Technology Of Inventory Managment And System Development Based On Demand Forecasting

The Sany *** Enterprise is changing from manufacturing enterprise to service-oriented one, and the after-sales service based on the supplying of spare parts is becoming the new profit growth point for the manufacturing enterprise. Effective inventory management for the spare parts can reduce the inventory costs and improve the service level. Therefore, some related technology must be researched to guide the inventtory management of the spare parts for the enterprises. The main research of this paper included demand forecasting, modeling of the inverntory management, solving of the model and development of the inventory management system.The demand of the spare parts for wearing parts accounts for a large scale of the total demand, therefore there were three types of demand forecasting of wearing parts. When the demand data of the spare parts was stationary, the simple exponential smoothing method was adopted. When the demand data had the rising trend, the secondary exponential smoothing metho was adopted. Besides, demand of spare part is affected by various factors, which results in a low forecasting accuracy for the demand forecasting of the cycle pattern. To solve this problem, a new approach for forecasting the periodic demand of spare parts based on feature synthesis was developed. This methodology firstly defined a similarity measuring model of the spare parts demand sample sets under equal space, and then adopted evolutionary algorithm to determine the optimal demand cycle length for the spare parts. Next, it applied regression model to build the demand model for spare parts in every cycle period, and then a method was proposed to integrate these models based on feature synthesis. Lastly, the synthesis method was applied to integrate multiple cycle demand models of the spare parts into one, which was the optimal demand forecasting model for the spare parts with periodic pattern. The proposed model was applied in forecasting the ring chain for the mine machine, and the experimental results showed that the model had good stability and accuracy.The demand pattern for the key spare parts is intermittent. I ntermittent demand is characterized by infrequent demand arrivals and variable deman d sizes, which results in the difficult of demand forecasting. To solve this problem, a new approach was developed to forecasting spare parts demand. The methodology provided mechanism to respectively forecast the demand arrivals couple with the demand values when demand occurs. It firstly used the method of modulation to transform the 0-1 demand arrival time series into the continuous time series, and then adopted the neural network model to forecast the processed time series. Next, it applied the method of time aggregation to forecast the real demand time series, and took the rolling forecasting method into disaggregating, then got the predictive demand values. Applying this approach in forecasting the demand of the concrete pistons, the experimental results showed that the prediction accuracy of this method was superior to others, proved the methodology to be effective and accurate.In the aspect of modelling, it analysised the supplying process of the spare parts of the large equipment enterprises, and decided to adopt the coordinated control strategy based on the lateral transshipment for the multi-warehouses inventory management system, which was an optimisation of the inventory management. Next, it analysised the key element which would affect the inven tory costs, and then established the inventory management model based on the inventory costs, which was solved by the genetic algorithm. Besisdes, it explained how the various schedulings affected the inventory costs through the experiments, and then picked the best scheduling.Based on the theory research results, as well as the actual needs, this paper developmented the system structures and function modes of the linventory management system for service spare parts. It included variouse function modules, such as the demand forecasting and information management for the spare parts, which will be the part of the after-sales service platform, and work with the maintenance system.