CN117313951A - Multi-sensor fusion flexible deburring management method and system - Google Patents

Multi-sensor fusion flexible deburring management method and system Download PDF

Info

Publication number
CN117313951A
CN117313951A CN202311405692.3A CN202311405692A CN117313951A CN 117313951 A CN117313951 A CN 117313951A CN 202311405692 A CN202311405692 A CN 202311405692A CN 117313951 A CN117313951 A CN 117313951A
Authority
CN
China
Prior art keywords
deburring
workpiece
burr
historical data
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311405692.3A
Other languages
Chinese (zh)
Other versions
CN117313951B (en
Inventor
章明
徐林森
于海武
赵宏磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Cascc Intelligent Industrial Equipment Co ltd
Original Assignee
Jiangsu Cascc Intelligent Industrial Equipment Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Cascc Intelligent Industrial Equipment Co ltd filed Critical Jiangsu Cascc Intelligent Industrial Equipment Co ltd
Priority to CN202311405692.3A priority Critical patent/CN117313951B/en
Publication of CN117313951A publication Critical patent/CN117313951A/en
Application granted granted Critical
Publication of CN117313951B publication Critical patent/CN117313951B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Processing And Handling Of Plastics And Other Materials For Molding In General (AREA)

Abstract

The invention discloses a multi-sensor fusion flexible deburring management method and system, and belongs to the technical field of deburring management. The system of the invention comprises: the system comprises a data acquisition module, a burr evaluation module, a using time length prediction model, a real-time data monitoring and adjusting module and a probability calculation and optimization adjusting module; the data acquisition module collects historical data and real-time data using a plurality of sensors; the burr evaluation module is used for classifying the historical data according to the calculated burr evaluation coefficient; the using time-long prediction model builds a using prediction model for the completely removed historical data; the real-time data monitoring and adjusting module adjusts corresponding data until the corresponding data is consistent with the prediction model; and the probability calculation and optimization adjustment module calculates the probability of excessive removal and incomplete removal under each burr evaluation coefficient in the historical data and the real-time data and performs optimization adjustment.

Description

Multi-sensor fusion flexible deburring management method and system
Technical Field
The invention relates to the technical field of deburring management, in particular to a multi-sensor fusion flexible deburring management method and system.
Background
Flexible deburring is a method of deburring surfaces of materials where burrs or sharp edges are often present during manufacture, and these uneven portions can negatively impact the quality and safety of the product. Flexible deburring corrects the problem of burrs on the surface of materials by using soft or resilient tools or materials, as well as suitable processing techniques.
Currently, there are some methods for flexible deburring for multisensor fusion, but these methods have the following problems: the prior art rarely provides prediction and control for the service life of the tool, so that operators are difficult to accurately judge the service life of the tool, and timely take maintenance and replacement measures, which may lead to premature scrapping of the tool or poor deburring effect in the use process, and the reject ratio of workpieces is improved.
Disclosure of Invention
The invention aims to provide a flexible deburring management method and system for multi-sensor fusion, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a flexible deburring management method for multi-sensor fusion comprises the following steps:
s100, acquiring historical data in the deburring process through a sensor, wherein the historical data comprises workpiece information and operation parameters, storing the historical data, and establishing a database; the workpiece information comprises workpiece size, material and burr information of the surface of the workpiece; the operating parameters include speed and pressure of deburring;
s200, acquiring burr information of each surface of the workpiece before deburring in the historical data, calculating burr evaluation coefficients of each surface of the workpiece before deburring, and classifying the historical data according to the difference of the burr evaluation coefficients; the burr information comprises the area and the number of burrs on each surface of the workpiece before the burrs are removed;
s300, evaluating historical data of the coefficients aiming at each burr, and further dividing the historical data into three parts, namely complete removal, excessive removal and incomplete removal, according to the deburring effect; constructing a prediction model of the use duration of the deburring tool by analyzing the completely removed historical data;
s400, analyzing historical data of incomplete removal and excessive removal according to a prediction model of the use duration of the deburring tool, and formulating corresponding optimization strategies and improvement measures; and (3) applying the formulated optimization strategy and improvement measure to the deburring process, monitoring and recording the operation parameter setting of the real-time data, comparing and analyzing with the historical data, and evaluating the effects of the optimization strategy and the improvement measure.
Further, step S100 includes:
historical data in the deburring process is collected through the sensor, corresponding workpiece information, operation parameters and equipment states are classified and collected according to different numbers of workpieces to form a database, namely, one workpiece number corresponds to one workpiece information, and one workpiece information is related to the operation parameters of corresponding deburring equipment in the deburring process.
Further, step 200 includes:
s201, acquiring burr information of each surface of a workpiece before deburring in historical data, wherein the burr information comprises burr areas s of each surface of the workpiece i And a number n; wherein n is an integer of 1 or more, s i Representing the area of the ith burr on the surface of a workpiece;
s202, according to the formulaCalculating the area proportion of the burr area of one surface of the workpiece to the area of the one surface of the workpiece, wherein S represents the area of the one surface of the workpiece; according to the formula->CalculatorThe number of burrs on one surface of the workpiece accounts for the proportion of the number of all burrs of one workpiece, wherein N is the number of all burrs of one workpiece; calculating a burr evaluation coefficient Q of each surface of each workpiece before deburring, and q=w 1 A 1 +w 2 A 2 Wherein w is 1 And w 2 Is a weighting coefficient;
s203, classifying historical data according to the calculated burr evaluation coefficients of all surfaces of the workpiece before deburring, wherein one burr evaluation coefficient is classified into one type, and the set is represented as Q= { Q 1 ,Q 2 ,...,Q m }, wherein Q 1 Burr evaluation coefficient representing the 1 st surface, Q 2 Burr evaluation coefficient representing the 2 nd surface, and so on, wherein Q m Representing the burr evaluation coefficient of the mth surface.
Further, step S300 includes:
s301, acquiring corresponding deburred images for historical data of each burr evaluation coefficient, performing edge detection to obtain an edge area of the surface of the deburred workpiece, and comparing the edge area with a preset target edge area;
s302, if the edge area of the surface of the workpiece after deburring is larger than a preset target edge area, marking the corresponding historical data as incomplete removal; if the edge area of the surface of the workpiece after deburring is equal to a preset target edge area, marking the corresponding historical data as completely removed; if the edge area of the surface of the workpiece after deburring is smaller than a preset target edge area, marking the corresponding historical data as excessive removal;
s303, acquiring completely removed historical data, and constructing a using time length prediction model of the deburring tool; correlating all the deburring speeds and the average values of deburring pressures corresponding to the using time length, namely, one deburring speed and one average value of deburring pressure corresponding to one using time length; the use time period is recorded from the moment of replacing the deburring tool to the moment of completing the deburring operation of one surface of the workpiece.
The construction of the in-use time length prediction model of the deburring tool comprises the following steps:
acquiring completely removed historical data, and constructing a prediction model of the use duration of the deburring tool; the input of the prediction model is the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring; the surface area of the deburring workpiece refers to the area of each surface of the deburring workpiece; the corresponding surface roughness of the surface of the deburring workpiece means that the area of each surface of the deburring workpiece corresponds to one surface roughness; the output of the prediction model is the using time of the deburring tool; normalizing the input and output data to construct a prediction model;
the model is as follows:
L＝β 0 +β 1 x 1 +β 2 x 2 +ε
wherein L is the use time length of the deburring tool, x 1 Representing the surface area, x, of the workpiece after deburring 2 Representing the corresponding surface roughness of the surface of the workpiece after deburring, beta 0 、β 1 Beta 2 Is a regression coefficient, ε is an error term;
the regression coefficient is estimated using the least square method, and the estimation formula of the regression coefficient is as follows:
where M is the number of groups of selected data.
Further, step S400 includes:
s401, analyzing historical data of incomplete removal and excessive removal to obtain the service time L of the deburring tool of incomplete removal and excessive removal 0 And all deburring toolsThe deburring speed and the average value of deburring pressure corresponding to the using time of the tool are related;
s402, acquiring historical data of incomplete removal and excessive removal to obtain the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring, wherein the corresponding service time L of the deburring tool exists in the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring 0 Inputting the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring into a use time length prediction model of the deburring tool to obtain a use time length L 'of the deburring tool output by the prediction model, finding an equal use time length L of the deburring tool in the history data of complete removal, and correlating the average value of the deburring speed and the deburring pressure corresponding to the use time length L of the deburring tool after complete removal with the use time length L' of the deburring tool output by the prediction model;
if the using time length L' of the deburring tool output by the prediction model is more than or equal to L 0 Then the history data L of incomplete removal and excessive removal is adjusted 0 The corresponding deburring speed and deburring pressure enable the average value after adjustment to be consistent with the average value of the deburring speed and deburring pressure corresponding to the using duration L' of the deburring tool output by the prediction model; the use time of the deburring tool for incomplete removal and excessive removal is within the use time of the deburring tool for complete removal, and the deburring tool can be normally used, but the deburring effect is not ideal due to the parameter values of the deburring speed and the deburring pressure, so that the parameter values of the deburring speed and the deburring pressure need to be adjusted; the average value of the deburring speed and the deburring pressure corresponding to the using time length L of the completely removed deburring tool is associated with the using time length L 'of the deburring tool output by the prediction model, so that the average value after adjustment is consistent with the average value of the deburring speed and the deburring pressure corresponding to the using time length L' of the deburring tool output by the prediction model only by adjusting the parameter values of the deburring speed and the deburring pressure, and the deburring effect is improved;
if the service time length L' of the deburring tool output by the prediction model is less than L 0 Replacing the deburring tool; since the use time of the deburring tool for incomplete removal and excessive removal is longer than that of the deburring tool for complete removal, which means that the deburring tool has been damaged and the burrs of the workpiece cannot be completely removed, the deburring tool needs to be replaced;
s403, calculating the probability P of excessive removal and incomplete removal in each burr evaluation coefficient in the historical data, andwherein T is the number of the workpieces with the same burr evaluation coefficients, and T is the number of the workpieces which are excessively removed and incompletely removed in the same burr evaluation coefficients;
in the real-time deburring process, taking the process of completing deburring of a batch of workpieces as a period, firstly classifying according to burr evaluation coefficients, and then calculating the probability P corresponding to excessive removal and incomplete removal in each burr evaluation coefficient 1 And (2) andwherein T is 1 For each same burr evaluation coefficient of each same burr in a period of real-time data, t 1 The real-time data is the number of the workpieces which are excessively removed and incompletely removed in each identical burr evaluation coefficient;
P 0 for ideal evaluation probability, if P 0 ≥P 1 Monitoring the next round of deburring process; if P 0 ＜P 1 < P, return to step S401 until P 1 Less than P 0 Until that is reached; due to P 1 < P, the deburring effect is improved after optimization and adjustment, but due to P 0 ＜P 1 Since the ideal state is not reached, the process also needs to return to step S401 for adjustment; if P 1 And if the pressure is more than or equal to P, feeding back to related operators, and overhauling the deburring equipment.
The system comprises a data acquisition module, a burr evaluation module, a using time length prediction model, a real-time data monitoring and adjusting module and a probability calculation and optimization adjusting module;
the data acquisition module uses a plurality of sensors to collect historical data and real-time data, wherein the historical data and the real-time data comprise parameters such as deburring speed, deburring pressure, equipment temperature, equipment vibration and the like; the burr evaluation module is used for classifying historical data according to the calculated burr evaluation coefficient Q, and classifying the historical data into three types of complete removal, incomplete removal and excessive removal; the using time length prediction model analyzes the using time length of the deburring tool for the completely removed historical data; the real-time data monitoring and adjusting module predicts excessive removal and incomplete removal according to a prediction model, compares the values of the deburring speed and the deburring pressure in the real-time data with a prediction result, and adjusts corresponding data until the values are consistent with the prediction model if the values are inconsistent with the output result of the prediction model; the probability calculation and optimization adjustment module calculates the probability of excessive removal and incomplete removal under each burr evaluation coefficient in the historical data and the real-time data, compares the probability obtained in the real-time data with the probability of the historical data, and if the probability of the real-time data is smaller than the probability of the historical data, continues to perform optimization adjustment; if the real-time data probability is greater than or equal to the historical data probability, feedback is sent to related operators and equipment overhaul is carried out;
the output end of the data acquisition module is connected with the input end of the burr evaluation module; the output end of the data burr evaluation module is connected with the input end of the used time length prediction model; the output end of the using time length prediction model is connected with the input end of the real-time data monitoring and adjusting module; the output end of the real-time data monitoring and adjusting module is connected with the input end of the probability calculating and optimizing adjusting module.
The burr evaluation module comprises a burr evaluation coefficient calculation unit and a burr classification unit;
the burr evaluation coefficient calculation unit is used for calculating the burr evaluation coefficient of each surface of each workpiece before deburring according to the burr information of each surface of each workpiece before deburring in the historical data; the burr classification unit classifies each evaluation coefficient into one type according to the calculation result of the burr evaluation coefficient calculation unit, and further classifies each evaluation coefficient into three types of complete removal, incomplete removal and excessive removal according to the deburring effect;
the output end of the burr evaluation coefficient calculating unit is connected with the input end of the burr classifying unit.
The real-time data monitoring and adjusting module comprises a data monitoring unit and a parameter adjusting unit;
the data monitoring unit is used for recording data in the real-time flexible deburring process in real time; the parameter adjusting unit is used for optimizing and adjusting the real-time data according to the used time length prediction model;
the output end of the data monitoring unit is connected with the input end of the parameter adjusting unit.
The probability calculation and optimization adjustment module comprises a probability calculation unit and an optimization adjustment unit;
the probability calculation unit calculates the probability P corresponding to the excessive removal and the incomplete removal in each burr evaluation coefficient in the history data, and calculates the probability P corresponding to the excessive removal and the incomplete removal in each burr evaluation coefficient in the real-time data 1 The method comprises the steps of carrying out a first treatment on the surface of the The optimization adjusting unit performs optimization adjustment on parameters and operation of the system according to the probability calculation result;
the output end of the probability calculation unit is connected with the input end of the optimization adjustment unit.
Compared with the prior art, the invention has the following beneficial effects: through multi-sensor fusion and data analysis, the intelligent management of the burr removal process is realized without depending on human experience and subjective judgment, the participation of operators is reduced, and the influence of human factors on the burr removal effect is reduced; by establishing a database of historical data and analyzing by utilizing a classification and evaluation model, the deburring effect can be rapidly and accurately determined, and workpieces are classified, so that the operation parameters and equipment adjustment can be effectively optimized, the deburring process efficiency is improved, and the time and resources are saved; by establishing a prediction model, the relation between the using time of the tool and the deburring speed and deburring pressure is analyzed, so that the wear condition of the tool can be predicted in advance, corresponding maintenance and replacement measures are adopted, the scrapping and replacement frequency of the tool is reduced, and the cost is reduced.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic illustration of steps of a multi-sensor fusion flexible deburring management method of the present invention;
fig. 2 is a schematic block diagram of a multi-sensor fusion flexible deburring management system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
the flexible deburring management method for the multi-sensor fusion comprises the following specific steps of:
s100, acquiring historical data in the deburring process through a sensor, wherein the historical data comprises workpiece information and operation parameters, storing the historical data, and establishing a database; the workpiece information comprises workpiece size, material and burr information of the surface of the workpiece; the operating parameters include speed and pressure of deburring;
s200, acquiring burr information of each surface of the workpiece before deburring in the historical data, calculating burr evaluation coefficients of each surface of the workpiece before deburring, and classifying the historical data according to the difference of the burr evaluation coefficients; the burr information comprises the area and the number of burrs on each surface of the workpiece before the burrs are removed;
s300, evaluating historical data of the coefficients aiming at each burr, and further dividing the historical data into three parts, namely complete removal, excessive removal and incomplete removal, according to the deburring effect; constructing a prediction model of the use duration of the deburring tool by analyzing the completely removed historical data;
s400, analyzing historical data of incomplete removal and excessive removal according to a prediction model of the use duration of the deburring tool, and formulating corresponding optimization strategies and improvement measures; and (3) applying the formulated optimization strategy and improvement measure to the deburring process, monitoring and recording the operation parameter setting of the real-time data, comparing and analyzing with the historical data, and evaluating the effects of the optimization strategy and the improvement measure.
The step S100 includes:
historical data in the deburring process is collected through the sensor, corresponding workpiece information, operation parameters and equipment states are classified and collected according to different numbers of workpieces to form a database, namely, one workpiece number corresponds to one workpiece information, and one workpiece information is related to the operation parameters of corresponding deburring equipment in the deburring process.
Step 2100 includes:
s201, acquiring burr information of each surface of a workpiece before deburring in historical data, wherein the burr information comprises burr areas s of each surface of the workpiece i And a number n; wherein n is an integer of 1 or more, s i Representing the area of the ith burr on the surface of a workpiece;
s202, according to the formulaCalculating the area proportion of the burr area of one surface of the workpiece to the area of the one surface of the workpiece, wherein S represents the area of the one surface of the workpiece; according to the formula->Calculating the proportion of the number of burrs on one surface of a workpiece to the number of all burrs on the workpiece, wherein N is the number of burrs on one surface of the workpieceThe number of burrs; calculating a burr evaluation coefficient Q of each surface of each workpiece before deburring, and q=w 1 A 1 +w 2 A 2 Wherein w is 1 And w 2 Is a weighting coefficient;
s203, classifying historical data according to the calculated burr evaluation coefficients of all surfaces of the workpiece before deburring, wherein one burr evaluation coefficient is classified into one type, and the set is represented as Q= { Q 1 ,Q 2 ,...,Q m }, wherein Q 1 Burr evaluation coefficient representing the 1 st surface, Q 2 Burr evaluation coefficient representing the 2 nd surface, and so on, wherein Q m Representing the burr evaluation coefficient of the mth surface.
Assuming a batch of workpieces, each workpiece has a plurality of surfaces, and according to historical data, burr information of each surface of each workpiece is obtained, including the area and the number of burrs.
Acquiring burr information of the workpiece 1 in the historical data:
surface 1: sum of burr areas s=10mm 2 The number of burrs n=3;
surface 2: sum of burr areas s=8mm 2 The number of burrs n=2;
the area of both surfaces was s=100 mm 2 。
Calculating a burr evaluation coefficient Q of the surface of the workpiece, and assuming w 1 ＝0.8，w 2 ＝0.2；
Burr area ratio A of surface 1 1 ＝s/S＝10mm 2 /100mm 2 ＝0.1；
The burr number of the surface 1 is a ratio 2 ＝n/N＝3/(3+2)＝0.6；
Burr evaluation coefficient Q of surface 1 1 ＝w 1 A 1 +w 2 A 2 ＝0.8*0.1+0.2*0.6＝0.2；
Burr area ratio A of surface 2 1 ＝s/S＝8mm 2 /100mm 2 ＝0.08；
The burr number of the surface 2 is a ratio 2 ＝n/N＝2/(3+2)＝0.4；
Burr evaluation coefficient Q of surface 2 2 ＝w 1 A 1 +w 2 A 2 =0.8×0.08+0.2×0.4=0.144. Classifying the calculated burr evaluation coefficients of the workpiece 1:
the burr evaluation coefficient set of the workpiece 1 is q= { Q 1 ,Q 2 }＝{0.2,0.144}
Step S300 includes:
s301, acquiring corresponding deburred images for historical data of each burr evaluation coefficient, performing edge detection to obtain an edge area of the surface of the deburred workpiece, and comparing the edge area with a preset target edge area;
s302, if the edge area of the surface of the workpiece after deburring is larger than a preset target edge area, marking the corresponding historical data as incomplete removal; if the edge area of the surface of the workpiece after deburring is equal to a preset target edge area, marking the corresponding historical data as completely removed; if the edge area of the surface of the workpiece after deburring is smaller than a preset target edge area, marking the corresponding historical data as excessive removal;
s303, acquiring completely removed historical data, and constructing a using time length prediction model of the deburring tool; correlating all the deburring speeds and the average values of deburring pressures corresponding to the using time length, namely, one deburring speed and one average value of deburring pressure corresponding to one using time length; the use time period is recorded from the moment of replacing the deburring tool to the moment of completing the deburring operation of one surface of the workpiece.
The construction of the in-use time length prediction model of the deburring tool comprises the following steps:
acquiring completely removed historical data, and constructing a prediction model of the use duration of the deburring tool; the input of the prediction model is the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring; the surface area of the deburring workpiece refers to the area of each surface of the deburring workpiece; the corresponding surface roughness of the surface of the deburring workpiece means that the area of each surface of the deburring workpiece corresponds to one surface roughness; the output of the prediction model is the using time of the deburring tool; normalizing the input and output data to construct a prediction model;
the model is as follows:
L＝β 0 +β 1 x 1 +β 2 x 2 +ε
wherein L is the use time length of the deburring tool, x 1 Representing the surface area, x, of the workpiece after deburring 2 Representing the corresponding surface roughness of the surface of the workpiece after deburring, beta 0 、β 1 Beta 2 Is a regression coefficient, ε is an error term;
the regression coefficient is estimated using the least square method, and the estimation formula of the regression coefficient is as follows:
where M is the number of groups of selected data.
Step S400 includes:
s401, analyzing historical data of incomplete removal and excessive removal to obtain the service time L of the deburring tool of incomplete removal and excessive removal 0 And correlating the deburring speeds and the average values of deburring pressures corresponding to the using time lengths of all deburring tools;
s402, acquiring historical data of incomplete removal and excessive removal to obtain the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring, wherein the corresponding service time L of the deburring tool exists in the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring 0 The surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring are processedInputting a using time length prediction model of the deburring tool, obtaining a using time length L 'of the deburring tool output by the prediction model, finding an equal using time length L of the deburring tool in the completely removed historical data, and correlating the average value of the deburring speed and the deburring pressure corresponding to the using time length L of the completely removed deburring tool with the using time length L' of the deburring tool output by the prediction model;
if the using time length L' of the deburring tool output by the prediction model is more than or equal to L 0 Then the history data L of incomplete removal and excessive removal is adjusted 0 The corresponding deburring speed and deburring pressure enable the average value after adjustment to be consistent with the average value of the deburring speed and deburring pressure corresponding to the using duration L' of the deburring tool output by the prediction model; the use time of the deburring tool for incomplete removal and excessive removal is within the use time of the deburring tool for complete removal, and the deburring tool can be normally used, but the deburring effect is not ideal due to the parameter values of the deburring speed and the deburring pressure, so that the parameter values of the deburring speed and the deburring pressure need to be adjusted; the average value of the deburring speed and the deburring pressure corresponding to the using time length L of the completely removed deburring tool is associated with the using time length L 'of the deburring tool output by the prediction model, so that the average value after adjustment is consistent with the average value of the deburring speed and the deburring pressure corresponding to the using time length L' of the deburring tool output by the prediction model only by adjusting the parameter values of the deburring speed and the deburring pressure, and the deburring effect is improved;
if the service time length L' of the deburring tool output by the prediction model is less than L 0 Replacing the deburring tool; since the use time of the deburring tool for incomplete removal and excessive removal is longer than that of the deburring tool for complete removal, which means that the deburring tool has been damaged and the burrs of the workpiece cannot be completely removed, the deburring tool needs to be replaced;
s403, calculating the probability P of excessive removal and incomplete removal in each burr evaluation coefficient in the historical data, andwherein T is the number of the workpieces with the same burr evaluation coefficients, and T is the number of the workpieces which are excessively removed and incompletely removed in the same burr evaluation coefficients;
in the real-time deburring process, taking the process of completing deburring of a batch of workpieces as a period, firstly classifying according to burr evaluation coefficients, and then calculating the probability P corresponding to excessive removal and incomplete removal in each burr evaluation coefficient 1 And (2) andwherein T is 1 For each same burr evaluation coefficient of each same burr in a period of real-time data, t 1 The real-time data is the number of the workpieces which are excessively removed and incompletely removed in each identical burr evaluation coefficient;
P 0 for ideal evaluation probability, if P 0 ≥P 1 Monitoring the next round of deburring process; if P 0 ＜P 1 < P, return to step S401 until P 1 Less than P 0 Until that is reached; if P 1 And if the pressure is more than or equal to P, feeding back to related operators, and overhauling the deburring equipment.
Assuming that the probability of excessive removal and incomplete removal in each burr evaluation coefficient in the historical data is calculated, wherein p_1 is the probability of excessive removal of the burr evaluation coefficient a in the historical data, and p_1=0.4; p_2 is the probability of incomplete removal of the burr evaluation coefficient a in the history data, and p_2=0.3;
assuming that in the process of real-time deburring, taking the process of completing one deburring as one period, calculating the probability of excessive removal p1_1=0.2 of the deburring evaluation coefficient a, and calculating the probability of incomplete removal p1_2=0.05 of the deburring evaluation coefficient a;
assuming ideal evaluation probability P 0 =0.05, since p_1 > p1_1, the deburring effect is improved after the adjustment and optimization, but since p1_1 > P 0 Therefore, it is necessary toContinuing to optimize the adjustment until P1_1 is reduced to 0.05; since p1_2=p 0 And after the adjustment and optimization are performed, the ideal state is reached, and the next round of evaluation is performed.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A flexible deburring management method for multi-sensor fusion is characterized in that: the method comprises the following steps:
s100, acquiring historical data in the deburring process through a sensor, wherein the historical data comprises workpiece information and operation parameters, storing the historical data, and establishing a database; the workpiece information comprises workpiece size, material and burr information of the surface of the workpiece; the operating parameters include speed and pressure of deburring;
s200, acquiring burr information of each surface of the workpiece before deburring in the historical data, calculating burr evaluation coefficients of each surface of the workpiece before deburring, and classifying the historical data according to the difference of the burr evaluation coefficients; the burr information comprises the area and the number of burrs on each surface of the workpiece before the burrs are removed;
s300, evaluating historical data of the coefficients aiming at each burr, and further dividing the historical data into three parts, namely complete removal, excessive removal and incomplete removal, according to the deburring effect; constructing a prediction model of the use duration of the deburring tool by analyzing the completely removed historical data;
s400, analyzing historical data of incomplete removal and excessive removal according to a prediction model of the use duration of the deburring tool, and formulating corresponding optimization strategies and improvement measures; and (3) applying the formulated optimization strategy and improvement measure to the deburring process, monitoring and recording the operation parameter setting of the real-time data, comparing and analyzing with the historical data, and evaluating the effects of the optimization strategy and the improvement measure.
2. The flexible deburring management method of multi-sensor fusion of claim 1, wherein: the step S100 includes:
historical data in the deburring process is collected through the sensor, corresponding workpiece information, operation parameters and equipment states are classified and collected according to different numbers of workpieces to form a database, namely, one workpiece number corresponds to one workpiece information, and one workpiece information is related to the operation parameters of corresponding deburring equipment in the deburring process.
3. The flexible deburring management method of multi-sensor fusion of claim 2, further comprising: the step 200 includes:
s201, acquiring burr information of each surface of a workpiece before deburring in historical data, wherein the burr information comprises burr areas s of each surface of the workpiece i And a number n; wherein n is an integer of 1 or more, s i Representing the area of the ith burr on the surface of a workpiece;
s202, according to the formulaCalculating the area proportion of the burr area of one surface of the workpiece to the area of the one surface of the workpiece, wherein S represents the area of the one surface of the workpiece; according to the formula->Calculating the proportion of the number of burrs on one surface of a workpiece to the number of all burrs of the workpiece, wherein N is the number of all burrs of the workpiece; calculating a burr evaluation coefficient Q of each surface of each workpiece before deburring, and q=w 1 A 1 +w 2 A 2 Wherein w is 1 And w 2 Is a weighting coefficient;
s203, classifying historical data according to the calculated burr evaluation coefficients of all surfaces of the workpiece before deburring, wherein one burr evaluation coefficient is classified into one type, and the set is represented as Q= { Q 1 ,Q 2 ,...,Q m }, wherein Q 1 Burr evaluation coefficient representing the 1 st surface, Q 2 Burr evaluation coefficient representing the 2 nd surface, and so on, wherein Q m Representing the burr evaluation coefficient of the mth surface.
4. A multi-sensor fusion flexible deburring management method as claimed in claim 3, wherein: the step S300 includes:
s301, acquiring corresponding deburred images for historical data of each burr evaluation coefficient, performing edge detection to obtain an edge area of the surface of the deburred workpiece, and comparing the edge area with a preset target edge area;
s302, if the edge area of the surface of the workpiece after deburring is larger than a preset target edge area, marking the corresponding historical data as incomplete removal; if the edge area of the surface of the workpiece after deburring is equal to a preset target edge area, marking the corresponding historical data as completely removed; if the edge area of the surface of the workpiece after deburring is smaller than a preset target edge area, marking the corresponding historical data as excessive removal;
s303, acquiring completely removed historical data, and constructing a using time length prediction model of the deburring tool; correlating the deburring speeds and the average values of deburring pressures corresponding to the using time lengths of all deburring tools, namely, the average value of one deburring speed and one deburring pressure corresponding to one using time length; the deburring tool usage time length is recorded from the deburring tool replacement time to the time period when the deburring operation of one surface of the workpiece is completed.
5. The flexible deburring management method of multi-sensor fusion of claim 4, further comprising: the construction of the long-time-to-use prediction model of the deburring tool comprises the following steps:
acquiring completely removed historical data, and constructing a prediction model of the use duration of the deburring tool; the input of the prediction model is the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring; the surface area of the deburring workpiece refers to the area of each surface of the deburring workpiece; the corresponding surface roughness of the surface of the deburring workpiece means that the area of each surface of the deburring workpiece corresponds to one surface roughness; the output of the prediction model is the using time of the deburring tool; normalizing the input and output data to construct a prediction model;
the model is as follows:
L＝β 0 +β 1 x 1 +β 2 x 2 +ε
wherein L is the use time length of the deburring tool, x 1 Representing the surface area, x, of the workpiece after deburring 2 Representing the corresponding surface roughness of the surface of the workpiece after deburring, beta 0 、β 1 Beta 2 Is a regression coefficient, ε is an error term;
the regression coefficient is estimated using the least square method, and the estimation formula of the regression coefficient is as follows:
where M is the number of groups of selected data.
6. The flexible deburring management method of multi-sensor fusion of claim 5, further comprising the steps of: the step S400 includes:
s401, analyzing historical data of incomplete removal and excessive removal to obtain the service time L of the deburring tool of incomplete removal and excessive removal 0 And correlating the deburring speeds and the average values of deburring pressures corresponding to the using time lengths of all deburring tools;
s402, acquiring historical data of incomplete removal and excessive removal to obtain the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring, wherein the corresponding service time L of the deburring tool exists in the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring 0 Inputting the surface area of the workpiece after deburring and the corresponding surface roughness of the surface of the workpiece after deburring into a use time length prediction model of the deburring tool to obtain a use time length L 'of the deburring tool output by the prediction model, finding an equal use time length L of the deburring tool in the history data of complete removal, and correlating the average value of the deburring speed and the deburring pressure corresponding to the use time length L of the deburring tool after complete removal with the use time length L' of the deburring tool output by the prediction model;
if the using time length L' of the deburring tool output by the prediction model is more than or equal to L 0 Then the history data L of incomplete removal and excessive removal is adjusted 0 Corresponding deburring speed and deburring pressure to ensure that the average value after adjustment is matched with a deburring tool output by a prediction modelThe deburring speed corresponding to the using time length L' is consistent with the average value of deburring pressure; if the service time length L' of the deburring tool output by the prediction model is less than L 0 Replacing the deburring tool;
s403, calculating the probability P of excessive removal and incomplete removal in each burr evaluation coefficient in the historical data, andwherein T is the number of the workpieces with the same burr evaluation coefficients, and T is the number of the workpieces which are excessively removed and incompletely removed in the same burr evaluation coefficients;
in the real-time deburring process, taking the process of completing deburring of a batch of workpieces as a period, firstly classifying according to burr evaluation coefficients, and then calculating the probability P corresponding to excessive removal and incomplete removal in each burr evaluation coefficient 1 And (2) andwherein T is 1 For each same burr evaluation coefficient of each same burr in a period of real-time data, t 1 The real-time data is the number of the workpieces which are excessively removed and incompletely removed in each identical burr evaluation coefficient;
P 0 for ideal evaluation probability, if P 0 ≥P 1 Monitoring the next round of deburring process; if P 0 ＜P 1 < P, return to step S401 until P 1 Less than P 0 Until that is reached; if P 1 And if the pressure is more than or equal to P, feeding back to related operators, and overhauling the deburring equipment.
7. A flexible deburring management system for multi-sensor fusion, characterized in that: the system comprises a data acquisition module, a burr evaluation module, a using time length prediction model, a real-time data monitoring and adjusting module and a probability calculation and optimization adjusting module;
the data acquisition module uses a plurality of sensors to collect historical data and real-time data, wherein the historical data and the real-time data comprise parameters such as deburring speed, deburring pressure, equipment temperature, equipment vibration and the like; the burr evaluation module is used for classifying historical data according to the calculated burr evaluation coefficient Q, and classifying the historical data into three types of complete removal, incomplete removal and excessive removal; the using time length prediction model analyzes the using time length of the deburring tool for the completely removed historical data; the real-time data monitoring and adjusting module predicts excessive removal and incomplete removal according to a prediction model, compares the values of the deburring speed and the deburring pressure in the real-time data with a prediction result, and adjusts corresponding data until the values are consistent with the prediction model if the values are inconsistent with the output result of the prediction model; the probability calculation and optimization adjustment module calculates the probability of excessive removal and incomplete removal under each burr evaluation coefficient in the historical data and the real-time data, compares the probability obtained in the real-time data with the probability of the historical data, and if the probability of the real-time data is smaller than the probability of the historical data, continues to perform optimization adjustment; if the real-time data probability is greater than or equal to the historical data probability, feedback is sent to related operators and equipment overhaul is carried out;
the output end of the data acquisition module is connected with the input end of the burr evaluation module; the output end of the data burr evaluation module is connected with the input end of the used time length prediction model; the output end of the used time length prediction model is connected with the input end of the real-time data monitoring and adjusting module; the output end of the real-time data monitoring and adjusting module is connected with the input end of the probability calculating and optimizing adjusting module.
8. The multi-sensor fusion flexible deburring management system of claim 7, wherein: the burr evaluation module comprises a burr evaluation coefficient calculation unit and a burr classification unit;
the burr evaluation coefficient calculation unit is used for calculating the burr evaluation coefficient of each surface of each workpiece before deburring according to the burr information of each surface of each workpiece before deburring in the historical data; the burr classification unit classifies each evaluation coefficient into one type according to the calculation result of the burr evaluation coefficient calculation unit, and further classifies each evaluation coefficient into three types of complete removal, incomplete removal and excessive removal according to the deburring effect;
the output end of the burr evaluation coefficient calculating unit is connected with the input end of the burr classifying unit.
9. The multi-sensor fusion flexible deburring management system of claim 7, wherein: the real-time data monitoring and adjusting module comprises a data monitoring unit and a parameter adjusting unit;
the data monitoring unit is used for recording data in the real-time flexible deburring process in real time; the parameter adjustment unit is used for optimizing and adjusting the real-time data according to the used time length prediction model;
the output end of the data monitoring unit is connected with the input end of the parameter adjusting unit.
10. The multi-sensor fusion flexible deburring management system of claim 7, wherein: the probability calculation and optimization adjustment module comprises a probability calculation unit and an optimization adjustment unit;
the probability calculation unit calculates the probability P corresponding to the excessive removal and the incomplete removal in each burr evaluation coefficient in the historical data and calculates the probability P corresponding to the excessive removal and the incomplete removal in each burr evaluation coefficient in the real-time data 1 The method comprises the steps of carrying out a first treatment on the surface of the The optimization adjusting unit performs optimization adjustment on parameters and operation of the system according to the probability calculation result;
the output end of the probability calculation unit is connected with the input end of the optimization adjustment unit.
CN202311405692.3A 2023-10-27 2023-10-27 Multi-sensor fusion flexible deburring management method and system Active CN117313951B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311405692.3A CN117313951B (en) 2023-10-27 2023-10-27 Multi-sensor fusion flexible deburring management method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311405692.3A CN117313951B (en) 2023-10-27 2023-10-27 Multi-sensor fusion flexible deburring management method and system

Publications (2)

Publication Number Publication Date
CN117313951A true CN117313951A (en) 2023-12-29
CN117313951B CN117313951B (en) 2024-02-20

Family

ID=89246337

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311405692.3A Active CN117313951B (en) 2023-10-27 2023-10-27 Multi-sensor fusion flexible deburring management method and system

Country Status (1)

Country Link
CN (1) CN117313951B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021003788A (en) * 2019-06-27 2021-01-14 ファナック株式会社 Control device and control method
CN115170563A (en) * 2022-09-06 2022-10-11 江苏中科云控智能工业装备有限公司 Detection system and method for die casting after deburring based on Internet of things
CN115729188A (en) * 2022-11-18 2023-03-03 江苏中科云控智能工业装备有限公司 Deburring production line control signal transmission system based on digital twinning
US20230214740A1 (en) * 2022-11-21 2023-07-06 CHINA CONSTRUCTION INDUSTRIAL & ENERGY ENGINEERING GROUP Co.,Ltd. Digital construction-based intelligent construction period early warning system and method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021003788A (en) * 2019-06-27 2021-01-14 ファナック株式会社 Control device and control method
CN115170563A (en) * 2022-09-06 2022-10-11 江苏中科云控智能工业装备有限公司 Detection system and method for die casting after deburring based on Internet of things
CN115729188A (en) * 2022-11-18 2023-03-03 江苏中科云控智能工业装备有限公司 Deburring production line control signal transmission system based on digital twinning
US20230214740A1 (en) * 2022-11-21 2023-07-06 CHINA CONSTRUCTION INDUSTRIAL & ENERGY ENGINEERING GROUP Co.,Ltd. Digital construction-based intelligent construction period early warning system and method

Also Published As

Publication number Publication date
CN117313951B (en) 2024-02-20

Similar Documents

Publication Publication Date Title
CN109270899B (en) Digital twin-based marine diesel engine heavy part manufacturing process control method
Mikołajczyk et al. Neural network approach for automatic image analysis of cutting edge wear
EP0509817B1 (en) System and method utilizing a real time expert system for tool life prediction and tool wear diagnosis
CN101710235B (en) Method for automatically identifying and monitoring on-line machined workpieces of numerical control machine tool
CN108846581A (en) A kind of machine tool reliability evaluation system and method
CN113909996B (en) High-end equipment machining state monitoring method and system based on digital twinning
CN109968671B (en) 3D printing process fault diagnosis method and device
US10983501B2 (en) Tool-life prediction system and method thereof
JP2020127968A (en) Learning device, and cutting processing evaluation system
CN115170563A (en) Detection system and method for die casting after deburring based on Internet of things
CN114742798A (en) Disc shear tool changing time prediction system and method based on shear blade wear detection
CN115601313A (en) Visual monitoring management system for tempered glass production process
CN112580935A (en) Industrial product production process traceability analysis method based on machine vision
CN117313951B (en) Multi-sensor fusion flexible deburring management method and system
CN112946072A (en) Abrasive belt wear state monitoring method based on machine learning
CN116703254B (en) Production information management system for mechanical parts of die
CN112859741A (en) Method and system for evaluating operation reliability of sequential action units of machine tool
Li et al. Adaptive network fuzzy inference system and support vector machine learning for tool wear estimation in high speed milling processes
CN116037705A (en) Real-time monitoring system for working state of cold stamping die
CN115933534A (en) Numerical control intelligent detection system and method based on Internet of things
CN117196414B (en) Metal processing quality control system
JEMIELNIAK Tool and process condition monitoring
CN117911415B (en) Automatic equipment supervision system and method based on machine vision
Li et al. A deep learning based method for cutting parameter optimization for band saw machine
CN115213735B (en) System and method for monitoring cutter state in milling process

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant