Intelligent fault monitoring system for numerical control machine tool

Abstract

The invention relates to the technical field of fault monitoring, in particular to a numerical control machine tool fault intelligent monitoring system, which comprises a machine tool data acquisition module used for acquiring operation data and acoustic emission data of a numerical control machine tool; the power analysis module is used for analyzing the consumption state of the spindle motor and adjusting the analysis process; the sound signal analysis module is used for constructing a sound energy abnormal coefficient; the temperature monitoring module is used for constructing a temperature anomaly coefficient according to the cutting area temperature collected in the monitoring period; the risk early warning module is used for analyzing the tool wear state according to the construction result of the motor consumption index, the sound energy abnormal coefficient and the temperature abnormal coefficient in the risk monitoring period and carrying out tool wear risk early warning on a user; the roughness analysis module is used for analyzing the surface quality state of the workpiece; and the control module is used for controlling the feeding speed of the next quality monitoring period. The fault monitoring efficiency of the numerical control machine tool is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and in particular to an intelligent fault monitoring system for numerically controlled machine tools. Background Art

[0002] In automobile manufacturing, when manufacturing high-precision engine parts, tool wear or damage during CNC machine cutting will directly affect the machining accuracy and surface finish of the parts. For example, when a CNC milling machine is used to process an engine block, tool wear will lead to a decrease in machining accuracy, thereby affecting the overall performance of the engine. In order to avoid defective products and long equipment downtime, there is an urgent need for an intelligent monitoring system that can promptly alarm and notify the operator when tool wear reaches a critical state or an abnormality occurs, and even trigger an automatic stop and issue maintenance recommendations.

[0003] Chinese patent publication number CN117991752B discloses an equipment fault prediction system and method based on digital twin and Internet of Things technology, which uses artificial intelligence technology based on deep learning to monitor and analyze the spindle speed value, spindle temperature value, feed speed value, operating power value and vibration signal of the CNC machine tool during operation, captures the time series characteristic expression of each monitoring parameter, and judges whether there is any abnormality in the operating status of the CNC machine tool based on the time series correlation characteristics of each monitoring parameter; it can be seen that when monitoring the operating status of the CNC machine tool, this scheme only analyzes the operating parameters of the CNC machine tool, but does not analyze the tools of the CNC machine tool, and there is a problem of low efficiency in CNC machine tool fault monitoring. Summary of the invention

[0004] The object of the present invention is to provide an intelligent fault monitoring system for CNC machine tools to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A CNC machine tool fault intelligent monitoring system, comprising: Machine tool data acquisition module, used to collect CNC machine tool operation data and acoustic emission data; The power analysis module is used to analyze the spindle motor consumption status according to the spindle power collected during the risk monitoring period to construct a motor consumption index, and adjust the analysis process according to the CNC machine tool operation data collected during the risk monitoring period; The sound signal analysis module is used to construct the sound energy anomaly coefficient according to the amplitude of the acoustic emission signal collected during the risk monitoring period; The temperature monitoring module is used to construct the temperature anomaly coefficient according to the cutting area temperature collected during the monitoring period; The risk warning module is used to analyze the tool wear status according to the results of the motor consumption index, the acoustic energy abnormality coefficient and the temperature abnormality coefficient during the risk monitoring period, and to issue a tool wear risk warning to the user; A roughness analysis module is used to analyze the surface quality status of the workpiece according to the workpiece surface roughness collected during the quality monitoring cycle; The control module is used to control the feed speed of the next quality monitoring cycle according to the tool wear risk warning results and the analysis results of the workpiece surface quality status during the quality monitoring cycle.

[0006] Further, the power analysis module includes a power analysis unit, which is used to compare the spindle power collected during the risk monitoring period with the preset power p0, and analyze the abnormality of the spindle power according to the comparison result, and the abnormality of the spindle power includes normal and abnormal; The power analysis unit analyzes the motor consumption status according to the analysis results of the abnormality of the spindle power within the risk monitoring period. The motor consumption status includes a normal state and a high consumption state. If the spindle motor consumption state in the current risk monitoring period is a normal state, the power abnormality coefficient is set to GL1; if the spindle motor consumption state in the current risk monitoring period is a high consumption state, the power abnormality coefficient is set to GL2.

[0007] Furthermore, the power analysis module also includes a removal rate analysis unit, which calculates the material removal rate QC of the workpiece according to the feed speed js, cutting depth qs and cutting width qk collected during the risk monitoring period, and compares the material removal rate QC of the workpiece with the preset removal rate q0 to analyze the cutting load state of the tool. The cutting load state of the tool includes a normal state and a high load state. If the cutting load state of the tool is a high load state, the preset power is adjusted to p0'.

[0008] Furthermore, the power analysis module also includes a hardness analysis unit, which is used to compare the collected workpiece hardness gy with the preset hardness gy0 to analyze the hardness state of the workpiece. The hardness state of the workpiece includes normal and abnormal. If the hardness state of the workpiece is abnormal, the preset removal rate q0 is adjusted to q0'.

[0009] Further, the sound signal analysis module includes an energy calculation unit, and the energy calculation unit is used to calculate the energy A of the acoustic emission signal according to the amplitude of the acoustic emission signal collected during the risk monitoring period; The sound signal analysis module also includes an energy state analysis unit, which analyzes the energy growth state of the acoustic emission signal according to the acoustic emission signal energy A within the risk monitoring period and the preset energy threshold A0. The acoustic emission signal energy growth state includes a normal state and an abnormal state. If the acoustic emission signal energy growth state in the current risk monitoring period is a normal state, the acoustic energy abnormality coefficient is set to SY1; if the acoustic emission signal energy growth state in the current risk monitoring period is an abnormal state, the acoustic energy abnormality coefficient is set to SY2.

[0010] Furthermore, the temperature monitoring module is used to compare the cutting area temperature t0 collected during the monitoring period with the preset temperature t1, and analyze the temperature state of the cutting area according to the comparison result. The temperature state includes a normal state and a high temperature state. If the temperature state of the cutting area in the current risk monitoring period is a normal state, the temperature anomaly coefficient is set to WD1; if the temperature state of the cutting area in the current risk monitoring period is a high temperature state, the temperature anomaly coefficient is set to WD2.

[0011] Furthermore, the risk warning module analyzes the tool wear status according to the construction results of the motor consumption index, the sound energy abnormality coefficient and the temperature abnormality coefficient during the risk monitoring period. The tool wear status includes normal wear and abnormal wear. If the tool wear status during the risk monitoring period is normal wear, no tool wear risk warning is issued to the user; if the tool wear status during the risk monitoring period is abnormal wear, a tool wear risk warning is issued to the user.

[0012] Furthermore, the roughness analysis module includes an abnormality analysis unit, which is used to compare the workpiece surface roughness q0 collected during the quality monitoring period with the preset surface roughness q1, and analyze the abnormality of the workpiece surface roughness based on the comparison result. The abnormality of the workpiece surface roughness includes normal and abnormal.

[0013] Furthermore, the roughness analysis module also includes a quality status analysis unit, which is used to analyze the workpiece surface quality status according to the analysis result of the surface roughness abnormality within the quality monitoring period, and the workpiece surface quality status includes a normal state and an abnormal state.

[0014] Furthermore, the control module is used to analyze the tool state according to the tool wear risk warning result and the analysis result of the workpiece surface quality state in the quality monitoring cycle, and control the feed speed of the next quality monitoring cycle according to the analysis result, wherein: When the surface quality state of the workpiece in the quality monitoring period is normal, if m1×r0 / R≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G1; if m1×r0 / R>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G2; When the surface quality state of the workpiece in the quality monitoring period is abnormal, if m1×r0 / R+m2×(d0 / D-β)≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G3; if m1×r0 / R+m2×(d0 / D-β)>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G4.

[0015] The beneficial effects of the present invention are as follows: The intelligent fault monitoring system for CNC machine tools of this embodiment can effectively realize comprehensive monitoring of the operating status of the machine tools. The system not only improves the working efficiency and safety of the machine tools, but also can significantly extend the service life of the tools and reduce maintenance costs, thus providing strong support for the intelligent management of CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 Schematic diagram of the structure of the intelligent monitoring system for CNC machine tool faults in this embodiment.

[0018] Figure 2 FIG. 4 is a schematic diagram of the structure of the power analysis module of this embodiment.

[0019] Figure 3 Schematic diagram of the structure of the sound signal analysis module of this embodiment.

[0020] Figure 4 Schematic diagram of the structure of the roughness analysis module of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, it is a structural diagram of the intelligent monitoring system for faults of numerically controlled machine tools in this embodiment, and the system includes: The machine tool data acquisition module is used to collect CNC machine tool operation data and acoustic emission data; the CNC machine tool operation data includes spindle power, cutting area temperature, feed speed, cutting depth, cutting width, workpiece hardness and workpiece surface roughness, and the acoustic emission data is the acoustic emission signal amplitude.

[0024] It can be understood that the present embodiment does not specifically limit the method for collecting the operation data and acoustic emission data of the CNC machine tool, and those skilled in the art can freely set it as long as the collection requirements of the operation data and acoustic emission data of the CNC machine tool are met. Among them, the spindle power can be collected by the built-in current and voltage sensors of the CNC machine tool, the temperature of the cutting area can be collected by the thermocouple, the feed speed can be collected by the control system of the CNC machine tool, the cutting depth and cutting width can be collected by the tool path planning software of the CNC machine tool, the hardness of the workpiece can be obtained through interaction, the surface roughness of the workpiece can be collected by the online non-contact surface quality monitoring equipment, and the acoustic emission data can be collected by the acoustic emission sensor.

[0025] Please continue reading Figure 1 As shown, the system includes a power analysis module for analyzing the spindle motor consumption status according to the spindle power collected during the risk monitoring period, and adjusting the analysis process according to the feed speed, cutting depth, cutting width and workpiece hardness collected during the risk monitoring period, and the power analysis module is connected to the machine tool data acquisition module; it can be understood that the setting of the risk monitoring period is not specifically limited in this embodiment, and those skilled in the art can set it freely, as long as the setting requirements of the risk monitoring period are met, wherein the risk monitoring period can be set to 3 seconds, 5 seconds, etc.

[0026] See also Figure 2 As shown, the power analysis module includes: The power analysis unit is used to compare the spindle power collected during the risk monitoring period with the preset power p0, and analyze the abnormality of the spindle power according to the comparison result, where: If pi≤p0, the power analysis unit determines that the i-th spindle power collected during the risk monitoring period is normal; If pi>p0, the power analysis unit determines that the i-th spindle power collected during the risk monitoring period is abnormal; The power analysis unit analyzes the motor consumption state according to the analysis result of the abnormality of the spindle power in the risk monitoring period, and constructs the motor consumption index according to the analysis result, wherein: When E0 / E≤α, the power analysis unit determines that the spindle motor consumption state in the current risk monitoring period is normal, and sets the power abnormality coefficient to GL1, setting GL1=0; When E0 / E>α, the power analysis unit determines that the spindle motor consumption state in the current risk monitoring period is a high consumption state, and sets the power abnormality coefficient to GL2, setting GL2=E0 / E-α; by comparing with the preset power, potential abnormalities are discovered in time, and by periodically monitoring the spindle power, the consumption state of the spindle motor is analyzed in real time, thereby improving the accuracy of tool wear risk warning; Among them, pi is the i-th spindle power collected during the risk monitoring period, E0 is the number of spindle power anomalies during the risk monitoring period, E is the total number of spindle power data collected during the risk monitoring period, and α is the preset anomaly ratio.

[0027] It can be understood that, in this embodiment, there is no specific limitation on the setting of the preset power and the preset abnormality ratio, and those skilled in the art can set them freely, as long as the setting requirements of the preset power and the preset abnormality ratio are met, wherein p0 can be set to 1.25 times the motor power of the workpiece in the normal processing state, and the optimal value of α is 0.05.

[0028] Please continue reading Figure 2 As shown, the power analysis module also includes: A removal rate analysis unit connected to the power analysis unit, wherein the removal rate analysis unit calculates the material removal rate QC of the workpiece according to the feed speed js, cutting depth qs and cutting width qk collected during the risk monitoring period, and sets QC=js×qs×qk; The removal rate analysis unit compares the material removal rate QC of the workpiece with the preset removal rate q0 to analyze the cutting load state of the tool, thereby adjusting the analysis process of the motor consumption state, thereby improving the accuracy of the tool wear risk warning; If QC≤q0, the removal rate analysis unit determines that the cutting load state of the tool is normal and does not make any adjustments; if QC>q0, the removal rate analysis unit determines that the cutting load state of the tool is high load and adjusts the preset power to p0', setting p0'=p0×{1+[e 4×（QC-q0） / (QC+q0) -1] / [e 4-1]}, e is the natural logarithm; this unit can effectively monitor the cutting load state of the tool by calculating the material removal rate of the workpiece and comparing it with the preset removal rate. If the cutting load is too high, the system will automatically adjust the preset power, thereby improving the accuracy of the spindle motor consumption status analysis.

[0029] It is understandable that the setting of the preset removal rate is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset removal rate are met. Among them, the optimal value of q0 is 10000mm 3 / min.

[0030] Please continue reading Figure 2 As shown, the power analysis module also includes: A hardness analysis unit connected to the removal rate analysis unit is used to compare the collected workpiece hardness gy with the preset hardness gy0 to analyze the hardness state of the workpiece, and adjust the analysis process of the cutting load state of the tool according to the analysis result, wherein: If gy≤gy0, the hardness analysis unit determines that the hardness state of the workpiece is normal and does not make any adjustments; if gy>gy0, the hardness analysis unit determines that the hardness state of the workpiece is abnormal, and adjusts the preset removal rate q0 to q0', setting q0'=q0×{1-exp[lg(gy-gy0) / (gy+gy0)]}; the unit dynamically adjusts the preset removal rate during the processing by comparing the hardness of the workpiece with the preset hardness. The dynamic adjustment mechanism enables the system to adapt to the processing requirements of different materials, thereby improving the accuracy of the spindle motor consumption status analysis.

[0031] It can be understood that the setting of the preset hardness is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset hardness are met, wherein the optimal value of gy0 is 160HB.

[0032] Please continue reading Figure 1 As shown, the system includes a sound signal analysis module, which is used to analyze the energy growth state of the acoustic emission signal according to the acoustic emission signal amplitude collected during the risk monitoring period, and to construct the acoustic energy abnormality coefficient according to the analysis result. The sound signal analysis module is connected to the machine tool data acquisition module.

[0033] See also Figure 3 As shown, the sound signal analysis module includes: The energy calculation unit is used to calculate the acoustic emission signal energy A according to the acoustic emission signal amplitude collected during the risk monitoring period, and is set as follows: G4=g0×exp{[γ-m1×r0 / R-m2×(d0 / D-β)]}, wherein Fj is the acoustic emission signal amplitude of the jth sampling point collected during the risk monitoring period, J is the number of sampling points in the risk monitoring period, and △t is the time interval between adjacent sampling points; the unit converts the acoustic emission signal amplitude into acoustic emission signal energy to improve the accuracy of the acoustic emission signal energy growth state analysis, thereby improving the accuracy of the acoustic energy coefficient construction.

[0034] Please continue reading Figure 3 As shown, the sound signal analysis module also includes: An energy state analysis unit is connected to the energy calculation unit. The energy state analysis unit analyzes the energy growth state of the acoustic emission signal according to the acoustic emission signal energy A within the risk monitoring period and the preset energy threshold A0, and constructs an acoustic energy abnormality coefficient according to the analysis result to quantify the abnormal degree of tool wear, wherein: If A / A0≤f, the energy state analysis unit determines that the energy growth state of the acoustic emission signal in the current risk monitoring period is normal, and sets the acoustic energy abnormality coefficient to SY1, setting: SY1=0; If A / A0>f, the energy state analysis unit determines that the energy growth state of the acoustic emission signal in the current risk monitoring period is abnormal, and sets the acoustic energy abnormality coefficient to SY2, setting: SY2=3×(A / A0-f) 2 -2×(A / A0-f) 3 , f is the preset proportional threshold; by comparing the acoustic emission signal energy with the set threshold, the growth state of the acoustic energy is judged. If the acoustic energy is abnormal, the module will generate the acoustic energy abnormality coefficient in time to quantify the abnormal degree of tool wear, thereby improving the accuracy of tool wear risk warning.

[0035] It can be understood that, in this embodiment, the setting of the preset energy threshold and the preset ratio threshold is not specifically limited, and those skilled in the art can set them freely, as long as the setting requirements of the preset energy threshold and the preset ratio threshold are met. Among them, A0 can be set by recording acoustic emission data for a period of time under stable cutting conditions, and the energy value obtained by statistics is then used as a benchmark value for future monitoring. The optimal value of f is 1.2.

[0036] Please continue reading Figure 1As shown, the system includes a temperature monitoring module, which is connected to the machine tool data acquisition module. The temperature monitoring module is used to compare the cutting area temperature t0 collected during the monitoring period with the preset temperature t1, and analyze the temperature state of the cutting area according to the comparison result, and construct the temperature anomaly coefficient according to the analysis result, wherein: If t0≤t1, the temperature monitoring module determines that the temperature state of the cutting area in the current risk monitoring period is normal, and sets the temperature anomaly coefficient to WD1, setting WD1=0; If t0>t1, the temperature monitoring module determines that the temperature state of the cutting area in the current risk monitoring period is a high temperature state, and sets the temperature anomaly coefficient to WD2, setting WD2=ln[4×(t0-t1) / (t0+t1)] / ln5; by real-time monitoring of the temperature of the cutting area, the temperature anomaly coefficient can be constructed when the temperature exceeds the preset value. This monitoring mechanism can avoid tool damage caused by overheating, thereby improving the accuracy of tool wear risk warning.

[0037] Specifically, the cutting area temperature collected during the monitoring period in this embodiment is the average cutting area temperature during the risk monitoring period.

[0038] It is understandable that the setting of the preset temperature is not specifically limited in this embodiment, and those skilled in the art can set it freely as long as the setting requirements of the preset temperature are met. Among them, when the tool is a cemented carbide tool, the optimal value of t1 is 800°C.

[0039] Please continue reading Figure 1 As shown, the system also includes: A risk warning module is connected to the power analysis module, the sound signal analysis module, and the temperature monitoring module; the risk warning module analyzes the tool wear state according to the construction results of the motor consumption index, the sound energy abnormality coefficient, and the temperature abnormality coefficient during the risk monitoring period, and issues a tool wear risk warning to the user, wherein: If x1×motor consumption index+x2×acoustic energy abnormal coefficient+x3×temperature abnormal coefficient≤u0, the risk warning module determines that the tool wear state within the risk monitoring period is normal wear, and does not issue a tool wear risk warning to the user; If x1×motor consumption index+x2×acoustic energy abnormal coefficient+x3×temperature abnormal coefficient>u0, the risk warning module determines that the tool wear state within the risk monitoring period is abnormal wear, and issues a tool wear risk warning to the user; by integrating the motor consumption index, the acoustic energy abnormal coefficient and the temperature abnormal coefficient, a comprehensive analysis of the tool wear state is performed, and the module can identify and alarm in time, and guide the operator to take corresponding measures to ensure production safety and the service life of the tool; Among them, x1 is the motor consumption weight, x2 is the sound energy weight, x3 is the temperature weight, x1+x2+x3=1, and u0 is the preset risk threshold.

[0040] It can be understood that the present embodiment does not impose any specific limitation on the setting of each weight and the preset risk threshold, and those skilled in the art can set them freely as long as the setting requirements of each weight and the preset risk threshold are met, among which the optimal value of x1 is 0.5, the optimal value of x2 is 0.3, the optimal value of x3 is 0.2, and the optimal value of u0 is 0.1.

[0041] Please continue reading Figure 1 As shown, the system includes a roughness analysis module, which is used to analyze the surface quality status of the workpiece according to the surface roughness of the workpiece collected during the quality monitoring period, and the roughness analysis module is connected to the machine tool data acquisition module; it can be understood that the setting of the quality monitoring period is not specifically limited in this embodiment, and those skilled in the art can set it freely, as long as the setting requirements of the quality monitoring period are met, wherein the setting of the quality monitoring period should be greater than the setting of the risk monitoring period, and the quality monitoring period can be set to 5min, 10min, etc.

[0042] See also Figure 4 As shown, the roughness analysis module includes: The abnormality analysis unit is used to compare the workpiece surface roughness q0 collected during the quality monitoring period with the preset surface roughness q1, and analyze the abnormality of the workpiece surface roughness according to the comparison result, wherein: If q0≤q1, the surface roughness analysis module determines that the surface roughness of the workpiece is normal; If q0>q1, the surface roughness analysis module determines that the surface roughness of the workpiece is abnormal.

[0043] It is understandable that the setting of the preset surface roughness is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset surface roughness are met, wherein the optimal value of q1 is 0.3 μm.

[0044] Please continue reading Figure 4 As shown, the roughness analysis module also includes: A quality status analysis unit connected to the abnormality analysis unit, the quality status analysis unit is used to analyze the surface quality status of the workpiece according to the analysis result of the surface roughness abnormality within the quality monitoring period to improve the accuracy of the tool status analysis, wherein: If d0 / D≤β, the quality status analysis unit determines that the surface quality status of the workpiece within the quality monitoring period is normal; If d0 / D>β, the quality state analysis unit determines that the workpiece surface quality state is abnormal during the quality monitoring period; based on the analysis result of the roughness abnormality, the overall workpiece surface quality state is evaluated, thereby improving the accuracy of the tool state analysis, and further improving the accuracy of the feed speed control; Among them, d0 is the duration of abnormal surface roughness of the workpiece during the quality monitoring cycle, D is the duration of the quality monitoring cycle, and β is the preset surface state threshold.

[0045] It can be understood that, in this embodiment, the setting of the preset surface state threshold is not specifically limited, and those skilled in the art can freely set it as long as the setting requirements of the preset surface state threshold are met, wherein the optimal value of β is 0.08.

[0046] Please continue reading Figure 1 As shown, the system also includes: A control module connected to the risk warning module and the roughness analysis module, the control module is used to analyze the tool state according to the tool wear risk warning result and the analysis result of the workpiece surface quality state in the quality monitoring cycle, and control the feed speed of the next quality monitoring cycle according to the analysis result, so as to flexibly adjust the feed speed of the next quality monitoring cycle, wherein: When the surface quality state of the workpiece in the quality monitoring period is normal, if m1×r0 / R≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G1, setting: G1=g0; if m1×r0 / R>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G2, setting: G2=g0×exp[(γ-m1×r0 / R)]; When the surface quality state of the workpiece in the quality monitoring period is abnormal, if m1×r0 / R+m2×(d0 / D-β)≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G3, setting: G3=g0; if m1×r0 / R+m2×(d0 / D-β)>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G4, setting: G4=g0×exp{[γ-m1×r0 / R-m2×(d0 / D-β)]}; the tool state is analyzed through the quality monitoring results, and the feed speed of the next quality monitoring period is flexibly adjusted. When analyzing the tool wear risk, the module can quickly adapt to and optimize the processing conditions, thereby reducing tool wear and effectively improving production efficiency; Among them, m1 is the risk warning weight, m2 is the surface quality status weight, m1+m2=1, r0 is the number of risk monitoring cycles for tool wear risk warning in the second monitoring week, R is the number of risk monitoring cycles in the quality monitoring cycle, γ is the preset abnormality coefficient, g0 is the preset feed speed, and when the control result of the feed speed in the next quality monitoring cycle is less than the feed speed threshold g1, the control module sets the control result of the feed speed in the next monitoring cycle to g1.

[0047] It can be understood that, in this embodiment, there is no specific limitation on the setting of each weight, preset abnormal coefficient, preset feed speed and feed speed threshold, and those skilled in the art can set them freely, as long as the setting requirements of each weight, preset abnormal coefficient, preset feed speed and feed speed threshold are met. Among them, when the workpiece is low carbon steel, the optimal value of g0 is 300 mm / min, the optimal value of m1 is 0.8, the optimal value of m2 is 0.2, the optimal value of γ is 0.1, and the optimal value of g1 is 220 mm / min.

[0048] Specifically, the system described in this embodiment is specifically applied to fault monitoring of CNC machine tool tools. It provides risk warning of tool wear status by combining motor consumption status, abnormal growth of sound signals and abnormal temperature status of cutting area, and controls the feed speed of CNC machine tools according to the surface roughness of the workpiece and the tool wear status, thereby improving the fault monitoring efficiency of CNC machine tools.

[0049] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. An intelligent fault monitoring system for CNC machine tools, characterized in that: include: Machine tool data acquisition module, used to collect CNC machine tool operation data and acoustic emission data; The power analysis module is used to analyze the spindle motor consumption status according to the spindle power collected during the risk monitoring period to construct a motor consumption index, and adjust the analysis process according to the CNC machine tool operation data collected during the risk monitoring period; The sound signal analysis module is used to construct the sound energy anomaly coefficient according to the amplitude of the acoustic emission signal collected during the risk monitoring period; The temperature monitoring module is used to construct the temperature anomaly coefficient according to the cutting area temperature collected during the monitoring period; The risk warning module is used to analyze the tool wear status according to the results of the motor consumption index, the acoustic energy abnormality coefficient and the temperature abnormality coefficient during the risk monitoring period, and to issue a tool wear risk warning to the user; A roughness analysis module is used to analyze the surface quality status of the workpiece according to the workpiece surface roughness collected during the quality monitoring cycle; The control module is used to control the feed speed of the next quality monitoring cycle according to the tool wear risk warning results and the analysis results of the workpiece surface quality status during the quality monitoring cycle.

2. The intelligent fault monitoring system for CNC machine tools according to claim 1 is characterized in that: The power analysis module includes a power analysis unit, which is used to compare the spindle power collected during the risk monitoring period with the preset power p0, and analyze the abnormality of the spindle power according to the comparison result, and the abnormality of the spindle power includes normal and abnormal; The power analysis unit analyzes the motor consumption status according to the analysis results of the abnormality of the spindle power within the risk monitoring period. The motor consumption status includes a normal state and a high consumption state. If the spindle motor consumption state in the current risk monitoring period is a normal state, the power abnormality coefficient is set to GL1; if the spindle motor consumption state in the current risk monitoring period is a high consumption state, the power abnormality coefficient is set to GL2.

3. The intelligent fault monitoring system for CNC machine tools according to claim 2 is characterized in that: The power analysis module also includes a removal rate analysis unit, which calculates the material removal rate QC of the workpiece based on the feed speed js, cutting depth qs and cutting width qk collected during the risk monitoring period, and compares the material removal rate QC of the workpiece with the preset removal rate q0 to analyze the cutting load state of the tool. The cutting load state of the tool includes a normal state and a high load state. If the cutting load state of the tool is a high load state, the preset power is adjusted to p0'.

4. The intelligent fault monitoring system for CNC machine tools according to claim 3 is characterized in that: The power analysis module also includes a hardness analysis unit, which is used to compare the collected workpiece hardness gy with the preset hardness gy0 to analyze the hardness state of the workpiece. The hardness state of the workpiece includes normal and abnormal. If the hardness state of the workpiece is abnormal, the preset removal rate q0 is adjusted to q0'.

5. The intelligent fault monitoring system for CNC machine tools according to claim 4 is characterized in that: The sound signal analysis module includes an energy calculation unit, which is used to calculate the energy A of the acoustic emission signal according to the amplitude of the acoustic emission signal collected during the risk monitoring period; The sound signal analysis module also includes an energy state analysis unit, which analyzes the energy growth state of the acoustic emission signal according to the acoustic emission signal energy A within the risk monitoring period and the preset energy threshold A0. The acoustic emission signal energy growth state includes a normal state and an abnormal state. If the acoustic emission signal energy growth state in the current risk monitoring period is a normal state, the acoustic energy abnormality coefficient is set to SY1; if the acoustic emission signal energy growth state in the current risk monitoring period is an abnormal state, the acoustic energy abnormality coefficient is set to SY2.

6. The intelligent fault monitoring system for CNC machine tools according to claim 5 is characterized in that: The temperature monitoring module is used to compare the cutting area temperature t0 collected during the monitoring period with the preset temperature t1, and analyze the temperature state of the cutting area according to the comparison result. The temperature state includes a normal state and a high temperature state. If the temperature state of the cutting area in the current risk monitoring period is a normal state, the temperature anomaly coefficient is set to WD1; if the temperature state of the cutting area in the current risk monitoring period is a high temperature state, the temperature anomaly coefficient is set to WD2.

7. The intelligent fault monitoring system for CNC machine tools according to claim 6 is characterized in that: The risk warning module analyzes the tool wear state according to the results of constructing the motor consumption index, the acoustic energy abnormality coefficient and the temperature abnormality coefficient during the risk monitoring period. The tool wear state includes normal wear and abnormal wear. If the tool wear state during the risk monitoring period is normal wear, no tool wear risk warning is issued to the user. If the tool wear status is abnormal during the risk monitoring period, a tool wear risk warning will be issued to the user.

8. The intelligent fault monitoring system for CNC machine tools according to claim 7 is characterized in that: The roughness analysis module includes an abnormality analysis unit, which is used to compare the workpiece surface roughness q0 collected during the quality monitoring period with the preset surface roughness q1, and analyze the abnormality of the workpiece surface roughness according to the comparison result. The abnormality of the workpiece surface roughness includes normal and abnormal.

9. The intelligent fault monitoring system for CNC machine tools according to claim 8 is characterized in that: The roughness analysis module also includes a quality status analysis unit, which is used to analyze the workpiece surface quality status according to the analysis result of the surface roughness abnormality within the quality monitoring period. The workpiece surface quality status includes a normal state and an abnormal state.

10. The intelligent fault monitoring system for CNC machine tools according to claim 9, characterized in that: The control module is used to analyze the tool state according to the tool wear risk warning result and the workpiece surface quality state analysis result in the quality monitoring cycle, and control the feed speed of the next quality monitoring cycle according to the analysis result, wherein: When the surface quality state of the workpiece in the quality monitoring period is normal, if m1×r0 / R≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G1; if m1×r0 / R>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G2; When the surface quality state of the workpiece in the quality monitoring period is abnormal, if m1×r0 / R+m2×(d0 / D-β)≤γ, the control module determines that the tool state in the quality monitoring period is normal, and controls the feed speed of the next quality monitoring period to G3; if m1×r0 / R+m2×(d0 / D-β)>γ, the control module determines that the tool state in the quality monitoring period is abnormal, and controls the feed speed of the next quality monitoring period to G4.

Images