This research proposes a Bayesian logistic regression model which is applied to the data from autoparts manufacturing machines. Factors related to defective and bad products are investigated. The proposed model is compared with the logistic regression using maximum likelihood method for parameter estimation. The data were collected from 132 machines in an autoparts manufacturing factory. The research found that useful life machine type 6 worker group 3 and 4 working step 1 and 2 influence to the risk of producing defective and bad products. When the useful life is increased by 1 month the risk of producing defective and bad products will be increased by 2.2%. The risk that the machine type 6 will produce defective and bad products is 4.078 times greater than the risk that the machine type will do. The risk that the worker group 3 will produce defective and bad products is 61.7% less than the risk that the worker group 12 will do. The risk that the worker group 4 will produce defective and bad products is 61.5% less than the risk that the worker group 12 will do. The risk that the working step 1 will produce defective and bad products is 2.831 times greater than the risk that the working step 4 will do. The risk that the working step 2 will produce defective and bad products is 13.8 % greater than the risk that the working step 4 will do. The parameter estimates from the Bayesian logistic regression are very close to the ones from the logistic regression using maximum likelihood method for parameter estimation

Nowadays the majority of environment problem is pollution of vehicle including the noise of engine combustion. For this reason this thesis aims to compare and study the parameters which affect noise reduction on exhaust pipe. Not only reduce the noise pollution but also maintain the efficiency of the engine. These two substances must be considered. Therefore the researcher emphasized to study the parameters on 3 types of muffler with an equal volume: direct reverse and offset type of mufflers. Initiated by data collection the pressure and the velocity in muffler at the speed of engine at 1000 RPM (slow-running engine mode) and 4000 RPM (maximum running engine mode) were investigated. The data were applied into the program that called “SolidWorks” in order to study parameters. In this step the relation between the pressure and velocity of exhaust were represented. In addition the muffler models were selected to manufacture and test by the standard of The Department of Land Transport. As a result there are two major parameters of the muffler. Firstly the metamorphism of the exhaust gas flow direction pleasurably causes the lower noise at the speed of engine at 1000 RPM. Besides an increase of the flow gas distance can diminish noise at the speed of engine at 4000 RPM as well. However this muffler models were tested under the working mode of catalytic device that is standard equipment for automotive vehicles.

This research proposes reliability analysis in order to find the probability that a machine will work properly the failure rates of a machine and the factors related to the failure rates. The data were collected from 8 types of machines in an autoparts manufacturing factory. They consist of the times measured from the first day of the study until the machine produces defective product workers and production steps. The study duration is 90 days. The results show that the probability that the machine type 4 will work properly more than days is 0.40 machine type 5 more than 68 days is 0.32 machine type 6 more than 72 days is 0.31 machine type 8 more than 85 days is 0.26 machine type 9 more than 109 days is 0.80 machine type 10 at more than 52 days is 0.38 machine type 11 more than 71 days is 0.32 and the probability that the machine type 12 will work properly more than 85 days is 0.26. The failure rate of the machine type 4 at day 51 is 6.61 machine type 5 at day 68 is 1.61 machine type 6 at day 72 is 0.77 machine type 8 at day 85 is 1.26 machine type 9 at day 109 is 1.31 machine type 10 at day 52 is 0.92 machine type 11 at day 71 is 1.24 and the failure rate of the machine type 12 at day 85 is 2.15. The factors influencing on the failure rates are worker group 2 and production step 3 at the significance of 0.05.

The research aimed 1) to develop the product of floral arrangement on pedestal made of Sanoh Hangkai (jointvetch / Aeschynemene Indics L.) with paper mache technique and 2) to study the target group’s satisfaction with floral arrangement on pedestal product made of jointvetch with paper mache technique. The result found that five specialists had a high satisfaction level to the second method of combining jointvetch with tissue from toilet paper. Mean of satisfaction level was 4.00. Fifty people in target group had a high satisfaction level on developing the floral arrangement on pedestal product made of jointvetch with paper mache technique. Mean of satisfaction level was 4.89 4.84 and 4.66. The details were as follows: 1. The specialists satisfied the study of the second method of combining jointvetch with tissue from toilet paper and had the overall comments about its features with the mean at 4.00 (high level). Mean of the material’s tenderness was 4.60 (highest level). The balance of the material was 4.10 (high level). The toughness of the material was 4.06 (high level) and the material’s softness was 3.50 (high level). 2. The satisfaction level of fifty people in target group to the development of floral arrangement on pedestal product made of jointvetch with paper mache technique showed that they satisfied the floral arrangement in rice-grain shaped on pedestal with its highest mean at 4.89. Mean of satisfaction level on the floral arrangement on pedestal with applied Thai style was 4.84 (highest level) followed by the floral arrangement with joss sticks and candles on pedestal which was 4.66 (highest level).

Thai desserts have unique appearance and characteristic cause ingredient and processing. Thai desserts processing is very complicate which Thai dessert is decreased to produce and consume. Difficulty Thai desserts processing were surveyed and ranked. Top 5 of difficulty processing were Kanom Kasornlamjeak Kanom Krok Kanom Beaung Thai Kanom Thong Ekk and Kanom Jamongkut. Kanom Kasornlamjeak consists with wrap flour and filler which made from coconut. The process of wrap flour is complicate. Flour mixing time (20 30 and 40 min) was studied. Increasing mixing time improved wrap flour forming. The sensory evaluation result showed that Kanom Kasornlamjeak with flour mixing time 20 min got a good preference score from the panelists. Kanom Krok consists with rice flour and coconut milk. The characteristic of Kanom Krok is crispy flour and forming. The concentration of lime water (0.5 1.0 and 1.5%) was studied. Increasing lime water concentration increased crispiness and hardness of Kanom Krok. Kanome Krok with 1.0% lime water received the highest preference score. Kanom Beaung Thai consists with casing flour and filler. The important characteristic of Kanom Beaung is crispy casing flour. The concentration of lime water (0.5 1.0 and 1.5%) was studied. Increasing lime water concentration increased crispiness and hardness. The sensory evaluation result showed that casing flour with 1.0% lime water got a high preference score. Coconut milk and wheat flour are the important ingredients in Kanom Thong Ekk. They were mixed and stirred until smooth paste to press in a plastic mold. Cooking temperature; 60 65 and 70C were studied. Increasing temperature increased oil separation and gelation. Kanom Thong EKK with cooking temperture at 65C received the highest preference score.Kanom Jamongkut is a Thai dessert that the shape looks like a crown. Watermelon seeds are the most important ingredient which are coated with sugar syrup and composed to be a crown. The amount of watermelon seeds coated with sugar were studied which were 50 100 and 150 seeds per batch. Increasing watermelon seed per batch to coat it with sugar syrup it did not look like a crown. Sensory evaluation result showed that 50 watermelon seeds coated with sugar received highest preference score.