阅读说明：本技术 一种铝合金熔铸配料系统 (Aluminum alloy casting batching system ) 是由 苏畅 孙勇 苏子宁 凌云汉 袁超 于 2019-10-12 设计创作，主要内容包括：本发明公开一种铝合金熔铸配料系统,包括配料目标决策层,用于提供铝熔铸配料生产线中的铝合金配料标准；熔铸配料优化层,在铝合金配料标准的约束基础上,提供满足质量指标的最优原料初始配比和成分调整配比方案；智能料仓执行层,根据熔铸配料优化层提供的配料数据,自动识别下料数据到投料明细,完成料仓下料称重任务。本发明优化了传统铝合金熔铸配料方法,为企业提供快速、高效、优质的铝合金产品配料方案。(The invention discloses an aluminum alloy casting batching system, which comprises a batching target decision layer, a batching target decision layer and a batching target decision layer, wherein the batching target decision layer is used for providing an aluminum alloy batching standard in an aluminum casting batching production line; the fusion casting ingredient optimization layer provides an optimal raw material initial ratio and component adjustment ratio scheme meeting quality indexes on the basis of constraint of aluminum alloy ingredient standards; and the intelligent stock bin execution layer automatically identifies the blanking data to the feeding details according to the ingredient data provided by the fusion casting ingredient optimization layer, and completes the stock bin blanking weighing task. The invention optimizes the traditional aluminum alloy casting batching method and provides a fast, efficient and high-quality aluminum alloy product batching scheme for enterprises.)

1. An aluminum alloy casting batching system, characterized by comprising:

the material mixing target decision layer is used for carrying out reasoning by combining an aluminum alloy casting material reasoning rule set and an expert rule according to an established aluminum alloy casting material knowledge base to provide an aluminum alloy material mixing standard in an aluminum alloy casting material production line;

the multi-target batching optimization layer is used for providing an optimal raw material initial batching and component adjusting batching scheme meeting quality indexes through an established multi-target optimizing batching model on the basis of the constraint of the aluminum alloy batching standard;

and the intelligent stock bin execution layer is used for automatically controlling blanking according to the optimal raw material initial ratio and component adjustment ratio scheme and finishing stock bin blanking weighing.

2. The aluminum alloy casting batching system as defined in claim 1, wherein the knowledge base of aluminum alloy casting batching is optimally established based on product processing properties, mechanical properties and physicochemical properties, and is established based on process characteristics of the aluminum alloy melting process and empirical knowledge accumulated in the batching, according to performance indexes and composition indexes of the product in combination with historical data during batching.

3. The aluminum alloy casting batch system of claim 1, wherein the aluminum alloy casting batch inference rule set comprises:

the ingredient target class rule set stores rules based on ingredient targets and product performance characteristics, is divided according to product classes and is used for adjusting the range of the current ingredient component control standard according to the ingredient targets and the product performance characteristics;

the historical burdening experience rule set is used for storing rules based on historical burdening targets and product performance characteristics of the products and adjusting the range of the current burdening component control standard according to the component control standard in the historical burdening card of the same type of products and in combination with the product performance characteristics;

and the historical production process parameter influence rule set stores the influence of the residual aluminum liquid quality inspection result of the last furnace on components, the component loss rate obtained from production experience and the rule obtained by analyzing the parameters of a furnace group, a process and a working procedure in the actual production process, and is formulated by using the experience of batching personnel by combining furnace group data, the working procedure step, the temperature of a hearth and furnace liquid.

4. The aluminum alloy casting batching system as set forth in claim 1, wherein said step of reasoning in combination with expert rules with an inference rule set for aluminum alloy casting batching is as follows:

determining an inference rule set of aluminum alloy casting ingredients;

determining a comment set of the aluminum alloy casting ingredient reasoning rule set, wherein the comment set distinguishes ingredient range values of single components into a plurality of range grades;

determining inference index weight of the aluminum alloy casting ingredient inference rule set;

and acquiring the inference result of the components according to the inference index weight and the established comprehensive inference matrix, and processing according to the maximum membership principle to obtain the final range evaluated by the single component.

5. The aluminum alloy casting batching system as defined in claim 1, wherein the multi-objective optimal proportioning model takes cost optimization as an objective function of aluminum alloy casting batching and takes product component qualification, raw material use limitations and furnace set capacity as constraints.

6. The aluminum alloy casting batching system as claimed in claim 5, wherein the multi-objective optimal proportioning model comprises cost optima as an objective function and constraints of the aluminum alloy casting batching, expressed as follows:

wherein the content of the first and second substances,wherein x_iIndicates the amount of the raw material used, c_iRepresents the price of raw material, m_iIndicating the stock quantity of raw materials, a_ijDenotes the content of the j component, Eu, in the i material_jRepresents the upper range requirement, El, of the jth ingredient in the dosing standard_jRepresents the lower limit range requirement of the jth ingredient in the batching standard, and Q represents the batching amount of a single furnace.

Technical Field

The invention relates to the technical field of aluminum alloy casting, in particular to an aluminum alloy casting batching system.

Background

Aluminum alloy casting is used as a first process for producing and manufacturing aluminum alloy materials, and provides raw materials for subsequent processes such as extrusion, rolling and forging. On the aluminum alloy ingot casting product, the size and the shape of the ingot casting need to meet the requirements of subsequent processing procedures of different manufacturers and product quality specifications, and more importantly, the internal quality and the performance of the ingot casting need to meet the requirements of different manufacturers. The guarantee of the internal quality and the performance of the cast ingot mainly depends on the gas content and the slag content in the melt, the content of impurities and the degree of grain refinement, and the quality and the performance are insufficient, so that the follow-up procedures are difficult to remedy, and the yield and the use effect of the product are also influenced; and the later the internal defects are exposed in the processing process, the longer the production equipment is occupied, the delivery time period of the product is prolonged, and the production cost is increased. In order to exert the potential of aluminum alloy materials as much as possible and obtain low-cost, high-performance and high-quality aluminum alloy ingots, the emphasis is placed on the production and quality control of the ingots, and the quality control in the casting process depends on the casting process and casting equipment and also depends on a scheme obtained by selecting and batching raw materials.

The research of the intelligent batching method in the aluminum alloy casting process is to produce low-cost and high-quality cast ingots. The aluminum alloy products in the early stage are repeatedly smelted due to uncertain material ratio and unqualified smelting quality, so that the smelting time is too long, the production cost is increased, and the improvement of enterprise benefits is limited. To produce high quality products in a minimum amount of time to increase efficiency, only a limited variety of raw materials are used and the experience of the formulator is more demanding. The varieties of main raw materials (scrap aluminum) of aluminum alloy ingots always change, and if the experience of experts cannot be kept and the formula cannot be improved, the quality and the factory benefit of aluminum alloy products are seriously influenced.

The traditional batching method for casting the aluminum alloy has the following problems:

1) big data

The types of products produced in the aluminum alloy casting workshop at present are more than thirty, and can be divided into two main types according to the difference of the used raw materials: pure aluminum series and secondary aluminum series. In addition, the aluminum materials of the secondary aluminum series are various in types, and can be divided into the following steps according to the production process: wrought aluminum alloys, cast aluminum alloys, forged aluminum alloys, wires and cables, and the like. Nearly hundreds of raw materials, each with more than 20 ingredients. The content of the components of the same type of secondary aluminum of different manufacturers can be different.

2) Multiple targets

The aluminum alloy ingot discharged from the furnace is also composed of a plurality of components, and there are limits such as maximum value, minimum value, inspection standard, etc. for each component. The chemical components of the product are required to be qualified: comprises main alloy components and impurity component content; the cost is intended to be the lowest: including the price of the raw materials used and the cost of the smelting process; it is desirable to minimize the smelting task: such as the minimum slagging times and types, the minimum addition of other auxiliary materials, and the like.

3) Multi-factor crossover and variation of each component in the smelting process

In the smelting process, one component exists in a plurality of materials, and in order to match the target content of one component, another component which needs to be reduced is possibly brought in, so that whether the content of other substituted components is qualified needs to be calculated; the components are burnt and increased, and the change amount is changed according to the adding mode and the adding time. For example, in order to improve the ratio of aluminum to silicon, the method comprises the steps of increasing the content of an aluminum component and reducing the content of a silicon component, wherein the increase of the aluminum component causes the alkali ratio to be reduced, and the reduction of the silicon component causes the calcium-silicon ratio to be improved.

The aluminum alloy casting proportion has the characteristics of multivariable, complex chemical components, large fluctuation quantity, strong coupling, nonlinearity and the like. The proportion of each raw material is determined by the ingredient technical personnel according to the ingredient detection data of the raw aluminum and the waste and impurity aluminum obtained by a quality inspection instrument, the ingredient experience of the ingredient technical personnel for a long time and the quality data of various raw materials, and because the product and the raw materials are various, the ingredient uncertainty of the waste and impurity aluminum, the ingredient fluctuation of batch materials and the metal ingredient burning loss in the smelting process, the accuracy of the manually determined proportion scheme in the aluminum alloy casting process is low, the workload is enlarged, and the fluctuation of the performance quality of the finished product is caused [. Therefore, how to solve the problems of big data, multiple targets, multi-factor intersection and change of each component in the smelting process existing in the traditional batching method, liberating the mental labor of people and letting batching experts put more energy on how to prepare high-quality products is a problem which needs to be solved.

In addition, although a specially-assigned person is arranged for burdening in the aluminum alloy casting industry at present, most enterprises still use the traditional burdening method for calculation, and the calculation mode has the defects of long burdening calculation time and low accuracy; moreover, the calculation result possibly differs from that of a batching auditor greatly, and the checking is needed, so that the batching working efficiency is reduced, the production cycle of products is prolonged, and the material weight is calculated inaccurately by the traditional batching in a forklift weighing mode.

Disclosure of Invention

The invention aims to provide an aluminum alloy casting batching system aiming at the technical defects in the prior art.

The technical scheme adopted for realizing the purpose of the invention is as follows:

an aluminum alloy casting batching system, comprising:

the material mixing target decision layer is used for carrying out reasoning by combining an aluminum alloy casting material reasoning rule set and an expert rule according to an established aluminum alloy casting material knowledge base to provide an aluminum alloy material mixing standard in an aluminum alloy casting material production line;

the multi-target batching optimization layer is used for providing an optimal raw material initial batching and component adjusting batching scheme meeting quality indexes through an established multi-target optimizing batching model on the basis of the constraint of the aluminum alloy batching standard;

and the intelligent stock bin execution layer is used for automatically controlling blanking according to the optimal raw material initial ratio and component adjustment ratio scheme and finishing stock bin blanking weighing.

The invention provides a method for optimizing the batching of aluminum alloy casting, which is based on the characteristics and requirements of an aluminum alloy casting production line, technical requirements of chemical components, mechanical properties and the like of products, the service performance of raw materials, the condition of a smelting furnace group and the like, and combines the limiting conditions in actual production, and takes the product performance, the component requirements and the raw material cost as important indexes for measuring the batching quality, thereby optimizing the traditional aluminum alloy casting batching method and providing a fast, efficient and high-quality aluminum alloy product batching scheme for enterprises.

Drawings

FIG. 1 is a schematic diagram of an aluminum alloy casting batching system provided by the invention.

Detailed Description

The invention is described in further detail below with reference to the figures and specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, the aluminum alloy casting batching system provided by the invention relates to a three-layer structure:

the first layer is a material mixing target decision layer based on an expert rule base, namely an aluminum alloy casting material knowledge base based on product technological property, mechanical property and physical and chemical property optimization is established, fuzzy reasoning is carried out by combining a reasoning rule set and an expert rule, and then an aluminum alloy material mixing standard in an aluminum casting material production line is obtained and is also an optimization constraint condition;

the second layer is a multi-objective based casting ingredient optimization layer, namely on the basis of the proposed constraint conditions, an objective function taking cost optimization as an aluminum alloy casting ingredient is established, and a linear programming-based multi-objective optimization proportioning model taking product components as qualified, raw material use limitation and furnace group capacity as constraint conditions is researched; further obtaining an optimal raw material initial ratio and component adjustment ratio scheme meeting the quality index;

the third layer is an automatic identification intelligent bin execution layer, after the batching scheme is published, the system automatically identifies the bins, the bin task is published on a touch screen of a bin control cabinet, and after automatic blanking, blanking data is automatically identified to feeding detail, so that the bin blanking weighing task is completed.