Location: Cotton Ginning Research
2023 Annual Report
Objectives
1. Develop methods and devices to enable the reduction of plastic contaminants in commercially harvested cotton.
1.1. Develop a UAV-based intelligent system to identify and remove plastic particles in cotton field.
1.2. Develop a sensor and control system to remove plastic contamination in ginning process.
2. Develop and evaluate tools and methods to enable the commercial preservation of cotton fiber quality and increase ginning efficiency.
2.1. Develop and evaluate sensors for cotton moisture measurement in real time in situ.
2.2. Detect moisture in cotton module using UAV-based platform.
2.3. Develop and evaluate air-bar lint cleaner to increase the turnout and preserve fiber quality.
2.4. Develop a sensing and control system to automatically adjust ginning process for optimal ginning efficiency.
3. Develop methods to enable the use of commercial cotton gin trash and seeds for bio-products and bio-energy.
3.1. Develop new methods to process gin trash for bio-products and energy.
3.2. Investigate moisture dynamics in cotton seeds.
Approach
The Cotton Ginning Research Unit seeks to develop cotton ginning technologies to maximize fiber quality, increase ginning efficiency, and minimize the environmental impact of ginning. Plastic contaminants in U.S. cotton are rapidly increasing in recent years and have become a serious threat to U.S. cotton industry by reducing marketable quality.
New sensing and control systems and ginning machinery are needed to clean the contaminants, improve fiber quality and ginning efficiency, and increase cotton producers’ profitability. Researchers will develop and evaluate sensing and control systems to remove plastic contaminants from cotton and develop new tools for accurate cotton moisture measurements. UAV (unmanned aerial vehicle) remote sensing will be used as a platform to find and remove the plastics from cotton fields and to detect moisture in cotton modules.
Optical sensors, data processing, automatic controls and the like will be designed and built to detect and remove the plastic materials during gin processing. Moisture sensors, coupled with improved measurement of mass-flow rate and new models, will be developed and tested to accurately determine moisture of seed cotton, cotton lint, and cotton seeds in real time. Using the data gathered, an improved control system will be designed and fabricated to optimize ginning efficiency.
Additional research includes developing and evaluating new lint cleaning technology to better preserve fiber quality and increase the ginning turnout. Studies on new methods to use gin trash for bio-energy will also be conducted in this project.
Progress Report
Plastic contamination of ginned lint has been an area of increasing concern for the cotton industry. Although there is on-going research aimed at the removal of contaminants from cotton during the ginning process (Whitelock et al., 2021; Pelletier et al., 2021), the preferred solution is to prevent plastic from entering the material stream during harvest. Work is ongoing to develop an annotated dataset containing 4 classes of contamination objects in cotton fields: plastic, trash, bottle, can. Image collection consists of adding known contaminants to cotton fields and then acquiring images of the contaminated fields with a UAV. During flights, the UAV captures 4K video or higher resolution still images with optional geotagging to locate the contaminates. To help the dataset generalize across conditions, the flights represent various heights and speeds. At this point the focus is to expand the dataset so that the models will be able to generalize across years as well as geospatial conditions. To date, the dataset contains over 14,000 annotated objects in over 11,000 images with many more images and videos waiting for annotations (a time-consuming process).
Researchers are interested in using ginning energy as a trait to differentiate breeding lines to develop new varieties which require less energy to gin and therefore have improved sustainability (Bechere et al. 2011). The laboratory gin stands used for these breeder trials have several possible sources of error which are often overlooked. The repeatability of measurements within and between laboratory gin stands is not known and may be impacted by differences in operator, sample size, or gin stand. This project establishes a standard protocol to improve the repeatability of energy data and aid breeders by addressing sources of error. Most common data loggers for 3-phase power are expensive making it hard to justify measuring power from a breeder scale gin stand. To make energy measures viable, a low-cost prototype power logger has been custom designed and constructed. The prototype can log three phase power at 240 volts. Initial testing is ongoing but early results indicate obtained values comparable to much more expensive equipment.
A software pipeline has been created to convert the relatively high-resolution still photos and frames extracted from the video into a formant acceptable to many AI approaches. This consists of breaking the images into smaller tiles which allows them to be resized with less loss of detail. Preliminary models trained on the SCINet platform using the Tensorflow Object Detection API have shown the feasibility of detecting plastic from RGB images. Initial modeling results look promising if the contaminants are within view of the camera and not completely obscured by the foliage.
Accomplishments
1. Co-pelletization of cotton gin trash with complementary bio-waste. Pelletization is an established process for improving both the density of the materials and the concentration of the nutrient (Garcia-Maraver & Manuel, 2015). The pelleting process has been successfully applied to Cotton Gib Byproduct (CGB), primarily for bioenergy applications. However, there are significant limitations in the quality/durability of pellets produced without adding binders, and the costs of most commercially available binding materials threaten the feasibility of the process for CBG (Holt et al., 2003). By contrast, pelleting has also been successfully applied to byproducts of animal production (i.e., manure, composts, and bedding materials) for soil amendment and nutrient supplements. The binding ability and other desirable properties of agricultural residues have also been explored as additives in the pelletization process. This study, by ARS researchers in Stoneville, Mississippi, seeks to pelletize CGB for soil fertilization in crop production. To overcome the challenge of poor pellet quality and durability, this study utilizes locally available and inexpensive byproducts of other agricultural processes. The targeted materials are also generated in high quantities and face similar limitations as unpelletized CGB. The accomplishment satisfies the objective focused on developing processes and formulations to improve the utilization of cotton gin trash for three main applications: (i) soil amendment; (ii) supplement in animal feeding; and (iii) bioenergy/biofuel.
2. Marketability of United States cotton is being threatened by the presence of plastic contamination. Previously funded years have tested camera types, lens, and commercially available UAVs for image collection in cotton fields. Fields in previous years were poor quality due to weather events. Having what appears to be the beginning of a good crop year, collecting larger number of high stand count cotton crops strengthens and diversifies the training of the artificial intelligence (AI) program developed by ARS researchers in Stoneville, Mississippi, for detection of contaminates found in the field prior to harvest. Additionally, global positioning system (GPS) coordinates continue to be collected from a tested unmanned aerial vehicle (UAV), but further testing of equipment to expand collecting GPS locations utilizing different camera options could prove beneficial in the removal of the contaminates. This accomplishment is of significant value to stakeholders requesting a low-cost solution to an issue demanding a certain degree of sophistication. The accomplishment satisfies the objective focused on developing methods and devices to enable the reduction of plastic contaminants in commercially harvested cotton.
3. Tabletop ginning energy: variable effects. The second largest consumer of electricity in a cotton gin is typically the gin stand. Evidence suggests that some cultivars take more energy to gin than others, which infers there is room to optimize cotton to lower costs. In addition, high energy cultivars may require slower ginning due to the power limits of the gin stand. Slower ginning increases marginal costs (labor per bale, etc.) which is beneficial to avoid. Reducing energy is key to helping the industry. An affordable custom multi-phase datalogger in development during previous funding years is being tested and calibrated to determine effectiveness against a commercially available data logger. Additionally, evaluation of variables such as operator, sample size, and variety are being evaluated for a comprehensive understanding of how each effects ginning energy. Dataloggers are being produced and distributed to fellow scientist in various locations to collect data from multiple operators and cotton varieties. Data from active and total ginning energy consumption, ginning rate, high volume instrument (HVI) and advanced fiber information system (AFIS) will be analyzed by ARS researchers in Stoneville, Mississippi, to determine the source and level of variance. Completion of this study will create a standardized methodology to produce more reliable and comparable data and ultimately reduced energy consumption in cotton gins.
