Intelligent management system for automobile part processing based on Internet of Things

Abstract

The invention discloses an automobile part processing intelligent management system based on Internet of Things, and relates to the technical field of intelligent manufacturing, and the system comprises a voiceprint monitoring module which is configured to collect a high-frequency structure sound signal generated when a cutter makes contact with a workpiece for cutting in the processing process of a numerical control machine tool in real time, the signal is converted into a digital real-time voiceprint data stream; the current monitoring module is configured to collect a multiphase load current signal of a numerical control machine tool spindle servo motor in real time and convert the signal into a digital real-time current data flow; the process association decision module is provided with a processor and a memory, an optimal state feature library corresponding to a specific tool-workpiece combination is preset in the memory, and the optimal state feature library at least comprises standard voiceprint feature vectors and standard current feature parameters; the problem that in existing static machining, efficiency and precision cannot be considered at the same time is solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, specifically to an intelligent management system for automotive parts processing based on the Internet of Things. Background Technology

[0002] The automotive industry is the cornerstone of modern industry, and its core components, such as engine blocks, gearbox gears, and turbine blades, have extremely stringent requirements for machining precision. Currently, CNC machine tools are the mainstream equipment for achieving high-precision machining of such parts. However, in actual production, there is always an inherent and irreconcilable contradiction: the negative correlation between machining precision and production efficiency.

[0003] On the one hand, to achieve submicron-level dimensional tolerances and extremely high surface finishes, factories typically employ a conservative machining strategy: "reducing speed for precision." Operators are forced to reduce machine spindle speed and tool feed rate, increase coolant usage, and shorten tool life for frequent replacements to ensure optimal performance. While this strategy guarantees quality, it significantly sacrifices production cycle time, lengthens the manufacturing cycle of individual products, and drastically increases production costs. On the other hand, to meet the efficiency requirements of mass production, factories seek to maximize machining speed. However, high-speed cutting generates severe vibrations, instantaneous high temperatures between the tool and workpiece, and significant thermal deformation. These physical phenomena directly compromise machining accuracy, leading to a sharp increase in product defect rates, and exacerbating tool wear and equipment deterioration.

[0004] Existing technologies, such as some adaptive machining systems, attempt to adjust parameters by monitoring cutting forces or vibration values. However, their logic often involves passively "reducing speed and minimizing losses" when the detected values ​​exceed limits. This does not fundamentally resolve the contradiction between accuracy and efficiency; it merely seeks a dynamic, but still unsatisfactory, balance between the two. Therefore, the industry urgently needs a disruptive technological solution that can completely break this deadlock and achieve both "speed increase" and "precision improvement." Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent management system for automotive parts processing based on the Internet of Things, so as to solve the problems mentioned in the background art.

[0006] To address the aforementioned technical problems, the present invention provides the following technical solution: an intelligent management system for automotive parts processing based on the Internet of Things, comprising: The voiceprint monitoring module is configured to collect high-frequency structural acoustic signals generated by the cutting tool and the workpiece during the machining process of a CNC machine tool in real time, and convert the signals into a digital real-time voiceprint data stream; The current monitoring module is configured to acquire multi-phase load current signals of the spindle servo motor of CNC machine tools in real time and convert the signals into digital real-time current data streams; The process association decision module is equipped with a processor and a memory. The memory contains a preset optimal state feature library corresponding to a specific tool-workpiece combination. The optimal state feature library includes at least a standard acoustic signature feature vector and a standard current feature parameter. The process association decision module is communicatively connected to the acoustic signature monitoring module and the current monitoring module, respectively, to receive and process the real-time data stream. By quantitatively comparing the data stream with the optimal state feature library, the module calculates in real time a processing state health index that characterizes the degree to which the current processing process deviates from the optimal state. Based on this index, the module generates linked, hierarchical control commands. An execution module, which is communicatively connected to the process-related decision module, is configured to receive and execute the control commands to perform closed-loop adjustment of at least one physical parameter of the processing procedure.

[0007] According to the above technical solution, the execution module includes a dynamic cooling module and a cutting parameter intervention module; and the process association decision module is configured to execute a priority linkage control logic: when the machining state health index is lower than a first preset threshold, the dynamic cooling module is driven to adjust first; when the index continues to be lower than the first threshold or further lower than the second preset threshold, the cutting parameter intervention module is driven to adjust while maintaining control of the dynamic cooling module.

[0008] According to the above technical solution, the voiceprint monitoring module further includes a wideband piezoelectric acoustic sensor, a signal conditioner for filtering and amplifying the signal output by the wideband piezoelectric acoustic sensor, and an analog-to-digital converter with a sampling rate of not less than 100kHz; the process association decision module processes the real-time voiceprint data stream by performing frame segmentation, windowing, and fast Fourier transform on the real-time voiceprint data stream to extract its power spectral density in the key frequency band, thereby forming a real-time voiceprint feature vector.

[0009] According to the above technical solution, the calculation formula for the Process Association Decision Module to calculate the Processing Status Health Index (MHI) is as follows: in, and These are the real-time voiceprint feature vector and the standard voiceprint feature vector, respectively. and These are the real-time current characteristic parameters and the standard current characteristic parameters, respectively. and This is a function used to calculate the normalized distance between features; and These are preset weighting coefficients used to adjust the sensitivity of acoustic and electrical characteristics.

[0010] According to the above technical solution, the method for establishing the optimal state feature library includes: In a pre-defined calibration process, the machining parameters are first adjusted by professionals to a recognized optimal cutting state. Then, the system continues to run in this optimal state for a preset period of time, and simultaneously commands the voiceprint detection module and the current monitoring module to perform full-load data acquisition; Finally, the process association decision module performs statistical analysis and feature extraction on the collected data segment, calculates the standard voiceprint feature vector and standard current feature parameters, binds them with the current processing condition information, and stores them in the storage.

[0011] According to the above technical solution, the operation method of the system includes: Step S1: After processing begins, the real-time acoustic signature signal and real-time load current signal are continuously and synchronously collected during the processing through the acoustic signature detection module and the current monitoring module. Step S2: The process association decision module extracts features from the real-time acoustic signature signal and real-time load current signal collected in step S1, and compares them with the standard features preset in the optimal state feature library to calculate the processing state health index for evaluating the current processing state. Step S3: The process association decision module generates and sends a linkage control command to the execution module for closed-loop adjustment of the processing physical parameters based on the processing status health index calculated in step S2, so as to actively and continuously maintain the current processing status near the optimal state defined by the standard features.

[0012] According to the above technical solution, the specific method for feature extraction of the real-time voiceprint signal in step S2 includes: Step S21: First, the acquired digital audio signal stream is divided into frames, and a Hamming window function is applied to each frame; Step S22: Perform a Fast Fourier Transform on each frame of windowed data to obtain its spectrum; Step S23: Calculate the average power spectral density of the spectrum in multiple preset key frequency bands, and combine the density values ​​into a multi-dimensional real-time voiceprint feature vector.

[0013] According to the above technical solution, the method for generating and sending linkage control commands in step S3 is based on a hierarchical priority decision-making model, specifically including: Step S31: Set at least one status warning threshold. and a state deterioration threshold ,in ; Step S32: When the processing status health index first falls below At that time, a first-level response command is generated and sent, which prioritizes driving the dynamic cooling module in the execution module to slightly increase the pressure or flow rate of the coolant. Step S33: After the Level 1 response command is issued, if the processing status health index fails to recover to the target within the preset response evaluation period... Above, or may fall further to below Then, a secondary response command is generated and sent. Based on the primary response, this command drives the cutting parameter intervention module in the execution module to slightly reduce the spindle speed or tool feed rate.

[0014] According to the above technical solution, the first-level response command includes an increase in the amount of coolant pressure or flow rate. It is based on the current processing status health index (MHI) and the warning threshold. The difference is calculated dynamically, and its calculation expression is: ,in, This is a preset proportional control coefficient; The amount of reduction in spindle speed or tool feed rate in the secondary response command. It is based on the current processing health index (MHI) and the deterioration threshold. The difference is calculated dynamically, and its calculation expression is: ,in This is the preset proportional control coefficient.

[0015] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: By incorporating a voiceprint monitoring module, a current monitoring module, a process correlation decision module, and a dynamic execution module, this invention can collect and deeply analyze high-fidelity voiceprint and current data streams during the machining process in real time. Furthermore, the MHI (Machining Health Index) algorithm transforms the fuzzy and subjective cutting state into precise and objective quantitative indicators. Then, using a hierarchical priority linkage control logic, it prioritizes fine-tuning the cooling state and assists in adjusting cutting parameters, thereby actively and in real-time locking the machining process within a physically optimal thermodynamic sweet spot. This fundamentally breaks the inherent contradiction between machining speed and machining accuracy, enabling high-precision automotive parts to achieve higher dimensional accuracy and surface finish at speeds exceeding conventional limits, while simultaneously significantly extending tool life. Ultimately, it achieves a disruptive effect of standardizing and replicating top expert processes, improving the overall stability and economic benefits of the production line, and demonstrating strong adaptability and high efficiency. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the system framework of the present invention; Figure 2 This is a schematic diagram of the execution module composition of the present invention; Figure 3 This is a schematic diagram of the system operation method of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1-3 The present invention provides a technical solution: an intelligent management system for automotive parts processing based on the Internet of Things, comprising: The voiceprint monitoring module is configured to collect high-frequency structural acoustic signals generated by the cutting tool and workpiece during the machining process of CNC machine tools in real time, and convert the signals into digital real-time voiceprint data streams; The current monitoring module is configured to acquire the multi-phase load current signal of the spindle servo motor of the CNC machine tool in real time and convert the signal into a digital real-time current data stream; The process-related decision-making module is equipped with a processor and a memory. The memory contains a preset optimal state feature library corresponding to a specific tool-workpiece combination. The optimal state feature library includes at least a standard acoustic signature feature vector and a standard current feature parameter. The process-related decision-making module is communicatively connected to the acoustic signature monitoring module and the current monitoring module to receive and process real-time data streams. By quantitatively comparing the data streams with the optimal state feature library, the module calculates in real time the processing state health index, which characterizes the degree to which the current processing process deviates from the optimal state. Based on this index, the module generates linked, hierarchical control commands. The execution module, which communicates with the process-related decision module, is configured to receive and execute control commands to perform closed-loop adjustments on at least one physical parameter of the machining process. Equipped with a soundprint monitoring module, a current monitoring module, a process-related decision module, and a dynamic execution module, it can collect and deeply analyze high-fidelity soundprint and current data streams during the machining process in real time. Furthermore, the MHI (Machining Health Index) algorithm transforms the fuzzy, subjective cutting state into precise, objective quantitative indicators. Then, using a hierarchical priority linkage control logic, it prioritizes fine-tuning the cooling state and assists in adjusting cutting parameters, actively and in real-time locking the machining process within a physically optimal thermodynamic sweet spot. This fundamentally breaks the inherent contradiction between machining speed and machining accuracy, enabling high-precision automotive parts to achieve higher dimensional accuracy and surface finish at speeds exceeding conventional limits, while simultaneously significantly extending tool life. Ultimately, it achieves a disruptive effect of standardizing and replicating top expert processes, improving the overall stability and economic efficiency of the production line, and demonstrating strong adaptability and high efficiency.

[0019] The execution module includes a dynamic cooling module and a cutting parameter intervention module; and the process association decision module is configured to execute a priority linkage control logic: when the machining status health index is lower than the first preset threshold, the dynamic cooling module is driven to adjust first; when the index continues to be lower than the first threshold or further lower than the second preset threshold, the cutting parameter intervention module is driven to adjust while maintaining control of the dynamic cooling module.

[0020] The voiceprint monitoring module further includes a wideband piezoelectric acoustic sensor, a signal conditioner for filtering and amplifying the signal output from the wideband piezoelectric acoustic sensor, and an analog-to-digital converter with a sampling rate of not less than 100kHz. The process association decision module processes the real-time voiceprint data stream by performing frame segmentation, windowing, and fast Fourier transform on the real-time voiceprint data stream to extract its power spectral density in the key frequency band, thereby forming a real-time voiceprint feature vector.

[0021] The formula for calculating the Process Health Index (MHI) in the Process Association Decision Module is as follows: in, and These are the real-time voiceprint feature vector and the standard voiceprint feature vector, respectively. and These are the real-time current characteristic parameters and the standard current characteristic parameters, respectively. and This is a function used to calculate the normalized distance between features; and These are preset weighting coefficients used to adjust the sensitivity of acoustic and electrical characteristics.

[0022] Methods for establishing an optimal state feature database include: In a pre-defined calibration process, the machining parameters are first adjusted by professionals to a recognized optimal cutting state. Then, the system continues to run in this optimal state for a preset period of time, and simultaneously commands the voiceprint detection module and the current monitoring module to perform full-load data acquisition; Finally, the process association decision module performs statistical analysis and feature extraction on the collected data, calculates the standard voiceprint feature vector and standard current feature parameters, and binds them with the current processing condition information before storing them.

[0023] The system's operation methods include: Step S1: After the processing begins, the real-time acoustic signal and real-time load current signal are continuously and synchronously collected during the processing through the acoustic detection module and the current monitoring module. Step S2: The process association decision module extracts features from the real-time acoustic signature signal and real-time load current signal collected in step S1, and compares them with the standard features preset in the optimal state feature library to calculate the processing state health index for evaluating the current processing state. Step S3: Based on the processing status health index calculated in step S2, the process association decision module generates and sends a linkage control command to the execution module for closed-loop adjustment of processing physical parameters, so as to actively and continuously maintain the current processing status near the optimal state defined by the standard features.

[0024] In step S2, the specific methods for feature extraction of the real-time voiceprint signal include: Step S21: First, the acquired digital audio signal stream is divided into frames, and a Hamming window function is applied to each frame; Step S22: Perform a Fast Fourier Transform on each frame of windowed data to obtain its spectrum; Step S23: Calculate the average power spectral density of the spectrum in multiple preset key frequency bands, and combine the density values ​​into a multi-dimensional real-time voiceprint feature vector.

[0025] In step S3, the method for generating and sending linkage control commands is based on a hierarchical priority decision-making model, specifically including: Step S31: Set at least one status warning threshold. and a state deterioration threshold ,in ; Step S32: When the processing health index first falls below... At that time, a first-level response command is generated and sent. This command prioritizes driving the dynamic cooling module in the execution module to slightly increase the pressure or flow rate of the coolant. Step S33: After the Level 1 response command is issued, if the processing status health index fails to recover to the target within the preset response evaluation period... Above, or may fall further to below Then, a secondary response command is generated and sent. Based on the primary response, this command drives the cutting parameter intervention module in the execution module to slightly reduce the spindle speed or tool feed rate.

[0026] In a Level 1 response command, the amount of increase in coolant pressure or flow rate is... It is based on the current processing status health index (MHI) and the warning threshold. The difference is calculated dynamically, and its calculation expression is: ,in, This is a preset proportional control coefficient; In a level 2 response command, the amount of reduction in spindle speed or tool feed rate. It is based on the current processing health index (MHI) and the deterioration threshold. The difference is calculated dynamically, and its calculation expression is: ,in This is a preset proportional control coefficient; The underlying logic of this application lies in firstly, based on a deep understanding of the physical process of cutting, namely, the discovery and definition of a thermodynamic sweet spot that can fundamentally unify machining speed and accuracy as an ideal target; and then, through two easily obtainable shadow indicators, acoustic signature and current, to accurately quantify this optimal state that cannot be directly measured; furthermore, by comparing with the optimal state feature library established under expert guidance, the degree of deviation is calculated in real time using the Machining State Health Index (MHI), and a hierarchical linkage control strategy prioritizing fundamental solutions is adopted. When the state deviates, the dynamic cooling module is driven first to push the process back to the sweet spot at the lowest cost. Only when the effect is not good is a secondary response initiated to fine-tune the cutting speed. Ultimately, a fundamental shift from passively avoiding abnormalities to actively managing the state is achieved, so that the entire machining process can always be locked on the optimal operating path, thereby achieving a breakthrough effect of both speed and quality.

[0027] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0028] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0029] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0030] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. An intelligent management system for automotive parts processing based on the Internet of Things, characterized in that, The system includes: The voiceprint monitoring module is configured to collect high-frequency structural acoustic signals generated by the cutting tool and the workpiece during the machining process of a CNC machine tool in real time, and convert the signals into a digital real-time voiceprint data stream; The current monitoring module is configured to acquire multi-phase load current signals of the spindle servo motor of CNC machine tools in real time and convert the signals into digital real-time current data streams; The process association decision module is equipped with a processor and a memory. The memory contains a preset optimal state feature library corresponding to a specific tool-workpiece combination. The optimal state feature library includes at least a standard acoustic signature feature vector and a standard current feature parameter. The process association decision module is communicatively connected to the acoustic signature monitoring module and the current monitoring module, respectively, to receive and process the real-time data stream. By quantitatively comparing the data stream with the optimal state feature library, the module calculates in real time a processing state health index that characterizes the degree to which the current processing process deviates from the optimal state. Based on this index, the module generates linked, hierarchical control commands. An execution module, which is communicatively connected to the process-related decision module, is configured to receive and execute the control commands to perform closed-loop adjustment of at least one physical parameter of the processing procedure.

2. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 1, characterized in that: The execution module includes a dynamic cooling module and a cutting parameter intervention module; and the process association decision module is configured to execute a priority linkage control logic: when the machining state health index is lower than a first preset threshold, the dynamic cooling module is driven to adjust first; when the index continues to be lower than the first threshold or further lower than the second preset threshold, the cutting parameter intervention module is driven to adjust while maintaining control of the dynamic cooling module.

3. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 1, characterized in that: The voiceprint monitoring module further includes a wideband piezoelectric acoustic sensor, a signal conditioner for filtering and amplifying the signal output by the wideband piezoelectric acoustic sensor, and an analog-to-digital converter with a sampling rate of not less than 100kHz. The process association decision module processes the real-time voiceprint data stream by performing frame segmentation, windowing, and fast Fourier transform on the real-time voiceprint data stream to extract its power spectral density in the key frequency band, thereby forming a real-time voiceprint feature vector.

4. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 1, characterized in that: The formula for calculating the processing status health index (MHI) by the process association decision module is as follows: in, and These are the real-time voiceprint feature vector and the standard voiceprint feature vector, respectively. and These are the real-time current characteristic parameters and the standard current characteristic parameters, respectively. and This is a function used to calculate the normalized distance between features; and These are preset weighting coefficients used to adjust the sensitivity of acoustic and electrical characteristics.

5. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 1, characterized in that: The method for establishing the optimal state feature library includes: In a pre-defined calibration process, the machining parameters are first adjusted by professionals to a recognized optimal cutting state. Then, the system continues to run in this optimal state for a preset period of time, and simultaneously commands the voiceprint detection module and the current monitoring module to perform full-load data acquisition; Finally, the process association decision module performs statistical analysis and feature extraction on the collected data segment, calculates the standard voiceprint feature vector and standard current feature parameters, binds them with the current processing condition information, and stores them in the storage.

6. A smart management system for automotive parts processing based on the Internet of Things as described in any one of claims 1-5, characterized in that: The system's operation methods include: Step S1: After processing begins, the real-time acoustic signature signal and real-time load current signal are continuously and synchronously collected during the processing through the acoustic signature detection module and the current monitoring module. Step S2: The process association decision module extracts features from the real-time acoustic signature signal and real-time load current signal collected in step S1, and compares them with the standard features preset in the optimal state feature library to calculate the processing state health index for evaluating the current processing state. Step S3: The process association decision module generates and sends a linkage control command to the execution module for closed-loop adjustment of the processing physical parameters based on the processing status health index calculated in step S2, so as to actively and continuously maintain the current processing status near the optimal state defined by the standard features.

7. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 6, characterized in that: In step S2, the specific method for feature extraction of the real-time voiceprint signal includes: Step S21: First, the acquired digital audio signal stream is divided into frames, and a Hamming window function is applied to each frame; Step S22: Perform a Fast Fourier Transform on each frame of windowed data to obtain its spectrum; Step S23: Calculate the average power spectral density of the spectrum in multiple preset key frequency bands, and combine the density values ​​into a multi-dimensional real-time voiceprint feature vector.

8. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 6, characterized in that: In step S3, the method for generating and sending linkage control commands is based on a hierarchical priority decision-making model, specifically including: Step S31: Set at least one status warning threshold. and a state deterioration threshold ,in ; Step S32: When the processing status health index first falls below At that time, a first-level response command is generated and sent, which prioritizes driving the dynamic cooling module in the execution module to slightly increase the pressure or flow rate of the coolant. Step S33: After the Level 1 response command is issued, if the processing status health index fails to recover to the target within the preset response evaluation period... Above, or may fall further to below Then, a secondary response command is generated and sent. Based on the primary response, this command drives the cutting parameter intervention module in the execution module to slightly reduce the spindle speed or tool feed rate.

9. The intelligent management system for automotive parts processing based on the Internet of Things according to claim 8, characterized in that: The first-level response command includes an increase in coolant pressure or flow rate. It is based on the current processing status health index (MHI) and the warning threshold. The difference is calculated dynamically, and its calculation expression is: ,in, This is a preset proportional control coefficient; The amount of reduction in spindle speed or tool feed rate in the secondary response command. It is based on the current processing health index (MHI) and the deterioration threshold. The difference is calculated dynamically, and its calculation expression is: ,in This is the preset proportional control coefficient.

Images