Monitoring system and method of optical cable concentric yarn binding machine, cloud platform and medium

Abstract

The invention provides a monitoring system and method of an optical cable concentric yarn binding machine, a cloud platform and a medium, and relates to the technical field of state monitoring of intelligent manufacturing equipment. The monitoring system of the optical cable concentric yarn binding machine comprises a plurality of sensors used for collecting multiple types of working state data of the optical cable concentric yarn binding machine to be monitored; the edge calculation unit is used for performing feature extraction on the working state data to obtain feature data; and the cloud platform is used for obtaining a fault diagnosis result of the optical cable concentric yarn binding machine according to the feature data and a trained fault diagnosis model. According to the scheme, the problem of state monitoring of the optical cable concentric yarn binding machine is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing equipment status monitoring, and in particular to a monitoring system, method, cloud platform and medium for an optical cable concentric yarn binding machine. Background Art

[0002] In the optical cable manufacturing process, the concentric cable binder is a critical piece of equipment, and its operating status directly impacts product quality and production efficiency. However, existing maintenance methods for concentric cable binders rely primarily on scheduled maintenance and manual monitoring, which can lead to unpredictable sudden failures, delayed fault detection, high repair costs, low monitoring efficiency, and inaccurate monitoring. Therefore, an intelligent condition monitoring solution for concentric cable binders is urgently needed to address these technical challenges. Summary of the Invention

[0003] The purpose of the technical solution of the present invention is to provide a monitoring system, method, cloud platform and medium for an optical cable concentric yarn binding machine, so as to solve the problem of status monitoring of the optical cable concentric yarn binding machine in the prior art.

[0004] To achieve the above object, the present invention is achieved as follows:

[0005] In a first aspect, an embodiment of the present invention provides a monitoring system for an optical cable concentric yarn binding machine, comprising:

[0006] Multiple sensors are used to collect various types of working status data of the optical cable concentric yarn binding machine to be monitored;

[0007] an edge computing unit, configured to extract features from the working status data to obtain feature data;

[0008] A cloud platform is used to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and a trained fault diagnosis model.

[0009] Optionally, in the monitoring system for the optical cable concentric yarn binding machine, the edge computing unit is configured to extract features from the working status data to obtain feature data, including:

[0010] At least one of time domain features, frequency domain features, time-frequency analysis features, nonlinear features, statistical features, and spatial features is extracted from the working status data to obtain feature data.

[0011] Optionally, in the monitoring system for the optical cable concentric yarn binding machine, the fault diagnosis model is used to obtain the fault diagnosis result based on the similarity between the characteristic data and the fault samples in the fault characteristic library.

[0012] Optionally, in the monitoring system of the optical cable concentric yarn binding machine, the cloud platform is further used to perform incremental training on the fault diagnosis model at intervals of a preset time length.

[0013] Optionally, in the monitoring system of the optical cable concentric yarn binding machine, the cloud platform is further used to determine the fault warning level of the optical cable concentric yarn binding machine based on the characteristic data, the fault diagnosis model and the dynamically updated fault warning threshold.

[0014] Optionally, in the monitoring system of the optical cable concentric yarn binding machine, the cloud platform is further used to obtain the dynamically updated fault warning threshold according to an adaptive algorithm.

[0015] Optionally, in the monitoring system of the optical cable concentric yarn binding machine, the multiple sensors include at least two of a vibration sensor, a tension sensor, a noise sensor, a temperature sensor, a current sensor, and a voltage sensor.

[0016] Optionally, the monitoring system of the optical cable concentric yarn binding machine, wherein the monitoring system of the optical cable concentric yarn binding machine, the multiple sensors are located at at least one of the bearing seat, pulley, transmission shaft, motor and yarn tension point of the optical cable concentric yarn binding machine.

[0017] In a second aspect, an embodiment of the present invention further provides a monitoring method for an optical cable concentric yarn binding machine, which is applied to a cloud platform, and the method includes:

[0018] Acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by the edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by multiple sensors;

[0019] A fault diagnosis result of the optical cable concentric yarn binding machine is obtained based on the characteristic data and the trained fault diagnosis model.

[0020] In a third aspect, an embodiment of the present invention further provides a monitoring device for an optical cable concentric yarn binding machine, which is applied to a cloud platform, and the device includes:

[0021] an acquisition module, configured to acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by the edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by a plurality of sensors;

[0022] An acquisition module is used to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and the trained fault diagnosis model.

[0023] In a fourth aspect, an embodiment of the present invention further provides a cloud platform comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the monitoring method of the optical cable concentric yarn binding machine as described in the first aspect is implemented.

[0024] In a fifth aspect, an embodiment of the present invention further provides a readable storage medium having a program stored thereon, and when the program is executed by a processor, the monitoring method of the optical cable concentric yarn binding machine as described in the first aspect is implemented.

[0025] In a sixth aspect, an embodiment of the present invention provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the method for monitoring the optical cable concentric yarn binding machine as described in the first aspect.

[0026] The beneficial effects of the above technical solution of the present invention are as follows:

[0027] In an embodiment of the present invention, the monitoring system for the optical cable concentric yarn binder includes: multiple sensors for collecting multiple types of working status data of the optical cable concentric yarn binder to be monitored; an edge computing unit for extracting features from the working status data to obtain feature data; and a cloud platform for obtaining a fault diagnosis result of the optical cable concentric yarn binder based on the feature data and a trained fault diagnosis model. Thus, the monitoring system for the optical cable concentric yarn binder is an intelligent monitoring system that integrates multiple types of working status data and collaborates with the edge and cloud. It solves the problem of status monitoring of the optical cable concentric yarn binder with high monitoring efficiency and accuracy, and simultaneously solves the problems of unpredictable sudden faults, delayed fault detection, and high maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 Schematic diagram of the structure of the monitoring system of the optical cable concentric yarn binding machine according to an embodiment of the present invention;

[0029] Figure 2 Schematic diagram of the architecture of a monitoring system for an optical cable concentric yarn binding machine according to an embodiment of the present invention;

[0030] Figure 3 Schematic diagram of the flow of a monitoring method for an optical cable concentric yarn binding machine according to an embodiment of the present invention;

[0031] Figure 4 This is a flow chart of one embodiment of the monitoring method for the optical cable concentric yarn binding machine according to an embodiment of the present invention;

[0032] Figure 5 Schematic diagram of the structure of the monitoring device of the optical cable concentric yarn binding machine according to an embodiment of the present invention;

[0033] Figure 6 Schematic diagram of the structure of the cloud platform according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0035] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0036] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0037] The terms "first," "second," and the like in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that embodiments of the present invention can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "first" and "second" generally distinguish objects of the same type, and do not limit the number of objects. For example, the first object can be one or more. Furthermore, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the connected objects are in an "or" relationship.

[0038] Please refer to Figure 1 The embodiment of the present invention provides a monitoring system for an optical cable concentric yarn binding machine, comprising:

[0039] Multiple sensors are used to collect various types of working status data of the optical cable concentric yarn binding machine to be monitored;

[0040] an edge computing unit, configured to extract features from the working status data to obtain feature data;

[0041] A cloud platform is used to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and a trained fault diagnosis model; the fault diagnosis model is used to perform fault diagnosis and fault classification on the characteristic data, that is, the fault diagnosis result includes a diagnosis result of whether the optical cable concentric yarn binding machine has a fault, and if a fault exists, a classification result of the fault.

[0042] In one embodiment, optionally, the plurality of sensors include at least two of a vibration sensor, a tension sensor, a noise sensor, a temperature sensor, a current sensor, and a voltage sensor.

[0043] Optionally, the multiple sensors are located at at least one of a bearing seat, a pulley, a transmission shaft, a motor and a yarn tension point of the optical cable concentric yarn binding machine.

[0044] In an embodiment of the present invention, the vibration sensor is used to capture the vibration characteristics of the optical cable concentric yarn binder in real time and perform mechanical vibration monitoring on the optical cable concentric yarn binder. The vibration sensor can be a three-axis (x / y / z axis) accelerometer with a sampling frequency ≥ 20kHz, such as 25.6kHz. The vibration sensor can be installed on at least one of the bearing seat, pulley, drive shaft, motor, and yarn tension point of the optical cable concentric yarn binder. Specifically, the vibration sensor is rigidly mounted on the radial and axial force points of the bearing seat via a magnetic base.

[0045] The tension sensor is used to capture the yarn tension characteristics of the optical cable concentric yarn binder in real time and monitor the yarn tension of the optical cable concentric yarn binder. The tension sensor can be a fiber optic tension sensor with a dynamic range of ≥100dB, enabling high-precision monitoring of tension fluctuations. The tension sensor can be installed at the yarn tension point of the optical cable concentric yarn binder.

[0046] The noise sensor is used to capture the operating sound signature of the optical cable concentric yarn binder in real time and monitor the operating noise of the optical cable concentric yarn binder. The noise sensor may be a microphone array. The noise sensor may be installed on at least one of the bearing seat, pulley, drive shaft, motor, and yarn tension point of the optical cable concentric yarn binder.

[0047] The temperature sensor is used to capture the temperature characteristics of the optical cable concentric yarn binder in real time and monitor the temperature of the optical cable concentric yarn binder. The temperature sensor can be a resistance thermometer or an infrared thermometer with an accuracy of ±0.5°C and is used to monitor the surface temperature field of the optical cable concentric yarn binder. The temperature sensor can be installed on at least one of the bearing seat, pulley, drive shaft, motor, and yarn tension point of the optical cable concentric yarn binder. Specifically, the temperature sensor is located 0.3m to 0.5m from the bearing seat, away from dusty areas, and regularly undergoes zero point calibration.

[0048] The current sensor and the voltage sensor may be power analyzers, which are used to collect electrical parameter fluctuations of the optical cable concentric yarn binding machine.

[0049] In addition, the multiple sensors may also include an acoustic emission sensor. The broadband acoustic emission sensor is used to monitor microcracks in the optical cable concentric yarn binding machine, and the frequency range is 50kHz to 1MHz. The broadband acoustic emission sensor can be installed on at least one of the bearing seat, pulley, drive shaft, motor and yarn tension point of the optical cable concentric yarn binding machine.

[0050] It should be noted that the temperature sensor and the tension sensor may also be installed on the belt of the optical cable concentric yarn binding machine to monitor belt temperature and tension fluctuations.

[0051] The temperature sensor and the acoustic emission sensor can be combined to analyze early bearing failures.

[0052] Corresponding to the multiple sensors, the working status data includes at least two of vibration monitoring data, pressure monitoring data, noise monitoring data, temperature monitoring data, current monitoring data, and voltage monitoring data.

[0053] In one embodiment, optionally, the edge computing unit is configured to extract features from the working status data to obtain feature data, including:

[0054] At least one of time domain features, frequency domain features, time-frequency analysis features, nonlinear features, statistical features, and spatial features is extracted from the working status data to obtain feature data.

[0055] It should be noted that the edge computing unit is used to preprocess (e.g., filter) and extract features from the operating status data to obtain feature data, and upload the feature data to the cloud platform. The edge computing unit can be an industrial-grade edge gateway or embedded industrial controller, using a four-wire wiring system with a cold-end supplementary circuit and a synchronization error of less than 1μs. The edge computing unit supports hot-swappable sensors and remote firmware updates to ensure system maintainability and selectivity.

[0056] In an embodiment of the present invention, the working status data includes at least two of vibration monitoring data, pressure monitoring data, noise monitoring data, temperature monitoring data, current monitoring data, and voltage monitoring data.

[0057] Performing time domain feature extraction on the vibration monitoring data to obtain time domain feature data includes at least one of the following:

[0058] Peak: The maximum amplitude of the vibration signal, reflecting sudden impact;

[0059] Mean: The average amplitude of the signal, representing the overall vibration intensity;

[0060] Variance: The degree of fluctuation in vibration energy, used to detect imbalance or looseness;

[0061] Kurtosis: The sharpness of the signal peak. Early faults (such as bearing spalling) will cause the kurtosis to increase.

[0062] Waveform Factor: The ratio of the effective value to the mean value, which distinguishes random vibration from periodic shock.

[0063] Performing frequency domain feature extraction on the vibration monitoring data to obtain frequency domain feature data includes at least one of the following:

[0064] Dominant Frequency: Extracts the dominant frequency in the vibration spectrum through FFT, which corresponds to the equipment rotation frequency or fault characteristic frequency (such as bearing fault frequency);

[0065] Spectral Energy: The sum of the energy in a specific frequency band (e.g., 1-3kHz), used to detect gear meshing anomalies.

[0066] Sideband: The modulation frequency on both sides of the main frequency, reflecting gear wear or shaft misalignment.

[0067] Performing time-frequency analysis feature extraction on the vibration monitoring data to obtain time-frequency analysis feature data includes at least one of the following:

[0068] Wavelet Packet Energy: Decomposes the signal into multiple frequency bands, calculates the energy contribution of each frequency band, and captures non-stationary vibration characteristics (such as transient vibration during startup / shutdown).

[0069] Performing time domain feature extraction on the noise monitoring data to obtain time domain feature data includes at least one of the following:

[0070] Sound pressure level (SPL): The RMS value of noise, reflecting the overall noise level of the equipment;

[0071] Short-Time Energy: Calculates noise energy frame by frame to detect sudden noise events (such as yarn breakage).

[0072] Performing frequency domain feature extraction on the noise monitoring data to obtain frequency domain feature data includes at least one of the following:

[0073] Mel-Frequency Cepstral Coefficients (MFCC): This simulates the human hearing characteristics and extracts 13-20 dimension coefficients to distinguish different fault sound patterns (such as poor bearing lubrication and gear meshing noise).

[0074] Spectral Centroid: The frequency of the "center of gravity" of noise energy, reflecting the brightness and darkness characteristics of the voiceprint.

[0075] Performing nonlinear feature extraction on the noise monitoring data to obtain nonlinear feature data includes:

[0076] Entropy: The complexity of the voiceprint. Abnormal noise (such as friction sound) will cause the entropy value to increase.

[0077] Statistical feature extraction is performed on the temperature monitoring data to obtain statistical feature data, including at least one of the following:

[0078] Maximum Temperature (Max Temp): The maximum temperature of key components (such as motor bearings), warning of overheating faults;

[0079] Temperature Gradient: The temperature difference between adjacent areas is used to detect local overheating (such as winding short circuit).

[0080] Performing spatial feature extraction on the temperature monitoring data to obtain spatial feature data includes at least one of the following:

[0081] Hotspot Area: The area of the temperature exceeding the threshold, quantifying the overheating range;

[0082] Thermal Symmetry: The temperature difference between the left and right bearings can be used to determine shaft misalignment or uneven lubrication.

[0083] Performing time domain feature extraction on the current monitoring data or the voltage monitoring data to obtain time domain feature data includes at least one of the following:

[0084] Current effective value (RMS): reflects the change of motor load;

[0085] Crest Factor: The ratio of peak current to RMS current, used to detect electrical shocks (such as stalls).

[0086] Performing frequency domain feature extraction on the current monitoring data or the voltage monitoring data to obtain frequency domain feature data includes at least one of the following:

[0087] Harmonics: The 5th and 7th harmonic contents reflect nonlinear loads on the motor or power supply quality issues.

[0088] Current Spectral Energy: Energy in a specific frequency band (e.g., 100-200 Hz), used to detect broken rotor bar faults.

[0089] Extracting time-frequency features from the current monitoring data or the voltage monitoring data to obtain time-frequency feature data includes:

[0090] Short-time Fourier transform (STFT): Analyzes transient harmonic changes in the current signal during startup / shutdown.

[0091] In addition, the edge computing unit is further configured to perform composite feature extraction on the working status data to obtain feature data, including at least one of the following:

[0092] Vibro-Current Coherence, used to analyze the phase consistency of the vibration monitoring data and the current monitoring data to detect electromechanical coupling faults (such as motor-load misalignment);

[0093] Thermal-vibration correlation features: The joint distribution of temperature gradient and vibration energy can be used to identify friction pair faults (such as bearing lubrication failure).

[0094] The edge computing unit is further configured to perform dimensionality reduction feature extraction on the working status data to obtain feature data, including:

[0095] Principal Component Analysis (PCA): Projects multidimensional features into a low-dimensional space, retaining the principal components with 95% variance, and reducing computational complexity.

[0096] It should be noted that the edge computing unit is further configured to perform at least one of the following:

[0097] Perform Z-Score standardization on the characteristic data (such as vibration amplitude, temperature, etc.) to eliminate dimensional differences;

[0098] The mutual information method is used to filter the feature data that is strongly correlated with the fault label and eliminate redundant dimensions.

[0099] A sliding window mechanism is used to update the feature data every 100ms to balance the computing load and response speed.

[0100] For example, the edge computing unit extracts the following feature data in real time during the operation of the optical cable concentric yarn binding machine and uploads the feature data to the cloud platform. By comparing the feature data with the fault feature library, typical problems such as early faults and abnormal yarn tension can be accurately diagnosed to achieve predictive maintenance:

[0101] Vibration: X-axis vibration kurtosis of the bearing seat (>3.5 triggers an early warning);

[0102] Noise: MFCC 4th dimension coefficient (abnormal voiceprint matching degree > 80%);

[0103] Temperature: Motor winding temperature gradient (>5°C / cm);

[0104] Current: 5th harmonic content (>7%).

[0105] Furthermore, the edge computing unit is further configured to perform data compression and encryption on the feature data, wherein:

[0106] Compression: using a lightweight algorithm (such as differential pulse code modulation DPCM) to compress the feature data to reduce the transmission bandwidth requirement;

[0107] Encryption: AES-128 end-to-end encryption is used to ensure the confidentiality of the characteristic data during transmission.

[0108] Furthermore, the feature data is uploaded to the cloud via a low-latency transmission protocol (such as MQTT over TLS protocol), and 5G network slicing technology is used to ensure sub-second transmission delay.

[0109] After receiving the feature data, the cloud platform performs data integrity verification (such as CRC check) on the feature data, and if the data integrity verification passes, decrypts the feature data to obtain the decrypted feature data.

[0110] It should be noted that, after obtaining the decrypted feature data, the cloud platform is configured to perform at least one of the following processing on the decrypted feature data:

[0111] Outlier processing: The isolation forest algorithm is used to detect and remove outliers caused by sensor noise;

[0112] Missing value filling: KNN interpolation method is used to fill missing data caused by occasional transmission interruptions;

[0113] Standardization: Z-Score standardization is performed on physical quantities such as vibration amplitude and temperature to eliminate dimensional differences.

[0114] In addition, the cloud platform is also used to perform feature enhancement and dimensionality reduction on the feature data, including:

[0115] Feature fusion: Combine the vibration spectrum and current harmonic feature data to construct composite feature data;

[0116] Principal Component Analysis (PCA): retaining 95% of the variance of the principal components, reducing the dimension of the feature data to 10 to 20 dimensions;

[0117] t-SNE visualization: Identifying clusters of potential failure modes in high-dimensional feature space.

[0118] In one embodiment, optionally, the fault diagnosis model is used to obtain the fault diagnosis result based on the similarity between the feature data and the fault samples in the fault feature library.

[0119] In an embodiment of the present invention, the fault diagnosis model may adopt a random forest model or a long short-term memory network.

[0120] The fault diagnosis result is obtained by matching the fault feature library with the fault diagnosis model.

[0121] It should be noted that if the similarity between the characteristic data and the fault sample exceeds a first similarity threshold, the fault diagnosis result obtained is the fault type corresponding to the fault sample.

[0122] If the similarities between the characteristic data and the plurality of fault samples all exceed the first similarity threshold, the fault diagnosis results are sorted according to the predicted probabilities, and a probability sorting list is output.

[0123] If the similarity between the characteristic data and all fault samples in the fault characteristic library is less than a second similarity threshold, a warning of a new fault type is triggered to achieve unknown fault detection. The second similarity threshold is less than the first similarity threshold.

[0124] The fault feature library includes characteristic data of typical faults such as bearing wear and belt slippage. The construction process of the fault feature library is as follows:

[0125] Historical data labeling: Using expert experience and semi-supervised learning, thousands of historical fault samples are labeled (such as bearing wear, yarn breakage, and motor overheating);

[0126] Feature extraction: Generate standardized feature data using the same method as the edge computing unit;

[0127] Cluster analysis: Use the DBSCAN algorithm to cluster unlabeled data and discover unknown failure modes.

[0128] Here, the following similarity matching algorithm is used to obtain the similarity between the feature data and the fault samples in the fault feature library:

[0129] Cosine similarity: Calculate the cosine value of the angle between the feature data and each fault sample in the fault feature library, and select the top-K similar samples;

[0130] Dynamic Time Warping (DTW): measures the similarity between sequences for time series feature data (such as vibration signal segments);

[0131] Deep Learning Model: Deploy a pre-trained Siamese network and learn the distance metric in the feature embedding space through a Siamese neural network.

[0132] In one embodiment, optionally, the cloud platform is further configured to perform incremental training on the fault diagnosis model at intervals of a preset duration.

[0133] In an embodiment of the present invention, the cloud platform is also used to update the fault feature library using an online learning algorithm (such as incremental SVM) for newly confirmed fault cases (after manual review) at preset time intervals to optimize classification accuracy.

[0134] and / or,

[0135] The cloud platform is also used to retrain the fault diagnosis model with all historical data at preset intervals (such as weekly) to improve long-term accuracy.

[0136] In one embodiment, optionally, the cloud platform is further configured to determine a fault warning level of the optical cable concentric yarn binding machine based on the characteristic data, the fault diagnosis model, and a dynamically updated fault warning threshold.

[0137] It should be noted that in order to achieve accurate early warning and graded response to the operating status of the optical cable concentric yarn binding machine, the cloud platform described in the embodiment of the present invention is also used to set a multi-level early warning mechanism as shown in Table 1, which corresponds to different response measures respectively, and determines the fault warning level of the optical cable concentric yarn binding machine based on the characteristic data, the fault diagnosis model and the dynamically updated fault warning threshold.

[0138] Table 1: Schematic diagram of multi-level early warning mechanism

[0139]

[0140] The warning level is determined not only based on a single characteristic data point (such as vibration), but also by integrating indicators such as temperature, noise, and current for a comprehensive assessment, improving accuracy. Trend analysis algorithms (such as sliding average, exponential weighting, and long-short-term memory network prediction models) are introduced to identify potential risks before the characteristic data reaches the alarm threshold. Warning information is pushed to operations and maintenance personnel via mobile applications, text messages, or apps, enabling rapid response.

[0141] Therefore, the monitoring system of the optical cable concentric yarn binding machine described in the embodiment of the present invention can accurately identify and warn the operating status of key parts of the optical cable concentric yarn binding machine (such as bearing seats, pulleys, transmission shafts, motors and yarn tension points), effectively reducing the probability of sudden failures.

[0142] In one embodiment, optionally, the cloud platform is further configured to obtain the dynamically updated fault warning threshold according to an adaptive algorithm.

[0143] In an embodiment of the present invention, the dynamically updated fault warning threshold is calculated using the following formula:

[0144] Fault warning threshold = reference fault warning threshold × (1 + 0.015 × ΔT), where ΔT is the deviation between the ambient temperature and the standard operating condition.

[0145] Figure 2 FIG. 1 is a schematic diagram of the architecture of the monitoring system of the optical cable concentric yarn binding machine according to an embodiment of the present invention. Figure 2 As shown, the monitoring system of the optical cable concentric yarn binding machine is aimed at the optical cable concentric yarn binding machine A and the optical cable concentric yarn binding machine B. The bearing seat, motor 1, motor 2 and motor 3 of each of the optical cable concentric yarn binding machines are respectively installed with sensors. For example, the bearing seat includes bearings 1 to bearings 6, and each bearing is installed with a sensor; the motor drive end of each motor is installed with a sensor. Each optical cable concentric yarn binding machine corresponds to an edge computing unit, and the edge computing unit can be an intelligent gateway. The working status data of the optical cable concentric yarn binding machine collected by each sensor is uploaded to the edge computing unit, and the edge computing unit performs data preprocessing and feature extraction on the working status data to obtain feature data, and the feature data is uploaded to the cloud platform. The cloud platform performs fault diagnosis and fault warning on the feature data, and realizes visual interaction.

[0146] Please refer to Figure 3 The embodiment of the present invention further provides a monitoring method for an optical cable concentric yarn binding machine, which is applied to a cloud platform, and the method includes:

[0147] Step 301: Acquire feature data of an optical cable concentric yarn binder to be monitored extracted by an edge computing unit, wherein the feature data is related to working status data of the optical cable concentric yarn binder collected by multiple sensors;

[0148] Step 302: Obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and the trained fault diagnosis model.

[0149] In one embodiment, optionally, the fault diagnosis model is used to obtain the fault diagnosis result based on the similarity between the feature data and the fault samples in the fault feature library.

[0150] In one embodiment, optionally, the method further comprises:

[0151] The fault diagnosis model is incrementally trained at intervals of a preset duration.

[0152] In one embodiment, optionally, the method further comprises:

[0153] The fault warning level of the optical cable concentric yarn binding machine is determined according to the characteristic data, the fault diagnosis model and the dynamically updated fault warning threshold.

[0154] In one embodiment, optionally, the method further comprises:

[0155] The dynamically updated fault warning threshold is obtained according to an adaptive algorithm.

[0156] Figure 4 FIG. 1 is a flow chart of one embodiment of the monitoring method of the optical cable concentric yarn binding machine according to the embodiment of the present invention. Figure 4 As shown, the monitoring method of the optical cable concentric yarn binding machine can achieve the following three aspects:

[0157] Data-driven alarm and diagnosis;

[0158] Plan-driven alerting, diagnosis, and prediction;

[0159] Demand-driven diagnosis and prediction.

[0160] Among them, multi-source, heterogeneous working status data is connected to the edge computing unit, which performs data preprocessing and feature extraction, and then the cloud platform realizes the status monitoring of the optical cable concentric yarn binding machine, performs intelligent alarms, and outputs alarm conclusions. It should be noted that the cloud platform performs intelligent alarms based on the fault diagnosis model, and can select a model from the AI model library for training to obtain a fault diagnosis model. After outputting the alarm conclusion, alarm management can also be performed, and experts / customers can provide feedback on the alarm conclusion, thereby continuously optimizing the model. In addition, the monitoring method of the optical cable concentric yarn binding machine also includes visual interaction with the edge computing unit, the alarm / defect business system, the equipment operation and maintenance business system, and the health and life prediction business system.

[0161] In summary, the monitoring system and method for the optical cable concentric yarn binder described in the embodiments of the present invention, based on multi-source data fusion, uses the collaborative collection of vibration, temperature, tension, and acoustic emission sensors, combined with edge and cloud-based big data analysis technology, to achieve early diagnosis and predictive maintenance of optical cable concentric yarn binder faults. Furthermore, the use of dynamically updated fault warning thresholds and a multi-level warning mechanism significantly improves fault identification accuracy and response efficiency, addressing the lag and inefficiency of existing maintenance methods for optical cable concentric yarn binders and making it suitable for equipment health management in intelligent manufacturing scenarios.

[0162] Please refer to Figure 5 The embodiment of the present invention further provides a monitoring device for an optical cable concentric yarn binding machine, which is applied to a cloud platform, and the device includes:

[0163] An acquisition module 501 is configured to acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by an edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by multiple sensors;

[0164] The acquisition module 502 is configured to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and the trained fault diagnosis model.

[0165] It should be noted that the seat allocation device provided in an embodiment of the present invention is a device capable of executing the above-mentioned monitoring method of the optical cable concentric yarn binding machine. All embodiments of the above-mentioned monitoring method of the optical cable concentric yarn binding machine are applicable to the device and can achieve the same or similar technical effects.

[0166] like Figure 6 As shown, an embodiment of the present invention also provides a cloud platform, including: a processor 601; and a memory 602 connected to the processor 601 through a bus interface, the memory 602 is used to store programs and data used by the processor 601 when performing operations, and the processor 601 calls and executes the programs and data stored in the memory 602.

[0167] The processor 601 is used to read the program in the memory 602 and execute the following process:

[0168] Acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by the edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by multiple sensors;

[0169] A fault diagnosis result of the optical cable concentric yarn binding machine is obtained based on the characteristic data and the trained fault diagnosis model.

[0170] The present invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the various processes of the above-mentioned embodiment of the monitoring method for the optical cable concentric yarn binding machine and can achieve the same technical effect. To avoid repetition, the above-mentioned computer-readable storage medium is not described here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0171] An embodiment of the present invention also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the various processes of the above-mentioned monitoring method embodiment of the optical cable concentric yarn binding machine are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0172] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0173] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0174] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A monitoring system for an optical cable concentric yarn binding machine, characterized in that: include: Multiple sensors are used to collect various types of working status data of the optical cable concentric yarn binding machine to be monitored; an edge computing unit, configured to extract features from the working status data to obtain feature data; A cloud platform is used to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and a trained fault diagnosis model.

2. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The edge computing unit is configured to extract features from the working status data to obtain feature data, including: At least one of time domain features, frequency domain features, time-frequency analysis features, nonlinear features, statistical features, and spatial features is extracted from the working status data to obtain feature data.

3. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The fault diagnosis model is used to obtain the fault diagnosis result according to the similarity between the characteristic data and the fault samples in the fault characteristic library.

4. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The cloud platform is further configured to perform incremental training on the fault diagnosis model at intervals of a preset duration.

5. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The cloud platform is further configured to determine a fault warning level of the optical cable concentric yarn binding machine based on the characteristic data, the fault diagnosis model, and the dynamically updated fault warning threshold.

6. The monitoring system for the optical cable concentric yarn binding machine according to claim 5, characterized in that: The cloud platform is further configured to obtain the dynamically updated fault warning threshold value according to an adaptive algorithm.

7. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The plurality of sensors include at least two of a vibration sensor, a tension sensor, a noise sensor, a temperature sensor, a current sensor, and a voltage sensor.

8. The monitoring system for the optical cable concentric yarn binding machine according to claim 1, characterized in that: The multiple sensors are located at at least one of a bearing seat, a pulley, a transmission shaft, a motor and a yarn tension point of the optical cable concentric yarn binding machine.

9. A monitoring method for an optical cable concentric yarn binding machine, characterized in that: Applied to a cloud platform, the method includes: Acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by the edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by multiple sensors; A fault diagnosis result of the optical cable concentric yarn binding machine is obtained based on the characteristic data and the trained fault diagnosis model.

10. A monitoring device for an optical cable concentric yarn binding machine, characterized in that: Applied to a cloud platform, the device includes: an acquisition module, configured to acquire characteristic data of the optical cable concentric yarn binder to be monitored extracted by the edge computing unit, wherein the characteristic data is related to working status data of the optical cable concentric yarn binder collected by a plurality of sensors; An acquisition module is used to obtain a fault diagnosis result of the optical cable concentric yarn binding machine based on the characteristic data and the trained fault diagnosis model.

11. A cloud platform, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for monitoring the optical cable concentric yarn binding machine according to claim 9 is implemented.

12. A readable storage medium, characterized in that: The readable storage medium stores a program, and when the program is executed by the processor, the monitoring method of the optical cable concentric yarn binding machine according to claim 9 is implemented.

13. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the method for monitoring the optical cable concentric yarn binding machine according to claim 9.

Images