Wooden door production line digital twin modeling and real-time simulation method and system

Abstract

The invention provides a digital twin modeling and real-time simulation method and system for a wooden door production line, and relates to the technical field of industrial intelligent manufacturing and predictive maintenance. And vibration source positioning is realized by using the phase change of backscattered light of the single-mode optical fiber. By dynamically adjusting the acquisition frequency of the sensor and matching the running state of the equipment, vibration signals are correlated across the equipment, and the cascade interaction characteristics of the production line are identified. And finally, equipment health state description is generated based on multi-source sensing data, digital twin bodies are input for performance degradation simulation, prediction of residual life and fault modes is realized, multi-equipment vibration cooperative monitoring and health state accurate simulation of the wooden door production line can be realized, and the accuracy of fault prediction and life evaluation is remarkably improved.

Description

Technical Field

[0001] This application relates to the fields of industrial intelligent manufacturing and predictive maintenance technology, and in particular to a digital twin modeling and real-time simulation method and system for a wooden door production line. Background Technology

[0002] Currently, wooden door production lines are developing towards intelligent and unmanned operation. The continuous and stable operation of key equipment (such as CNC milling machines and sanders) is crucial to ensuring production efficiency and product quality. To achieve predictive maintenance and avoid unplanned downtime, there is an urgent need for a technology that can accurately sense the health status of equipment in real time and perform advanced simulation and prediction of its remaining lifespan and failure risks.

[0003] In existing technologies, a targeted approach involves using piezoelectric accelerometers installed at specific points on critical equipment (such as spindle bearing housings) for vibration monitoring. This is combined with operating parameters (such as spindle speed) read from the equipment's CNC system to construct a digital twin model of the single device. By comparing real-time vibration data with preset fault thresholds or physical degradation models within the twin model, the health status of the equipment can be assessed and fault warnings can be provided.

[0004] However, this existing solution has significant drawbacks: First, point sensors have limited monitoring range, making it difficult to comprehensively capture the overall state information of the equipment, especially complex vibration sources, which can easily lead to false alarms or missed alarms. Second, this solution focuses on isolated analysis of single equipment and fails to consider the interactive effects of vibration coupling and transmission between multiple devices operating in a cascaded manner on a production line, resulting in insufficient accuracy of its state assessment in real production environments. Finally, the updating and simulation of its digital twin model often rely on preset fixed parameters, making it difficult to dynamically adjust the monitoring strategy and model accuracy according to the real-time operating conditions of the equipment (such as drastic changes in feed rate), leading to lagging or inaccurate prediction results. Summary of the Invention

[0005] The purpose of this application is to provide a digital twin modeling and real-time simulation method, system, electronic device and storage medium for wooden door production lines, so as to solve the problem of limited monitoring range caused by the use of point sensors in the prior art.

[0006] To address the aforementioned technical problems, in a first aspect, this application provides a method for digital twin modeling and real-time simulation of a wooden door production line, comprising: Broadband vibration and sound wave signals generated during the operation of key equipment in the wooden door production line are collected to form multi-source sensor data, and the working parameters of the key equipment, including spindle speed and feed rate, are synchronously associated. By demodulating the phase change of the backscattered light in the single-mode optical fiber laid on the base of the key equipment, the entire single-mode optical fiber is transformed into a continuously distributed vibration sensing array, and the vibration source of the key equipment is located and the vibration signal is acquired based on the multi-source sensing data. Adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters to ensure that the acquired vibration signal matches the equipment operating status. By performing cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters, the interactive characteristics of the interaction between equipment in the cascaded operation state of the production line can be identified. Based on the multi-source sensor data, the associated operating parameters, and the interaction features, state description data representing the health status and fault modes of the equipment is automatically generated through data calculation. At the same time, the state description data is input into the equipment model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential fault modes of the key equipment.

[0007] Optionally, based on the multi-source sensor data, the correlated operating parameters, and the interaction features, status description data representing the health status and fault modes of the device is automatically generated through data calculation, including: Vibration signal data and sound wave signal data are separated and extracted from multi-source sensor data, and the amplitude variation characteristics and frequency distribution characteristics of the vibration signal data and the spectral characteristics of the sound wave signal data are extracted respectively. The extracted amplitude variation features, frequency distribution features, and spectrum features are combined with the associated operating parameters to form a device operation status dataset; The state dataset and the interaction features are merged to obtain the corresponding comprehensive operational features. The feature analysis unit performs calculations on the comprehensive operating features to generate health status data reflecting the health level of the equipment, and generates fault mode data representing the types of faults that the equipment may fail. The health status data and the fault mode data are combined to generate the final status description data.

[0008] Optionally, the state description data is simultaneously input into the device model of the digital twin, and a physical-law-based performance degradation simulation is run to determine the remaining useful life and potential failure modes of the critical equipment, including: Input the device's health status data and fault mode data codes from the status description data into the corresponding parameters of the device model in the digital twin; Based on the mechanical properties of equipment materials, the wear patterns of moving parts, and the fatigue characteristics of structural components, performance degradation calculation rules are established. In the environment of the digital twin, the device model is driven to run according to the actual working parameters, while the performance degradation calculation rules are applied to simulate the gradual change in device performance; By monitoring the changing trends of key performance parameters during the simulation process, the remaining useful life of the equipment is calculated as the operating time required for the equipment to reach the predetermined failure threshold. Record abnormal states and performance mutations that occur during the simulation process, and identify them as potential failure modes and their corresponding occurrence conditions; By integrating parameters from all simulation processes, the remaining useful life and potential failure modes of the critical equipment are ultimately determined.

[0009] Optionally, broadband vibration and acoustic signals generated during the operation of key equipment in the wooden door production line are collected to form multi-source sensor data, and the operating parameters of the key equipment, including spindle speed and feed rate, are synchronously correlated, including: Vibration sensing units are installed on key equipment to capture vibration signals and sound sensing units are installed to capture sound wave signals, the vibration signals and the sound wave signals covering a wide frequency range; The spindle speed and feed rate parameters are obtained in real time from the control system of the key equipment. A high-precision time synchronization device is used to mark the vibration signal, the acoustic signal, the spindle speed parameter, and the feed rate parameter with the same time stamp. The vibration signal data, the acoustic signal data, the spindle speed parameter and the feed rate parameter under the same time mark are combined into a multi-source sensing data unit; The continuously collected multi-source sensor data units are organized into a complete set of multi-source sensor data in chronological order.

[0010] Optionally, by demodulating the phase change of the backscattered light in the single-mode fiber laid on the base of the key equipment, the entire single-mode fiber is converted into a continuously distributed vibration sensing array, and the vibration source of the key equipment is located and the vibration signal is acquired based on the multi-source sensing data, including: Single-mode optical fiber is laid along the base surface of the key equipment to ensure close contact between the optical fiber and the base surface. At the same time, a light pulse signal of a specific wavelength is sent to one end of the single-mode optical fiber, and the light signal returned from the single-mode optical fiber is received. The phase change of the optical signal relative to the transmitted optical signal is detected, and the vibration point and vibration intensity of the optical fiber are determined based on the magnitude and position of the phase change. By analyzing the differences in phase change between adjacent fiber segments and combining the device operating parameters in the multi-source sensing data, the specific coordinates of the vibration source on the base of the key device are calculated. Based on the time-series characteristics of the phase change, the frequency components and amplitude characteristics of the vibration signal are extracted.

[0011] Optionally, adjusting the signal acquisition frequency and spatial resolution of the distributed sensors according to the operating parameters to match the acquired vibration signals with the equipment operating status includes: Real-time monitoring of spindle speed and feed rate parameters in the operating parameters; Based on the spindle speed parameters, a sampling frequency adjustment rule is established to adjust the signal sampling frequency of the distributed sensors so that the sampling frequency increases with the increase of the spindle speed parameters. Based on the feed rate parameter, establish a spatial resolution adjustment rule, adjust the spatial resolution of the distributed sensor, and make the spatial resolution adapt to the change of the feed rate parameter. By continuously monitoring the degree of matching between the adjusted vibration signal characteristics and the equipment operating status, the parameter settings of the adjustment rules can be further optimized.

[0012] Optionally, vibration signals from different key equipment are correlated with the operating parameters across equipment to identify the interactive characteristics of equipment interactions under cascaded operation of the production line, including: Collect vibration data and operating parameter data of various key equipment in the production line, and establish a multi-equipment dataset under a unified time reference. Establish a time correspondence between the vibration data of adjacent devices and analyze the propagation timing characteristics of vibration signals between devices; The operating parameters of each device are correlated with vibration characteristics to identify the correspondence between the intensity of the vibration signal and the operating status of the device. By analyzing the transmission path and intensity changes of the vibration signal between devices, the interaction characteristics of the mechanical connection state between devices are determined. Based on the response delay and attenuation of the vibration signal among different devices, the dynamic coupling characteristics between devices in the cascaded operation state of the production line are identified.

[0013] Secondly, this application provides a digital twin modeling and real-time simulation system for a wooden door production line, including: The acquisition module is used to collect broadband vibration and sound wave signals generated by the key equipment of the wooden door production line during operation, form multi-source sensor data, and synchronously associate the working parameters of the key equipment, including spindle speed and feed rate. The acquisition module is used to convert the entire single-mode fiber into a continuously distributed vibration sensing array by demodulating the phase change of the backscattered light in the single-mode fiber laid on the base of the key equipment, and to realize the location of the vibration source and acquisition of vibration signal of the key equipment based on the multi-source sensing data. The acquisition module is also used to adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters, so that the acquired vibration signal matches the equipment operating status. The analysis module is used to perform cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters to identify the interaction characteristics between equipment in the cascaded operation state of the production line. The calculation module is used to automatically generate state description data representing the health status and failure modes of the equipment based on the multi-source sensor data, the associated working parameters, and the interaction features. At the same time, the state description data is input into the equipment model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential failure modes of the key equipment.

[0014] Thirdly, this application provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of a digital twin modeling and real-time simulation method for a wooden door production line as described in the first aspect above.

[0015] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the digital twin modeling and real-time simulation method for a wooden door production line as described in the first aspect above.

[0016] This application provides a digital twin modeling and real-time simulation method for a wooden door production line. By collecting multi-source sensor data from key equipment and synchronously associating it with their operating parameters, a comprehensive sensing foundation reflecting the equipment's operating status can be constructed. By utilizing the phase change of backscattered light from single-mode optical fibers to achieve distributed vibration sensing, vibration sources can be accurately located and complete vibration signals can be acquired. By dynamically adjusting the sensor acquisition strategy based on operating parameters, the data acquisition can be ensured to accurately match the real-time operating status of the equipment. By cross-equipment correlation analysis of vibration signals and operating parameters, the interaction characteristics of equipment in cascaded operation of the production line can be identified. Finally, based on multi-source data, operating parameters, and interaction characteristics, state description data is generated and digital twin simulation is driven, enabling accurate prediction of the remaining lifespan and failure modes of the equipment.

[0017] Furthermore, by separating vibration and acoustic signal data and extracting their multi-dimensional features, these features are combined with operating parameters to form a state dataset. This dataset is then fused with interactive features to form comprehensive operational features. After processing by the feature analysis unit, health status and fault mode data are generated and combined to form the final state description data. Through deep fusion and intelligent feature extraction of multi-source heterogeneous data, a comprehensive and accurate quantitative description of equipment status is generated, providing highly reliable data input for subsequent digital twin simulation and significantly improving the accuracy and interpretability of health status assessment and fault mode identification. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a digital twin modeling and real-time simulation method for a wooden door production line, provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a digital twin modeling and real-time simulation system for a wooden door production line, provided in an embodiment of this application. Detailed Implementation

[0020] In the field of intelligent manufacturing of wooden doors, existing equipment monitoring solutions based on point sensors have fundamental limitations: their limited sensing range makes it difficult to capture the overall vibration status of the equipment, resulting in blind spots in health assessment; at the same time, this solution analyzes a single piece of equipment in isolation, ignoring the coupling effect of vibration transmission and superposition between multiple pieces of equipment operating in tandem on the entire production line, causing the condition diagnosis to be inaccurate under real working conditions; in addition, its model based on fixed parameters cannot adapt to the real-time changes in the operating load of the equipment (such as feed rate fluctuations), causing a mismatch between the monitoring strategy and the operating status, ultimately leading to delayed or false alarms in predictive maintenance warnings.

[0021] To address the aforementioned shortcomings, this application proposes a digital twin modeling method for wooden door production lines based on distributed optical fiber sensing and data fusion. Its core lies in: transforming single-mode optical fibers laid on the equipment base into a continuously distributed vibration sensor array, achieving full-domain, high-precision capture and vibration source localization of broadband vibration signals from key equipment; ensuring real-time matching of data acquisition and operational status by synchronously associating equipment operating parameters and dynamically adjusting sensing strategies; furthermore, accurately identifying the inter-equipment interaction characteristics in cascaded production line operation for the first time through cross-equipment correlation analysis of vibration signals and operating parameters. Finally, all multi-source data are fused and calculated to drive the digital twin for high-performance degradation simulation. This solution fundamentally solves the problems of blind spots in point-based sensing, neglect of equipment coupling in isolated analysis, and rigidity in fixed-parameter models, achieving deep fusion perception and accurate prediction of the health status of the entire production line, significantly improving the accuracy and reliability of predictive maintenance.

[0022] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The core of this application is to provide a digital twin modeling and real-time simulation method for a wooden door production line, and a flowchart of one specific implementation is shown below. Figure 1 As shown, the method includes: S101. Collect broadband vibration and sound wave signals generated during the operation of key equipment in the wooden door production line, form multi-source sensor data, and synchronously associate the working parameters of the key equipment, including spindle speed and feed rate. Optionally, step S101 may specifically include the following steps: S1011. Install a vibration sensing unit on key equipment to capture vibration signals and a sound sensing unit to capture sound wave signals, wherein the vibration signals and the sound wave signals cover a wide frequency range. S1012. Obtain spindle speed parameters and feed rate parameters in real time from the control system of the key equipment; S1013. A high-precision time synchronization device is used to mark the vibration signal, the acoustic signal, the spindle speed parameter and the feed rate parameter with the same time mark. S1014. Combine the data of the vibration signal, the data of the acoustic signal, the spindle speed parameter and the feed rate parameter under the same time mark into a multi-source sensing data unit; S1015. Organize the continuously acquired multi-source sensor data units into a complete set corresponding to the multi-source sensor data according to the time sequence.

[0024] In the above scheme, a vibration sensing unit refers to a sensor device installed on key equipment to capture mechanical vibration signals, capable of detecting physical vibrations generated during equipment operation. A sound sensing unit refers to a microphone or acoustic sensor used to capture sound wave signals generated during equipment operation, capable of recording sound within the audible frequency range. Wide frequency range refers to the signal's coverage spectrum extending from low to high frequencies, such as from tens of hertz to kilohertz. Spindle speed parameter refers to the speed at which the equipment spindle rotates, usually measured in revolutions per minute. Feed rate parameter refers to the speed at which material is pushed or moved during processing. A high-precision time synchronization device refers to a device capable of providing a unified time reference for different data sources, such as a GPS clock or a precision time protocol synchronizer. A timestamp refers to the timestamp information added to data points to identify the exact moment the data was generated. A multi-source sensor data unit refers to a data package containing vibration, sound wave signals, and operating parameters, combined under the same timestamp. A multi-source sensor data set refers to a series of multi-source sensor data units organized in chronological order, forming a complete time-series dataset.

[0025] In this embodiment, firstly, vibration sensors and acoustic sensors are installed at key locations on critical equipment via S1011. These sensors capture broadband vibration and sound signals generated during equipment operation. For example, an accelerometer and a directional microphone are installed near the spindle of a wood door machining center to collect mechanical vibration signals and sound signals generated during processing, respectively. Secondly, in S1012, working parameters are read in real time from the CNC system or PLC controller of the critical equipment. For example, parameters such as the current spindle speed of 3000 revolutions per minute and the feed rate of 500 millimeters per minute are obtained from the CNC controller via the OPC UA protocol. Then, in S1013, a high-precision time synchronization device, such as a synchronization system based on the IEEE 1588 precision time protocol, is used to assign a unified and identical time stamp to all collected signals and parameters, ensuring that all data sources have the same time reference benchmark, for example, synchronizing all data to microsecond-level accuracy. Next, in step S1014, the vibration signal data, acoustic signal data, spindle speed, and feed rate parameters collected at the same time are combined into a complete multi-source data unit. For example, vibration waveform data, acoustic spectrum data, and corresponding operating parameter values ​​within a 10-millisecond time window are packaged into a data packet, forming a multi-source sensing data unit. Finally, in step S1015, these data units are organized into a complete time-series dataset according to time order. For example, continuously acquired data packets are sorted by timestamps to form a multi-source sensing data set that can be used for subsequent analysis.

[0026] In practical applications, in the processing workshop of Factory A, a wooden door manufacturer, a piezoelectric accelerometer is installed on CNC milling machine B as a vibration sensing unit and a condenser microphone as a sound sensing unit to collect vibration and sound signals during the processing. Simultaneously, the spindle speed setpoint of 2400 rpm and the feed rate setpoint of 400 mm / min are read in real time from the Siemens CNC system of machine B via industrial Ethernet. A time synchronization device based on the PTP protocol provides a unified time reference for all data sources, adding microsecond-accurate time stamps to each batch of data. The vibration waveform data, sound spectrum data, and corresponding operating parameter values ​​collected within every 100-millisecond time window are combined into a multi-source data unit. Finally, these data units are arranged in chronological order to form a complete multi-source sensor dataset for subsequent equipment status monitoring and analysis.

[0027] This solution achieves multi-dimensional data capture of equipment operating status through multi-sensor collaborative acquisition and synchronous acquisition of equipment parameters, combined with high-precision time synchronization technology. It ensures the spatiotemporal consistency between vibration, acoustic signals and operating parameters, providing a high-quality, synchronized multi-source sensor data foundation for subsequent analysis and modeling, and effectively improving the integrity and accuracy of data acquisition.

[0028] S102. By demodulating the phase change of the backscattered light in the single-mode optical fiber laid on the base of the key equipment, the entire single-mode optical fiber is transformed into a continuously distributed vibration sensing array, and the vibration source of the key equipment is located and the vibration signal is acquired based on the multi-source sensing data. Optionally, step S102 may specifically include the following steps: S1021. Lay single-mode optical fiber along the base surface of the key equipment to ensure close contact between the optical fiber and the base surface. At the same time, send a light pulse signal of a specific wavelength to one end of the single-mode optical fiber and receive the light signal returned from the single-mode optical fiber. S1022. Detect the phase change of the optical signal relative to the transmitted optical signal, and determine the vibration point and vibration intensity of the optical fiber based on the magnitude and position of the phase change. S1023. By analyzing the difference in phase change between adjacent fiber segments and combining the device operating parameters in the multi-source sensing data, calculate the specific coordinates of the vibration source on the base of the key device. S1024. Based on the time series characteristics of the phase change, extract the frequency components and amplitude characteristics of the vibration signal.

[0029] In the above scheme, single-mode fiber refers to optical fiber that allows only a single mode of light transmission, characterized by a small core diameter and high transmission bandwidth. Backscattered light refers to the optical signal reflected back due to Rayleigh scattering during light transmission in the optical fiber. Phase change refers to the change in the phase angle of the light wave, caused by mechanical vibration or deformation of the optical fiber. Optical pulse signal refers to a laser pulse with a certain wavelength and duration, used to detect the state of the optical fiber. Vibration sensing array refers to using the entire optical fiber as a distributed sensor network, capable of continuously monitoring vibration along the line. Vibration point refers to the specific location on the optical fiber where mechanical vibration occurs. Vibration intensity refers to the quantitative representation of vibration energy. Phase change refers to the phase difference between the backscattered light and the original optical signal. Adjacent fiber segments refer to continuous segments on the optical fiber that are spatially close. Time series characteristics refer to the pattern characteristics of phase change over time. Frequency components refer to the composition of each frequency component in the vibration signal. Amplitude characteristics refer to the magnitude characteristics of the vibration signal amplitude.

[0030] In this embodiment, firstly, in S1021, single-mode optical fiber is tightly laid on the base surface of the key equipment to ensure close contact between the fiber and the base surface. Simultaneously, a specific wavelength optical pulse is injected into the fiber, and the returned backscattered light signal is received. For example, a 1550 nm wavelength laser pulse is injected into the optical fiber laid on the base of equipment B through an optical fiber coupler, and a photodetector receives the returned light signal. Secondly, in S1022, phase-sensitive optical time-domain reflectometry is used to detect the phase change of the backscattered light relative to the transmitted optical signal. Based on the magnitude and location of the phase change, the vibration point and vibration intensity are determined. For example, a demodulation algorithm detects a significant phase change at a location on the base, indicating the presence of a vibration source with a moderate vibration intensity. Then, in S1023, the time difference positioning principle is used to analyze the phase change differences between adjacent fiber segments. Combined with the equipment's operating parameters, the precise coordinates of the vibration source are calculated. For example, based on the time difference of the phase change reaching different fiber segments, combined with the spindle speed of 2400 rpm, the vibration source is calculated to be located at coordinates X = 2.3 meters and Y = 1.1 meters on the base. Finally, the phase change was analyzed by S1024 to extract the spectral characteristics and amplitude characteristics of the vibration signal. For example, the main frequency components of the vibration signal were found to be concentrated in the range of 100-500 Hz by fast Fourier transform, and the amplitude showed periodic variation characteristics.

[0031] In practical application, on the base surface of equipment B in the wooden door production line of factory A, single-mode optical fiber manufactured by company C was laid along the length of the equipment. A model D distributed optical fiber sensor demodulator was used to send 1550 nm light pulses into the optical fiber and receive backscattered signals. When the equipment was running, a significant phase change was detected in a section of the optical fiber in the middle of the base, with a phase change amount of 0.5 radians. By analyzing the phase change time difference of adjacent 1-meter optical fiber segments, which was found to be 0.2 milliseconds, and combining this with the current spindle speed of 2400 rpm, the precise location of the vibration source was calculated to be 5.2 meters from the beginning of the optical fiber. Spectral analysis of the phase change time series at this location revealed two main vibration frequencies: 350 Hz and 480 Hz, with amplitudes of 0.3 V and 0.2 V, respectively.

[0032] This solution converts single-mode optical fiber into a distributed vibration sensing array, enabling precise localization of equipment vibration sources and detailed extraction of vibration characteristics. It provides high spatial resolution vibration monitoring capabilities, accurately identifies the vibration status of various parts of the equipment base, and provides a rich foundation of vibration information for equipment condition analysis and fault diagnosis.

[0033] S103. Adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters to ensure that the acquired vibration signal matches the equipment operating status. Optionally, step S103 may specifically include the following steps: S1031. Real-time monitoring of spindle speed and feed rate parameters in the working parameters; S1032. Establish a sampling frequency adjustment rule based on the spindle speed parameter, and adjust the signal sampling frequency of the distributed sensor so that the sampling frequency increases with the increase of the spindle speed parameter; S1033. Establish spatial resolution adjustment rules based on the feed rate parameters, and adjust the spatial resolution of the distributed sensor so that the spatial resolution adapts to the changes in the feed rate parameters. S1034. By continuously monitoring the degree of matching between the adjusted vibration signal characteristics and the equipment operating status, the parameter settings of the adjustment rules are further optimized.

[0034] In the above scheme, operating parameters refer to the key operational parameters of the equipment during operation, including control variables such as spindle speed and feed rate. Spindle speed parameter refers to the angular velocity of the equipment spindle rotation, usually expressed in revolutions per minute (rpm). Feed rate parameter refers to the linear velocity of the workpiece or tool movement during machining. Distributed sensors refer to sensing systems based on single-mode optical fibers, capable of continuously monitoring vibration signals along the fiber path. Signal acquisition frequency refers to the rate at which the sensor system acquires data, measured in Hertz (Hz). Spatial resolution refers to the minimum distance at which the sensor system can distinguish adjacent vibration sources. Acquisition frequency adjustment rules refer to the mathematical relationship for dynamically adjusting the acquisition frequency based on changes in spindle speed. Spatial resolution adjustment rules refer to the mathematical relationship for adjusting spatial resolution based on changes in feed rate. Matching degree refers to the level of consistency between the characteristics of the acquired vibration signal and the actual operating state of the equipment.

[0035] In this embodiment, firstly, the spindle speed and feed rate parameters in the equipment control system are monitored in real time via S1031. For example, the spindle speed value of 2400 rpm and the feed rate value of 400 mm / min are continuously read from the CNC system of equipment B. Secondly, in S1032, a sampling frequency adjustment rule is established based on the spindle speed parameters. A linear relationship model is used to increase the sampling frequency as the speed increases. For example, when the spindle speed is 2400 rpm, the sampling frequency of the distributed sensor is adjusted from the default 1000 Hz to 2400 Hz to ensure that high-frequency vibration components related to the speed can be captured. Then, in S1033, a spatial resolution adjustment rule is established based on the feed rate parameters. An inverse proportional relationship model is used to increase the spatial resolution as the feed rate increases. For example, when the feed rate is 400 mm / min, the spatial resolution is adjusted from the default 1 meter to 0.5 meters to adapt to the more precise vibration positioning requirements during rapid feed. Finally, by monitoring the characteristics of the adjusted vibration signal, such as the vibration frequency distribution and amplitude characteristics, and their consistency with the equipment operating status through S1034, the parameter settings of the adjustment rules are further optimized using a feedback control algorithm. For example, based on the actual monitoring results, the acquisition frequency adjustment coefficient is optimized from 1.0 to 1.2, so that the signal acquisition is more in line with the equipment operating status.

[0036] In practical application, during the operation of equipment B on the wooden door production line of Factory A, real-time monitoring showed that the spindle speed increased from 2000 rpm to 3000 rpm, and the feed rate increased from 300 mm / min to 450 mm / min. According to preset adjustment rules, the sampling frequency of the distributed sensors correspondingly increased from 2000 Hz to 3000 Hz, and the spatial resolution increased from 0.67 m to 0.44 m. The system continuously monitored the adjusted vibration signal and found that when the spindle speed was 3000 rpm, the collected vibration signal clearly showed the fundamental frequency of 150 Hz and its harmonic components, perfectly matching the theoretically calculated spindle rotation frequency. Through a feedback optimization mechanism, the system gradually optimized the sampling frequency adjustment coefficient from the initial value of 1.0 to 1.1, allowing the signal acquisition to better adapt to the high-speed operation of the equipment.

[0037] This solution establishes dynamic adjustment rules for operating parameters and sensor acquisition parameters, enabling the signal acquisition system to adaptively match the equipment's operating status. This ensures that high-quality, highly matched vibration signal data can be obtained under different operating conditions, improving the accuracy and effectiveness of vibration monitoring and providing a reliable data foundation for subsequent analysis and diagnosis.

[0038] S104. Perform cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters to identify the interaction characteristics between equipment in the cascaded operation state of the production line; Optionally, step S104 may specifically include the following steps: S1041. Collect vibration data and operating parameter data of each key equipment in the production line, and establish a multi-equipment dataset under a unified time reference. S1042. Establish a time correspondence between the vibration data of adjacent devices and analyze the propagation timing characteristics of vibration signals between devices; S1043. Correlate the operating parameters of each device with vibration characteristics to identify the correspondence between the intensity of the vibration signal and the operating state of the device; S1044. By analyzing the transmission path and intensity change of the vibration signal between the devices, the interaction characteristics of the mechanical connection state between the devices are determined; S1045. Based on the response delay and attenuation of the vibration signal between different devices, identify the dynamic coupling characteristics between devices in the cascaded operation state of the production line.

[0039] In the above scheme, cross-device correlation analysis refers to the joint analysis of vibration signals and operating parameters of different devices in the production line to discover the mutual influence relationships between devices. A unified time reference means that all device data uses the same time reference system to ensure timestamp consistency. A multi-device dataset refers to an integrated dataset containing vibration data and operating parameters from multiple devices. Time correspondence refers to the alignment and matching relationship of vibration signals from different devices on the time axis. Propagation timing characteristics refer to the time delay and waveform change characteristics of vibration signals transmitted from one device to another. Mechanical connection status refers to the connection status between devices formed by physical connectors (such as conveyor belts and couplings). Interaction characteristics refer to the vibration transmission and energy exchange patterns generated between devices through mechanical connections. Response delay refers to the time difference required for a vibration signal to propagate from the source device to the target device. Attenuation degree refers to the energy reduction of the vibration signal during propagation between devices. Dynamic coupling characteristics refer to the mutual vibration influence characteristics between devices due to mechanical connections.

[0040] In this embodiment, firstly, vibration data and operating parameters of key equipment in the production line are collected via S1041. A unified time synchronization system is used to ensure that all data have a consistent time reference. For example, in the wooden door production line of Factory A, the vibration signals and operating parameters of equipment B (CNC milling machine) and equipment C (sanding machine) are integrated into the same time coordinate system to form a multi-equipment dataset. Secondly, via S1042, a time correspondence is established for the vibration data of adjacent equipment. A cross-correlation algorithm is used to analyze the propagation timing characteristics of vibration signals between equipment. For example, it is found that the vibration signal of equipment B appears in the vibration data of equipment C after 0.5 milliseconds. Then, via S1043, the operating parameters and vibration characteristics of each equipment are correlated and analyzed. A regression analysis method is used to identify the correspondence between vibration signal intensity and equipment operating status. For example, when the spindle speed of equipment B increases to 3000 revolutions per minute, the vibration intensity of equipment C increases accordingly. Next, via S1044, the transmission path and intensity changes of vibration signals between equipment are analyzed. A transmission path analysis method is used to determine the interaction characteristics of the mechanical connection state between equipment. For example, it is found that vibration is mainly transmitted between equipment B and equipment C through the base connector. Finally, based on the response delay and attenuation of vibration signals between different devices, the S1045 system identification method is used to identify the dynamic coupling characteristics between devices in the cascaded operation state of the production line. For example, the vibration transfer function from device B to device C is calculated, showing obvious second-order system characteristics.

[0041] In practical applications, vibration data and operating parameters of the CNC milling machine (Equipment B) and the sanding machine (Equipment C) were collected in the wooden door production line of Factory A. A unified time synchronization system ensured data consistency. Analysis revealed significant vibration at a spindle speed of 2800 revolutions per minute (rpm) on Equipment B. This vibration was transmitted to Equipment C after a 0.6-millisecond delay, with the amplitude decreasing from 0.8 volts to 0.3 volts. Correlation analysis showed that as the feed rate of Equipment B increased, the vibration frequency distribution of Equipment C changed significantly, introducing new harmonic components. Transmission path analysis indicated that vibration was primarily transmitted between the two machines via the concrete base and connecting bolts. Dynamic coupling analysis revealed strong coupled vibration modes between the two machines in the 80-120 Hz frequency range.

[0042] This solution effectively identifies the interaction relationships and dynamic coupling characteristics between equipment in the production line through cross-equipment correlation analysis, reveals the propagation law and influence mechanism of vibration signals between equipment, provides an important basis for understanding the overall operating status of the production line, and helps to discover potential inter-equipment interference problems and optimize the coordinated operation of the production line.

[0043] S105. Based on the multi-source sensor data, the associated operating parameters, and the interaction features, state description data representing the health status and fault modes of the equipment is automatically generated through data calculation. At the same time, the state description data is input into the equipment model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential fault modes of the key equipment.

[0044] Optionally, step S105 may specifically include the following steps: S1051. Separate and extract vibration signal data and acoustic signal data from multi-source sensor data, and extract the amplitude variation characteristics and frequency distribution characteristics of the vibration signal data and the spectral characteristics of the acoustic signal data, respectively. S1052. The extracted amplitude variation features, frequency distribution features, and spectrum features are combined with the associated operating parameters to form a device operation status dataset. S1053. Merge the state dataset with the interaction features to obtain the corresponding comprehensive operation features; S1054. The feature analysis unit performs calculations on the comprehensive operating features to generate health status data reflecting the health level of the equipment, and generates fault mode data representing the types of faults that the equipment may fail. S1055. Combine the health status data and the fault mode data to generate the final status description data.

[0045] S1056. Input the health status data and fault mode data codes of the device in the status description data into the corresponding parameters of the device model of the digital twin; S1057. Based on the mechanical properties of equipment materials, the wear patterns of moving parts, and the fatigue characteristics of structural components, establish performance degradation calculation rules; S1058. In the environment of the digital twin, the device model is driven to run according to the actual working parameters, and the performance degradation calculation rules are applied to simulate the gradual change of device performance. S1059. By monitoring the changing trends of key performance parameters during the simulation process, the remaining useful life is calculated as the operating time required for the equipment to reach the predetermined failure threshold. S10510 Record abnormal states and performance mutation points that occur during the simulation process, and identify them as potential fault modes and corresponding occurrence conditions. S10511. Integrate the parameters of all simulation processes to finally determine the remaining useful life and potential failure modes of the critical equipment.

[0046] In the above scheme, condition description data refers to structured data generated through multi-source data fusion analysis, which comprehensively reflects the health status and potential failure types of equipment. Health status data is a numerical indicator that quantifies the overall health of the equipment, ranging from perfectly healthy to severely degraded. Failure mode data refers to information on the types of failures that the equipment may experience and their probabilities. A digital twin equipment model is a virtual replica of the physical equipment, capable of simulating the actual equipment's operating behavior and performance changes. Performance degradation calculation rules are mathematical models based on materials science and mechanical principles, describing the gradual decline in equipment performance over time. Mechanical properties refer to the deformation and failure characteristics of materials under stress, including parameters such as elastic modulus and yield strength. Wear patterns refer to the regular patterns of material loss in moving parts under friction. Fatigue characteristics refer to the characteristics of structural components developing cracks and failing under cyclic loading. Failure threshold refers to the critical value at which equipment performance degrades to an unacceptable level. Remaining useful life refers to the expected time for the equipment to continue operating normally from its current state until it reaches the failure threshold. Potential failure modes refer to the types of failures that the equipment may experience and the conditions under which they occur.

[0047] In this embodiment, firstly, vibration signal data and acoustic signal data are separated from multi-source sensor data in step S1051. The amplitude variation characteristics and frequency distribution characteristics of the vibration signal data, and the spectral characteristic parameters of the acoustic signal data are extracted respectively. For example, the amplitude envelope characteristics and frequency spectrum characteristics of the vibration signal, and the spectral peak characteristics of the acoustic signal are extracted from the monitoring data of device B. Secondly, in step S1052, the extracted spectral characteristic parameters are combined with the associated operating parameters to form a state dataset containing vibration characteristics, acoustic characteristics, and operating parameters. For example, a vibration amplitude of 0.8 volts, a main frequency of 350 Hz, an acoustic spectral peak of 1200 Hz, and a spindle speed of 2800 revolutions per minute are combined into a single data sample. Then, in step S1053, the state dataset and the interaction characteristics between devices are merged to obtain comprehensive operating characteristics, such as adding the vibration transfer function characteristics from device B to device C. Next, in S1054, the feature analysis unit calculates the comprehensive operating characteristics to generate health status data and fault mode data. For example, a health assessment algorithm calculates a health index of 0.85 and identifies two potential fault modes: bearing wear and spindle imbalance. Then, in S1055, these data are combined into the final state description data. In S1056, the health status data and fault mode data codes are input into the corresponding parameters of the equipment model in the digital twin; for example, the health index of 0.85 is assigned as a health status parameter in the model. Next, in S1057, performance degradation calculation rules are established based on the mechanical properties, wear patterns, and fatigue characteristics of the equipment materials, such as establishing a bearing wear model. ,in, Indicates the amount of wear. The wear coefficient is... For rotational speed, The simulation process begins with S1058, where the model is driven to run within the digital twin environment according to actual operating parameters. Simultaneously, performance degradation calculation rules are applied to simulate equipment performance changes; for example, running the virtual model at 2800 rpm calculates the gradual increase in bearing wear. Next, S1059 monitors the changing trends of key performance parameters during the simulation and calculates the remaining useful life. For instance, when the bearing clearance reaches the failure threshold of 0.2 mm, the remaining useful life is calculated to be 180 days. Subsequently, S10510 records abnormal states and performance mutation points that occur during the simulation, identifying potential failure modes and their occurrence conditions. For example, resonance is identified when the rotational speed exceeds 3000 rpm. Finally, S10511 integrates all simulation parameters to ultimately determine the remaining useful life and potential failure modes of the key equipment.

[0048] In practical applications, within the digital twin system of the wooden door production line at Factory A, vibration amplitude characteristics (0.75 volts), frequency characteristics (320 Hz), and acoustic spectrum characteristics (1100 Hz) were extracted from multi-source sensor data of equipment B. Combined with the operating parameter of a spindle speed of 2600 rpm, a health status index of 0.82 was generated. After inputting this data into the digital twin model, the performance degradation process under 2600 rpm operating conditions was simulated based on the fatigue characteristics and wear patterns of bearing steel. The system monitored a gradual increase in the spindle bearing clearance from an initial 0.1 mm. When the clearance reached the failure threshold of 0.25 mm, the remaining service life was calculated to be 210 days. Simultaneously, it identified a risk of bearing overheating when the speed exceeded 2800 rpm and a risk of lubrication failure when continuous operation exceeded 8 hours. These potential failure modes and their occurrence conditions were recorded as important references for equipment maintenance.

[0049] This solution combines multi-source monitoring data with digital twin technology to achieve accurate assessment of equipment health status and scientific prediction of remaining life. It can identify potential failure modes and their occurrence conditions in advance, provide decision support for preventive maintenance, effectively avoid sudden failures, and improve equipment reliability and production efficiency.

[0050] The digital twin modeling and real-time simulation method for a wooden door production line provided in this application achieves synchronized and integrated acquisition of multi-dimensional data on equipment operating status through step S101, establishing a high-quality multi-source sensor data foundation; through step S102, single-mode optical fiber is converted into a distributed vibration sensor array, enabling precise positioning of equipment vibration sources and refined extraction of vibration characteristics; through step S103, a dynamic adjustment mechanism for sensor acquisition parameters and equipment operating parameters is established to ensure optimal matching between vibration signal acquisition and equipment operating status; through step S104, cross-equipment correlation analysis is completed, revealing the interaction laws and dynamic coupling characteristics between equipment under cascaded operation of the production line; through step S105, equipment health status assessment based on multi-source data fusion and performance degradation simulation driven by digital twin are realized, ultimately generating equipment remaining useful life prediction and potential failure mode identification results, providing a scientific basis for predictive maintenance of equipment.

[0051] Figure 2 This is a schematic diagram illustrating a specific implementation of a digital twin modeling and real-time simulation system for a wooden door production line, as provided in this application. (Refer to...) Figure 2 The system may include: The acquisition module 21 is used to acquire broadband vibration and sound wave signals generated during the operation of key equipment in the wooden door production line, form multi-source sensor data, and synchronously associate the working parameters of the key equipment, including spindle speed and feed rate. The acquisition module 22 is used to convert the entire single-mode fiber into a continuously distributed vibration sensing array by demodulating the phase change of the backscattered light in the single-mode fiber laid on the base of the key equipment, and to realize the location of the vibration source and acquisition of vibration signal of the key equipment based on the multi-source sensing data. The acquisition module 21 is also used to adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters, so that the acquired vibration signal matches the equipment operating status. Analysis module 23 is used to perform cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters to identify the interaction characteristics between equipment in the cascaded operation state of the production line; The calculation module 24 is used to automatically generate state description data representing the health status and failure mode of the equipment based on the multi-source sensor data, the associated working parameters and the interaction features, and input the state description data into the equipment model of the digital twin to run a performance degradation simulation based on physical laws to determine the remaining useful life and potential failure modes of the key equipment.

[0052] This application provides a digital twin modeling and real-time simulation system for a wooden door production line, which is used to implement the aforementioned digital twin modeling and real-time simulation method for a wooden door production line. Therefore, the specific implementation of the digital twin modeling and real-time simulation system for a wooden door production line can be found in the embodiment section of the aforementioned digital twin modeling and real-time simulation method for a wooden door production line. The specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0053] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described method for digital twin modeling and real-time simulation of a wooden door production line.

[0054] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described methods for digital twin modeling and real-time simulation of a wooden door production line.

[0055] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, random access memory, portable hard drives, magnetic disks, or optical disks.

[0056] Embodiments of the present invention also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the embodiments of the above-described digital twin modeling and real-time simulation method for wooden door production lines.

[0057] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0058] The foregoing has provided a detailed description of the digital twin modeling and real-time simulation method, system, electronic device, and storage medium for a wooden door production line provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for digital twin modeling and real-time simulation of a wooden door production line, characterized in that, include: Broadband vibration and sound wave signals generated during the operation of key equipment in the wooden door production line are collected to form multi-source sensor data, and the working parameters of the key equipment, including spindle speed and feed rate, are synchronously associated. By demodulating the phase change of backscattered light in the single-mode fiber laid on the base of the key equipment, the entire single-mode fiber is transformed into a continuously distributed vibration sensing array, and the vibration source of the key equipment is located and the vibration signal is acquired based on the multi-source sensing data. Adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters to ensure that the acquired vibration signal matches the equipment operating status. By performing cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters, the interactive characteristics of the interaction between equipment in the cascaded operation state of the production line can be identified. Based on the multi-source sensor data, the associated operating parameters, and the interaction features, state description data representing the health status and fault modes of the equipment is automatically generated through data calculation. At the same time, the state description data is input into the equipment model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential fault modes of the key equipment.

2. The method according to claim 1, characterized in that, Based on the multi-source sensor data, the correlated operating parameters, and the interaction features, status description data representing the device's health status and fault modes is automatically generated through data calculation, including: Vibration signal data and sound wave signal data are separated and extracted from multi-source sensor data, and the amplitude variation characteristics and frequency distribution characteristics of the vibration signal data and the spectral characteristics of the sound wave signal data are extracted respectively. The extracted amplitude variation features, frequency distribution features, and spectrum features are combined with the associated operating parameters to form a device operation status dataset; The state dataset and the interaction features are merged to obtain the corresponding comprehensive operational features. The feature analysis unit performs calculations on the comprehensive operating features to generate health status data reflecting the health level of the equipment, and generates fault mode data representing the types of faults that the equipment may fail. The health status data and the fault mode data are combined to generate the final status description data.

3. The method according to claim 1, characterized in that, Simultaneously, the state description data is input into the device model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential failure modes of the key equipment, including: Input the device's health status data and fault mode data codes from the status description data into the corresponding parameters of the device model in the digital twin; Based on the mechanical properties of equipment materials, the wear patterns of moving parts, and the fatigue characteristics of structural components, performance degradation calculation rules are established. In the environment of the digital twin, the device model is driven to run according to the actual working parameters, while the performance degradation calculation rules are applied to simulate the gradual change in device performance; By monitoring the changing trends of key performance parameters during the simulation process, the remaining useful life of the equipment is calculated as the operating time required for the equipment to reach the predetermined failure threshold. Record abnormal states and performance mutations that occur during the simulation process, and identify them as potential failure modes and their corresponding occurrence conditions; By integrating parameters from all simulation processes, the remaining useful life and potential failure modes of the critical equipment are ultimately determined.

4. The method according to claim 1, characterized in that, Broadband vibration and acoustic signals generated during the operation of key equipment in the wooden door production line are collected to form multi-source sensor data, which is then synchronously correlated with the operating parameters of the key equipment, including spindle speed and feed rate. Vibration sensing units are installed on key equipment to capture vibration signals and sound sensing units are installed to capture sound wave signals, the vibration signals and the sound wave signals covering a wide frequency range; The spindle speed and feed rate parameters are obtained in real time from the control system of the key equipment. A high-precision time synchronization device is used to mark the vibration signal, the acoustic signal, the spindle speed parameter, and the feed rate parameter with the same time stamp. The vibration signal data, the acoustic signal data, the spindle speed parameter and the feed rate parameter under the same time mark are combined into a multi-source sensing data unit; The continuously collected multi-source sensor data units are organized into a complete set of multi-source sensor data in chronological order.

5. The method according to claim 1, characterized in that, By demodulating the phase change of backscattered light in the single-mode fiber laid on the base of the key equipment, the entire single-mode fiber is transformed into a continuously distributed vibration sensing array. Based on the multi-source sensing data, the vibration source of the key equipment is located and the vibration signal is acquired, including: Single-mode optical fiber is laid along the base surface of the key equipment to ensure close contact between the optical fiber and the base surface. At the same time, a light pulse signal of a specific wavelength is sent to one end of the single-mode optical fiber, and the light signal returned from the single-mode optical fiber is received. The phase change of the optical signal relative to the transmitted optical signal is detected, and the vibration point and vibration intensity of the optical fiber are determined based on the magnitude and position of the phase change. By analyzing the differences in phase change between adjacent fiber segments and combining the device operating parameters in the multi-source sensing data, the specific coordinates of the vibration source on the base of the key device are calculated. Based on the time-series characteristics of the phase change, the frequency components and amplitude characteristics of the vibration signal are extracted.

6. The method according to claim 1, characterized in that, Adjusting the signal acquisition frequency and spatial resolution of the distributed sensor according to the aforementioned operating parameters to match the acquired vibration signal with the equipment's operating state includes: Real-time monitoring of spindle speed and feed rate parameters in the operating parameters; Based on the spindle speed parameters, a sampling frequency adjustment rule is established to adjust the signal sampling frequency of the distributed sensors so that the sampling frequency increases with the increase of the spindle speed parameters. Based on the feed rate parameter, establish a spatial resolution adjustment rule, adjust the spatial resolution of the distributed sensor, and make the spatial resolution adapt to the change of the feed rate parameter. By continuously monitoring the degree of matching between the adjusted vibration signal characteristics and the equipment operating status, the parameter settings of the adjustment rules can be further optimized.

7. The method according to claim 1, characterized in that, By performing cross-equipment correlation analysis on vibration signals from different key devices and the operating parameters, the interactive characteristics of inter-equipment interactions under cascaded production line operation are identified, including: Collect vibration data and operating parameter data of various key equipment in the production line, and establish a multi-equipment dataset under a unified time reference. Establish a time correspondence between the vibration data of adjacent devices and analyze the propagation timing characteristics of vibration signals between devices; The operating parameters of each device are correlated with vibration characteristics to identify the correspondence between the intensity of the vibration signal and the operating status of the device. By analyzing the transmission path and intensity changes of the vibration signal between devices, the interaction characteristics of the mechanical connection state between devices are determined. Based on the response delay and attenuation of the vibration signal among different devices, the dynamic coupling characteristics between devices in the cascaded operation state of the production line are identified.

8. A digital twin modeling and real-time simulation system for a wooden door production line, characterized in that, include: The acquisition module is used to collect broadband vibration and sound wave signals generated by the key equipment of the wooden door production line during operation, form multi-source sensor data, and synchronously associate the working parameters of the key equipment, including spindle speed and feed rate. The acquisition module is used to convert the entire single-mode fiber into a continuously distributed vibration sensing array by demodulating the phase change of the backscattered light in the single-mode fiber laid on the base of the key equipment, and to realize the location of the vibration source and acquisition of vibration signal of the key equipment based on the multi-source sensing data. The acquisition module is also used to adjust the signal acquisition frequency and spatial resolution of the distributed sensor according to the operating parameters, so that the acquired vibration signal matches the equipment operating status. The analysis module is used to perform cross-equipment correlation analysis on vibration signals from different key equipment and the operating parameters to identify the interaction characteristics between equipment in the cascaded operation state of the production line. The calculation module is used to automatically generate state description data representing the health status and failure modes of the equipment based on the multi-source sensor data, the associated working parameters, and the interaction features. At the same time, the state description data is input into the equipment model of the digital twin, and a performance degradation simulation based on physical laws is run to determine the remaining useful life and potential failure modes of the key equipment.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of a digital twin modeling and real-time simulation method for a wooden door production line as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables a digital twin modeling and real-time simulation method for a wooden door production line as described in any one of claims 1 to 7.

Images