A tool failure monitoring method for titanium alloy parts based on vibration signals

Abstract

This application belongs to the field of CNC machining, specifically relating to a tool fault monitoring method for titanium alloy parts based on vibration signals. The method includes the following steps: acquiring historically collected machine tool data, preprocessing the data, and storing the processed data in Datas; performing noise reduction processing on the machine tool vibration during cutting; determining the period of the vibration signal; calculating the period of all collected data items in Datas; calculating the machine tool's travel speed; establishing a table corresponding to the cutting parameters of titanium alloy parts for aerospace structural components; and providing machining early warning based on the table. This method monitors and diagnoses tool wear based on discrete vibration signals collected by an accelerometer mounted on the spindle during the machining of titanium alloy parts on a CNC machine tool, using the collected spindle speed, spindle power, and spindle travel speed. When tool wear and damage occur, an alarm signal is promptly issued, reducing surface quality problems of the parts caused by tool wear.

Description

Technical Field

[0001] This application belongs to the field of CNC machining, specifically relating to a tool fault monitoring method for titanium alloy parts based on vibration signals. Background Technology

[0002] Vibration signal-based tool fault monitoring for titanium alloy parts in aerospace structural components is a key technology developed in the aerospace manufacturing industry to address the difficult machining characteristics of titanium alloys and the high reliability requirements of parts. Its core logic is to collect vibration signals during the cutting process, analyze signal characteristics (such as amplitude, frequency, energy distribution, etc.) to determine the tool status (normal, worn, chipped, etc.), and thus achieve real-time early warning and intervention for faults.

[0003] In the prior art, there is a Chinese invention patent with patent publication number CN116690313A entitled "A Method for Monitoring the Failure of Cutting Tools for Web Processing of Aircraft Structural Components," which discloses the following steps for fault monitoring: S1, using historical data for model training, specifically referring to: inputting the feature values ​​of the test group batch data, calculating the tool status through the classification model, comparing it with the label data, calculating the accuracy of accurate identification; classifying the accuracy of the classification model; determining the selection rules for signal feature values ​​and saving the classification model training data; S2, monitoring by driving the classification model with real-time data.

[0004] For example, Chinese invention patent CN116061006A, entitled "A Tool Monitoring Method, Device, Equipment and Medium," discloses the following steps: acquiring monitoring parameters, including the number of tool teeth z0; collecting vibration signals during CNC machining; obtaining a polar coordinate graph of the vibration signal based on the monitoring parameters and vibration signals; performing noise reduction processing on the polar coordinate graph of the vibration signal; calling a constructed neural network classification model to identify the noise-reduced polar coordinate graph of the vibration signal to obtain the identification result, the number of teeth z; comparing the identification result, the number of teeth z, with the number of tool teeth z0; if z = z0, returning to the step of drawing the polar coordinate graph of the vibration signal based on the vibration signal; if z < z0, then issuing an alarm.

[0005] The patent publication number CN117170306A, entitled "A Tool Status Monitoring Method, System, Electronic Device and Storage Medium", describes a method that obtains the label of the current tool trajectory map through a constructed tool trajectory classification model, identifies whether it is the first layer of the tool trajectory, calculates the scaling ratio and the feature value; identifies the feature value through the constructed tool status monitoring model, calculates the proportion of signals identified as non-chipped segments, and generates a tool status alarm signal if it exceeds the set monitoring threshold, instructing the machine tool to perform alarm function and stop operation, thereby improving the accuracy of online identification of tool status for aircraft structural parts machining with different tool trajectory types.

[0006] However, in the solutions CN116690313A, CN116061006A and CN117170306A, the root mean square of each revolution could not be extracted when facing high-speed machining conditions of titanium alloys, and the signal values ​​could not be assigned to different quadrants when facing high-speed machining conditions of titanium alloys, so it was impossible to process the machining of titanium alloy parts. Summary of the Invention

[0007] The purpose of this invention is to solve the above-mentioned problems. A tool fault monitoring method for titanium alloy parts based on vibration signals is proposed.

[0008] To achieve the above effects, the technical solution of this application is as follows:

[0009] A method for monitoring tool failures in titanium alloy parts based on vibration signals includes the following steps:

[0010] Step 11. Obtain historically collected machine tool data, preprocess the data, and store the processed data in Datas;

[0011] Step 12. Noise reduction treatment for machine tool vibration during cutting;

[0012] Step 13. Determine the period of the vibration signal;

[0013] Step 14. Calculate the period Ta of all collected data items in Datas according to the method in Step 13;

[0014] Step 15. The moving speed Ms of the computer bed;

[0015] Step 16. Establish the machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components;

[0016] Step 21. Perform machining early warning based on the corresponding table of cutting parameters for titanium alloy aerospace structural components.

[0017] Furthermore, step 11 is as follows:

[0018] Acquire historical machine tool data, including: machine tool number (No), timestamp (T), machine tool coordinates (X, Y, Z), spindle speed (s) during cutting, machine tool power (P), and vibration data collected by the accelerometer during that cutting time. ,Right now

[0019]

[0020] in The collected vibration data consists of N vibration data points in each data set.

[0021] Acquire all data collected during the processing:

[0022]

[0023] in This refers to the Data collected at time tk.

[0024] The noise reduction process in step 12 is implemented as follows:

[0025] The vibration data is processed according to the Fourier discrete transform formula to obtain the processed signal. :

[0026] Formula 1

[0027] in Vibration signal The first one collected in n Vibration data, N for The number of vibration signals collected in any one set. The th Fourier transform k Each frequency domain signal quantity i It is an imaginary root. n for Its position in Datas.

[0028] Furthermore, let X be the set after transforming all elements according to Formula 1:

[0029]

[0030] The noise in the signal data is filtered according to the following formula, retaining low-frequency signals and some high-frequency signals:

[0031] Formula 2

[0032] in This is the low-frequency filter cutoff frequency. The cutoff frequency reserved for the beginning of the high-frequency range.

[0033] Furthermore, and The method for determining the value is as follows:

[0034] Formula 3

[0035] Furthermore, To The set of elements after truncating all elements according to Formula 2:

[0036]

[0037] Step 13 is implemented as follows:

[0038] The filtered signal obtained in step 12 is processed using the inverse Fourier method and Fourier series. Perform the inverse Fourier transform according to the following formula:

[0039] Formula 4

[0040] in for The k-th element in.

[0041] Furthermore, To The result of inverse transformation of all elements in formula 4:

[0042]

[0043] beg The derivative of is obtained by the following formula:

[0044] Formula 5

[0045] calculate The derivative of each element Store the derivative values ​​of all elements. middle;

[0046]

[0047] calculate The determination method for all zeros in the equation is as follows:

[0048] Formula 6

[0049] if If formula 6 is satisfied, then There exists a zero point, and record i as the coordinate of the zero point.

[0050] Furthermore, according to Formula 6, calculate All zero coordinates :

[0051]

[0052] Where i is The index of the i-th element, where m is the index of the last element satisfying formula 6, according to... For all elements in the equation, the cutting cycle T is calculated using the following formula:

[0053] Formula 7.

[0054] Furthermore, in step 14

[0055] Where M is the total number of data entries collected in Datas.

[0056] Furthermore, in step 15, the moving speed of the computer tool is calculated based on the position information collected in step 11 according to the following formula:

[0057]

[0058]

[0059] The range of values ​​for i is: . This refers to the position information of the machine tool coordinates (X, Y, Z) corresponding to the i-th data group in the collected data Datas. The cutting cycle corresponding to the i-th group of data in Datas is calculated in Formula 7.

[0060] The machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components in step 16 includes machine tool number No, machine tool travel speed MS, machine tool spindle speed RS, machine tool power P, and cutting cycle T:

[0061]

[0062] Where T is the i-th cutting cycle in Ta mentioned in step 14.

[0063] Step 21 specifically involves:

[0064] The vibration parameters at the current time are collected as shown in step 11. The current cycle Tc is calculated according to steps 13 and 15 respectively. Based on the current machine tool status, the current machine tool's moving speed MS, spindle speed RS, and power P are matched with the machining parameters from the corresponding table of cutting parameters for titanium alloy machine tools for aerospace structural parts. The normal machining cycle T in history is then searched.

[0065] The rate of change of the computer bed cycle is calculated according to the following formula.

[0066] Formula 9

[0067] if If the value is between [0.0, 0.1], then the tool will not have any problems during the cutting process; otherwise, the tool will be damaged.

[0068] The beneficial effects of this application are as follows:

[0069] This method monitors, diagnoses, and analyzes tool wear based on discrete vibration signals collected by an accelerometer mounted on the spindle during the machining of titanium alloy parts on a CNC machine tool, using the collected spindle speed, spindle power, and spindle travel speed. When tool wear and damage occur, an alarm signal is given in a timely manner, reducing surface quality problems of parts caused by tool wear. Attached Figure Description

[0070] Figure 1 This is a flowchart illustrating the method. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of the embodiments of the invention clearer, the technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, not all embodiments. The components of the embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0072] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0073] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0074] In the description of this invention, it should be noted that the terms "upper," "vertical," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are only used for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. In addition, the terms "first," "second," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0075] The present invention will now be described in detail with reference to the accompanying drawings:

[0076] Example 1

[0077] like Figure 1 As shown, a tool failure monitoring method for titanium alloy parts based on vibration signals includes the following steps:

[0078] Step 11. Obtain historically collected machine tool data, preprocess the data, and store the processed data in Datas;

[0079] Step 12. Noise reduction treatment for machine tool vibration during cutting;

[0080] Step 13. Determine the period of the vibration signal;

[0081] Step 14. Calculate the period Ta of all collected data items in Datas according to the method in Step 13;

[0082] Step 15. The moving speed Ms of the computer bed;

[0083] Step 16. Establish the machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components;

[0084] Step 21. Perform machining early warning based on the corresponding table of cutting parameters for titanium alloy aerospace structural components.

[0085] This method monitors, diagnoses, and analyzes tool wear based on discrete vibration signals collected by an accelerometer mounted on the spindle during the machining of titanium alloy parts on a CNC machine tool, using the collected spindle speed, spindle power, and spindle travel speed. When tool wear and damage occur, an alarm signal is given in a timely manner, reducing surface quality problems of parts caused by tool wear.

[0086] Example 2

[0087] like Figure 1 As shown, a tool failure monitoring method for titanium alloy parts based on vibration signals includes the following steps:

[0088] Step 11. Obtain historically collected machine tool data, preprocess the data, and store the processed data in Datas;

[0089] Step 12. Noise reduction treatment for machine tool vibration during cutting;

[0090] Step 13. Determine the period of the vibration signal;

[0091] Step 14. Calculate the period Ta of all collected data items in Datas according to the method in Step 13;

[0092] Step 15. The moving speed Ms of the computer bed;

[0093] Step 16. Establish the machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components;

[0094] Step 21. Perform machining early warning based on the corresponding table of cutting parameters for titanium alloy aerospace structural components.

[0095] The process of step 11 is as follows:

[0096] Acquire historical machine tool data, including: machine tool number (No), timestamp (T), machine tool coordinates (X, Y, Z), spindle speed (s) during cutting, machine tool power (P), and vibration data collected by the accelerometer during that cutting time. ,Right now

[0097]

[0098] in For the collected vibration data, each data set contains N vibration data points. All collected data during the processing are obtained (Datas).

[0099]

[0100] in This refers to the Data collected at time tk.

[0101] Furthermore, in step 12, the noise reduction process is implemented as follows:

[0102] The vibration data is processed according to the Fourier discrete transform formula to obtain the processed signal. :

[0103] Formula 1

[0104] in Vibration signal The first one collected in n Vibration data, N for The number of vibration signals collected in any one set. The th Fourier transform k Each frequency domain signal quantity i It is an imaginary root. n for Its position in Datas.

[0105] Furthermore, let X be the set after transforming all elements according to Formula 1:

[0106]

[0107] The noise in the signal data is filtered according to the following formula, retaining low-frequency signals and some high-frequency signals:

[0108] Formula 2

[0109] in This is the low-frequency filter cutoff frequency. The cutoff frequency reserved for the beginning of the high-frequency range.

[0110] Furthermore, and The method for determining the value is as follows:

[0111] Formula 3

[0112] Furthermore, To The set of elements after truncating all elements according to Formula 2:

[0113]

[0114] Furthermore, step 13 is implemented as follows:

[0115] The filtered signal obtained in step 12 is processed using the inverse Fourier method and Fourier series. Perform the inverse Fourier transform according to the following formula:

[0116] Formula 4

[0117] in for The k-th element in.

[0118] Furthermore, To The result of inverse transformation of all elements in formula 4:

[0119]

[0120] beg The derivative of is obtained by the following formula:

[0121] Formula 5

[0122] calculate The derivative of each element Store the derivative values ​​of all elements. middle;

[0123]

[0124] calculate The determination method for all zeros in the equation is as follows:

[0125] Formula 6

[0126] if If formula 6 is satisfied, then There exists a zero point, and record i as the coordinate of the zero point.

[0127] Calculated according to Formula 6 All zero coordinates :

[0128]

[0129] Where i is The index of the i-th element, where m is the index of the last element satisfying formula 6, according to... For all elements in the equation, the cutting cycle T is calculated using the following formula:

[0130] Formula 7.

[0131] In step 14

[0132] Where M is the total number of data entries collected in Datas.

[0133] In step 15, the moving speed of the computer tool is calculated based on the position information collected in step 11 using the following formula:

[0134]

[0135]

[0136] The range of values ​​for i is: . This refers to the position information of the machine tool coordinates (X, Y, Z) corresponding to the i-th data group in the collected data Datas. The cutting cycle corresponding to the i-th group of data in Datas is calculated in Formula 7.

[0137] The machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components in step 16 includes the machine tool number (No), machine tool travel speed (MS), spindle speed (RS) during cutting, machine tool power (P), and cutting cycle (T).

[0138]

[0139] Step 21 is as follows:

[0140] The vibration parameters at the current time are collected as shown in step 11. The current cycle Tc is calculated according to steps 13 and 15 respectively. Based on the current machine tool status, the current machine tool's moving speed MS, spindle speed RS, and power P are matched with the machining parameters from the corresponding table of cutting parameters for titanium alloy machine tools for aerospace structural parts. The normal machining cycle T in history is then searched.

[0141] The rate of change of the computer bed cycle is calculated according to the following formula.

[0142] Formula 9

[0143] if If the value is between [0.0, 0.1], then the tool will not have any problems during the cutting process; otherwise, the tool will be damaged.

[0144] Example 3

[0145] Based on Examples 1 and 2, the collected data, after preprocessing, is as follows:

[0146]

[0147] A total of 500 vibration data points were collected.

[0148]

[0149] The method described in step 12 is implemented using the following pseudocode: Fourier transform pseudocode.

[0150]

[0151] X represents vibration data. The frequency domain value.

[0152] According to step 12, take ,but

[0153]

[0154] As described in step 12, the truncated and filtered frequency domain signal is

[0155]

[0156] The values ​​for 0-25 and 474-499 remain unchanged, while the frequency domain values ​​for the remaining positions are 0.

[0157] As described in step S13, the inverse Fourier transform formula is used to... Pseudocode for performing inverse operation and inverse Fourier transform

[0158]

[0159] Calculate according to step S13 derivative Its pseudocode is as follows:

[0160]

[0161] Based on the zero-point calculation method in step S13, its pseudocode is as follows:

[0162]

[0163] The pseudocode for calculating the period according to step S13 is as follows:

[0164]

[0165] In summary, the above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for monitoring tool failures in titanium alloy parts based on vibration signals, characterized in that, Includes the following steps: Step 11. Obtain historically collected machine tool data, preprocess the data, and store the processed data in Datas; Step 12. Noise reduction treatment for machine tool vibration during cutting; Step 13. Determine the period of the vibration signal; Step 14. Calculate the period Ta of all collected data items in Datas according to the method in Step 13; Step 15. The moving speed Ms of the computer bed; Step 16. Establish the machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components; Step 21. Perform machining early warning according to the corresponding table of cutting parameters for titanium alloy aerospace structural parts; In step 14 Where M is the total number of data entries collected in Datas; The machine tool cutting parameter correspondence table PTable for titanium alloy aerospace structural components in step 16 includes machine tool number No, machine tool travel speed MS, spindle speed RS during cutting, machine tool power P, and cutting cycle T. Where T is the i-th cutting cycle in Ta in step 14; Step 21 specifically involves: The vibration parameters at the current time are collected as shown in step 11. The current cycle Tc is calculated according to steps 13 and 15 respectively. Based on the current machine tool status, the current machine tool's moving speed MS, spindle speed RS, and power P are matched with the machining parameters from the corresponding table of cutting parameters for titanium alloy machine tools for aerospace structural parts. The normal machining cycle T in history is then searched. The rate of change of computer bed cycle is calculated according to the following formula. Official 9 if If the value is between [0.0, 0.1], then the tool will not have any problems during the cutting process; otherwise, the tool will be damaged.

2. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 1, characterized in that, The process of step 11 is as follows: Acquire historical machine tool data, including: machine tool number (No), timestamp (T), machine tool coordinates (X, Y, Z), spindle speed (s) during cutting, machine tool power (P), and vibration data collected by the accelerometer during that cutting time. ,Right now in For the collected vibration data, each data set contains N vibration data points. All collected data during the processing are obtained (Datas). in This refers to the Data collected at time tk.

3. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 1, characterized in that, The noise reduction process in step 12 is implemented as follows: The vibration data is processed according to the Fourier discrete transform formula to obtain the processed signal. : Official 1 in Vibration signal The first one collected in n Vibration data, N for The number of vibration signals collected in any one set. The th Fourier transform k Each frequency domain signal quantity i It is an imaginary root. n for Its position in Datas.

4. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 3, characterized in that, X is the set after transforming all elements according to Formula 1: The noise in the signal data is filtered according to the following formula, retaining low-frequency signals and some high-frequency signals: Official 2 in This is the low-frequency filter cutoff frequency. The cutoff frequency that is reserved at the beginning of the high-frequency range.

5. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 4, characterized in that, and The method for determining the value is as follows: Official 3.

6. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 5, characterized in that, To The set of elements after truncating all elements according to Formula 2: 。 7. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 6, characterized in that, Step 13 is implemented as follows: The filtered signal obtained in step 12 is processed using the inverse Fourier method and Fourier series. Perform the inverse Fourier transform according to the following formula: Official 4 in for The k-th element in.

8. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 7, characterized in that, To The result of inverse transformation of all elements in formula 4: beg The derivative of is obtained by the following formula: Official 5 calculate The derivative of each element Store the derivative values ​​of all elements. middle; calculate The determination method for all zeros in the equation is as follows: Official 6 if If formula 6 is satisfied, then There exists a zero point, and record i as the coordinate of the zero point.

9. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 8, characterized in that, Calculated according to Formula 6 All zero coordinates : Where i is The index of the i-th element, where m is the index of the last element satisfying formula 6, according to... For all elements in the equation, the cutting cycle T is calculated using the following formula: Official 7.

10. The method for monitoring tool failures in titanium alloy parts based on vibration signals according to claim 1, characterized in that, In step 15, the moving speed of the computer tool is calculated based on the collected position information according to the following formula: The range of values ​​for i is: , This refers to the position information of the machine tool coordinates (X, Y, Z) corresponding to the i-th data set in the collected data set, The cutting cycle corresponding to the i-th group of data in Datas is calculated in step 14.

Images