An aeronautical field workpiece processing real-time online monitoring method and monitoring system

Abstract

The application relates to an aviation workpiece processing real-time online monitoring method, which comprises the following steps: generating a phased acquisition instruction and sending the same to a multi-type sensor group on a processing device; receiving a real-time signal set from the sensor group, aligning the acquired power, vibration and sound signals according to time points, and generating an integrated feature sequence; performing a matching operation on the integrated feature sequence and a pre-stored workpiece feature template library; when a unique template is matched, outputting a current processing workpiece type and a corresponding standard parameter threshold set; when the matching fails or multiple templates are matched, activating an abnormality detection channel; through the abnormality detection channel, comparing actual operation parameters of the processing device with the standard parameter threshold set in real time, and when the actual operation parameters continuously deviate from the standard parameter threshold set, generating a shutdown or alarm triggering signal and outputting the same to an execution terminal. The application overcomes signal interference, adapts to a mixed processing scene, and comprehensively uses multiple data to quickly find abnormalities.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of workpiece processing monitoring, in particular to an aviation field workpiece processing real-time online monitoring method and a monitoring system. BACKGROUND

[0002] In the field of aviation manufacturing, real-time monitoring of the workpiece processing process is a core link for ensuring the quality of aircraft parts, ensuring the safety of aircraft and improving the efficiency of precision machining. The processing process is easily affected by multiple factors such as thermal deformation, tool wear, process system vibration, etc. The traditional monitoring method mainly relies on sensors (such as power, vibration and sound sensors) to collect processing state signals, and combines data processing technology to realize abnormal detection, workpiece identification or tool wear evaluation.

[0003] A commonly used technical solution in the aviation manufacturing field at present is to analyze the power signal of the spindle motor of the machine tool, compare it in real time by constructing a power curve template library of typical workpieces, identify the workpiece type and monitor the compliance of the processing parameters. However, in the mixed processing scene of multiple varieties and small batches of aviation parts, it is easy to cause identification errors, environmental noise interference will cause inaccurate signal analysis, and workers' private modification of processing parameters may also cause quality problems.

[0004] Therefore, the existing method cannot simultaneously meet the complex needs of high-precision monitoring, strong anti-interference ability and process compliance traceability in the aviation manufacturing scene, and it is urgent to provide a more reliable monitoring method that can overcome signal interference, adapt to mixed processing scenes, and realize accurate state perception and quality risk early warning of the aviation part processing process. SUMMARY

[0005] In order to solve at least one of the above technical problems, the application provides an aviation field workpiece processing real-time online monitoring method and a monitoring system.

[0006] In the first aspect, the application provides an aviation field workpiece processing real-time online monitoring method, which adopts the following technical scheme:

[0007] Generate a phased acquisition instruction and send it to a multi-type sensor group on the processing equipment, the sensor group at least including a power sensor, a vibration sensor and a sound sensor;

[0008] Receive a real-time signal set from the sensor group, align the collected power, vibration and sound signals by time point, and eliminate abnormal values with an amplitude exceeding 150% of a preset threshold, to generate an integrated feature sequence;

[0009] Match the integrated feature sequence with a pre-stored workpiece feature template library;

[0010] When a unique template is matched, the current workpiece type and the corresponding set of standard parameter thresholds are output.

[0011] The standard parameter threshold set is dynamically updated based on the historical median value of parameters from consecutive processing batches.

[0012] When a match fails or multiple templates are matched, the anomaly detection channel is activated, and the audio signal sampling rate is increased to over 10kHz.

[0013] Through the anomaly detection channel, the actual operating parameters of the processing equipment are compared with the standard parameter threshold set in real time. When the actual operating parameters continue to deviate from the standard parameter threshold set, a shutdown or alarm trigger signal is generated and output to the execution terminal.

[0014] By adopting the above technical solutions, a phased and collaborative control process for multi-sensor data acquisition is implemented. This allows power, vibration, and sound signals to form an effective integrated feature sequence even under strong interference, avoiding misidentification of mixed-line workpieces due to signal asynchrony. Simultaneously, the parameter range is automatically refreshed based on the median value of historical parameters from consecutive processing batches, enabling the system to adapt to dynamic conditions such as tool wear and material variations in real time. Compared to traditional manual calibration methods, this eliminates false alarms caused by threshold fixing and improves system stability. Furthermore, when template matching fails or conflicts occur, transient features are captured by increasing the sound signal sampling rate. Simultaneously, real-time comparison of operating parameters with dynamic thresholds is performed, and control commands are immediately output for continuous deviations. This significantly improves the anomaly response speed without relying on complex algorithms. In summary, this achieves the ability to overcome signal interference, adapt to mixed processing scenarios, and quickly detect anomalies by integrating multiple data sources.

[0015] In one possible implementation, the step of generating synchronous acquisition instructions and sending them to a multi-type sensor group on the processing equipment, wherein the sensor group includes at least a power sensor, a vibration sensor, and a sound sensor, specifically includes the following phased acquisition instructions:

[0016] During the preparation phase, the readiness status of each sensor is checked, and the sampling frequency is initialized.

[0017] During the triggering phase, when a workpiece clamping completion signal is received, all sensors are simultaneously activated to collect data.

[0018] During the compensation phase, when any sensor data is lost, compensation data is generated. This compensation data includes...

[0019] When the vibration signal is lost, the vibration waveform can be deduced based on the trend of power signal change;

[0020] When the sound signal is lost, the sound spectrum is reconstructed based on the main frequency components of the vibration signal.

[0021] By adopting the above technical solution, the sensors are initialized during the preparation stage to eliminate start-up delay; during the triggering stage, synchronous acquisition of clamping signals avoids timing misalignment; and during the compensation stage, lost signals are reconstructed to ensure data integrity. The three-level segmented control enables multiple sensors to generate an effective integrated signal sequence even in environments with strong interference, improving the accuracy of identifying mixed-line workpieces.

[0022] Meanwhile, since load changes directly reflect mechanical vibrations, the vibration waveform can be calculated using power change trends. Furthermore, since cutting noise and structural vibrations originate from the same source, the sound spectrum can be reconstructed using the dominant vibration frequency. This compensation mechanism avoids the distortion caused by traditional mean filling, maintains data availability even in the event of sensor failure, and reduces the false negative rate.

[0023] In one possible implementation, the step of receiving a real-time signal set from the sensor group, aligning the collected power, vibration, and sound signals by time points, and removing outliers with amplitudes exceeding a preset threshold of 150%, to generate an integrated feature sequence, specifically includes aligning the collected signals by time points:

[0024] The timing of the vibration and sound signals is adjusted based on the starting time of the power signal.

[0025] The aligned signal is filtered in segments of 10ms to eliminate interference noise generated during equipment start-up and shutdown.

[0026] By adopting the above technical solution, the property of the processing start-up marked by the rise of the power signal is used as a benchmark to correct the transmission delay of vibration / sound signals. At the same time, segmented filtering can eliminate transient noise during start-up and shutdown, retain effective processing features, and prevent environmental noise from masking key features, thereby achieving the effects of improving the signal-to-noise ratio and increasing the template matching fault tolerance.

[0027] In one possible implementation, the step of dynamically updating the standard parameter threshold set based on the median value of historical parameters of consecutive processing batches specifically includes:

[0028] After processing 5 identical workpieces, calculate the median values ​​of power and vibration parameters for the normal processing cycle of that batch.

[0029] Set the new threshold range to a fluctuation range of ±8%-12% of the extracted median value and update it to the template library.

[0030] By adopting the above technical solution, the threshold range is updated every 5 workpieces, thereby automatically adapting to progressive tool wear and material hardness fluctuations. Simultaneously, a fluctuation range of ±8%-12% is set, balancing stability and sensitivity, reducing false alarm rates, and solving the problem of fixed thresholds being unsuitable for changing operating conditions. Compared to traditional manual calibration, the response time can also be shortened to real-time adjustment.

[0031] In one possible implementation, the step of activating the anomaly detection channel and increasing the audio signal sampling rate to above 10kHz when matching fails or multiple templates are matched further includes, after activating the anomaly detection channel:

[0032] It focuses on sound signals in the 200Hz-10kHz frequency band and detects sudden popping sounds in 0.1ms increments.

[0033] If the intensity of the popping sound exceeds 200% of the baseline value three times in a row, the tool is determined to have broken and an emergency stop is executed.

[0034] By adopting the above technical solution, the 200Hz-10kHz frequency band can cover the frequency band of tool fracture characteristics, and the transient signal can be captured by sampling at 0.1ms, avoiding the situation of delayed response to sudden abnormalities. At the same time, under the setting of three consecutive over-threshold judgments, it avoids accidental interference that may cause false triggering and avoids batch scrapping.

[0035] In one possible implementation, the step of comparing the actual operating parameters of the processing equipment with a standard parameter threshold set in real time through an anomaly detection channel, and generating a shutdown or alarm trigger signal and outputting it to the execution terminal when the actual operating parameters continuously deviate from the standard parameter threshold set, further includes the following after generating the shutdown or alarm trigger signal:

[0036] Send an anomaly report to the MES system, including the workpiece type, deviation parameters, and deviation magnitude;

[0037] Save the integrated feature sequence of the abnormal period to local memory.

[0038] By adopting the above technical solution, a structured report containing workpiece type, deviation parameters, and deviation magnitude is sent to the MES system, which supports rapid location of processing defects, avoids the problem of difficulty in tracing the cause of abnormalities, and saves data of abnormal periods locally, providing a chain of evidence for optimizing processing parameters, thereby improving the efficiency of quality analysis.

[0039] One possible implementation also includes tamper-proof monitoring steps:

[0040] Real-time monitoring of processing equipment parameter modification commands;

[0041] If unauthorized parameter modifications are found, immediately freeze the current standard parameter threshold set and initiate manual verification;

[0042] The sound sensor is activated synchronously to collect operator audio in a directional manner, identify abnormal voiceprints, and associate them with tampered event records.

[0043] By adopting the above technical solution, parameter modification commands are monitored in real time. Unauthorized operations are detected and the threshold set is immediately frozen to prevent incorrect judgments. At the same time, voiceprints in the operation area are collected and stored in association with events, forming a closed loop of operation behavior and audio evidence. This improves the detection rate of tampering and solves the problem of difficulty in tracing parameter tampering.

[0044] Secondly, this application provides a real-time online monitoring system for workpiece processing in the aerospace field, comprising:

[0045] Timing control module: Built-in state machine model, configured to control the start and stop times of power, vibration and sound sensors in stages, including sensor initialization, synchronization triggering and data loss compensation units;

[0046] Dynamic data compensation module: Connects multiple sensor data sequences. When missing sensor data is detected, it generates a filling curve based on data from adjacent nodes to fill the gap.

[0047] Adaptive parameter adjustment module: Stores historical processing parameters for continuous processing of the same type of workpiece, dynamically updates the standard parameter threshold set based on the median value ±10%, and outputs parameter offset alarm signals.

[0048] By adopting the above technical solutions, the timing control module achieves hardware-level signal synchronization, the dynamic compensation module ensures data integrity, and the adaptive module optimizes thresholds in a closed loop. The synergy of these three components significantly improves the accuracy of mixed-line identification, enhances anomaly response speed, and increases the anti-tampering detection rate, thereby improving overall performance and solving the problem of the difficulty in synchronously optimizing multi-dimensional defects.

[0049] Thirdly, this application provides an electronic device including a memory and a processor, wherein the memory is used to store computer program code, and the processor is used to execute the computer program code stored in the memory to implement the methods in the first aspect and any one of the first aspects, or in the second aspect and any possible implementation of the second aspect.

[0050] Fourthly, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement the methods described in the first aspect and any one thereof, or the second aspect and any possible implementation thereof. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a real-time online monitoring method for workpiece processing in the aerospace field, provided as an embodiment of this application.

[0052] Figure 2This is a schematic diagram of a real-time online monitoring system for workpiece processing in the aerospace field, provided as an embodiment of this application.

[0053] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0054] The technical solutions in this application will now be described with reference to all the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0055] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Furthermore, in the description of the embodiments of this application, "plural" or "multiple" refers to two or more than two.

[0056] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0057] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one, two, or more than two.

[0058] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "one embodiment," "some embodiments," "another embodiment," "other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0059] This application provides a method for real-time online monitoring of workpiece processing in the aerospace field, executed by an electronic device. This electronic device can be a standalone physical electronic device, a cluster of multiple physical electronic devices, a distributed system, or a cloud electronic device providing cloud computing services. This application does not impose limitations on this method. Figure 1 As shown, the method includes:

[0060] S1. Generate phased acquisition instructions and send them to the multi-type sensor group on the processing equipment.

[0061] Specifically, the sensor array includes at least a power sensor, a vibration sensor, and a sound sensor. The power sensor is installed on the CNC machine tool spindle power supply line to collect real-time current / voltage phase differences. The vibration sensor is fixed to the workpiece fixture via a magnetic base to detect three-axis vibration acceleration. The sound sensor is installed within 30cm of the tool cutting point and equipped with a windproof cover to suppress airflow noise. The sensor array is connected to the monitoring system's main control board via shielded twisted-pair cables, and the main control board has built-in state machine control firmware.

[0062] In some embodiments, to further illustrate how multiple sensors can still generate an effective integrated signal sequence under strong interference conditions and improve the accuracy of mixed-line workpiece identification, the phased acquisition instructions in S1 specifically include:

[0063] S101, Preparation phase: Detect the readiness status of each sensor and initialize the sampling frequency.

[0064] Specifically, the main control board sends initialization commands to each sensor, such as setting the power sampling rate to 1kHz, the vibration sampling rate to 5kHz, and the sound sampling rate to 20kHz; and receives ready signals returned by each sensor, such as voltage > 4.5V as ready.

[0065] S102, Triggering stage: When the workpiece clamping completion signal is received, all sensors are simultaneously activated to collect data.

[0066] Specifically, the pressure sensor installed on the fixture detects the pressure. When the detected pressure value is >10MPa, it sends a clamping completion signal to the main control board. The main control board then simultaneously triggers the three sensors to start the data sequence for data acquisition.

[0067] S103, Compensation Phase: When any sensor data is lost, compensation data is generated.

[0068] Specifically, the compensation data includes calculating the vibration waveform based on the changing trend of the power signal when the vibration signal is lost; and reconstructing the sound spectrum based on the main frequency components of the vibration signal when the sound signal is lost.

[0069] Specifically, the main control board monitors the integrity of data packets in real time with a period of 10ms. If the vibration signal is lost, for example, three consecutive sampling points are zero, the power signal change gradient library is called, such as the load-vibration mapping table pre-stored on the main control board, to generate a simulated vibration waveform. If the sound signal is lost, the fundamental frequency and the third harmonic component of the vibration sensor are extracted to reconstruct the sound spectrum.

[0070] Furthermore, by adopting the aforementioned three-stage segmented control steps—initializing the sensors during the preparation stage to eliminate startup delays, synchronously acquiring clamping signals during the triggering stage to avoid timing misalignments, and reconstructing lost signals during the compensation stage to ensure data integrity—multiple sensors can still generate an effective integrated signal sequence even in environments with strong interference, thereby improving the accuracy of identifying mixed-line workpieces.

[0071] Meanwhile, since load changes directly reflect mechanical vibrations, the vibration waveform can be calculated using power change trends. Furthermore, since cutting noise and structural vibrations originate from the same source, the sound spectrum can be reconstructed using the dominant vibration frequency. This compensation mechanism avoids the distortion caused by traditional mean filling, maintains data availability even in the event of sensor failure, and reduces the false negative rate.

[0072] In this embodiment, the method further includes:

[0073] S2. Receive the real-time signal set from the sensor group, align the collected power, vibration and sound signals according to time points, and remove outliers with amplitudes exceeding a preset threshold of 150%, generating an integrated feature sequence.

[0074] Specifically, the sensor group is connected to a synchronous acquisition card with a built-in temperature-controlled crystal oscillator clock source to ensure a unified time reference. When a rising edge of the power signal is detected, for example, when the current value jumps from 5A to 45A, a time point T0 is generated as the reference for determination.

[0075] Furthermore, based on the rising edge of the power signal, dynamic compensation is applied to the vibration signal and the sound signal. For the vibration signal, a pre-stored cable delay parameter table is called to shift the original signal time axis forward for compensation. For the sound signal, the delay is calculated based on the distance between the microphone and the processing point (in this embodiment, it is calibrated in real time using a laser rangefinder) to shift the sound signal time axis forward for compensation.

[0076] Furthermore, the outlier handling mechanism monitors the peak values ​​of various signals. For example, when the power signal exceeds 150% of the rated value, a threshold locking circuit is triggered; when the vibration signal exceeds the normal peak value, an anomaly marker is activated. Simultaneously, anomaly point replacement is implemented, using copies of previous normal sampling points to fill the gaps.

[0077] In some embodiments, to avoid environmental noise masking key features, the step of aligning the acquired signals by time points in S2 specifically includes:

[0078] S201. Adjust the timing of vibration and sound signals based on the starting time of the power signal.

[0079] Specifically, the power sensor monitors the spindle current in real time. When the current jumps from the static value (≤5A) to the machining threshold (≥45A), a rising edge signal is generated within 0.1ms as the time reference T0. The property of the rising power signal indicating the start of machining is used as a reference to correct the transmission delay of vibration / sound signals.

[0080] Furthermore, based on the pre-stored cable delay parameter table, the time axis of the original vibration signal is shifted forward for compensation; based on the microphone-processing point distance measured in real time by the laser rangefinder, the delay is calculated and shifted forward for compensation according to the speed of sound 340m / s.

[0081] S202. The aligned signal is filtered in segments of 10ms to eliminate interference noise generated during equipment start-up and shutdown.

[0082] Specifically, the aligned signal is processed within a 10ms window (corresponding to 2-3 spindle revolutions) and input to an adjustable analog filter array. During the start-up and stop phase (typically T0±30ms), a strong attenuation mode is activated, reducing the cutoff frequency to 300Hz to eliminate impact noise; during the steady-state phase, it switches to a standard bandpass filter (200Hz-5kHz) to preserve the processing characteristic frequency band.

[0083] Furthermore, for background noise monitoring, low-frequency interference in the 20-200Hz range is analyzed in real time. When the ambient noise is >85dB, the power sampling rate is increased to 2kHz to enhance the signal-to-noise ratio. When high-frequency impact vibration (>5kHz) is detected, the vibration sensor automatically switches to protection mode.

[0084] In summary, segmented filtering can eliminate start-stop transient noise, retain effective processing features, and prevent environmental noise from masking key features, thereby improving the signal-to-noise ratio and template matching fault tolerance.

[0085] In this embodiment, the method further includes:

[0086] S3. Perform a matching operation between the integrated feature sequence and the pre-stored workpiece feature template library.

[0087] Specifically, standard workpiece feature templates are pre-stored in the main control board of the monitoring system. Each template includes power waveform feature code, vibration spectrum envelope and acoustic fingerprint, and new templates are generated by receiving process parameters issued by the MES system.

[0088] Furthermore, the main control board performs anti-aliasing processing on the integrated feature sequence, dividing it into standard feature vectors of 10ms / segment, and simultaneously calculates the similarity between the current feature vector and each template. Specifically, the power feature vector is compared with the current rise slope and steady-state fluctuation mode; the vibration feature vector is matched with the dominant frequency distribution.

[0089] S4. When a unique template is matched, output the current workpiece type and the corresponding set of standard parameter thresholds.

[0090] Specifically, when the current feature vector has a similarity of more than 95% with a single template, the workpiece type code is output and the threshold set of associated parameters is retrieved.

[0091] S5. Dynamically update the standard parameter threshold set based on the median value of historical parameters of continuous processing batches.

[0092] Specifically, the main control board sets a circular buffer to store the processing parameters of the most recent 20 workpieces. After removing outliers, it extracts the median value of power / vibration parameters by sorting and automatically selects a floating coefficient (such as ±8% for new tools and ±12% for old tools) based on the tool wear condition to determine the new threshold.

[0093] Furthermore, the main control board's preset update area receives new thresholds (such as power [42-52A]) and covers the work area when the 5th workpiece is completed, thus completing the dynamic update.

[0094] In some embodiments, to address the problem that fixed thresholds are not adaptable to changes in operating conditions, the step of dynamically updating the standard parameter threshold set in S5 specifically includes:

[0095] S501. After processing 5 workpieces of the same type, calculate the median values ​​of power and vibration parameters for the normal processing cycle of that batch.

[0096] Specifically, the main control board internally stores the raw power / vibration data (sampling rate 1kHz) of the five most recent workpieces of the same type, and automatically removes two abnormal values ​​in advance: transient pulses with power > 150% of the rated value and non-processing frequency components in the vibration signal > 8kHz.

[0097] Furthermore, after receiving the processing completion signal, the main control board triggers the freezing of the data in the storage area and removes the first and last 10% of the start and stop periods, thereby retaining the parameters within the normal processing cycle.

[0098] Furthermore, the parameters of the main control board during normal processing cycles are sorted in parallel. Among them, the power parameters are sorted synchronously for 128 channels, using a 5-point dataset and taking the 3rd value as the median value; the vibration parameters are sorted independently for each channel to eliminate interference between channels.

[0099] S502. Set the new threshold range to a fluctuation range of ±8%-12% of the extracted median value and update it to the template library.

[0100] Specifically, for the new tool stage, a narrow floating range of ±8% is adopted, for example, the median power value is 40A, and the corresponding range [36.8A, 43.2A] is generated; for the tool in the wear warning stage, a wide floating range of ±12% is automatically switched.

[0101] Furthermore, the main control board is designed with dual storage areas. The working area provides the current threshold for real-time monitoring, while the update area receives newly calculated thresholds. When the fifth workpiece is completed, the original threshold is overwritten within 1ms.

[0102] In summary, by updating the threshold range every 5 workpieces, the system automatically adapts to progressive tool wear and material hardness fluctuations. Simultaneously, a fluctuation range of ±8%-12% is set, balancing stability and sensitivity, reducing false alarm rates, and resolving the issue of fixed thresholds being unsuitable for changing operating conditions. Compared to traditional manual calibration, the response time can also be shortened to real-time adjustment.

[0103] In this embodiment, the method further includes:

[0104] S6. When matching fails or multiple templates are matched, activate the anomaly detection channel and increase the audio signal sampling rate to above 10kHz.

[0105] Specifically, when the main control board detects a "matching failure" or "multi-template conflict" status bit, it generates an activation signal to the sound sensor control board and switches to the high-speed processing channel to improve the sampling rate. The sensor power supply is increased from 5V to 12V to support the current required for a high sampling rate.

[0106] In some embodiments, to avoid delays in responding to sudden anomalies, after activating the anomaly detection channel in step S6, the following steps are also included:

[0107] S601 focuses on sound signals in the 200Hz-10kHz frequency band and detects sudden popping sounds in 0.1ms increments.

[0108] Specifically, in this embodiment, when a sudden anomaly is predicted to be tool breakage, the main control board activates the hardware bandpass filter of the sound sensor, forcing the passband to 200Hz-10kHz to cover the characteristic frequency band of tool breakage. Simultaneously, a 0.1ms time window trigger signal is generated to perform segmented sampling.

[0109] S602. If the intensity of the popping sound exceeds 200% of the baseline value three times in a row, the tool is determined to have broken and an emergency stop is executed.

[0110] Specifically, the current sound pressure peak value is compared with the baseline by 200% in real time. The preset shift register in the main control board records the state of three consecutive blast sound intensity exceeding the threshold. When the register status bit shows that the blast sound intensity exceeds the baseline value by 200% for three consecutive times, it is determined that the tool has broken and the main control board issues a stop command.

[0111] In summary, the 200Hz-10kHz frequency band can cover the frequency band of tool fracture characteristics, and the 0.1ms sampling captures transient signals, avoiding the situation of delayed response to sudden abnormalities. At the same time, with the setting of three consecutive over-threshold judgments, it avoids accidental interference that may cause false triggering and avoids batch scrapping.

[0112] In this embodiment, the method further includes:

[0113] S7. Through the anomaly detection channel, the actual operating parameters of the processing equipment are compared with the standard parameter threshold set in real time. When the actual operating parameters continue to deviate from the standard parameter threshold set, a shutdown or alarm trigger signal is generated and output to the execution terminal.

[0114] Specifically, the real-time comparison of the anomaly detection channel is achieved in the following way: the main control board presets a signal acquisition layer and a comparator array. In the signal acquisition layer, the power signal is converted into a 4-20mA standard signal in real time by the sensor, the vibration signal is output as ±10V voltage through the conditioning circuit, and all signals are connected to the high-speed ADC module with a sampling rate of 50kHz.

[0115] The hardware comparator array is divided into three channels: Channel 1 compares the actual power with the upper limit of the threshold 52A in real time; Channel 2 monitors whether the vibration RMS value exceeds the threshold of 8m / s² for 5 consecutive seconds; and Channel 3 is for the transient peak detection of the sound signal, which is the same as the plosive sound determination in this embodiment, and will not be described in detail.

[0116] Furthermore, when the actual operating parameter exceeds the limit by a preset timer, a 0.5-second countdown is started. If the limit is exceeded three times in a row, the actual operating parameter is marked as continuously deviating from the standard parameter threshold set.

[0117] Specifically, the response method of the anomaly detection channel is as follows: when in the early warning state, the three-color light is activated to flash yellow slowly; when it continues to deviate, an alarm is triggered, at which point the light switches to flashing red quickly and a level three alarm code is sent to the MES.

[0118] Furthermore, the main control board is directly connected to the emergency stop circuit of the CNC system via hardwire, and the spindle drive power is synchronously cut off through a relay matrix.

[0119] In some embodiments, to avoid difficulties in tracing the cause of anomalies, after generating a shutdown or alarm trigger signal in step S7, the following steps are also included:

[0120] S701. Send an anomaly report to the MES system, including the workpiece type, deviation parameters, and deviation magnitude.

[0121] Specifically, when the abnormal detection channel generates a shutdown / alarm signal, the main control board immediately latches the current workpiece type code (such as G1270), deviation parameters (power / vibration / sound), and over-limit amplitude (such as vibration +35%).

[0122] Furthermore, the raw power / vibration / sound signals are captured at a 10kHz sampling rate, and data for 5 seconds before and 2 seconds after an abnormal trigger is saved, enabling simultaneous and rapid reading of multiple signals.

[0123] Furthermore, the main control board's circular storage area retains the 50 most recent abnormal records, while using an industrial camera to capture the processing status at the moment of abnormality, and binding the images with the data stream for storage to achieve the association of physical evidence.

[0124] S702. Save the integrated feature sequence of the abnormal period to local memory.

[0125] In summary, sending structured reports containing workpiece type, deviation parameters, and deviation magnitude to the MES system enables rapid location of processing defects, avoids difficulties in tracing the causes of anomalies, and simultaneously saves data from abnormal periods locally, providing a chain of evidence for optimizing processing parameters and improving the efficiency of quality analysis.

[0126] In some embodiments, the method further includes a tamper-proof monitoring step:

[0127] S8, Real-time monitoring and modification instructions for processing equipment parameters.

[0128] Specifically, a command sniffing module is deployed on the main control board to intercept the modification commands of feed rate (F value) / spindle speed (S value) in real time.

[0129] S9. If unauthorized parameter modifications are found, immediately freeze the current standard parameter threshold set and initiate manual verification.

[0130] Specifically, the main control board has a pre-stored database of authorized processing parameters, which is a whitelist. The hardware comparator compares the modified values ​​with the whitelist in real time. When the deviation is greater than 5% and there is no process authorization code, it is marked as an unauthorized operation.

[0131] Furthermore, the main control board immediately switches the storage area, transferring the current dynamic threshold set to the read-only area, while activating the alarm light and sending an SMS to the process engineer for manual verification.

[0132] S10. Synchronously activate the sound sensor to collect operator audio in a directional manner, identify abnormal voiceprints, and associate them with tampered event records.

[0133] Specifically, the directional microphone array is activated to focus the operation station, extract the fundamental frequency and harmonic energy distribution, and generate a voiceprint fingerprint code.

[0134] Furthermore, voiceprint and fingerprint codes, altered timestamps, and screenshots of the user interface are bound and stored on an encrypted SD card. Simultaneously, an industrial camera is used to capture images of employee badges.

[0135] In summary, by monitoring parameter modification commands in real time, the threshold set is immediately frozen upon detecting unauthorized operations to prevent erroneous judgments. At the same time, voiceprints from the operation area are collected and stored in association with events, forming a closed loop of operation behavior and audio evidence. This improves the detection rate of tampering and solves the problem of difficulty in tracing parameter tampering.

[0136] Based on this, a phased, collaborative control process using multiple sensors enables power, vibration, and sound signals to form an effective integrated feature sequence even in environments with strong interference, avoiding misidentification of mixed-line workpieces due to signal asynchrony. Simultaneously, the parameter range is automatically refreshed based on the median value of historical parameters from consecutive processing batches, allowing the system to adapt in real-time to dynamic conditions such as tool wear and material variations. Compared to traditional manual calibration schemes, this eliminates false alarms caused by fixed thresholds, improving system stability. Furthermore, when template matching fails or conflicts occur, transient features are captured by increasing the sound signal sampling rate. Simultaneously, real-time comparison of operating parameters with dynamic thresholds immediately outputs control commands for continuous deviations, significantly improving anomaly response speed without relying on complex algorithms. In summary, this approach overcomes signal interference, adapts to mixed processing scenarios, and rapidly detects anomalies by integrating multiple data sources.

[0137] The following describes the real-time online monitoring system for workpiece processing in the aerospace field provided in the embodiments of this application. The real-time online monitoring system for workpiece processing in the aerospace field described below can be referred to in correspondence with the real-time online monitoring method for workpiece processing in the aerospace field described above.

[0138] refer to Figure 2 Real-time online monitoring systems for workpiece processing in the aerospace field include:

[0139] The timing control module 1 has a built-in state machine model and is configured to control the start and stop times of the power, vibration and sound sensors in stages, including sensor initialization, synchronization triggering and data loss compensation units.

[0140] Specifically, during the initialization phase, the main control board sends configuration commands to the sensors: a sampling rate of 1kHz for the power sensor, 5kHz for the vibration sensor, and 20kHz for the sound sensor. During the synchronization trigger phase, when the clamp pressure sensor detects a signal >10MPa, it sends synchronization pulses to all sensors to trigger data acquisition. During the compensation phase, a data packet integrity counter is used; if three consecutive sampling points are missing, the compensation logic is triggered.

[0141] Dynamic data compensation module 2 connects to a multi-sensor data sequence. When missing sensor data is detected, a filling curve is generated based on the data of adjacent nodes to fill the gap.

[0142] Specifically, power compensation for vibration uses the power gradient change rate to drive a lookup table to output the corresponding vibration amplitude; vibration compensation for sound uses the vibration main frequency to be sent to the audio synthesizer after passing through a programmable bandpass filter.

[0143] The adaptive parameter adjustment module 3 stores historical processing parameters for continuous processing of the same type of workpiece, dynamically updates the standard parameter threshold set based on the median value ±10%, and outputs a parameter offset alarm signal.

[0144] Specifically, the circular buffer retains the data of the most recent 20 workpieces (power / vibration effective values), and the sorting engine is used to extract the median value. At the same time, a new threshold is calculated as median value ± (median value × K). The value of K is switched according to the tool wear status, 8% for new tools and 12% for old tools.

[0145] In summary, the timing control module achieves hardware-level signal synchronization, the dynamic compensation module ensures data integrity, and the adaptive module optimizes thresholds in a closed loop. The synergy of these three modules significantly improves the accuracy of mixed-line identification, enhances anomaly response speed, and increases the tamper-proof detection rate, thereby improving overall performance and solving the problem of simultaneously optimizing multi-dimensional defects.

[0146] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0147] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in connection with the embodiments of this application. Processor 301 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0148] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0149] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0150] The memory 303 is used to store application code that executes the scheme of the embodiments of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0151] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments described in this application.

[0152] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned method for real-time online monitoring of workpiece processing in the aerospace field.

[0153] Since the embodiments of the computer-readable storage medium portion correspond to the embodiments of the method portion, please refer to the description of the embodiments of the method portion for the embodiments of the computer-readable storage medium portion.

[0154] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0155] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for real-time online monitoring of workpiece machining in the aerospace field, characterized in that, include: A multi-type sensor group is generated and sent to the processing equipment in stages to acquire data. The sensor group includes at least a power sensor, a vibration sensor, and a sound sensor. It receives a real-time signal set from the sensor group, aligns the collected power, vibration and sound signals by time point, removes outliers with amplitudes exceeding a preset threshold of 150%, and generates an integrated feature sequence. The integrated feature sequence is matched with a pre-stored workpiece feature template library; When a unique template is matched, the current workpiece type and the corresponding set of standard parameter thresholds are output. The standard parameter threshold set is dynamically updated based on the historical median value of parameters from consecutive processing batches. When a match fails or multiple templates are matched, the anomaly detection channel is activated, and the audio signal sampling rate is increased to over 10kHz. Through the anomaly detection channel, the actual operating parameters of the processing equipment are compared with the standard parameter threshold set in real time. When the actual operating parameters continue to deviate from the standard parameter threshold set, a shutdown or alarm trigger signal is generated and output to the execution terminal.

2. The method according to claim 1, characterized in that, In the step of generating phased acquisition instructions and sending them to a multi-type sensor group on the processing equipment, wherein the sensor group includes at least a power sensor, a vibration sensor, and a sound sensor, the phased acquisition instructions specifically include: During the preparation phase, the readiness status of each sensor is checked, and the sampling frequency is initialized. During the triggering phase, when a workpiece clamping completion signal is received, all sensors are simultaneously activated to collect data. During the compensation phase, when any sensor data is lost, compensation data is generated. This compensation data includes... When the vibration signal is lost, the vibration waveform can be deduced based on the trend of power signal change; When the sound signal is lost, the sound spectrum is reconstructed based on the main frequency components of the vibration signal.

3. The method according to claim 1, characterized in that, The step of receiving real-time signal sets from the sensor group, aligning the collected power, vibration, and sound signals by time points, and removing outliers with amplitudes exceeding a preset threshold of 150%, to generate an integrated feature sequence, specifically includes aligning the collected signals by time points: The timing of the vibration and sound signals is adjusted based on the starting time of the power signal. The aligned signal is filtered in segments of 10ms to eliminate interference noise generated during equipment start-up and shutdown.

4. The method according to claim 1, characterized in that, The step of dynamically updating the standard parameter threshold set based on the median value of historical parameters of continuous processing batches specifically includes: After processing 5 identical workpieces, calculate the median values ​​of power and vibration parameters for the normal processing cycle of that batch. Set the new threshold range to a fluctuation range of ±8%-12% of the extracted median value and update it to the template library.

5. The method according to claim 1, characterized in that, In the step of activating the anomaly detection channel and increasing the audio signal sampling rate to above 10kHz when matching fails or multiple templates are matched, the following further steps are included after activating the anomaly detection channel: It focuses on sound signals in the 200Hz-10kHz frequency band and detects sudden popping sounds in 0.1ms increments. If the intensity of the popping sound exceeds 200% of the baseline value three times in a row, the tool is determined to have broken and an emergency stop is executed.

6. The method according to claim 1, characterized in that, The step of comparing the actual operating parameters of the processing equipment with the standard parameter threshold set in real time through the anomaly detection channel, and generating a shutdown or alarm trigger signal and outputting it to the execution terminal when the actual operating parameters continuously deviate from the standard parameter threshold set, further includes the following steps after generating the shutdown or alarm trigger signal: Send an anomaly report to the MES system, including the workpiece type, deviation parameters, and deviation magnitude; Save the integrated feature sequence of the abnormal period to local memory.

7. The method according to claim 1, characterized in that, It also includes anti-tampering monitoring steps: Real-time monitoring of processing equipment parameter modification commands; If unauthorized parameter modifications are found, immediately freeze the current standard parameter threshold set and initiate manual verification; The sound sensor is activated synchronously to collect operator audio in a directional manner, identify abnormal voiceprints, and associate them with tampered event records.

8. An electronic device, characterized in that, include: One or more processors; One or more memory units; And one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, the one or more computer programs including instructions that, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The storage medium stores a program or instructions that, when executed, implement the method as described in any one of claims 1 to 7.

Images