Low-temperature cutting machining process monitoring and quality feedback control system

Abstract

The invention provides a low-temperature cutting machining process monitoring and quality feedback control system, comprising: a sensor detection module comprising a vibration sensor, a temperature sensor, an acoustic emission sensor, a pressure sensor, a flow sensor and a structured light sensor; the signal processing and analyzing module is used for performing preprocessing, decomposition and feature extraction on the signal data acquired by each sensor and performing surface topography reconstruction on the point cloud data to obtain processing signal features and a processing surface three-dimensional topography model; the machining state and quality analysis module is used for analyzing the machining signal characteristics and the machining surface three-dimensional shape model and judging the machining state and the machining quality of the part to obtain machining state information and machining quality information; and the process parameter adjusting module is used for comparing and identifying the processing state information and the processing quality information with existing data in a database, so that process parameters are adjusted according to expert knowledge and process rules in the database.

Description

Technical Field

[0001] The invention relates to the technical field of cryogenic cutting processing, and in particular to a cryogenic cutting processing process monitoring and quality feedback control system. Background Art

[0002] Low temperature processing technology can deliver dry ice, liquid nitrogen and their gas-liquid mixture to the shear surface of material processing, and by changing the properties of the material to be removed in the material cutting area, the material removal mechanism undergoes essential changes, effectively improving the material processing performance. Due to its advantages of being green, high precision, high efficiency, and high processing surface quality, the processed materials and parts have the characteristics of high fatigue resistance, high impact resistance, and high creep resistance, etc., and have received more and more widespread attention.

[0003] The cooling methods used in low-temperature machining are mainly divided into three types: tool internal circulation cooling, external spray cooling, and tool internal spray cooling. Among them, the cooling medium of tool internal circulation cooling is not sprayed to the tool tip, but is cooled inside the tool body through the circulation structure on the tool, that is, only the tool is cooled but not the part. Therefore, although this method has a general cooling effect on the cutting area, it is suitable for some materials with moderate cutting temperature, large thermal expansion coefficient, but high requirements for machining dimensional accuracy; external spray cooling is to spray low-temperature cooling medium into the cutting area through the nozzle of external auxiliary equipment. This method is easy to implement, but there are problems such as low cooling medium utilization, poor machine tool function integration, and weak drilling and milling cooling capacity; tool internal spray cooling is to transport the cooling medium to the tool tip through the internal channel of the tool, and spray the cooling medium directly onto the part processing surface through the tool tip opening to achieve direct and sufficient cooling of the cutting area, with low cooling medium consumption and higher cooling efficiency.

[0004] Whether it is conventional processing or low temperature processing, in the process of studying the processing surface quality, the surface geometric characteristics of the parts are usually used to evaluate the processing quality, such as judging the processing accuracy, corrosion resistance and fatigue strength of the parts by the size of the surface roughness. With the continuous development of materials science, people have begun to try to comprehensively examine and evaluate the quality of parts from the aspects of mechanical, physical and chemical properties of parts, including microhardness, residual stress, surface density and metallographic structure of the surface and subsurface of parts. Due to the different use requirements of parts, there are many factors that affect the processing quality. Generally, it is necessary to use a variety of different indicators to comprehensively evaluate the parts according to the specific processing objects.

[0005] There are many processing states and processing quality indicators that need to be monitored in the cryogenic cutting process. In addition to the online monitoring of the machine tool operation status, tool life and part processing surface during the conventional processing, the low-temperature cooling medium jet state, such as gas pressure, flow rate and cooling temperature, needs to be monitored in real time. With the development of sensor technology and artificial intelligence technology, automatic monitoring and control methods for the processing process have been more and more widely used. During cutting, the interaction between the tool and the workpiece will generate various physical information such as force, heat and vibration. Using various sensors to collect these signals that can characterize the processing state, and through signal processing technology and feature engineering, an accurate and reliable method for monitoring the processing surface quality is proposed. This has become the focus of theoretical research and engineering application of cutting process monitoring.

[0006] Existing cutting process monitoring technologies can be mainly divided into direct monitoring and indirect monitoring. Among them, direct monitoring technology uses measuring instruments and equipment to directly measure the monitoring target, such as using an optical microscope to measure the wear of the tool, and using a roughness meter to measure the surface roughness of the part after processing. However, the direct measurement method cannot detect the condition of the tool or part online or in situ, so it has a great impact on the processing efficiency. At the same time, since the measuring instrument cannot communicate with the machine tool, the machine tool CNC system cannot adjust and control the processing technology according to the quality of the test results. Therefore, the application of this type of method is very limited and is only suitable for random inspection of small batches of parts.

[0007] Indirect monitoring technology uses sensors to collect changes in physical signals during the processing process, and obtains signal features that can characterize tool wear and part surface quality through signal processing, feature fusion and machine learning methods. According to the change rules of these features, the cutting state can be indirectly understood. Compared with direct monitoring technology, indirect monitoring technology can understand the operation of machine tools and part processing conditions in the processing process online and in real time, without stopping the machine for detection, thereby improving processing efficiency; at the same time, the acquisition method of sensor signals is relatively convenient. At present, most CNC systems are equipped with basic spindle power and current detection modules, which can grasp certain processing conditions through changes in power and current, and external dynamometers, vibration sensors and temperature sensors can also provide multi-physical field information during the processing process. This information is transmitted back to the machine tool through a certain feedback mechanism, and combined with expert systems and knowledge bases to provide process adjustment decisions. In recent years, machine learning has been increasingly used in the manufacturing field. Its powerful ability to handle nonlinear and complex problems has improved the accuracy of monitoring the processing process.

[0008] At present, the research on cryogenic processing technology focuses on cryogenic cooling implementation technology and cryogenic processing equipment development, and there is still little research on cryogenic processing process monitoring and control system and strategy. In some basic studies, the influence of cryogenic cooling on material properties has been explored, and the threshold of ultra-low temperature medium on different materials has been determined, but the low temperature has not been linked to the feedback control of tool life, machine tool operation stability and part processing surface quality.

[0009] Therefore, the technical problem that needs to be solved urgently is how to establish a closed-loop system of low-temperature environment-process status-machining quality-parameter adjustment, control the cooling temperature by adjusting the flow and pressure of the cooling medium, and make the low-temperature environment affect the performance change of the material, thereby improving the tool life and machining performance, and ultimately improving the machining quality. Summary of the invention

[0010] The present invention is made to solve the above-mentioned problems, and its purpose is to provide a low-temperature cutting process monitoring and quality feedback control system to improve tool life and processing performance and enhance processing quality.

[0011] The present invention provides a low-temperature cutting process monitoring and quality feedback control system, which has the following characteristics, including: a sensor detection module, which is installed near the part tooling in the low-temperature processing machine tool, and the sensor detection module includes a vibration sensor for detecting machine tool vibration, a temperature sensor for detecting cutting temperature, an acoustic emission sensor for detecting material removal energy, a pressure sensor for detecting processing pressure, a flow sensor for detecting cooling medium flow, and a structured light sensor for detecting parts with white film formed on the surface; a signal processing and analysis module, which is connected to each sensor of the sensor detection module and is used to pre-process and decompose the signal data collected by each sensor and feature extraction, as well as surface morphology reconstruction of point cloud data to obtain processing signal characteristics and a three-dimensional morphology model of the processing surface; a processing state and quality analysis module, which is connected to the signal processing and analysis module, and is used to analyze the processing signal characteristics and the three-dimensional morphology model of the processing surface, and to judge the processing state and the processing quality of the parts to obtain processing state information and processing quality information; and a process parameter adjustment module, which is connected to the processing state and quality analysis module and the low-temperature processing machine tool, and is used to compare and identify the processing state information and processing quality information with the existing data in the database, so as to adjust the process parameters according to the expert knowledge and process rules in the database.

[0012] The low-temperature cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the temperature sensor, pressure sensor and flow sensor are installed at the outlet of the low-temperature cooling device, and the structured light sensor is installed on the machine tool workbench.

[0013] The low-temperature cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the signal processing and analysis module includes a data acquisition unit and a signal analysis unit.

[0014] In the cryogenic cutting process monitoring and quality feedback control system provided by the present invention, it may also have the following features: wherein the data acquisition unit acquires the physical signal from the sensor detection module through the data acquisition card, and converts the analog voltage signal into a digital signal that can be read by a computer;

[0015] The cryogenic cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the signal analysis unit pre-processes, decomposes and extracts features of the part processing signal detected by the sensor detection module, and reconstructs the surface morphology of the point cloud data. The specific process of processing and analysis includes:

[0016] Signal preprocessing: Identify and classify the imported vibration signals, temperature signals and acoustic emission signals according to the coordinate direction of the processing system, perform spectrum analysis on them, and use filters of different bandwidths to filter and preprocess them according to the frequency characteristics of the signals to eliminate noise signals that are not related to the processing process in the process system and data acquisition system;

[0017] Signal decomposition: Fourier transform, wavelet packet transform and variational mode decomposition are used to decompose the signal after noise reduction preprocessing to obtain the processed signal in time domain and frequency domain;

[0018] Feature extraction: extract indicators that can reflect the machining process from the imported time-frequency domain signals, and use statistical methods to extract the time domain features of the cutting signal. The time domain features include: effective value, mean value, standard deviation, entropy, etc.; use the power spectrum density estimation method to extract the frequency domain features of the cutting signal. The frequency domain features include: skewness, kurtosis, peak frequency, crest factor and centroid frequency, etc.

[0019] Reconstruction of machining surface morphology: The structured light sensor projects dot matrix light onto the machined surface and captures the deformed image of the projected area. The signal analysis unit analyzes the deformation of the pattern in the image and calculates the depth information of each point to generate the corresponding three-dimensional point cloud data. The reconstruction algorithm is applied to transform the point cloud data into a three-dimensional morphology model of the machined surface. Finally, the reconstructed morphology model is smoothed, repaired, and texture mapped.

[0020] In the low-temperature cutting process monitoring and quality feedback control system provided by the present invention, it can also have the following characteristics: wherein, the processing state and quality analysis module includes a processing state analysis unit and a processing quality analysis unit, wherein the processing state information obtained by the processing state analysis unit includes chatter, tool wear and low-temperature cooling state, and the processing state information obtained by the processing quality analysis unit includes surface roughness, residual stress and defective area.

[0021] The low-temperature cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the processing state analysis unit uses vibration and acoustic emission signal characteristics to detect and warn processing chatter and tool life. According to the signal feature-processing state association knowledge stored in the low-temperature processing technology database, when chatter occurs during processing and tool wear is severe, the vibration signal characteristic amplitude used to monitor chatter and the acoustic emission signal amplitude of tool wear will increase significantly. The detected vibration signal and acoustic emission signal are compared with the signal threshold in the low-temperature processing technology database. According to expert knowledge and process rules, process parameter adjustment instructions such as reducing cutting speed and cutting depth are sent to the machine tool control unit. By adjusting the corresponding parameters, chatter is suppressed, the degree of tool wear is reduced, or the operator is prompted to replace the tool. The processing quality analysis unit uses machine learning technology to predict quality information such as residual stress and hardness of the processing surface that cannot be detected by structured light sensors through vibration, temperature and acoustic emission signals. The low-temperature temperature-material property association knowledge and process parameter-machining quality association knowledge stored in the process database are used. When the quality indicators such as part machining roughness, residual stress, hardness, defects, etc. are close to the quality indicator threshold in the database, the jet parameters of the low-temperature cooling medium, including flow rate and pressure, are adjusted according to the low-temperature temperature-material property association knowledge to create a low-temperature machining environment that adapts to the current working conditions and quality inspection results, including reducing the cooling medium flow rate when the machining surface roughness increases, increasing the low-temperature temperature to reduce the material strength, and making it easier to form the cutting surface; when the residual stress increases, increasing the cooling medium flow rate, lowering the cutting temperature, reducing the residual tensile stress while increasing the residual compressive stress; when the predicted or detected quality indicators exceed the quality indicator threshold in the database, or changing the low-temperature temperature cannot improve the machining quality, according to the process parameter-machining quality association knowledge, adjust the machining process parameters such as cutting speed, feed rate, cutting depth, including reducing the feed rate when the surface roughness is too large, and increasing the cutting speed when the surface defects increase.

[0022] The low-temperature cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the process parameter adjustment module includes a low-temperature machining process database and a machine tool control unit.

[0023] In the low-temperature cutting process monitoring and quality feedback control system provided by the present invention, it can also have the following characteristics: wherein, the low-temperature processing technology database stores the correlation between process parameters, sensor signals, machine tool processing status and material processing performance, and the low-temperature processing technology database gives corresponding process parameter adjustment decisions based on the processing status and chatter, tool life or processing quality results predicted or detected by the quality analysis module; according to the decision of the low-temperature processing technology database, the machine tool control unit adjusts the corresponding process parameters in the numerical control system, and the correlation relationships stored in the low-temperature processing technology database include the relationship between the low-temperature environment and material performance, the relationship between process parameters and processing quality, and the relationship between signal characteristics and processing status.

[0024] The low-temperature cutting process monitoring and quality feedback control system provided by the present invention may also have the following features: wherein the process parameters adjusted by the machine tool control unit include increasing the flow control valve when the cooling temperature is insufficient, reducing the cutting depth when chatter occurs, reducing the cutting speed and issuing a warning when the tool is approaching its service life, and increasing the cutting speed and reducing the feed rate when the machining surface roughness deteriorates.

[0025] Functions and Effects of the Invention

[0026] According to the low-temperature cutting process monitoring and quality feedback control system involved in the present invention, the present invention adopts a low-temperature machining process monitoring and quality feedback control closed-loop system of low-temperature cooling environment-process state perception-machining quality analysis-process parameter adjustment. During machining, the system detects the machine tool machining state and part machining quality while adjusting the process parameters according to the state and quality results, forming real-time closed-loop detection and control of the machining process, realizing five functions including machining environment and state monitoring, tool life monitoring and early warning, machining quality analysis and evaluation, cooling medium jet state regulation and process parameter feedback control, so that the low-temperature cooling environment and machining process adjustment meet the optimal machining performance of the parts and improve the machining quality of the parts in the low-temperature machining environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a low temperature processing state monitoring and processing quality feedback control system in an embodiment of the present invention;

[0028] Figure 2 It is a process of processing signal and reconstructing processing surface in an embodiment of the present invention;

[0029] Figure 3 is a processing status and quality analysis flow in an embodiment of the present invention; and

[0030] Figure 4 This is the process parameter adjustment and processing quality control process in the embodiment of the present invention. DETAILED DESCRIPTION

[0031] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or mutual communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0032] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the following embodiments are combined with the accompanying drawings to specifically explain the low-temperature cutting process monitoring and quality feedback control system of the present invention.

[0033] Figure 1 It is a low temperature processing state monitoring and processing quality feedback control system in an embodiment of the present invention.

[0034] like Figure 1 As shown, the cryogenic cutting process monitoring and quality feedback control system 100 in this embodiment includes a sensor detection module 10 , a signal processing and analysis module 20 , a processing state and quality analysis module 30 and a process parameter adjustment module 40 .

[0035] The sensor detection module 10 includes a vibration sensor 11 for detecting machine tool vibration, a temperature sensor 14 for detecting cutting temperature, an acoustic emission sensor 12 for detecting material removal energy, a pressure sensor 13 for detecting machining pressure, a flow sensor 15 for detecting cooling medium flow, and a structured light sensor 16 for detecting parts with a white film formed on the surface.

[0036] The signal processing and analysis module 20 includes a data acquisition unit 21 and a signal processing and analysis unit 22 .

[0037] The signal processing and analysis module 20 is connected to each sensor of the sensor detection module 10, and is used to preprocess, decompose and extract features of the signal data collected by each sensor, and reconstruct the surface morphology of the point cloud data to obtain processing signal features and a three-dimensional morphology model of the processing surface.

[0038] The data acquisition unit 21 acquires the physical signal from the sensor detection module 10 through a data acquisition card, and converts the analog voltage signal into a digital signal that can be read by a computer.

[0039] The signal processing and analysis unit 22 pre-processes, decomposes and extracts features of the part processing signal detected by the sensor detection module 10, and reconstructs the surface morphology of the point cloud data. The specific process of processing and analysis includes:

[0040] The processing state and quality analysis module 30 includes a processing state analysis unit 31 and a processing quality analysis unit 32 .

[0041] The processing state and quality analysis module 30 is connected to the signal processing and analysis module 20, and is used to analyze the processing signal characteristics and the three-dimensional morphology model of the processing surface, and to judge the processing state and the processing quality of the parts to obtain the processing state information and processing quality information.

[0042] The machining state analysis unit 31 detects and warns machining chatter and tool 17 life using vibration and acoustic emission signal characteristics.

[0043] The processing quality analysis unit 32 uses machine learning technology to predict the quality information such as residual stress and hardness of the processing surface that cannot be detected by the structured light sensor 16 through vibration, temperature and acoustic emission signals.

[0044] The process parameter adjustment module 40 includes a cryogenic machining process database 41 and a machine tool control unit 42 .

[0045] The process parameter adjustment module 40 is connected to the processing state and quality analysis module 30 and the cryogenic processing machine 50, and is used to compare and identify the processing state information and processing quality information with the existing data in the database, so as to adjust the process parameters according to the expert knowledge and process rules in the database.

[0046] The low-temperature machining process database 41 stores the correlation between process parameters and sensor signals and the machine tool machining state and material processing performance. The low-temperature machining process database 41 gives corresponding process parameter adjustment decisions based on the machining state and the chatter, tool 17 life or machining quality results predicted or detected by the quality analysis module 30; according to the decision of the low-temperature machining process database 41, the machine tool control unit 42 adjusts the corresponding process parameters in the numerical control system. The correlations stored in the low-temperature machining process database 41 include the relationship between the low-temperature environment and material performance, the relationship between process parameters and machining quality, and the relationship between signal characteristics and machining state.

[0047] The process parameters adjusted by the machine tool control unit 42 include increasing the flow control valve when the cooling temperature is insufficient, reducing the cutting depth when vibration occurs, reducing the cutting speed and issuing a warning when the tool 17 is close to its service life, and increasing the cutting speed and reducing the feed rate when the machining surface roughness deteriorates.

[0048] Figure 2 This is the process of processing signal and reconstructing processing surface in the embodiment of the present invention. Figure 3 This is the processing status and quality analysis flow in the embodiment of the present invention. Figure 4 This is the process parameter adjustment and processing quality control process in the embodiment of the present invention.

[0049] like Figure 1-4 As shown, the working principle and steps of the low temperature cutting process monitoring and quality feedback control system 100 of the present invention are as follows:

[0050] S1: Figure 1 As shown, a vibration sensor 11, a temperature sensor 14, and an acoustic emission sensor 12 are installed near the part tooling in the low-temperature processing machine 50, a temperature sensor 14, a pressure sensor 13, and a flow sensor 15 are installed at the outlet of the low-temperature cooling device, a structured light sensor 16 is installed on the machine tool workbench, and all sensors are connected to the signal processing and analysis module 20.

[0051] S2: Set the flow and pressure of the low-temperature cooling medium in the CNC system, and set the cutting process parameters, including: spindle speed, workpiece feed speed, cutting thickness, etc.

[0052] S3: Start processing parts.

[0053] S4: During the machining process, the vibration sensor 11, the temperature sensor 14, and the acoustic emission sensor 12 collect the cutting vibration, cutting temperature, and acoustic emission signals of the parts in real time. The temperature sensor 14, the pressure sensor 13, and the flow sensor 15 at the outlet of the cryogenic cooling device are used to monitor the jet state of the cryogenic cooling medium, and the structured light sensor 16 detects the machined surface. The sensor signal data is uploaded to the host computer through the data acquisition unit 21 in the signal processing and analysis module 20.

[0054] S5: Figure 2 As shown, in the signal analysis unit 22, the part processing signal is preprocessed, decomposed and feature extracted, and the surface morphology of the point cloud data is reconstructed:

[0055] S5-1 Signal preprocessing: Identify and classify the imported vibration signals, temperature signals and acoustic emission signals according to the coordinate direction of the processing system, perform spectrum analysis on them, and use filters of different bandwidths to filter and preprocess the signals according to their frequency characteristics to eliminate noise signals that are not related to the processing in the process system and data acquisition system.

[0056] S5-2 Signal decomposition: Fourier transform, wavelet packet transform and variational mode decomposition are used to decompose the signal after noise reduction preprocessing to obtain time domain and frequency domain processed signals.

[0057] S5-3 Feature extraction: Extract indicators that can reflect the machining process from the imported time-frequency domain signals. Use statistical methods to extract the time domain features in the cutting signal. The extractable time domain features include: effective value, mean value, standard deviation, entropy, etc. Use power spectrum density estimation method to extract the frequency domain features in the cutting signal. The extractable frequency domain features include: skewness, kurtosis, peak frequency, crest factor and centroid frequency, etc.

[0058] S5-4 Reconstruction of machining surface morphology: The structured light sensor 16 projects dot matrix light onto the machined surface, captures the deformed image of the projected area, and the signal analysis unit 22 analyzes the deformation of the pattern in the image and calculates the depth information of each point, generates corresponding three-dimensional point cloud data, and applies a reconstruction algorithm to transform the point cloud data into a three-dimensional morphology model of the machined surface. Finally, the reconstructed morphology model is smoothed, repaired, and texture mapped.

[0059] S6: Figure 3 As shown, the processing signal characteristics and the three-dimensional morphology model of the processing surface are transmitted to the processing state analysis unit 31 and the processing quality analysis unit 32 in the processing state and quality analysis module 30. Both units contain multiple machine learning prediction models. The input of the model is various signal characteristics and the three-dimensional surface morphology model, and the output of the model is the judgment result of the processing state and processing quality.

[0060] S6-1: The machining state analysis unit 31 mainly analyzes whether the machining state is stable. According to the characteristic input of the signal characteristics, the state model is predicted and trained, and finally the machining chatter judgment, the remaining life of the tool 17 and the cooling medium state are output. For example, the vibration signal characteristics of the parts are combined to judge whether chatter occurs and whether the machining process is stable; the cutting temperature and acoustic emission signal characteristics are combined to judge the wear condition and remaining service life of the tool 17. When the tool 17 is severely worn, the tool 17 prediction model will issue an alarm and issue a tool change command; the temperature, flow and pressure signal characteristics of the cooling medium are combined to judge whether the jet state of the low-temperature cooling medium is normal.

[0061] S6-2: The processing quality analysis unit 32 mainly analyzes the processing quality of the parts, predicts and trains the quality model according to the signal characteristics, and then combines the surface morphology model to finally output the residual stress prediction, surface roughness prediction and defect area calculation. Specifically, for example, the processing residual stress of the parts is predicted by combining the cutting temperature and acoustic emission signal characteristics; the surface three-dimensional morphology model is used to calculate the surface roughness, defect area and other surface quality quantitative indicators.

[0062] S7: Figure 4As shown, all the processing state information (chatter, tool 17 wear, cryogenic cooling state, etc.) and processing quality information (surface roughness, residual stress, defective area, etc.) obtained in the processing state and quality analysis module 30 are transmitted to the cryogenic processing process database 41 in the process parameter adjustment module 40, and these information are compared and identified with the existing data in the database. The results of the comparison and identification are sent to the machine tool control unit 42 according to the expert knowledge and process rules in the database, which are used to adjust the cutting speed, feed rate, cutting depth, cryogenic cooling medium flow, pressure, etc., to ensure stable processing and good processing quality.

[0063] (1) Determination of abnormal machining status and parameter adjustment: According to the signal feature-machining status association knowledge stored in the low-temperature machining process database 41, when chatter occurs during machining and the tool 17 is severely worn, the characteristic amplitude of the vibration signal used to monitor the chatter and the amplitude of the acoustic emission signal for tool 17 wear will increase significantly. The detected vibration signal and acoustic emission signal are compared with the signal threshold in the low-temperature machining process database 41. According to expert knowledge and process rules, process parameter adjustment instructions such as reducing cutting speed and cutting depth are sent to the machine tool control unit 42. By adjusting the corresponding parameters, chatter is suppressed, the degree of tool 17 wear is reduced, or the operator is prompted to replace the tool 17.

[0064] (2) Determination of abnormal processing quality and parameter adjustment: According to the low temperature temperature-material property association knowledge and process parameter-processing quality association knowledge stored in the low temperature processing process database 41, when the quality indicators such as the processing roughness, residual stress, hardness, and defects of the parts are close to the quality indicator threshold in the database, the jet parameters of the low temperature cooling medium, such as flow rate and pressure, are adjusted according to the low temperature temperature-material property association knowledge to create a low temperature processing environment that adapts to the current working conditions and quality inspection results. For example, when the processing surface roughness increases, the cooling medium flow rate is reduced, and the low temperature temperature is increased to reduce the material strength, making it easier to form the cutting surface; when the residual stress increases, the cooling medium flow rate is increased, the cutting temperature is reduced, and the residual tensile stress is reduced while the residual compressive stress is increased. When the predicted or detected quality indicators exceed the quality indicator threshold in the database, or changing the low temperature temperature cannot improve the processing quality, the processing parameters such as cutting speed, feed rate, and cutting depth are adjusted according to the process parameter-processing quality association knowledge. For example, when the surface roughness is too large, the feed rate is reduced, and when the surface defects increase, the cutting speed is increased.

[0065] Repeat S4, S5, S6 and S7 during the cryogenic cutting process. If the cutting state is stable, there is no need to adjust the process parameters. If the monitoring system indicates that the tool 17 is severely worn and the surface quality monitoring result of the part exceeds the preset threshold, adjust the process parameters to realize the cryogenic cooling environment-process state perception-machining quality analysis-process parameter adjustment cryogenic processing process monitoring and quality feedback control closed loop, thereby improving the part processing quality.

[0066] Functions and Effects of the Embodiments

[0067] According to the low-temperature cutting process monitoring and quality feedback control system involved in the present invention, the present invention adopts a low-temperature machining process monitoring and quality feedback control closed-loop system of low-temperature cooling environment-process state perception-machining quality analysis-process parameter adjustment. During machining, the system detects the machine tool machining state and part machining quality while adjusting the process parameters according to the state and quality results, forming real-time closed-loop detection and control of the machining process, realizing five functions including machining environment and state monitoring, tool life monitoring and early warning, machining quality analysis and evaluation, cooling medium jet state regulation and process parameter feedback control, so that the low-temperature cooling environment and machining process adjustment meet the optimal machining performance of the parts and improve the machining quality of the parts in the low-temperature machining environment.

[0068] The present invention stores various related knowledge such as the relationship between low temperature environment and material performance, the relationship between process parameters and processing quality, the relationship between signal characteristics and processing status in the low temperature processing technology database. The relationship between low temperature environment and material performance is given priority when performing feedback control, and the influence of low temperature on material performance is fully utilized to improve the effectiveness of processing quality control.

[0069] The cryogenic cooling medium vaporizes rapidly under the influence of cutting heat, forming a white film on the surface of the part, making it difficult to detect the processed surface online in real time using two-dimensional images taken by industrial cameras. The present invention adopts a structured light sensor to project stripes, grids or dot matrix lights onto the processed surface, and captures the deformation of these lights on the surface. It can obtain three-dimensional surface morphology information with length, width and depth information. Therefore, it can be used in low-temperature processing process monitoring and control systems to provide more accurate processing surface morphology and quality assessment.

[0070] The present invention adopts a structured light sensor to obtain point cloud data of the processed surface and reconstructs the generated three-dimensional morphology of the surface, which more comprehensively reflects the processing quality from two dimensions of processing size accuracy and processing surface morphology.

[0071] The present invention adopts the low-temperature processing feedback control logic that prioritizes the low-temperature environment. When the processing state is abnormal or the processing quality does not meet the standard, the influence of the low-temperature environment on the material cutting performance is comprehensively considered, and the jet state of the cooling medium is adjusted preferentially, so as to more reasonably adjust the cutting process parameters.

[0072] Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A low temperature cutting process monitoring and quality feedback control system, used to monitor, control and analyze the processing process of a low temperature machining machine tool, characterized in that: include: A sensor detection module is installed near a part tooling in a cryogenic processing machine tool, wherein the sensor detection module includes a vibration sensor for detecting machine tool vibration, a temperature sensor for detecting cutting temperature, an acoustic emission sensor for detecting material removal energy, a pressure sensor for detecting processing pressure, a flow sensor for detecting cooling medium flow, and a structured light sensor for detecting a part with a white film formed on the surface; A signal processing and analysis module, which is connected to each sensor of the sensor detection module and is used to preprocess, decompose and extract features of the signal data collected by each sensor, and reconstruct the surface morphology of the point cloud data to obtain processing signal features and a three-dimensional morphology model of the processing surface; A processing state and quality analysis module, which is connected to the signal processing and analysis module and is used to analyze the processing signal characteristics and the three-dimensional morphology model of the processing surface, and to judge the processing state and the processing quality of the parts, so as to obtain processing state information and processing quality information; as well as A process parameter adjustment module is connected to the processing status and quality analysis module and the low-temperature processing machine tool, and is used to compare and identify the processing status information and processing quality information with the data already in the database, so as to adjust the process parameters according to the expert knowledge and process rules in the database.

2. The cryogenic cutting process monitoring and quality feedback control system according to claim 1, characterized in that: in, The temperature sensor, pressure sensor and flow sensor are installed at the outlet of the low-temperature cooling device, and the structured light sensor is installed on the machine tool workbench.

3. The cryogenic cutting process monitoring and quality feedback control system according to claim 1, characterized in that: in, The signal processing and analysis module includes a data acquisition unit and a signal analysis unit.

4. The cryogenic cutting process monitoring and quality feedback control system according to claim 3, characterized in that: in, The data acquisition unit acquires the physical signal from the sensor detection module through a data acquisition card, and converts the analog voltage signal into a digital signal that can be read by a computer.

5. The cryogenic cutting process monitoring and quality feedback control system according to claim 3, Features: The signal analysis unit preprocesses, decomposes and extracts features of the part processing signal detected by the sensor detection module, and reconstructs the surface morphology of the point cloud data. The specific process of the processing and analysis includes: Signal preprocessing: Identify and classify the imported vibration signals, temperature signals and acoustic emission signals according to the coordinate direction of the processing system, perform spectrum analysis on them, and use filters of different bandwidths to filter and preprocess them according to the frequency characteristics of the signals to eliminate noise signals that are not related to the processing process in the process system and data acquisition system; Signal decomposition: Fourier transform, wavelet packet transform and variational mode decomposition are used to decompose the signal after noise reduction preprocessing to obtain the processed signal in time domain and frequency domain; Feature extraction: extract indicators that can reflect the machining process from the imported time-frequency domain signals, and use statistical methods to extract the time-domain features of the cutting signal, including effective value, average value, standard deviation, entropy, etc.; use power spectrum density estimation method to extract the frequency-domain features of the cutting signal, including skewness, kurtosis, peak frequency, crest factor and centroid frequency, etc.; Reconstruction of machining surface morphology: The structured light sensor projects dot matrix light onto the machined surface and captures the deformed image of the projected area. The signal analysis unit analyzes the deformation of the pattern in the image and calculates the depth information of each point to generate the corresponding three-dimensional point cloud data. The reconstruction algorithm is applied to transform the point cloud data into a three-dimensional morphology model of the machined surface. Finally, the reconstructed morphology model is smoothed, repaired, and texture mapped.

6. The cryogenic cutting process monitoring and quality feedback control system according to claim 1, characterized in that: in, The processing state and quality analysis module includes a processing state analysis unit and a processing quality analysis unit, wherein the processing state information obtained by the processing state analysis unit includes chatter, tool wear and low-temperature cooling state, and the processing state information obtained by the processing quality analysis unit includes surface roughness, residual stress and defective area.

7. The cryogenic cutting process monitoring and quality feedback control system according to claim 6, characterized in that: in, The processing state analysis unit uses vibration and acoustic emission signal characteristics to detect and warn processing chatter and tool life. According to the signal feature-processing state association knowledge stored in the low-temperature processing technology database, when chatter occurs and tool wear is serious during processing, the characteristic amplitude of the vibration signal used to monitor chatter and the amplitude of the acoustic emission signal for tool wear will increase significantly. The detected vibration signal and acoustic emission signal are compared with the signal threshold in the low-temperature processing technology database. According to expert knowledge and process rules, process parameter adjustment instructions such as reducing cutting speed and cutting depth are sent to the machine tool control unit. By adjusting the corresponding parameters, chatter is suppressed, tool wear is reduced, or the operator is prompted to replace the tool. The processing quality analysis unit uses machine learning technology to predict quality information such as residual stress and hardness of the processing surface that cannot be detected by structured light sensors through vibration, temperature and acoustic emission signals. According to the low-temperature temperature-material properties stored in the low-temperature processing technology database, Associated knowledge, process parameter-processing quality associated knowledge. When the quality indicators such as part processing roughness, residual stress, hardness, defects, etc. are close to the quality indicator threshold in the database, the jet parameters of the low-temperature cooling medium, including flow rate and pressure, are adjusted according to the low-temperature temperature-material performance associated knowledge to create a low-temperature processing environment that adapts to the current working conditions and quality inspection results, including when the surface roughness of the processing increases, reducing the cooling medium flow rate, increasing the low-temperature temperature to reduce the material strength, and making it easier to form the cutting surface; when the residual stress increases, increasing the cooling medium flow rate, lowering the cutting temperature, reducing the residual tensile stress while increasing the residual compressive stress. When the predicted or detected quality indicators exceed the quality indicator threshold in the database, or changing the low-temperature temperature cannot improve the processing quality, according to the process parameter-processing quality associated knowledge, adjust the processing parameters such as cutting speed, feed rate, and cutting depth, including reducing the feed rate when the surface roughness is too large, and increasing the cutting speed when the surface defects increase.

8. The cryogenic cutting process monitoring and quality feedback control system according to claim 1, characterized in that: in, The process parameter adjustment module includes a low-temperature processing process database and a machine tool control unit.

9. The cryogenic cutting process monitoring and quality feedback control system according to claim 8, Features: The cryogenic machining process database stores the correlation between process parameters and sensor signals and the machining state of the machine tool and the machining performance of the material. The cryogenic machining process database gives corresponding process parameter adjustment decisions according to the machining state and chatter, tool life or machining quality results predicted or detected by the quality analysis module; According to the decision of the low-temperature machining process database, the machine tool control unit adjusts the corresponding process parameters in the numerical control system. The low-temperature machining process database stores the association relationships including the relationship between the low-temperature environment and material properties, the relationship between process parameters and machining quality, and the relationship between signal characteristics and machining status.

10. The cryogenic cutting process monitoring and quality feedback control system according to claim 8, characterized in that: in, The process parameters adjusted by the machine tool control unit include increasing the flow control valve when the cooling temperature is insufficient, reducing the cutting depth when chatter occurs, reducing the cutting speed and issuing a warning when the tool is approaching the end of its service life, and increasing the cutting speed and reducing the feed rate when the roughness of the machined surface deteriorates.

Images