A method and system for intelligent monitoring of numerical control machine tools

Abstract

The present invention discloses an intelligent monitoring method and system for numerically controlled machine tools, and relates to the technical field of machine tool monitoring. The intelligent monitoring method and system for numerically controlled machine tools realize comprehensive monitoring and optimization of the operating status of machine tools by setting a data acquisition module, a precision monitoring module, and an abnormal warning module. The data acquisition module collects machine tool operating data in real time through sensors to ensure the accuracy and timeliness of the data, and provide a reliable basis for subsequent analysis. The precision monitoring module analyzes the working status of the machine tool in real time and identifies the trend of periodic abnormal fluctuations, so as to timely discover potential problems and avoid the expansion of processing errors. The cutting speed and feed rate are intelligently adjusted through the fuzzy control algorithm, which significantly improves the processing accuracy and efficiency and reduces manual intervention. The abnormal warning module monitors the machine tool operating data in real time, generates warning information, and ensures that the operator can take measures in time, thereby improving the intelligence level of the numerically controlled machine tool.

Description

Technical Field

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

[0002] With the popularization of automation equipment, one of the challenges facing enterprises is how to efficiently manage a large number of machine tools. Traditional manual monitoring and maintenance methods are inefficient, time-consuming, and prone to downtime and production losses. Through intelligent monitoring systems, predictive maintenance can be achieved, unexpected failures can be reduced, and equipment utilization can be maximized. This demand comes from the strong demand of enterprises to improve production efficiency and reduce operating costs.

[0003] For example, the publication number CN115220396B is a method and system for intelligent monitoring of CNC machine tools. This invention relates to the field of machine tool monitoring technology, and specifically to a method and system for intelligent monitoring of CNC machine tools. The method includes: deploying multiple sensors on the CNC machine tools to collect the operating data of various detection parameters during the operation of the machine tools, which are used to detect and analyze the data of various parameters of the machine tools; establishing a data analysis model, based on the analysis of the individual detection parameter data, extracting the characteristic parameters during the operation of the machine tools, which are used to analyze the operating status of the machine tools; based on the extracted characteristic parameters of the machine tool operation, automatically detecting the machine tool status, and realizing intelligent monitoring of CNC machine tools. The present invention accurately extracts abnormal data and avoids the influence of noise data on its detection process.

[0004] However, the above system still has problems such as untimely response and incomplete data analysis when dealing with complex operating conditions and high-frequency parameter changes. These limitations may result in the machine tool failing to achieve the optimal operating state in actual production, and failing to effectively reduce processing errors and improve production efficiency. Therefore, a more advanced intelligent monitoring method and system is urgently needed to improve the overall performance of CNC machine tools and ensure the stability and reliability of the production process. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method and system for intelligent monitoring of CNC machine tools, which solve the problems of the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent monitoring system for CNC machine tools, comprising the following modules: a data acquisition module, a precision monitoring module, and an abnormal warning module; the data acquisition module is used to acquire the operation data of the CNC machine tools through sensors; the precision monitoring module includes a processing state monitoring unit, an error analysis unit, and an error correction unit; the processing state monitoring unit is used to extract the spindle speed spectrum characteristics through Fourier transform based on the operation data of the CNC machine tools, construct a spindle speed frequency domain characteristic model, and identify the periodic abnormal fluctuation trend of the spindle speed; the error analysis unit is used to acquire the processing error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, and acquire the spindle speed abnormal fluctuation index by analyzing the spindle speed spectrum characteristics; the error correction unit is used to control the CNC machine tools to adjust the cutting speed and feed rate through a fuzzy control algorithm based on the processing error index and the spindle speed abnormal fluctuation index; the abnormal monitoring module is used to monitor the operation data of the CNC machine tools and generate real-time warning information.

[0007] Furthermore, based on the CNC machine tool operation data, the specific process of extracting the spindle speed spectrum characteristics through Fourier transform is as follows: based on the CNC machine tool operation data, the spindle speed time series data is extracted, and data preprocessing and segmentation processing are performed; fast Fourier transform is applied to the spindle speed time series data, and its frequency components and corresponding amplitudes are calculated and summarized to obtain the spindle speed spectrum characteristics.

[0008] Furthermore, the specific process of constructing the frequency domain characteristic model of the spindle speed is as follows: statistical analysis is performed on the extracted spectrum characteristics of the spindle speed to identify the main frequency components and their amplitudes in the spectrum; the frequency components are associated with the corresponding processing states through curve fitting to construct the frequency domain characteristic model of the spindle speed.

[0009] Furthermore, the specific process of identifying the periodic abnormal fluctuation trend of the spindle speed is as follows: based on the frequency domain characteristic model of the spindle speed, the amplitude and phase changes of each frequency component in the spectrum are analyzed, the threshold is set, the frequency components beyond the normal fluctuation range are identified, and marked as abnormal signals; the periodic change pattern of the spindle speed is detected through the time series, the periodic characteristics of the abnormal fluctuation of the spindle speed are identified, and a report on the periodic abnormal fluctuation trend of the spindle speed is generated.

[0010] Furthermore, by analyzing the periodic abnormal fluctuation trend of the spindle speed, the specific process of obtaining the machining error index is as follows: monitor the periodic abnormal fluctuation trend of the spindle speed, and record the amplitude and fluctuation frequency of the spindle speed; according to the periodic characteristics of the abnormal fluctuation of the spindle speed, compare the amplitude and fluctuation frequency of the spindle speed with the standard machining parameters to obtain the machining error index.

[0011] Furthermore, by analyzing the spindle speed spectrum characteristics, the specific process of obtaining the spindle speed abnormal fluctuation index is as follows: statistical analysis is performed on the extracted spindle speed spectrum characteristics, the amplitude and phase of the spindle speed frequency components are recorded, the frequency components beyond the normal range are identified, and marked as abnormal signals; based on the identified abnormal signals, the spindle speed abnormal fluctuation index is calculated.

[0012] Furthermore, the specific process of controlling the CNC machine tool to adjust the cutting speed and feed rate through the fuzzy control algorithm is as follows: the machining error index and the spindle speed abnormal fluctuation index are defined as input variables, and they are divided into different fuzzy sets respectively; the cutting speed and feed rate of the CNC machine tool are defined as output variables, and they are divided into fuzzy sets; a fuzzy control rule base is constructed, and fuzzy rules are formulated to describe the influence of the machining error index and the spindle speed abnormal fluctuation index on the cutting speed and feed rate of the CNC machine tool; fuzzy reasoning is performed according to the fuzzy rules to determine the cutting speed and feed rate of the CNC machine tool.

[0013] An intelligent monitoring method for CNC machine tools comprises the following steps: S1. acquiring the operation data of the CNC machine tools through sensors; S2. extracting the frequency spectrum characteristics of the spindle speed through Fourier transform based on the operation data of the CNC machine tools, constructing a frequency domain characteristic model of the spindle speed, and identifying the periodic abnormal fluctuation trend of the spindle speed; S3. acquiring a machining error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, and acquiring an abnormal spindle speed fluctuation index by analyzing the frequency spectrum characteristics of the spindle speed; S4. controlling the CNC machine tools to adjust the cutting speed and feed rate through a fuzzy control algorithm based on the machining error index and the abnormal spindle speed fluctuation index; S5. monitoring the operation data of the CNC machine tools and generating real-time warning information.

[0014] The present invention has the following beneficial effects:

[0015] (1) This intelligent monitoring system for CNC machine tools acquires the operation data of CNC machine tools by setting up data acquisition modules, precision monitoring modules, and abnormal warning modules, providing a basis for subsequent analysis and ensuring the accuracy and reliability of the monitoring system. The frequency spectrum characteristics of the spindle speed are extracted by Fourier transform, and the frequency domain characteristic model of the spindle speed is constructed to identify the periodic abnormal fluctuation trend of the spindle speed. It can identify potential abnormal patterns, timely discover early signs of equipment failure, and improve the fault warning capability.

[0016] (2) This intelligent monitoring method for CNC machine tools obtains the machining error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, obtains the spindle speed abnormal fluctuation index by analyzing the spindle speed spectrum characteristics, quantifies the machining error and abnormal fluctuation, makes the process control more precise, optimizes the machining quality, and reduces the production defect rate. Based on the machining error index and the spindle speed abnormal fluctuation index, the CNC machine tool is controlled by the fuzzy control algorithm to adjust the cutting speed and feed rate. By intelligently adjusting the cutting parameters, the machining efficiency and stability are improved, the energy consumption is reduced, and the flexibility and adaptability of the production process are improved. The operation data of the CNC machine tool is monitored, and real-time warning information is generated to realize real-time monitoring of the equipment status, which can quickly respond to abnormal situations, reduce downtime, and improve overall production efficiency and safety.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of an intelligent monitoring system for CNC machine tools.

[0019] Figure 2 The present invention is a flow chart of a method for intelligent monitoring of CNC machine tools. DETAILED DESCRIPTION

[0020] The embodiment of the present application solves the problem of machining errors and low efficiency caused by the inability to detect and adjust the operating status of machine tools in real time under traditional monitoring methods through an intelligent monitoring method and system for CNC machine tools.

[0021] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0022] Acquire CNC machine tool operation data through sensors.

[0023] Based on the operation data of CNC machine tools, the frequency spectrum characteristics of spindle speed are extracted by Fourier transform, and the frequency domain characteristic model of spindle speed is constructed to identify the periodic abnormal fluctuation trend of spindle speed.

[0024] The machining error index is obtained by analyzing the periodic abnormal fluctuation trend of the spindle speed, and the abnormal fluctuation index of the spindle speed is obtained by analyzing the spectrum characteristics of the spindle speed.

[0025] Based on the machining error index and the abnormal fluctuation index of spindle speed, the CNC machine tool is controlled to adjust the cutting speed and feed rate through fuzzy control algorithm.

[0026] Monitor the operation data of CNC machine tools and generate real-time warning information.

[0027] Example 1: Please refer to Figure 1The embodiment of the present invention provides a technical solution: an intelligent monitoring system for CNC machine tools, comprising the following modules: a data acquisition module, a precision monitoring module, and an abnormal warning module; the data acquisition module is used to acquire the operation data of the CNC machine tool through a sensor; the precision monitoring module includes a processing state monitoring unit, an error analysis unit, and an error correction unit; the processing state monitoring unit is used to extract the frequency spectrum characteristics of the spindle speed through Fourier transform based on the operation data of the CNC machine tool, construct a frequency domain characteristic model of the spindle speed, and identify the periodic abnormal fluctuation trend of the spindle speed; the error analysis unit is used to acquire the processing error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, and acquire the abnormal fluctuation index of the spindle speed by analyzing the frequency spectrum characteristics of the spindle speed; the error correction unit is used to control the CNC machine tool to adjust the cutting speed and feed rate through a fuzzy control algorithm based on the processing error index and the abnormal fluctuation index of the spindle speed; the abnormal monitoring module is used to monitor the operation data of the CNC machine tool and generate real-time warning information.

[0028] In this implementation scheme, data acquisition module: This module obtains the operation data of the CNC machine tool through sensors, including spindle speed, feed rate, temperature, and vibration parameters. These data are an important basis for subsequent analysis and decision-making. Precision monitoring module: This module consists of three sub-units: Processing state monitoring unit: Based on the acquired operation data, this unit uses Fourier transform (a mathematical transformation used to convert signals from the time domain to the frequency domain) to extract the spectral characteristics of the spindle speed, thereby constructing a frequency domain characteristic model of the spindle speed. Through this model, the periodic abnormal fluctuation trend of the spindle speed can be identified to help monitor the working status of the machine tool. Error analysis unit: This unit analyzes the periodic abnormal fluctuation trend of the spindle speed to obtain the processing error index (an indicator reflecting the processing accuracy), and at the same time, by analyzing the spectral characteristics of the spindle speed, the spindle speed abnormal fluctuation index (an indicator reflecting the stability of the spindle operation) is obtained. These indices help to evaluate the processing quality and operating status of the machine tool. Error correction unit: According to the above-obtained machining error index and spindle speed abnormal fluctuation index, the fuzzy control algorithm (a control method based on fuzzy logic for dealing with uncertainty and ambiguity) is used to adjust the cutting speed and feed rate of the CNC machine tool, thereby improving machining accuracy and efficiency. Abnormal monitoring module: This module is responsible for real-time monitoring of the machine tool's operating data and generating early warning information. When an abnormal situation is detected, the system can issue an alarm in time to help the operator take corresponding measures quickly to avoid potential failures and losses. Fourier transform: A mathematical tool used to convert time domain signals into frequency domain signals to help analyze the frequency components and amplitude of the signal, and is often used in signal processing. Spectral characteristics: Describes the amplitude and phase information of the signal at different frequencies, and is used to analyze the periodicity and stability of the signal to identify potential anomalies. Spindle speed frequency domain characteristic model: A model established based on Fourier transform, which reflects the characteristics of the spindle speed in the frequency domain and is used to identify and analyze abnormal fluctuations. Machining error index: An indicator to measure the machining accuracy of a machine tool, obtained by analyzing the abnormal fluctuation trend of the spindle speed, reflecting the error level in the machining process. Abnormal spindle speed fluctuation index: an indicator that reflects the stability of the spindle speed, indicating whether there is abnormal fluctuation in the spindle speed, which can help determine the operating status of the machine tool. Fuzzy control algorithm: a control strategy based on fuzzy logic, used to deal with uncertainty in the system and adjust machine tool parameters according to fuzzy rules to optimize the processing effect.

[0029] Specifically, based on the CNC machine tool operation data, the specific process of extracting the spindle speed spectrum characteristics through Fourier transform is as follows: based on the CNC machine tool operation data, the spindle speed time series data is extracted, and data preprocessing and segmentation processing are performed; fast Fourier transform is applied to the spindle speed time series data segment, and its frequency components and corresponding amplitudes are calculated and summarized to obtain the spindle speed spectrum characteristics.

[0030] In this implementation scheme, extract the spindle speed time series data: extract the time series data related to the spindle speed from the operation data of the CNC machine tool. These data reflect the changes in the spindle speed at different time points and are the basis for spectrum analysis. Data preprocessing: clean and process the extracted time series data to remove noise and outliers to ensure the accuracy of the data. This step may include smoothing and normalization to make the data suitable for subsequent analysis. Segment processing: divide the processed time series data into several segments for local analysis. Each segment of data will be regarded as an independent signal to identify its frequency components. Apply fast Fourier transform: apply fast Fourier transform to each data segment. This transform converts the time domain signal into a frequency domain signal, revealing the frequency components contained in the signal. Fast Fourier transform FFT is an efficient computing algorithm that can quickly perform Fourier transform and is suitable for processing large-scale data. Calculate frequency components and corresponding amplitudes: After completing the Fourier transform, calculate the amplitude (i.e., the strength of the signal at that frequency) and phase information of each frequency component. This information helps to understand the frequency characteristics of the spindle speed. Summarize and obtain the spindle speed spectrum characteristics: Summarize the frequency components and amplitudes of all data segments to form a complete spindle speed spectrum characteristic. These characteristics can be used for further anomaly detection and analysis to help monitor the operating status of the machine tool. The fast Fourier transform formula is as follows, ;in, : The complex form of the frequency domain signal, : Time domain signal, i.e. time series data of spindle speed, Number of sample points, Represents the complex exponential function, that is, the rotation factor, e: the base of the natural logarithm, j: the imaginary unit, which represents the imaginary part of the complex number, and f: the current frequency index, which represents the frequency we want to analyze in the frequency domain. Frequency component calculation: ;in, No. frequency components, Sampling frequency, The index of the frequency component. The amplitude calculation formula is as follows, ; :frequency The corresponding amplitude, The real part of the frequency domain signal, Imaginary part of the frequency domain signal.

[0031] Specifically, the specific process of constructing the frequency domain characteristic model of the spindle speed is as follows: statistical analysis is performed on the extracted spectrum characteristics of the spindle speed to identify the main frequency components and their amplitudes in the spectrum; the frequency components are associated with the corresponding processing states through curve fitting to construct the frequency domain characteristic model of the spindle speed.

[0032] In this implementation scheme, the extracted spindle speed spectrum features are statistically analyzed: the spectrum features extracted from the CNC machine tool operation data are statistically analyzed. This includes calculating the mean, variance and frequency distribution index of each frequency component in the spectrum to understand the performance of the spindle speed at different frequencies. Identify the main frequency components and their amplitudes in the spectrum: Based on the statistical analysis, identify the most significant frequency components in the spectrum. These frequency components are usually closely related to the normal operating state of the machine tool. The corresponding amplitude represents the strength of the spindle speed at these frequencies, reflecting the stability of the operating state. Associate the frequency components with the corresponding processing states through curve fitting: Use curve fitting technology to associate the identified main frequency components with the specific processing state of the machine tool (such as cutting speed, feed rate). This process reveals the relationship between frequency components and processing states by constructing a mathematical model, which can help understand the performance of the machine tool under different working conditions. Construct a spindle speed frequency domain feature model: Based on the above analysis and fitting results, a spindle speed frequency domain feature model is finally constructed. This model integrates frequency components, amplitudes and processing states, providing a quantitative basis for subsequent fault detection and performance monitoring. The model can be used for real-time monitoring and early warning. By comparing the actual spectrum characteristics with the model, it can be judged whether the machine tool is operating normally.

[0033] Specifically, the specific process of identifying the periodic abnormal fluctuation trend of the spindle speed is as follows: based on the frequency domain characteristic model of the spindle speed, analyze the amplitude and phase changes of each frequency component in the spectrum, set the threshold, identify the frequency components beyond the normal fluctuation range, and mark them as abnormal signals; detect the periodic change pattern of the spindle speed through the time series, identify the periodic characteristics of the abnormal fluctuation of the spindle speed, and generate a report on the periodic abnormal fluctuation trend of the spindle speed.

[0034] In this implementation scheme, based on the frequency domain characteristic model of the spindle speed: the constructed frequency domain characteristic model of the spindle speed is used, which contains information about each frequency component and its amplitude and phase, and is used to analyze the operating status of the spindle speed. Analyze the amplitude and phase changes of each frequency component in the spectrum: conduct in-depth analysis of the extracted spectrum, focusing on the amplitude (indicating signal strength) and phase (indicating signal time offset) of the frequency component. The changes in amplitude and phase can reflect the abnormality of the spindle speed. For example, a sudden increase in the amplitude of the frequency component may indicate a vibration problem. Set thresholds: During the analysis process, reasonable thresholds need to be set. These thresholds are used to distinguish normal fluctuations from abnormal fluctuations. An amplitude range is determined based on historical data statistics. When the amplitude exceeds this range, it is considered abnormal. Identify frequency components that exceed the normal fluctuation range and mark them as abnormal signals: According to the set threshold, identify frequency components that exceed the normal fluctuation range. These components will be marked as abnormal signals, indicating that there may be mechanical failures or processing problems. Detect the periodic change pattern of the spindle speed through time series: Use the time series analysis method to detect the periodic change pattern of the spindle speed. Helps identify regular fluctuations in spindle speed and distinguish between normal operation and abnormal fluctuations. Identify the periodic characteristics of abnormal fluctuations in spindle speed: By analyzing time series data, extract the periodic characteristics of abnormal fluctuations in spindle speed. These characteristics can include the frequency, duration, and amplitude of fluctuations.

[0035] Specifically, by analyzing the periodic abnormal fluctuation trend of the spindle speed, the specific process of obtaining the machining error index is as follows: monitor the periodic abnormal fluctuation trend of the spindle speed, and record the amplitude and fluctuation frequency of the spindle speed; according to the periodic characteristics of the abnormal fluctuation of the spindle speed, compare the amplitude and fluctuation frequency of the spindle speed with the standard machining parameters to obtain the machining error index.

[0036] In this implementation scheme, the trend of abnormal periodic fluctuations in the spindle speed is monitored: by monitoring the spindle speed in real time, its data is collected to identify the pattern of periodic fluctuations and obtain the dynamic characteristics of the spindle. The amplitude and fluctuation frequency of the spindle speed are recorded: the monitored spindle speed signal is analyzed to extract its amplitude (the size of the speed) and fluctuation frequency (the frequency of the fluctuation) to understand the operating status of the spindle. According to the periodic characteristics of abnormal fluctuations in the spindle speed: the fluctuation pattern of the spindle speed is analyzed and the periodic characteristics are identified to quantify the impact of the fluctuation on the processing. The amplitude and fluctuation frequency of the spindle speed are compared with the standard processing parameters: the extracted amplitude and frequency are compared with the preset standard processing parameters to evaluate the deviation of the current processing state. Obtain the processing error index: through the comparison results, the processing error index is calculated to indicate the difference between the processing state and the standard. The calculation formula involved, amplitude calculation: ;

[0037] in, is the amplitude, is the sample value of the time domain signal, is the total number of samples. Fluctuation frequency calculation:

[0038] ;in. is the fluctuation frequency, is the number of sample points in the period, is the cycle time. Processing error index calculation: ;in, is the machining error index, is the target processing parameter, is the actual measured processing parameter.

[0039] Specifically, by analyzing the spindle speed spectrum characteristics, the specific process of obtaining the spindle speed abnormal fluctuation index is as follows: statistical analysis is performed on the extracted spindle speed spectrum characteristics, the amplitude and phase of the spindle speed frequency components are recorded, the frequency components beyond the normal range are identified, and marked as abnormal signals; based on the identified abnormal signals, the spindle speed abnormal fluctuation index is calculated.

[0040] In this implementation scheme, a statistical analysis is performed on the extracted spectral features of the spindle speed: the extracted spectral features, including the amplitude and phase information of the frequency components, are analyzed to understand the frequency domain characteristics of the spindle speed. The amplitude and phase of the spindle speed frequency components are recorded: the amplitude (intensity) and phase (time delay) of each frequency component in the spectrum are recorded to provide data support for subsequent analysis. Frequency components outside the normal range are identified: thresholds are set to identify those frequency components whose amplitude or phase exceeds the normal fluctuation range, and they are marked as abnormal signals for further processing. The spindle speed abnormal fluctuation index is calculated based on the identified abnormal signals: a comprehensive indicator is calculated using the identified abnormal signal data to quantify the degree of abnormal fluctuation of the spindle speed. The calculation formulas involved are as follows: the amplitude and phase formulas are, ;in, It is The amplitude of the frequency component, is the frequency domain signal, is the phase. Anomaly Detection: If or Marked as abnormal signal and are the thresholds of amplitude and phase respectively set, and the calculation formula of abnormal fluctuation index of spindle speed is as follows: ;in, is the spindle speed abnormal fluctuation index, is the number of abnormal signals, It is the amplitude reference under normal conditions.

[0041] Specifically, the specific process of controlling the CNC machine tool to adjust the cutting speed and feed rate through the fuzzy control algorithm is as follows: the machining error index and the spindle speed abnormal fluctuation index are defined as input variables, and they are divided into different fuzzy sets respectively; the cutting speed and feed rate of the CNC machine tool are defined as output variables, and they are divided into fuzzy sets; a fuzzy control rule base is constructed, and fuzzy rules are formulated to describe the influence of the machining error index and the spindle speed abnormal fluctuation index on the cutting speed and feed rate of the CNC machine tool; fuzzy reasoning is performed according to the fuzzy rules to determine the cutting speed and feed rate of the CNC machine tool.

[0042] In this embodiment, the fuzzy control algorithm is used to adjust the cutting speed and feed rate through the machining error index and the spindle speed abnormal fluctuation index. and spindle speed abnormal fluctuation index It is divided into three fuzzy sets: low (L), medium (M), and high (H), which correspond to the slow (S), moderate (N), and fast (F) cutting speed and feed rate respectively. Then, according to the set fuzzy control rules. Fuzzy control rules: Rule 1: If and , then the cutting speed , feed rate , Rule 2: If and , then the cutting speed , feed rate , Rule 3: If and , then the cutting speed , feed rate , Rule 4: If and , then the cutting speed , feed rate , Rule 5: If and , then the cutting speed , feed rate , Rule 6: If and , then the cutting speed , feed rate F, Rule 7: If and , then the cutting speed , feed rate , Rule 8: If and , then the cutting speed , feed rate , Rule 9: If and , then the cutting speed , feed rate = F. Fuzzy set partitioning, each input and output variable can be represented by a triangular or trapezoidal fuzzy set. For example: machining error index, low: 0-30, , high: 40-100; spindle speed abnormal fluctuation index: low: 0-30, medium: 20-50, high: 40-100. Input the current machining error index and spindle speed abnormal fluctuation index, use the fuzzy rule base for reasoning and use the center of gravity method or the maximum membership method to convert the fuzzy output into a specific value. Assume that the fuzzy value obtained is that the membership of the cutting speed fuzzy value of "fast" is 0.8, and the membership of "moderate" is 0.2. The membership of the feed rate fuzzy value of "moderate" is 1.0. Defuzzification calculation is performed based on these memberships to obtain the final cutting speed and feed rate.

[0043] Embodiment 2: A method for intelligent monitoring of CNC machine tools, applied to the intelligent monitoring system of CNC machine tools described in Embodiment 1; comprising the following steps: S1. Acquiring CNC machine tool operation data through sensors; S2. Based on the CNC machine tool operation data, extracting the frequency spectrum characteristics of the spindle speed through Fourier transform, constructing a frequency domain characteristic model of the spindle speed, and identifying the trend of periodic abnormal fluctuations of the spindle speed; S3. Acquiring a machining error index by analyzing the trend of periodic abnormal fluctuations of the spindle speed, and acquiring an abnormal spindle speed fluctuation index by analyzing the frequency spectrum characteristics of the spindle speed; S4. Based on the machining error index and the abnormal spindle speed fluctuation index, controlling the CNC machine tool to adjust the cutting speed and feed rate through a fuzzy control algorithm; S5. Monitoring the operation data of the CNC machine tool and generating real-time warning information.

[0044] In this implementation scheme, Fourier transform is used to analyze the acquired spindle speed data, convert the time domain signal into a frequency domain signal, and extract the spectrum characteristics from it. This process helps to construct a frequency domain characteristic model of the spindle speed and identify its periodic abnormal fluctuation trend, laying the foundation for subsequent analysis. By analyzing the periodic abnormal fluctuation of the spindle speed, the machining error index is calculated to reflect the deviation of the machining accuracy. At the same time, based on the spectrum characteristics of the spindle speed, the abnormal fluctuation index is calculated to quantify the stability of the spindle speed. These two indexes provide a quantitative basis for adjusting the machine tool parameters. Combined with the acquired machining error index and the spindle speed abnormal fluctuation index, real-time adjustment is performed through the fuzzy control algorithm. This process includes defining fuzzy sets of inputs and outputs and formulating control rules to optimize the cutting speed and feed rate, thereby improving the machining quality and efficiency. The operation data of the CNC machine tool is continuously monitored, and once an abnormal trend is detected or the preset warning conditions are reached, real-time warning information is generated immediately. This helps to quickly respond to potential faults, reduce downtime, and ensure the stability of the production process.

[0045] In summary, this application has at least the following effects:

[0046] An intelligent monitoring method and system for CNC machine tools is provided. By setting a data acquisition module, an accuracy monitoring module, and an abnormal warning module, the operation data of the CNC machine tools are acquired, which provides a basis for subsequent analysis and ensures the accuracy and reliability of the monitoring system. The frequency spectrum characteristics of the spindle speed are extracted by Fourier transform, and the frequency domain characteristic model of the spindle speed is constructed to identify the periodic abnormal fluctuation trend of the spindle speed. The potential abnormal mode can be identified, and the early signs of equipment failure can be discovered in time to improve the fault warning capability. The machining error index is obtained by analyzing the periodic abnormal fluctuation trend of the spindle speed. The abnormal fluctuation index of the spindle speed is obtained by analyzing the frequency spectrum characteristics of the spindle speed. The machining error and abnormal fluctuation are quantified, making the process control more accurate, optimizing the machining quality, and reducing the production defect rate. Based on the machining error index and the abnormal fluctuation index of the spindle speed, the CNC machine tool is controlled by the fuzzy control algorithm to adjust the cutting speed and feed rate. By intelligently adjusting the cutting parameters, the machining efficiency and stability are improved, the energy consumption is reduced, and the flexibility and adaptability of the production process are improved. Monitor the operation data of CNC machine tools, generate real-time warning information, and realize real-time monitoring of equipment status, which can quickly respond to abnormal situations, reduce downtime, and improve overall production efficiency and safety.

[0047] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0051] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0052] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent monitoring system for CNC machine tools, characterized in that: It includes the following modules: data acquisition module, accuracy monitoring module, and abnormal warning module; The data acquisition module is used to acquire the operation data of the CNC machine tool through sensors; The precision monitoring module includes a processing state monitoring unit, an error analysis unit, and an error correction unit; The machining state monitoring unit is used to extract the spindle speed spectrum characteristics through Fourier transform based on the CNC machine tool operation data, construct a spindle speed frequency domain characteristic model, and identify the periodic abnormal fluctuation trend of the spindle speed; The error analysis unit is used to obtain a machining error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, and to obtain an abnormal fluctuation index of the spindle speed by analyzing the spectrum characteristics of the spindle speed; The error correction unit is used to control the CNC machine tool to adjust the cutting speed and feed rate through a fuzzy control algorithm based on the machining error index and the spindle speed abnormal fluctuation index; The abnormal warning module is used to monitor the operation data of the CNC machine tool and generate real-time warning information; The specific process of identifying the periodic abnormal fluctuation trend of the spindle speed is as follows: Based on the frequency domain characteristic model of the spindle speed, the amplitude and phase changes of each frequency component in the spectrum are analyzed, and the threshold is set to identify the frequency components that exceed the normal fluctuation range and mark them as abnormal signals; Detect the periodic change pattern of the spindle speed through time series, identify the periodic characteristics of the abnormal fluctuation of the spindle speed, and generate a report on the trend of the periodic abnormal fluctuation of the spindle speed; The specific process of obtaining the machining error index by analyzing the periodic abnormal fluctuation trend of the spindle speed is as follows: Monitor the periodic abnormal fluctuation trend of the spindle speed and record the amplitude and fluctuation frequency of the spindle speed; According to the periodic characteristics of the abnormal fluctuation of the spindle speed, the amplitude and fluctuation frequency of the spindle speed are compared with the standard processing parameters to obtain the processing error index; The specific process of obtaining the spindle speed abnormal fluctuation index by analyzing the spindle speed spectrum characteristics is as follows: Perform statistical analysis on the extracted spindle speed spectrum features, record the amplitude and phase of the spindle speed frequency components, identify the frequency components that exceed the normal range, and mark them as abnormal signals; According to the identified abnormal signal, the abnormal fluctuation index of the spindle speed is calculated; The specific process of controlling the CNC machine tool to adjust the cutting speed and feed rate by using the fuzzy control algorithm is as follows: The machining error index and spindle speed abnormal fluctuation index are defined as input variables and divided into different fuzzy sets respectively. The cutting speed and feed rate of CNC machine tools are defined as output variables and divided into fuzzy sets; Construct a fuzzy control rule base and formulate fuzzy rules to describe the influence of machining error index and spindle speed abnormal fluctuation index on the cutting speed and feed rate of CNC machine tools; Fuzzy reasoning is performed based on fuzzy rules to determine the cutting speed and feed rate of CNC machine tools.

2. The intelligent monitoring system for CNC machine tools according to claim 1, characterized in that: Based on the CNC machine tool operation data, the specific process of extracting the spindle speed spectrum characteristics through Fourier transform is as follows: Based on the CNC machine tool operation data, the spindle speed time series data is extracted, and data preprocessing and segmentation processing are performed; Fast Fourier transform is applied to the spindle speed time series data, and its frequency components and corresponding amplitudes are calculated and summarized to obtain the spindle speed spectrum characteristics.

3. The intelligent monitoring system for CNC machine tools according to claim 2 is characterized in that: The specific process of constructing the frequency domain characteristic model of spindle speed is as follows: Perform statistical analysis on the extracted spindle speed spectrum characteristics to identify the main frequency components and their amplitudes in the spectrum; The frequency components are associated with the corresponding machining states through curve fitting, and the frequency domain characteristic model of the spindle speed is constructed.

4. A method for intelligent monitoring of CNC machine tools, applied to a CNC machine tool intelligent monitoring system according to any one of claims 1 to 3, characterized in that: The following steps are involved: S1. Obtain CNC machine tool operation data through sensors; S2. Based on the operation data of CNC machine tools, the frequency spectrum characteristics of the spindle speed are extracted through Fourier transform, and the frequency domain characteristic model of the spindle speed is constructed to identify the periodic abnormal fluctuation trend of the spindle speed; S3. Obtain the machining error index by analyzing the periodic abnormal fluctuation trend of the spindle speed, and obtain the abnormal fluctuation index of the spindle speed by analyzing the spectrum characteristics of the spindle speed; S4. Based on the machining error index and the spindle speed abnormal fluctuation index, the CNC machine tool is controlled by the fuzzy control algorithm to adjust the cutting speed and feed rate; S5. Monitor the operation data of CNC machine tools and generate real-time warning information.

Images