Milling wireless vibration measuring tool shank manufacturing system based on FPC flexible packaging

Abstract

A kind of milling wireless vibration measuring tool shank manufacturing system based on FPC flexible packaging, including milling machine and the wireless intelligent tool shank arranged on it and the cutter at its end, workpiece is arranged opposite cutter, wherein: workpiece is arranged on milling machine workbench by vice, wireless intelligent tool shank is connected with host computer by wireless mode and transmits three-dimensional vibration signal of tool shank position in cutting process, three-dimensional vibration signal is handled and analyzed by host computer by artificial intelligence algorithm, realize to the tool wear value for real-time monitoring, predict the residual life of tool and optimize cutting parameter, provide more reasonable cutting parameter for the cutting processing of workpiece, improve the service life of tool.The present application compensates the strength and stiffness decline caused by the original tool shank structure damage through composite material, ensures the feasibility in high-speed, high-precision cutting task;At the same time, signal acquisition module and charging module are based on FPC flexible distribution with tool shank outer cylindrical surface, minimize the overall size of intelligent tool shank, ensure the applicability in complex path working condition.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent manufacturing, and particularly relates to a milling wireless vibration measuring tool shank manufacturing system based on FPC flexible packaging. BACKGROUND

[0002] Cutting vibration data is a signal in cutting processing, monitoring and analyzing the cutting vibration data can realize real-time monitoring of the tool state in processing, avoid waste caused by early replacement in the actual processing process to ensure processing quality, and realize cost reduction and benefit increase of the processing process. With the development of sensor integration technology, the intelligent tool shank integrated with the sensor has been widely studied. Compared with the traditional wired vibration sensor, the sensor in the intelligent tool shank is closer to the cutting area and can collect more real vibration signals. Moreover, the sensor position in the intelligent tool shank is fixed, and the problem of poor repeatability caused by the un-fixed installation position of the sensor each time is avoided. However, the existing intelligent tool shank has many problems. The overall size of part of the intelligent tool shank is too large, and the intelligent tool shank has limitations in complex processing path tasks. In order to reduce the size, part of the intelligent tool shank destroys the original structure of the tool shank, and the strength and rigidity of the tool shank are reduced, so that the intelligent tool shank has limitations in high-speed and high-precision processing tasks. Moreover, the deployment of the signal acquisition module in the metal tool shank has the problem of electromagnetic shielding, and the collected signal is distorted. SUMMARY

[0003] The application is proposed in response to the fact that the prior art is difficult to meet the engineering detection needs in terms of strength and rigidity, and is easy to produce greater vibration in the processing process, especially when the rigidity is insufficient, the tool shank is easy to deviate under the action of cutting force, the cutting path deviates from the predetermined track, and the processing precision and quality are seriously affected. The application provides a milling wireless vibration measuring tool shank manufacturing system based on FPC flexible packaging. The strength and rigidity caused by the damage of the original tool shank structure are compensated by the composite material, the feasibility in high-speed and high-precision cutting processing tasks is ensured, the signal acquisition module and the charging module are distributed on the outer cylindrical surface of the tool shank based on the FPC flexibility, the overall size of the intelligent tool shank is minimized, the applicability in complex path working conditions is ensured, and the acquisition module is deployed on the composite material, so that the electromagnetic shielding is avoided and the quality of the collected signal is ensured.

[0004] The application is implemented by the following technical scheme:

[0005] The application relates to a milling wireless vibration measuring tool shank manufacturing system based on FPC flexible packaging, which comprises a milling machine, a wireless intelligent tool shank arranged on the milling machine and a tool arranged at the tail end of the wireless intelligent tool shank, and a workpiece arranged opposite to the tool, wherein the workpiece is arranged on the milling machine workbench through a vice, the wireless intelligent tool shank is connected with an upper computer in a wireless mode and transmits three-direction vibration signals of the tool shank position in a cutting process, the three-direction vibration signals are processed and analyzed through the upper computer through an artificial intelligence algorithm, the tool wear value is monitored in real time, the residual life of the tool is predicted, and the cutting parameters are optimized, more reasonable cutting parameters are provided for the cutting process of the workpiece, and the service life of the tool is prolonged.

[0006] The artificial intelligence algorithm refers to that a Kolmogorov-Arnold neural network (KAN) is adopted to monitor the tool wear state, a complex high-dimensional function is decomposed into a simple one-dimensional function combination to process a complex data fitting problem, accurate mapping between cutting vibration signals and tool wear is realized, and the specific process is as follows: wherein Φ q,p is a spline curve, Φ q,p and Φ q are single-variable continuous functions, X is a feature set from the vibration signal, and f is a real mapping between the feature set and the tool wear value.

[0007] The wireless intelligent tool shank comprises a tool shank base body, a turning part and a composite material reinforcing layer arranged outside the turning part which are sequentially connected, wherein the composite material reinforcing layer is provided with an annular groove and two module grooves.

[0008] The composite material reinforcing layer is realized through the following mode:

[0009] i) different tool shank models are established for simulation, the maximum thickness of the turning part and the laying direction are determined under the premise of ensuring the overall strength and rigidity of the tool shank, the number of layers of the composite material is determined according to the wall thickness of the tool shank turning part;

[0010] ii) the resin is uniformly applied on the tool shank turning part, the composite material is wound on the cylindrical surface layer by layer, air bubbles are discharged by using a roller, the composite material is ensured to be closely attached, air is extracted by a vacuum pump to create a negative pressure environment, internal air bubbles are removed to improve adhesion, the composite material is wound again, vacuum is extracted again, and finally high-temperature curing is carried out. The FPC flexible module groove and the flexible wire arrangement groove are processed through microfabrication technology.

[0011] iii) the prepared composite material reinforcing tool shank is checked for static structural strength, dynamic structural strength and inherent frequency, the FPC flexible module is assembled, and a signal acquisition test is carried out.

[0012] The annular groove is provided with a lithium battery.

[0013] The two module slots are respectively provided with an FPC packaged signal acquisition module and an FPC packaged charging module, the charging module is connected with a lithium battery, and the input voltage between the signal acquisition module and the wireless transmission module is stabilized.

[0014] The FPC packaged signal acquisition module comprises an acceleration sensor, a microprocessor and a Wi-Fi transmission module, wherein the acceleration sensor acquires a tool holder vibration signal in a cutting process and transmits the signal to the microprocessor through serial communication, the microprocessor transmits the processed signal to a Wi-Fi module as a server based on serial communication, and the Wi-Fi module communicates with an upper computer as a client based on a TCP / IP protocol.

[0015] The charging module comprises a power management chip, a voltage stabilizing chip and a ring lithium battery, wherein the power management chip realizes power conversion, distribution and monitoring, guarantees power supply requirements of the acquisition module, the voltage stabilizing chip provides a 3.3v voltage for the acquisition module and limits voltage fluctuation, and the ring lithium battery is a power supply of the acquisition module.

[0016] The FPC packaging is that flexible printing materials are selected as base materials of the flexible acquisition module and the charging module, a circuit pattern is transferred to the base materials through a photoetching technology, electronic components are mounted on the FPC flexible circuit board using a surface mounting technology, and a protective coating is used for overall encapsulation of the circuit to enhance durability.

[0017] The composite material reinforcing layer is externally provided with a protective shell.

[0018] Technical effects

[0019] This invention designs and fabricates vibration signal acquisition and charging modules based on FPC flexible packaging technology and applies them to wireless smart toolholders to acquire vibration signals during the cutting process. It uses KAN (Kear-Actuated) technology to monitor tool wear, constructing a KAN-Wear wear monitoring model. Compared to existing technologies, the signal acquisition and charging modules designed and fabricated using FPC flexible packaging technology can fully utilize the outer cylindrical surface of the toolholder, reducing structural damage and preventing excessive degradation of toolholder stiffness and strength. Simultaneously, it reduces the overall size of the wireless smart toolholder, making it completely consistent with the size of traditional commercial toolholders of the same model, eliminating the need for user modifications during actual processing. Traditional square rigid signal acquisition and charging modules designed and manufactured based on PCB boards struggle to simultaneously achieve the requirements of minimal structural damage and small overall size. In this invention, the flexible signal acquisition and charging modules are deployed within a composite material reinforcement layer. Compared to existing wireless smart toolholders deployed inside metal toolholders, this invention avoids electromagnetic shielding, effectively improving signal transmission quality. Compared with traditional models such as CNN, LSTM, and MLP, the KAN-Wear tool wear condition monitoring model developed by this method can converge faster and has a significant improvement in RMSE and MAE values ​​for tool wear monitoring on the test set. Attached Figure Description

[0020] Figure 1 This is a diagram illustrating the usage conditions of the wireless intelligent tool holder of the present invention.

[0021] Figure 2 This is a composite material reinforcement structure diagram of the wireless smart knife handle of the present invention;

[0022] Figure 3 This is an overall assembly diagram of the wireless intelligent tool holder of the present invention;

[0023] Figure 4 This is the structure of the KAN-Wear tool condition monitoring model embedded in the wireless intelligent tool holder software system of this invention;

[0024] Figure 5 This is a schematic diagram of the test conditions of the PHM2010 public cutting dataset used in this invention to verify the effectiveness of the KAN-Wear model;

[0025] Figure 6 This is a full life cycle wear curve of three tools in the PHM2010 common cutting dataset. Detailed Implementation

[0026] like Figure 1As shown, the manufacturing system of the wireless intelligent tool holder system is related to the embodiment, which comprises a milling machine 10, a wireless intelligent tool holder 20 arranged on the milling machine 10, a tool 30 at the end of the wireless intelligent tool holder 20, and a workpiece 40 arranged opposite the tool 30. The workpiece 40 is arranged on the workbench of the milling machine 10 through a vice 50. The wireless intelligent tool holder 20 is connected to an upper computer 60 through a wireless mode and transmits a three-dimensional vibration signal of the tool holder position during cutting. The upper computer 60 processes and analyzes the three-dimensional vibration signal through an artificial intelligence algorithm, realizes real-time monitoring of the tool wear value, predicts the remaining life of the tool, and optimizes the cutting parameters, so as to provide more reasonable cutting parameters for the cutting process of the workpiece 40 and improve the service life of the tool 30.

[0027] As shown in the figure, the wireless intelligent tool holder 20 comprises a tool holder base body turning part 21 and a composite material reinforcing layer 22 arranged outside the turning part 21, which are connected in sequence. The composite material reinforcing layer 22 is provided with an annular groove 23, a signal acquisition module groove 24 and a charging module groove 25. Figure 2

[0028] The tool holder base body 21 is taken as an example of a mainstream commercial HSK-63A tool holder. In order to avoid the electromagnetic shielding problem caused by deploying the acquisition module on the metal material and avoid the overall size of the intelligent tool holder being too large, the tool holder base body 21 is turned and processed to form the turning part 22 at the end.

[0029] The built-in algorithms in the life prediction module 53 and the wear monitoring module 54 are realized based on deep learning. After the three-dimensional original data is input into the algorithm, the KAN is used to realize the life prediction and wear monitoring of the tool, and the feature extraction of the operator is not required throughout the process, which belongs to an end-to-end monitoring algorithm. Figure 4 The KAN-Wear structure is built. The input is the time domain features (maximum value, mean value and variance) extracted from the cutting vibration data. The number of nodes in the KAN is set to 3, 7 and 1 respectively.

[0030] The PHM2010 public cutting data set (https: / / phmsociety.org / phm_competition / 2010-phm-society-conference-data-challenge / ) is used to verify the KAN-Wear tool state monitoring algorithm. The test working condition of the PHM2010 public milling data set is shown in the figure. Figure 5 ​The experimental machine tool is Roder Tech RFM769 high-speed CNC machine tool 61. The workpiece 65 is clamped on the workbench of the high-speed CNC machine tool 61. The tool used is a 3-tooth ball-end mill 62. The cutting method adopts dry milling and side milling. The length of each pass is 108 mm. During the cutting process, the cutting forces in three directions are measured using a Kistler three-component platform dynamometer 66. In addition, a Kistler piezoelectric accelerometer 63 is deployed to measure the three-axis vibration of the workpiece. A Kistler acoustic emission sensor 64 is used to measure the high-frequency stress waves generated during the cutting process. The data collected by the three sensors are collected by an NI data acquisition card 68 to form a 7-channel signal, which are x-direction cutting force, y-direction cutting force, z-direction cutting force, x-direction vibration, y-direction vibration, z-direction vibration and acoustic emission signal respectively. After each pass, the average wear band width VB of the rear face of each blade is measured using a LEICZ12 microscope 67 as the wear value of the blade. The average wear value of the three blades is taken as the wear value of the entire tool. The tool life cycle wear curves of the three groups of experiments are as shown in FIG. 2. Figure 6

[0031] Each pass will generate a large amount of data, and directly using the data of the whole pass as sample input will cause the calculation amount of the model to be too large, and even cause overfitting of the model. In this embodiment, the data of each pass is divided into 100 sub-sequences, and the maximum value, mean value and variance of each sub-sequence are extracted to form a shorter time sequence (100x3) as the input of the KAN-Wear tool monitoring model. In the tool wear value monitoring task, the VB value is directly taken as the label of each input feature; in the tool residual life prediction task, the VB=150μm is taken as the threshold, and the use time when the wear of the rear face of the three milling cutters reaches 150μm is calculated as the life of the tool, and the residual life of each pass is calculated as the label of each input feature, which is R L = T-T i , where R L is the residual life, T is the tool life, and T i is the cumulative use time of the tool in the ith pass.

[0032] Table 1 Specific settings of cross-data set

[0033]

[0034] ​The embodiment specifically adopts the KAN-Wear model and uses GPU for training under the Windows 10 platform. The graphics card model is RTX 3090, and the CPU model is AMD EPYC 7624. The KAN-Wear network is built by the Pytorch 1.11.0 framework. The Python version is 3.8, and the Cuda version is 11.3. Adam is used as the optimizer during training to improve the generalization of the model and prevent overfitting during model training by setting the weight decay. The MAE is used to calculate the loss function, and the hyperparameter settings of the model during training are shown in Table 2. The tool wear monitoring model and the tool residual life prediction model are trained on the data sets T1, T2 and T3 respectively, and the performance of the model on the test set is shown in Table 3.

[0035] Table 2 Model training hyperparameter table

[0036]

[0037] As Figure 3 shown, the overall assembly of the wireless intelligent tool handle involved in the embodiment includes a tool handle base body 31, three annular lithium batteries 32, a composite material reinforcing layer 33, an FPC packaged signal acquisition module 34, an FPC packaged charging module 34, a protective shell 36, and a wireless intelligent tool handle 37.

[0038] The annular lithium battery 32 is arranged in the annular groove of the composite material reinforcing layer 33; the FPC packaged signal acquisition module 34 is assembled in the left groove of the composite material reinforcing layer 33; the FPC packaged signal acquisition module 35 is assembled in the right groove of the composite material reinforcing layer 33; the composite material reinforcing layer 33, the signal acquisition module 34, the charging module 35 and the three annular lithium batteries 32 are all packaged in the protective shell 36 to obtain the assembled wireless intelligent tool handle 37.

[0039] The above specific embodiments can be adjusted in different ways by those skilled in the art without departing from the principles and purposes of the present application. The protection scope of the present application is subject to the claims and is not limited by the above specific embodiments. Each implementation within the scope is subject to the constraints of the present application.

Claims

1. A manufacturing system of a wireless smart shank based on FPC flexible packaging, characterized in that, The application relates to a milling machine and a wireless intelligent tool holder and a tool arranged at the end of the wireless intelligent tool holder, and a workpiece arranged opposite the tool, wherein the workpiece is arranged on a milling machine workbench through a vice, the wireless intelligent tool holder is connected with an upper computer in a wireless mode and transmits three-direction vibration signals of the tool holder position in a cutting process, the three-direction vibration signals are processed and analyzed through the upper computer through an artificial intelligence algorithm, the tool wear value is monitored in real time, the residual life of the tool is predicted, and the cutting parameters are optimized, more reasonable cutting parameters are provided for the cutting machining of the workpiece, and the service life of the tool is prolonged. The artificial intelligence algorithm is a Kolmogorov-Arnold neural network (KAN) for tool wear state monitoring, complex high-dimensional functions are decomposed into simple one-dimensional function combinations to process complex data fitting problems, and accurate mapping between cutting vibration signals and tool wear is realized. The wireless intelligent tool holder comprises a tool holder base body, a turning part and a composite material reinforcing layer arranged outside the turning part which are sequentially connected, wherein the composite material reinforcing layer is provided with an annular groove and two module grooves. The composite material reinforcing layer is realized through the following modes: i) different tool holder models are established for simulation, the maximum thickness of the turning part and the laying direction are determined under the premise of ensuring the overall strength and rigidity of the tool holder, the number of layers of the composite material is determined according to the wall thickness of the tool holder turning part; ii) the resin is uniformly applied on the tool holder turning part, the composite material is wound on the surface of the cylinder layer by layer, air bubbles are discharged by using a roller, the composite material is ensured to be closely attached, air is extracted by a vacuum pump to create a negative pressure environment, internal air bubbles are removed to improve adhesion, the composite material is wound again, vacuum is extracted again, high-temperature curing is finally carried out, and FPC flexible module grooves and soft wire arrangement grooves are processed through micro-machining technology; iii) the prepared composite material reinforcing tool holder is checked for static structural strength, dynamic structural strength and inherent frequency, and the FPC flexible module is assembled for signal acquisition test. FPC packaged signal acquisition modules and FPC packaged charging modules are arranged in the two module grooves, the charging module is connected with a lithium battery, and the input voltage between the signal acquisition module and the wireless transmission module is stabilized.

2. The manufacturing system of the wireless smart shank based on FPC flexible packaging described in claim 1, characterized in that, The FPC packaged signal acquisition module comprises an acceleration sensor, a microprocessor and a Wi-Fi transmission module, wherein the acceleration sensor acquires tool holder vibration signals in a cutting process and transmits the tool holder vibration signals to the microprocessor through serial communication; the microprocessor transmits the processed signals to a Wi-Fi module serving as a server based on serial communication; and the Wi-Fi module communicates with an upper computer serving as a client based on a TCP / IP protocol.

3. The manufacturing system of the FPC-based flexible package wireless intelligent shank according to claim 2, characterized in that, The charging module comprises a power management chip, a voltage stabilizing chip and an annular lithium battery, wherein the power management chip realizes power conversion, distribution and monitoring to guarantee the power supply requirement of the acquisition module; the voltage stabilizing chip stably provides 3.3v voltage for the acquisition module and limits voltage fluctuation; and the annular lithium battery is arranged in the annular groove and serves as the power supply of the acquisition module.

4. The manufacturing system of the FPC-based flexible package wireless intelligent shank according to claim 2, characterized in that, ​ 5. The manufacturing system of the FPC-based flexible package wireless smart tool shank according to claim 1, characterized in that, The composite reinforcing layer is externally provided with a protective shell.

Images