Engineering working operations based on parameters of product manufacturability using a computer-aided design algorithm

The study aimed to develop an algorithm for computer-aided design (CAD) of working operations. A processing route for machining components was developed based on the criteria of production manufacturability, industrial data and a digital model of the product. The process of machining a workpiece was analysed using a method of theoretical separation. The machining process of a frame workpiece was used as a model. The identified formal parameters formed a basis for developing a CAD algorithm and a model of manufacturing route associated with the mechanical processing of a work-piece applying a condition-action rule, as well as mathematical logic. The research afforded a scheme for selecting process operations, given the manufacturability parameters of a product design. The concept of CAD algorithm was developed to design a production process of engineering products with given manufacturability parameters, including industrial data. The principle of forming a route and selecting a machining process was proposed. Several criteria of production manufacturability (labour intensity, consumption of materials, production costs) were selected to evaluate mechanical processing. A CAD algorithm for designing technological operations considering the parameters of manufacturability was developed. The algorithm was tested by manufacturing a frame workpiece. The developed algorithm can be used for reducing labour costs and development time, at the same time as improving the quality of production processes. The formalisation of process design is a crucial stage in digitalisation and automation of all production processes.

Multivariate Statistics Between Two-Observation Spaces

As mentioned in the previous chapter, industrial data are usually divided into two categories, process data and quality data, belonging to different measurement spaces. The vast majority of smart manufacturing problems, such as soft measurement, control, monitoring, optimization, etc., inevitably require modeling the data relationships between the two kinds of measurement variables. This chapter’s subject is to discover the correlation between the sets in different observation spaces.

Multivariate Statistics in Single Observation Space

The observation data collected from continuous industrial processes usually have two main categories: process data and quality data, and the corresponding industrial data analysis is mainly for the two types of data based on the multivariate statistical techniques.

A Regional Industrial Economic Forecasting Model Based on a Deep Convolutional Neural Network and Big Data

To accurately predict the economic development of each industry in different types of regions, a deep convolutional neural network model was designed for predicting the annual GDP; GDP growth index; and primary, secondary and tertiary industry growth values of each. In the model, raw industrial data are preprocessed by a normalization operation and subsequently transformed by the BoxCox method to approach the normal distribution. Panel data of consecutive years are constructed and used as input to the deep convolutional neural network, and industrial data of year t + 1 are used as the output of the network. Simulation experiments were conducted to analyze 23 years of industrial economic data from 31 provinces, municipalities, and autonomous regions in China. The experimental results show that R-squared value is larger than 0.91 for all 31 provinces and root mean squared log errors (RMSLE) of all regions are less than 0.1, which demonstrate that the proposed method achieves high prediction accuracy with generalization capability and can accurately predict the economic growth trends of different types of regions.

Calibration and Validation of a Cone Crusher Model with Industrial Data

This paper reports the calibration and validation of a cone crusher model using industrial data. Usually, there are three calibration parameters in the condensed breakage function; by contrast, in this work, every entry of the lower triangular breakage function matrix is considered a calibration parameter. The calibration problem is cast as an optimization problem based on the least squares method. The results show that the calibrated model is able to fit the validation datasets closely, as seen from the low values of the objective function. Another significant advantage of the proposed approach is that the model can be calibrated on data that are usually available from industrial operation; no additional laboratory tests are required. Calibration and validation tests on datasets collected from two different mines show that the calibrated model is a strong candidate for use in various dynamic simulation applications, such as control system design, equipment sizing, operator training, and optimization of crushing circuits.