Micro-powder batching method and system based on MES (Manufacturing Execution System)

Abstract

The invention relates to the technical field of micro-powder production, in particular to a micro-powder batching method and system based on an MES system, and the method comprises the following steps: a data collection step: obtaining data through the MES system, the data including test results, control center values, floatable ranges and purchase costs of various ores, and inputting a batching material control standard range; a model construction and application step: establishing a micro-powder batching model, and solving the micro-powder batching model by applying the obtained data and through an artificial fish swarm algorithm to obtain an optimal value of the ore batching proportion; and a data sending step: issuing the optimal value of the ore batching proportion to a central control DCS (Distributed Control System) through an MES (Manufacturing Execution System), and automatically executing broken stone batching by the central control DCS. According to the method, the ore blending scheme which meets the requirements of chemical components and quality indexes of the batch and has the lowest cost can be rapidly given, the production cost of micro powder products is reduced, the operation efficiency of enterprises is improved, and the purpose of refined and intelligent production management of the enterprises is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of micro powder production, and in particular to a micro powder batching method and system based on an MES system. Background Art

[0002] At present, micro powder production belongs to process-based production, with a complete set of production processes, mainly composed of five production units, including feeding, crushing, grinding, homogenization, gas conveying and other links. Any link in the production process will have an impact on the subsequent links. In the micro powder production process, crushed stone batching is the most basic part of the process production, and the accuracy of crushed stone batching directly affects the quality of the micro powder finished product. Crushed stone batching is not just a simple mixture of several materials. The process involves many materials, complex ingredients and multiple quality and cost targets, resulting in a large amount of calculations for workers and difficulty in accurately adjusting the ratio of raw materials, which ultimately leads to production problems such as fluctuations in micro powder product quality and reduced pass rate.

[0003] In the process of micro powder production, crushed stone batching is a key step in the production process, and its control accuracy plays a vital role in the smooth production of downstream processes. In the existing production process of micro powder plants, most of the ore proportion calculation and control processes are completed manually, relying mostly on manual experience, and the interference of human factors is large. In addition, the domestic mining is not standardized, the raw material composition fluctuates greatly, and the feeding equipment is unstable. It is easy to cause problems such as low accuracy of raw material proportion, untimely adjustment of target value, and long lag time, resulting in an increase in the operating costs of enterprises, and it is easy to cause low accuracy of raw material proportion, affecting the quality of micro powder products. In the situation of increasingly tight mineral resources, enterprises need to save production costs by reasonably allocating the use of ore. However, the traditional manual calculation scheme cannot take into account multiple goals such as quality and cost at the same time, and the production needs of enterprises are becoming increasingly diversified, making the calculation and automatic control of proportioning ratio the focus of attention in the field of micro powder batching. Summary of the invention

[0004] One of the purposes of the present invention is to provide a micro-powder batching method based on the MES system, which can quickly provide a ore batching plan that meets the requirements of the chemical composition and quality indicators of the batch and has the lowest cost, thereby reducing the cost of micro-powder product production, improving the efficiency of enterprise operations, and achieving the purpose of refined and intelligent production management of the enterprise.

[0005] In order to achieve the above object, a micro powder batching method and system based on an MES system is provided, comprising the following steps:

[0006] Data collection steps: obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and enter the standard range of material control;

[0007] Model construction and application steps: Use the acquired data to establish a micro-powder batching model, and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio;

[0008] Data sending steps: Through the MES system, the optimal value of the ore batching ratio is sent to the central control DCS system, and the central control DCS system automatically executes the crushed stone batching.

[0009] Further, the method further comprises the following steps:

[0010] Data preprocessing step: preprocess the acquired data to check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

[0011] Further, the steps of constructing the micropowder batching model are as follows:

[0012] Step 1: According to the test results of various ores, the ore proportions of each type of ore are set as follows:

[0013] Independent variable X=x1,x2,x3...,x n ,

[0014] Step 2: Set constraints based on the control center value, floating range, and standard range of material mixing control. The constraints are as follows:

[0015] x1+x2+x3+......+x n =1

[0016] x1≧0,x2≧0,x3≧0,...x n ≧0

[0017] max1≧x1≧min1,max2≧x2≧min2,...,max n ≧x n ≧min n

[0018] A imin ≤a i x1+a i x2+......+a i x n ≤A imax

[0019] Among them, a i It is the content of a single chemical component in the ore raw material. imin ,A imax It is the lower and upper limits of the content of a single chemical component in the batch;

[0020] Step 3: Set the objective function based on the purchase cost. The objective function is the cost per ton of ore:

[0021] Z=C1x l +C2x2+......+C n x n .

[0022] Furthermore, the steps of the artificial fish swarm algorithm in the model construction and application steps are as follows:

[0023] Step 1. Initialization parameter settings, including the total number of artificial fish individuals N, the initial position of each artificial fish is randomly generated and filtered through constraints, the initial position is a set of ore ingredient ratios and recorded as the state or position of the artificial fish, the field of view of the artificial fish, the maximum step length of the artificial fish movement, and the upper limit of the number of attempts and the crowding factor;

[0024] Step 2. Calculate the individual fitness of each artificial fish through the objective function, find the artificial fish with the best status, and record its status on the bulletin board; the individual fitness is the ore cost per ton corresponding to the ore proportion; the optimal status is the ore proportion corresponding to the lowest ore cost per ton. n ;

[0025] Step 3. Evaluate each artificial fish and perform foraging behavior, chasing behavior, flocking behavior, and random behavior respectively;

[0026] Step 4. Each artificial fish moves forward and updates its status information;

[0027] Step 5. After comparing one by one, update the bulletin board record;

[0028] Step 6. Determine whether the number of iterations reaches the maximum value. If so, output the optimal solution; otherwise, go to step 2 and continue execution.

[0029] The second object of the present invention is to provide a micro-powder batching system based on the MES system, which applies the above-mentioned micro-powder batching method based on the MES system and includes the following modules:

[0030] Data acquisition module: used to obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and input of the standard range of material control;

[0031] Model building and application module: used to establish a micro-powder batching model using the acquired data, and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio;

[0032] Data sending module: used to send the optimal value of ore batching ratio to the central control DCS system through the MES system, and the central control DCS system automatically executes the crushed stone batching.

[0033] Furthermore, the following modules are also included:

[0034] Data preprocessing module: used to preprocess the acquired data and check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

[0035] Principles and advantages:

[0036] 1. A mathematical model was established for the ore batching calculation process, with the goal of minimizing the batching cost. Then, an artificial fish swarm algorithm was introduced to solve the mathematical model of micro-powder ore batching to obtain the optimal result. The optimal solution was directly sent to the central control DCS system through the MES system. The central control DCS system directly executed it, which greatly reduced the time for crushed stone batching, improved the quality of micro-powder products, and improved the efficiency of enterprise production. It also provided a feasible solution and method for quickly calculating the ore batching in the micro-powder production process, effectively optimized the crushed stone batching cost, and ensured the stability of subsequent production.

[0037] 2. Optimized the daily operation and production management process of micro powder enterprises, improved the efficiency of on-site operations, and achieved safe and efficient operation of the factory.

[0038] 3. Analyze and mine the value of production data, improve the level of enterprise operation and management, realize green, low-carbon and sustainable development of factories, and reduce the operating costs of micro powder production enterprises;

[0039] 4. Realize the refined management of micro powder enterprises, improve the efficiency of factory site operations, improve the level of intelligent management of enterprises, help enterprises "reduce costs and increase efficiency" and build smart factories. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a flowchart of a micro-powder batching method based on an MES system. DETAILED DESCRIPTION

[0041] The following is further described in detail through specific implementation methods:

[0042] Example

[0043] A micro powder batching method based on MES system, basically as follows Figure 1 As shown, the following steps are included:

[0044] Data collection steps: obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and enter the standard range of material control;

[0045] MES system (Manufacturing Execution System) is a production control software in industrial software and is a production information management system for manufacturing enterprise workshops. MES system provides real-time production management functions, connecting the underlying automation equipment with the upper-level ERP, PLM and other systems to achieve lean production and timely resolution of production problems, thereby improving production efficiency and product quality.

[0046] Data preprocessing step: preprocess the acquired data to check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

[0047] Model construction and application steps: Use the acquired data to establish a micro-powder batching model, and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio;

[0048] At present, micro powder production mainly consists of five production units, including feeding, crushing, grinding, homogenization, gas conveying and other links. The crushed stone batching process is between crushing and grinding. The batching process is to mix the raw materials in proportion. In most cases, the batch is produced by batching 5 to 10 kinds of raw materials. The batch is directly transported to the front bin of the mill through a belt and waits for the mill to grind. The uniform mixing of various ore raw materials is a physical change process. According to the principle of material conservation as the main basis for establishing the micro powder batching model, with improving the quality of micro powder and reducing the cost of raw materials as the objective function, and with the actual production process requirements as constraints, the optimal ratio of micro crushed stone batching is achieved.

[0049] The steps for constructing the micropowder batching model are as follows:

[0050] Step 1: According to the test results of various ores, the ore proportions of each type of ore are set as follows:

[0051] Independent variable X=x1,x2,x3...,x n ,

[0052] Step 2: Set constraints based on the control center value, floating range, and standard range of material mixing control. The constraints are as follows:

[0053] Constraint 1: x1+x2+x3+......+x n =1 (the sum of the ore proportions is 1)

[0054] Constraint 2: x1≧0,x2≧0,x3≧0,...xn ≧0 (ore ratio is non-negative)

[0055] Constraint 3: max1≧x1≧min1, max2≧x2≧min2, ..., max n ≧x n ≧min n (Upper and lower limits of the proportion of various ores purchased and used)

[0056] Constraint 4: A imin ≤a i x1+a i x2+......+a i x n ≤A imax (Ore batching is to mix various raw materials evenly, which is a physical change process. The chemical composition index of the batch is the weighted sum of the indexes of various raw materials according to the proportion. The chemical composition index in the batch (such as SiO2, Al2O3) should meet the standard requirement range)

[0057] Among them, a i It is the content of a single chemical component in the ore raw material. imin ,A imax It is the lower and upper limit of the content of a single chemical component in the batch.

[0058] Step 3: Set the objective function based on the purchase cost. The objective function is the cost per ton of ore:

[0059] Z=C1x l +C2x2+......+C n x n .

[0060] On the basis of satisfying the above constraints, find a set of X values ​​so that the ore cost Z value reaches the minimum value Z min .

[0061] The steps of the artificial fish swarm algorithm in the model construction and application steps are as follows:

[0062] The behavior of the artificial fish can be described as follows: vector X = (x1, x2..., x n ) T is recorded as the state or position of the artificial fish, where x i (i=1,...,n) is the target optimization variable of the i-th dimension; Z=f(X) is the concentration of food currently caught by the artificial fish, and Z is the value of the objective function; the distance between artificial fish individuals is expressed as d ij =||X i -X j||, visual represents the field of view of the artificial fish; step represents the maximum step length of the artificial fish; δ is the crowding factor.

[0063] Step 1. Initialize parameter settings, including the total number of artificial fish individuals N, randomly generate the initial position of each artificial fish and filter it through constraints, the initial position is a set of ore proportions and is recorded as the state or position of the artificial fish, the visual range of the artificial fish visual, the maximum step length of the artificial fish step, and the upper limit of the number of attempts (iterations) Try number and the crowding factor δ;

[0064] Step 2. Calculate the individual fitness of each artificial fish through the objective function, find the artificial fish with the best status, and record its status on the bulletin board; the individual fitness is the ore cost per ton corresponding to the ore proportion; the optimal status is the ore proportion corresponding to the lowest ore cost per ton. n ;

[0065] Step 3. Evaluate each artificial fish and perform foraging behavior, chasing behavior, flocking behavior, and random behavior respectively;

[0066] (1) Foraging behavior

[0067] Artificial FishX i It will randomly select an initial position X within its initial field of view. j , then the artificial fish compares the food density at the two locations. If Z i >Z j , then the artificial fish will move to X according to the following formula j One step forward in the direction; if Z i <Z j , then randomly select a new position X j , continue to compare the food density at the two locations, and then repeat the previous behavior. If the food is not found after repeated attempts for the set number of times.

[0068]

[0069] (2) Group behavior

[0070] By calculating the number of individual fish in the current field of view of the artificial fish, and comparing it with the center position X of the artificial fish school in the field of view c (i.e. the current highest food density) for comparison, if Z c / nf<δZ i , it means that the food density value at the current center is high and there are not many individual fish around. At this time, the artificial fish will move one step in that direction according to the following formula. c / nf>δZi , the algorithm performs foraging behavior.

[0071]

[0072] (3) Rear-end collision

[0073] By searching for the artificial fish X at the place with the highest food density within the current field of view of the artificial fish max And make judgment:

[0074] If Z max / nf<δZ i , then it means that the artificial fish X max There are not many artificial fish around, so artificial fish X i It should move one step in the direction given by the following formula. max / nf>δZ i , the algorithm performs foraging behavior.

[0075]

[0076] (4) Random Behavior

[0077] The movement direction of fish in the water in nature is usually random, so when simulating fish activities, random behavior means that the current artificial fish randomly chooses a direction to move within the initially set field of view, as shown in the following formula. In fact, after the number of attempts of foraging behavior reaches the initial setting, if it still fails, the random behavior will be executed.

[0078] X i|next =X i +Rand()×visual

[0079] Step 4. Each artificial fish moves forward and updates its status information;

[0080] Step 5. After comparing one by one, update the bulletin board record;

[0081] Step 6. Determine whether the number of iterations reaches the maximum value. If so, output the optimal solution; otherwise, go to step 2 and continue execution.

[0082] Data sending steps: Through the MES system, the optimal value of the ore batching ratio is sent to the central control DCS system, and the central control DCS system automatically executes the crushed stone batching.

[0083] Through the micro-powder batching method based on the MES system, the optimal ratio is automatically calculated directly through the MES system, and the optimal ratio calculation result is sent to the DCS automatic control system with one click, and the DCS system automatically executes the batching process.

[0084] A micro powder batching system based on an MES system, which applies the micro powder batching method based on an MES system as described above, includes the following modules:

[0085] Data acquisition module: used to obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and input of the standard range of material control;

[0086] Data preprocessing module: used to preprocess the acquired data and check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

[0087] Model building and application module: used to establish a micro-powder batching model, use the acquired data and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio;

[0088] Data sending module: used to send the optimal value of ore batching ratio to the central control DCS system through the MES system, and the central control DCS system automatically executes the crushed stone batching.

[0089] This solution establishes a mathematical model for the ore proportioning calculation process, and then introduces an artificial fish swarm algorithm to solve the mathematical model of micro-powder ore proportioning to obtain the optimal result. The optimal solution is then sent directly to the central control DCS system through the MES system, which is directly executed by the central control DCS system. This greatly reduces the time for crushed stone proportioning, improves the quality of micro-powder products, and improves the efficiency of enterprise production.

[0090] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A micro powder batching method based on MES system, characterized in that: The following steps are involved: Data collection steps: obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and enter the standard range of material control; Model construction and application steps: Use the acquired data to establish a micro-powder batching model, and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio; Data sending steps: Through the MES system, the optimal value of the ore batching ratio is sent to the central control DCS system, and the central control DCS system automatically executes the crushed stone batching.

2. The micro powder batching method based on the MES system according to claim 1, characterized in that: The following steps are also included: Data preprocessing step: preprocess the acquired data to check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

3. A micro powder batching method based on MES system according to claim 2, characterized in that: The steps for constructing the micropowder batching model are as follows: Step 1: According to the test results of various ores, the ore proportions of each type of ore are set as follows: Independent variable X=x1,x2,x3...,x n , Step 2: Set constraints based on the control center value, floating range, and standard range of material mixing control. The constraints are as follows: x1+x2+x3+......+x n =1 x1≧0,x2≧0,x3≧0,...x n ≧0 max1≧x1≧min1,max2≧x2≧min2,...,max n ≧x n ≧min n A imin ≤a i x1+a i x2+......+a i x n ≤A imax Among them, a i It is the content of a single chemical component in the ore raw material. imin ,A imax It is the lower and upper limits of the content of a single chemical component in the batch; Step 3: Set the objective function based on the purchase cost. The objective function is the cost per ton of ore: Z=C1x l +C2x2+......+C n x n 。 4. The micro powder batching method based on the MES system according to claim 3 is characterized in that: The steps of the artificial fish swarm algorithm in the model construction and application steps are as follows: Step 1. Initialization parameter settings, including the total number of artificial fish individuals N, the initial position of each artificial fish is randomly generated and filtered through constraints, the initial position is a set of ore ingredient ratios and recorded as the state or position of the artificial fish, the field of view of the artificial fish, the maximum step length of the artificial fish movement, and the upper limit of the number of attempts and the crowding factor; Step 2. Calculate the individual fitness of each artificial fish through the objective function, find the artificial fish with the best status, and record its status on the bulletin board; the individual fitness is the ore cost per ton corresponding to the ore proportion; the optimal status is the ore proportion corresponding to the lowest ore cost per ton. n ; Step 3. Evaluate each artificial fish and perform foraging behavior, chasing behavior, flocking behavior, and random behavior respectively; Step 4. Each artificial fish moves forward and updates its status information; Step 5. After comparing one by one, update the bulletin board record; Step 6. Determine whether the number of iterations reaches the maximum value. If so, output the optimal solution. Otherwise, go to step 2 and continue.

5. A micro powder batching system based on MES system, characterized by: The micro powder batching method based on the MES system as described in any one of claims 1 to 4 is applied, comprising the following modules: Data acquisition module: used to obtain data through the MES system, including the test results of various types of ores, control center values, floating ranges, procurement costs, and input of the standard range of material control; Model building and application module: used to establish a micro-powder batching model using the acquired data, and solve the micro-powder batching model through the artificial fish swarm algorithm to obtain the optimal value of the ore batching ratio; Data sending module: used to send the optimal value of ore batching ratio to the central control DCS system through the MES system, and the central control DCS system automatically executes the crushed stone batching.

6. The micro powder batching system based on the MES system according to claim 5, characterized in that: Also includes the following modules: Data preprocessing module: used to preprocess the acquired data and check whether there is any data that affects the analysis results. The data that affects the analysis results includes abnormal values, special symbols, repeated values, and missing values. When abnormal data is detected, an alarm reminder will be issued.

Images