Research On The Discharge Of Oily Sewage From Fishing Boats Based On Support Vector Machine

According to the "2018 China Fisheries Statistical Yearbook",the total number of Chinese fishing boats has reached 946,200,of which mobile fishing vessels are the mainstay.When fishing vessels operate,they will inevitably produce oily sewage in the machinery.Although the oily sewage of fishing boats has no accidental pollution to the water environment,it is shocking,but because of the concealment and long-term nature of its emissions,the marine environment is suffering from chronic oil pollution.Nowadays,it is a crucial period for China to move from a traditional fishery country to a modern fishery power.It is extremely important to increase research investment in pollution prevention of fishing vessels.The water pollutants caused by the fishing vessels in the operation process include domestic sewage and oily sewage from machinery spaces,among which the discharge of oily sewage is the most harmful.Domestic and international emissions of oily sewage from ships are mainly strictly regulated and regulated by merchant ships,and the importance attached to fishing vessels is relatively insufficient.The “Collection Table of Coastal Fishing Vessel Sewage Discharge Information” formulated in this paper contains many indicators that affect the oil discharge of fishing vessel oil wastewater.The field of discharge of oily wastewater from fishing vessels in three provinces,seven waters and eight fishing ports In the survey,a total of 97 samples of fishing vessel samples were collected,and 81 samples of oily sewage from fishing vessels collected by full-scale sampling method were used on the actual ship.The oil density was measured by ultraviolet spectrophotometry and gravimetric method.The gray correlation theory is used to screen out important indicators that are easy to quantify.The basic mathematical model of petroleum quality in fishing boat oil wastewater with support vector regression machine(SVR)was established.In order to improve the prediction accuracy,particle swarm optimization(PSO)was introduced to optimize the penalty factor C and nuclear parameter g of support vector regression machine(SVR)to establish PSO.-SVR prediction model.In order to further improve the accuracy and convergence speed of the prediction model,dynamic adjustment linear decrement weights,nonlinear decrement weights,particle-based adaptive weights,asynchronous learning factors and trigonometric function learning factors are introduced in the PSO algorithm.Through the simulation of MATLAB simulation,the simulation results of PSO-SVR model and BP and RBF neural network prediction model are compared and analyzed,and the feasibility and superiority of the model are proved.The PSO-SVR prediction model adjusted to 12 sets of parameters is adjusted.The simulation results of 12 sets of PSO-SVR prediction models applied to the test set data are used to optimize the model with the highest prediction accuracy as the final mathematical model.The rationality of the forecast of annual oil discharge in sewage.Based on a variety of improved PSO-SVR prediction models,the operator's lack of experience in parameter setting can be solved,which can effectively reduce the cost of field research and testing.This model provides a new idea and effective method for predicting oil emissions in oily wastewater from fishing vessels.At the end of the study,27 fishing boat information from a small fishing port in a small fishing port was selected as a test set.As an example,the group with the highest prediction accuracy calculated the annual oil discharge in the oily wastewater of the fishing boat in the port.It is 166.5674 kg.In the case where the sample size of the training set is constant,the sample size of the test set does not affect the prediction accuracy,and only affects the calculation time.By obtaining enough relevant test set data,we can predict the amount of oil discharged from the oily wastewater of the fishing boat in the area we need to master.This study conducts an objective,comprehensive and in-depth investigation of the pollution situation of China's fishing vessels.It is of great significance for accurately grasping the water pollution situation of fishing vessels in China,predicting the amount of oil emissions from oily wastewater,developing a sustainable fishery economy,and improving the harmful emissions of fishing vessels.