied to natural fibers for producing a pulp or paper product, the method comprising:
for each of a plurality of pulp or paper products, developing predictive machine learning models by observing correlations over time between outcomes, associated with fiber surface substrate characterization and fiber quality characterization for the respective pulp or paper product, and various combinations of process inputs, comprising characteristics of a respective enzyme blend;
for a particular pulp or paper product to be produced, using an associated model to select an initial enzyme blend to be applied, and respective dose rates for one or more components thereof, based at least in part on input data comprising an expected fiber surface substrate characterization for the pulp or paper product, and an expected fiber quality characterization for the pulp or paper product;
upon application of the initial enzyme blend and respective dose rates for the one or more components thereof, providing real-time feedback data comprising measured values corresponding to an actual fiber surface substrate characterization and an actual fiber quality characterization; and
dynamically selecting a replacement enzyme blend, and respective dose rates for one or more components thereof, based at least in part on the feedback data; and
applying the selected replacement enzyme blend in place of at least a portion of the initial enzyme blend during the industrial process.
2. The method of claim 1 , wherein the initial enzyme blend to be applied and the respective dose rates are selected further based on expected values for one or more industrial process characteristics, and the real-time feedback data further comprises measured values for the one or more industrial process characteristics.
3. The method of claim 2 , wherein the real-time feedback data further comprises measured values for industrial process characteristics comprising one or more of a temperature, a system flow rate, a pH value, a conductivity value, an ORP value, a biocide residual value, and a residence time.
4. The method of claim 1 , wherein the method further comprises selectively altering the predetermined model based at least in part on the provided real-time feedback data.
5. The method of claim 1 , further comprising:
blending the one or more components of the initial enzyme blend in accordance with a first overall dose rate, and
applying said blended one or more components of the initial enzyme blend in the industrial process.
6. The method of claim 5 , further comprising:
blending the one or more components of the selected replacement enzyme blend in accordance with an overall dose rate, and
applying said blended one or more components of the selected replacement enzyme blend in place of one or more components of the initial enzyme blend.
7. The method of claim 1 , wherein the fiber quality characterization is determined with respect to one or more of a fiber length, width, fibrillation, cell wall thickness, fines density/distribution, fiber kink, and fiber curl.
8. The method of claim 1 , wherein the real-time feedback data further comprises system performance data regarding one or more of a fiber strength, a porosity, a caliper, a softness, a crepe count, a freeness and a drainage of the pulp or paper product.
9. The method of claim 1 , wherein the selected initial enzyme blend and the dynamically selected replacement enzyme blend to be applied, and respective dose rates thereof, are provided to a pulp bleaching process controller.
10. The method of claim 1 , wherein the selected initial enzyme blend and the dynamically selected replacement enzyme blend to be applied, and respective dose rates thereof, are provided to a paper manufacturing controller.