Binding machine fault monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of data processing, and discloses a bridle machine fault monitoring method and system based on the Internet of Things. The method comprises the following steps: collecting multi-source operation data through a sensor; performing filtering segmentation processing on the data to obtain feature data; analyzing the feature data to obtain an abnormal identifier and a fault type; establishing a component association map to position a fault source and predict a development trend; calculating a maintenance priority to generate a maintenance scheme; and recording the actual maintenance result and the prediction deviation to update the fault library and the knowledge parameters. Through multi-source data fusion, intelligent fault diagnosis, predictive maintenance and knowledge self-adaptive updating mechanisms, early recognition and accurate positioning of faults of the bridle machine are realized, the non-planned downtime is effectively shortened, and the equipment reliability and the production efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for monitoring faults of a strapping machine based on the Internet of Things. Background Art

[0002] The strapping machine is a commonly used packaging equipment in industrial production. It is mainly used to bundle and fix products or components. It is widely used in logistics, manufacturing, food processing and other fields. With the improvement of industrial automation level, modern strapping machines have developed into complex equipment integrating mechanical, electrical and control. Its operating status directly affects production efficiency and product quality. The maintenance of traditional strapping machines mainly relies on two modes: regular maintenance and post-fault repair, that is, inspection and maintenance according to fixed cycles, or maintenance only after obvious failure of the equipment. Some advanced companies have introduced simple condition monitoring technology, which monitors the status of key components in real time by installing a single type of sensor (such as vibration or temperature sensor), and triggers an alarm when the monitoring data exceeds the preset threshold.

[0003] However, the existing fault monitoring methods for strapping machines have obvious shortcomings. First, the traditional regular maintenance method lacks pertinence, which may lead to a waste of maintenance resources and fail to effectively prevent sudden failures; second, the monitoring method of a single sensor cannot fully reflect the complex working status of the equipment, resulting in low fault diagnosis accuracy and high false alarm rates; third, the existing monitoring systems generally lack intelligent analysis capabilities and cannot predict fault trends based on historical data, making it difficult to achieve early identification and prevention of faults; finally, the existing methods lack a closed-loop learning mechanism and cannot automatically optimize the diagnostic model based on actual maintenance results, making it difficult to continuously improve the diagnostic accuracy. These shortcomings lead to low maintenance efficiency of strapping machines and frequent unplanned downtime, which seriously affects production continuity and corporate economic benefits. Summary of the invention

[0004] The present application provides a method and system for monitoring faults of a tie-belt machine based on the Internet of Things, which is used to achieve early identification and accurate positioning of tie-belt machine faults through multi-source data fusion, intelligent fault diagnosis, predictive maintenance and knowledge adaptive update mechanism, effectively reduce unplanned downtime, and improve equipment reliability and production efficiency.

[0005] In a first aspect, the present application provides a method for monitoring faults of a strapping machine based on the Internet of Things, the method comprising: collecting operating data of key parts of the strapping machine through a sensor network to obtain multi-source operating data including motor temperature data, tension control parameters, binding robot arm displacement data, cutting device operating status and strap deformation rate; filtering and segmenting the data according to the multi-source operating data to obtain strapping machine state characteristic data with a timestamp; based on the strapping machine state characteristic data, analyzing and comparing the strapping machine operating status to obtain the strapping machine abnormal state identification and fault type determination results; establishing a strapping machine component association map according to the strapping machine abnormal state identification and fault type determination results to obtain fault cause location results and fault development trend prediction values; calculating maintenance priorities based on the fault cause location results and fault development trend prediction values ​​in combination with the strapping machine maintenance database to obtain maintenance plans and operation time recommendations; recording actual maintenance results and predicted deviations according to the strapping machine operating effect after the maintenance plan is implemented to obtain an updated strapping machine fault feature library and maintenance knowledge parameters.

[0006] In a second aspect, the present application provides a strapping machine fault monitoring system based on the Internet of Things, and the strapping machine fault monitoring system based on the Internet of Things includes: The extraction module is used to collect the operating data of each key part of the strapping machine through the sensor network, and obtain multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate; A segmentation module, used for filtering and segmenting the data according to the multi-source operation data to obtain the state characteristic data of the strapping machine with a timestamp; A comparison module, used for analyzing and comparing the running state of the strapping machine based on the state characteristic data of the strapping machine, and obtaining the abnormal state identification and fault type determination result of the strapping machine; A positioning module is used to establish a component association map of the strapping machine according to the abnormal state identification and fault type determination result of the strapping machine, and obtain the fault cause positioning result and the fault development trend prediction value; A calculation module, for calculating the maintenance priority according to the fault cause location result and the fault development trend prediction value in combination with the belt machine maintenance database, and obtaining a maintenance plan and operation time recommendation; The prediction module is used to record the actual maintenance results and the prediction deviation according to the operation effect of the strapping machine after the maintenance plan is implemented, and obtain the updated strapping machine fault feature library and maintenance knowledge parameters.

[0007] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned Internet of Things-based strapping machine fault monitoring method.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned Internet of Things-based strapping machine fault monitoring method.

[0009] In the technical solution provided in this application, multi-source operating data of key parts of the strapping machine are collected through a sensor network, the data is processed in a refined manner, and a complete fault diagnosis and maintenance system is established, achieving significant technical effects. The multi-source operating data collection mechanism solves the problem of the limitations of single sensor information. The fusion of multi-dimensional data such as motor temperature data, tension control parameters, bundling robot arm displacement data, cutting device operating status, and strap deformation rate provides a comprehensive operating status portrait of the strapping machine, greatly improving the integrity and accuracy of monitoring; the data is filtered and segmented to obtain the strapping machine state feature data with timestamps, effectively eliminating the interference of environmental noise and irrelevant signals, and improving the reliability of feature extraction; the operating status is analyzed and compared based on the strapping machine state feature data, and an artificial intelligence model with adaptive thresholds and multi-feature fusion is used. When determining the type of fault, the machine learning algorithm is combined with expert knowledge, which greatly reduces the probability of missed reports and false alarms; fourth, the establishment The cause of the fault is located by using the association map of the components of the vertical strapping machine, and a causal reasoning algorithm is introduced. This algorithm fully considers the physical connection and functional dependency between the components, making the fault location more accurate, and can predict the development trend of the fault in advance, providing a sufficient time window for maintenance decisions; fifthly, the maintenance priority is calculated in combination with the maintenance database to form a scientific maintenance plan and operation time recommendation. The three requirements of equipment safety, maintenance resources and production plan are balanced through a multi-objective optimization algorithm, reducing unplanned downtime; most importantly, the present invention establishes a complete knowledge feedback loop, by recording the actual maintenance results and predicted deviations, continuously updating the fault feature library and maintenance knowledge parameters, and the system's self-learning ability enables the accuracy of fault diagnosis to gradually improve with the use time. In the specific functional field of the belting machine, the present invention gives full play to the advantages of artificial intelligence technologies such as adaptive filtering algorithm, causal propagation algorithm and multi-objective optimization algorithm, especially the application of causal propagation algorithm in fault tracing, breaking through the limitation of traditional correlation analysis that it is difficult to identify the root cause of hidden faults, enabling the system to handle complex fault propagation chains, providing new technical ideas for industrial equipment fault diagnosis, and realizing the transformation of maintenance mode from passive response to active prevention, significantly extending the effective operation time of the belting machine, and improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0011] Figure 1 A schematic diagram of an embodiment of a method for monitoring a belt machine failure based on the Internet of Things in an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of a strapping machine fault monitoring system based on the Internet of Things in an embodiment of the present application; Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a method and system for monitoring faults of a strapping machine based on the Internet of Things. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiment of the present application, an embodiment of the method for monitoring the fault of a strapping machine based on the Internet of Things includes: Step S101, collecting operating data of key parts of the strapping machine through a sensor network to obtain multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate; Step S102, filtering and segmenting the data according to the multi-source operation data to obtain the state characteristic data of the strapping machine with a timestamp; Step S103, based on the state characteristic data of the strapping machine, analyzing and comparing the running state of the strapping machine to obtain the abnormal state identification and fault type determination result of the strapping machine; Step S104, according to the abnormal state identification of the strapping machine and the fault type determination result, establish a strapping machine component association map to obtain the fault cause location result and the fault development trend prediction value; Step S105, based on the fault cause location result and the fault development trend prediction value, the maintenance priority is calculated in combination with the belt machine maintenance database to obtain a maintenance plan and operation time recommendation; Step S106: According to the running effect of the strapping machine after the maintenance plan is implemented, the actual maintenance result and the predicted deviation are recorded to obtain an updated strapping machine fault feature library and maintenance knowledge parameters.

[0014] It is understandable that the execution subject of the present application can be a strapping machine fault monitoring system based on the Internet of Things, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0015] Specifically, the sensor network collects the operating data of each key part of the strapping machine, which is the basis of the whole method. Specifically, temperature sensors and current sensors are installed on the motor drive device of the strapping machine to collect the motor surface temperature and current waveform data; tension sensors and displacement sensors are arranged in the tension control mechanism to record the change of strap tension and the displacement of the control rod; acceleration sensors and angle sensors are configured on the bundling mechanical arm to measure the movement state and working angle of the mechanical arm; vibration sensors and sound sensors are installed on the cutting device to monitor the vibration frequency and noise characteristics during the cutting process; and optical sensors are used to measure the deformation of the strap during the bundling process. These data are transmitted to the data processing unit through an industrial-grade wireless communication network to form multi-source operation data. For example, the motor temperature sensor collects data once a second and records the motor surface temperature as 85°C. At the same time, the current sensor records the current waveform showing periodic fluctuations. The tension sensor detects that the belt tension is 450N, and the displacement sensor shows that the control rod displacement is 2.8mm. The acceleration sensor measures the acceleration of the robot arm as 0.5m / s², and the angle sensor measures the working angle as 75°. The vibration sensor detects that the vibration frequency of the cutting device is 120Hz, and the sound sensor records the noise decibel value as 78dB. The optical sensor measures the belt deformation rate as 0.15.

[0016] The purpose of filtering and segmenting multi-source operation data is to extract effective information. The noise and interference signals in the data are removed by the adaptive filtering algorithm to obtain a pure data stream. The adaptive filtering algorithm dynamically adjusts the filtering parameters according to the signal characteristics, such as smoothing the sudden interference in the motor temperature data. Then the pure data stream is divided into data segments according to the sliding window method with a width of 5 seconds and a 50% overlap rate to form segmented processing data. Accurate time tags are added to each data segment to construct a time-aligned data frame. Time domain features are extracted from the time-aligned data frame, including mean, peak, root mean square value, kurtosis and skewness. At the same time, the data frame is converted into the frequency domain to obtain the spectrum energy distribution and main frequency component information. The time domain feature quantity is fused with the frequency domain information to generate the state feature data of the belting machine with a timestamp. For example, after processing the motor temperature data, the average temperature of this period is 83.5℃, the peak is 87.2℃, the root mean square value is 84.1℃, the kurtosis of the temperature data is 2.3, the skewness is 0.5, and the frequency domain analysis shows that the main frequency component is concentrated in the low frequency band. The purpose of analyzing and comparing the operating status of the belting machine is to detect abnormal conditions in a timely manner. A normal operating benchmark parameter library of the belting machine is constructed from historical data, which contains the boundary values ​​of the standard characteristic distribution under various working conditions. Then, the difference between the state characteristic data of the belting machine and the corresponding data in the benchmark parameter library is calculated to obtain the characteristic deviation matrix. The abnormal weight coefficient is set according to the degree of deviation of each parameter in the characteristic deviation matrix to generate a comprehensive abnormal index. The threshold comparison is used to determine whether the comprehensive abnormal index exceeds the preset warning threshold, and the abnormal state identification of the belting machine is formed. The characteristic deviation matrix is ​​similarly matched according to the typical fault feature template of the belting machine to identify the target fault category. For example, when it is detected that the average motor temperature exceeds the upper limit of the normal range by 5°C, the high-frequency component in the current waveform increases, and the vibration sensor data shows abnormal vibration frequency, the system calculates the comprehensive abnormality index as 0.78, exceeding the warning threshold of 0.65, and identifies the motor bearing fault type through similarity matching.

[0017] The purpose of establishing a component association map of the strapping machine is to accurately locate the cause of the fault. The structural knowledge of the strapping machine is used to construct a component association map containing the physical connection and functional dependency between components. The abnormal component nodes are marked in the map according to the fault type judgment result. The abnormal signal transmission path is traced back in the map through the causal propagation algorithm, and the probability value of each related component as the root cause of the fault is calculated. The target fault component and its impact range are sorted to determine the fault cause location result. Based on the development law in historical similar fault cases, the fault location results are extrapolated in time series to construct a fault severity change curve. Combined with the fault severity change curve and the equipment safety threshold, the fault development time window and potential risk level are predicted. For example, when the motor bearing fault is identified, the system marks the motor bearing node as abnormal in the association map. The causal propagation algorithm calculates that the drive shaft and pulley connected to it are also affected, but the root cause of the fault is located at the bearing, with a probability value of 0.85, which is much higher than other components. Historical data shows that if this type of fault is not handled, it will develop into complete damage to the motor within 120 hours, and the predicted risk level is high.

[0018] The maintenance priority is calculated in combination with the belt machine maintenance database in order to scientifically arrange the maintenance work. The historical maintenance cases matching the fault cause location results are extracted from the maintenance database to construct a maintenance knowledge base set. The fault development trend is predicted according to the maintenance knowledge base set to obtain the fault development trend prediction value, and the fault risk index is calculated according to the fault development trend prediction value. The fault risk index is weighted and combined with the production task priority, spare parts inventory status and technician availability to generate a maintenance urgency index. The maintenance tasks are graded according to the maintenance urgency index to determine the maintenance operation level. The corresponding standard maintenance process is extracted according to the maintenance knowledge base set and the maintenance operation level to form a maintenance plan. The optimal maintenance time window is determined by combining the fault development trend prediction value with the production plan schedule, and an operation time recommendation is generated. For example, for the identified motor bearing fault, the system extracts similar cases from the maintenance database and calculates the fault risk index as 0.82. Considering that the current production plan urgency is medium, the spare parts inventory is sufficient, and the technicians are available on weekdays, the maintenance urgency index is generated as 0.75, which is determined as a secondary maintenance operation. It is recommended to replace the bearing within 48 hours and perform maintenance during the next weekend production gap.

[0019] The purpose of recording the deviation between the actual maintenance results and the prediction is to continuously optimize the monitoring system. The performance index data of the belting machine after the maintenance plan is implemented is collected through the sensor network to build a post-maintenance operation effect evaluation report. The post-maintenance operation effect evaluation report is compared and analyzed with the state before maintenance to calculate the maintenance effect improvement metric. The fault cause location results are compared with the fault source found in the actual maintenance, and the fault diagnosis accuracy evaluation data is recorded. According to the deviation in the fault diagnosis accuracy evaluation data, the feature threshold of the corresponding fault mode in the fault feature library of the belting machine is adjusted. According to the difference between the predicted value of the fault development trend and the actual fault development trajectory, the timing parameters in the prediction algorithm are updated. The maintenance effect improvement metric and the associated data of the maintenance plan are integrated and written into the maintenance knowledge parameter library to form an updated fault feature library and maintenance knowledge parameters. For example, after replacing the motor bearing, the temperature sensor shows that the motor temperature has fallen back to the normal range, the vibration frequency has returned to normal, and the comprehensive performance has increased by 90%. However, the actual maintenance found that the bearing is indeed the root cause of the fault, with a diagnostic accuracy of 95%, but the fault development speed is 15% slower than predicted. Therefore, the system adjusts the feature threshold of the motor bearing fault in the fault feature library and the timing parameters in the prediction algorithm accordingly, which improves the accuracy of future diagnosis.

[0020] In the embodiment of the present application, multi-source operating data of each key part of the strapping machine is collected through a sensor network, the data is processed in a refined manner, and a complete fault diagnosis and maintenance system is established, achieving significant technical effects. The multi-source operating data collection mechanism solves the problem of the limitations of single sensor information. The fusion of multi-dimensional data such as motor temperature data, tension control parameters, bundling robot arm displacement data, cutting device operating status, and strap deformation rate provides a comprehensive operating status portrait of the strapping machine, greatly improving the integrity and accuracy of monitoring; the data is filtered and segmented to obtain the strapping machine state feature data with timestamps, effectively eliminating the interference of environmental noise and irrelevant signals, and improving the reliability of feature extraction; based on the strapping machine state feature data, the operating status is analyzed and compared, and an artificial intelligence model with adaptive thresholds and multi-feature fusion is used. When determining the type of fault, the machine learning algorithm is combined with expert knowledge, which greatly reduces the probability of missed reports and false alarms; fourth, the establishment The cause of the fault is located by using the association map of the components of the vertical strapping machine, and a causal reasoning algorithm is introduced. This algorithm fully considers the physical connection and functional dependency between the components, making the fault location more accurate, and can predict the development trend of the fault in advance, providing a sufficient time window for maintenance decisions; fifthly, the maintenance priority is calculated in combination with the maintenance database to form a scientific maintenance plan and operation time recommendation. The three requirements of equipment safety, maintenance resources and production plan are balanced through a multi-objective optimization algorithm, reducing unplanned downtime; most importantly, the present invention establishes a complete knowledge feedback loop, by recording the actual maintenance results and predicted deviations, continuously updating the fault feature library and maintenance knowledge parameters, and the system's self-learning ability enables the accuracy of fault diagnosis to gradually improve with the use time. In the specific functional field of the belting machine, the present invention gives full play to the advantages of artificial intelligence technologies such as adaptive filtering algorithm, causal propagation algorithm and multi-objective optimization algorithm, especially the application of causal propagation algorithm in fault tracing, breaking through the limitation of traditional correlation analysis that it is difficult to identify the root cause of hidden faults, enabling the system to handle complex fault propagation chains, providing new technical ideas for industrial equipment fault diagnosis, and realizing the transformation of maintenance mode from passive response to active prevention, significantly extending the effective operation time of the belting machine, and improving production efficiency and product quality.

[0021] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Install temperature sensors and current sensors on the motor drive device of the strapping machine to collect the motor surface temperature and current waveform to obtain motor temperature data; (2) Arrange a tension sensor and a displacement sensor in the tension control mechanism of the strapping machine to record the tension change of the strapping machine and the displacement of the control rod to form the tension control parameters; (3) An acceleration sensor and an angle sensor are configured on the binding robot arm of the strapping machine to measure the motion state and working angle of the robot arm and generate displacement data of the binding robot arm; (4) Install vibration sensors and sound sensors on the cutting device of the strapping machine to monitor the vibration frequency and noise characteristics during the cutting process and generate the operating status of the cutting device; (5) Using an optical sensor to measure the deformation of the strap during the bundling process, the degree of deformation of the strap due to stress is calculated to obtain the strap deformation rate; (6) The motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status, and strap deformation rate are transmitted to the data processing unit through an industrial-grade wireless communication network to form multi-source operating data with corresponding time stamps.

[0022] Specifically, a temperature sensor and a current sensor are installed on the motor drive device of the strapping machine to collect the surface temperature and current waveform of the motor and obtain the motor temperature data. The motor drive device is the core power source of the strapping machine and is responsible for providing the power required for the operation of the strapping machine. The temperature sensor adopts the principle of thermocouple or thermistor, is directly attached to the surface of the motor, and regularly samples the surface temperature of the motor with a sampling frequency of 1 time per second; the current sensor is based on the Hall effect principle, is installed around the motor power line, and records the current change waveform when the motor is working in real time with a sampling frequency of 100 times per second. Through the coordinated use of these two sensors, a motor temperature data set containing temperature scalars and current vectors is formed to effectively reflect the working state of the motor. Tension sensors and displacement sensors are arranged in the tension control mechanism of the strapping machine to record the tension changes of the strapping machine and the displacement of the control rod to form tension control parameters. The tension control mechanism is a key component for adjusting the tightening force of the strapping machine and has a direct impact on the quality of the strapping. The tension sensor uses the principle of strain gauges and is fixed on the bearing seat of the tension adjustment wheel to measure the force of the tension wheel and then calculate the tension value of the strap. The sampling frequency is 20 times per second. The displacement sensor is based on the principle of linear variable differential transformer and is installed on the active part of the control rod to accurately measure the displacement change of the control rod during operation. The sampling frequency is 50 times per second. After the two sets of data are aligned in time, a parameter set reflecting the tension control state of the strapping machine is formed.

[0023] The binding robot arm of the strapping machine is equipped with an acceleration sensor and an angle sensor to measure the movement state and working angle of the robot arm and generate the displacement data of the binding robot arm. The binding robot arm is an actuator that realizes the wrapping and fixing of the strap, and its movement accuracy and stability directly affect the binding effect. The acceleration sensor is based on the principle of piezoelectric effect and is installed at the joint of the robot arm. The three axes simultaneously collect the acceleration of the robot arm movement with a sampling frequency of 200 times per second. The angle sensor adopts the principle of photoelectric encoder and is installed on the shaft of the robot arm to monitor the rotation angle of the robot arm in real time with an accuracy of 0.1 degrees and a sampling frequency of 100 times per second. Through the integral operation of acceleration data and combined with angle data, a complete three-dimensional motion trajectory model of the robot arm is constructed.

[0024] Vibration sensors and sound sensors are installed on the cutting device of the strapping machine to monitor the vibration frequency and noise characteristics during the cutting process and generate data on the operating status of the cutting device. The cutting device is responsible for cutting the straps after they are tied, and its working status affects the quality of the strap cuts. The vibration sensor is based on the principle of piezoelectric effect and is directly fixed on the base of the cutting mechanism to collect vibration signals during the cutting process. The frequency response range is 0-1000Hz and the sampling frequency is 1000 times per second. The sound sensor uses the principle of a capacitive microphone and is installed near the cutting area to record the sound characteristics generated during the cutting process. The frequency response range is 20Hz-20kHz and the sampling frequency is 8000 times per second. After spectral analysis, the vibration data and sound data form a feature vector that reflects the working status of the cutting device.

[0025] The deformation of the strap during the bundling process is measured by an optical sensor, the degree of deformation of the strap due to stress is calculated, and the strap deformation rate is obtained. The optical sensor uses the principle of laser ranging, is installed on a fixed bracket, and is irradiated vertically on the strap surface to measure the thickness change of the strap before and after stress is applied. The sampling frequency is 50 times per second. The strap deformation rate calculation formula is as follows:

[0026] in, represents the deformation rate of the strap, Indicates the initial thickness of the strap (mm), Indicates the thickness of the strap under stress (mm). represents the compensation factor of the strap material (dimensionless), represents the elastic characteristic parameter of the strap, Represents the tension acting on the strap. Convert the thickness change data into a deformation rate indicator that reflects the material properties and actual usage status of the strap. Transmit the motor temperature data, tension control parameters, bundling robot arm displacement data, cutting device operating status and strap deformation rate to the data processing unit through the industrial wireless communication network to form multi-source operating data with corresponding time stamps. The industrial wireless communication network adopts industrial Internet of Things protocols, such as MQTT or OPC UA, to ensure the reliability and real-time performance of data transmission. After receiving the scattered sensor data, the data processing unit performs time synchronization processing and adds a unified timestamp mark to each set of data with a time accuracy of milliseconds; then the data format is unified and different types of sensor data are converted into a standard format; a multidimensional data matrix is ​​created, in which each row represents the complete state at a time point and each column represents the specific parameters of different sensors.

[0027] For example: after the strapping machine is started, the motor temperature gradually rises from the normal temperature of 25℃, and stabilizes at 78℃ after 10 minutes. At the same time, the current sensor records that the motor working current fluctuates between 4.8A-5.2A, and the waveform shows typical periodic characteristics; the tension sensor measures that the strap tension is stable at 420N, and the displacement sensor records that the control rod displacement gradually increases from 0mm to 2.5mm during the adjustment process and then remains stable; the acceleration sensor measures that the acceleration of the mechanical arm reaches 0.6m / s² at the beginning of the bundling action, and the angle sensor records that the mechanical arm rotates from the initial position 0° to the working position 85°; the vibration sensor detects a vibration signal with a peak frequency of 150Hz at the moment of cutting, and the sound sensor records 75dB of noise; the optical sensor measures that the initial thickness of the strap is 0.8mm, which is compressed to 0.68mm under the tension of 420N. Substituting it into the formula, the deformation rate of the strap is 0.15, which is within the normal range. These data are transmitted to the data processing unit in real time through the industrial wireless network, forming a complete multi-source operation data matrix, providing a basis for subsequent fault analysis. In the data matrix, a complete status record is generated every 100ms, including all sensor readings at the current moment, and is accompanied by a precise timestamp, such as "2024-10-15 14:30:25.700", which facilitates time series comparison and correlation analysis in subsequent analysis.

[0028] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Use adaptive filtering algorithms to remove noise and interference signals from multi-source operating data to obtain pure data streams; (2) Divide the pure data stream into data segments using a sliding window method with a width of 5 seconds and an overlap rate of 50% to form segmented processing data; (3) The time synchronization mechanism adds precise time tags to the segmented processed data and constructs time-aligned data frames; (4) Extracting time domain features including mean, peak, root mean square value, kurtosis and skewness from the time-aligned data frame through time domain analysis method; (5) Perform frequency domain conversion on the time-aligned data frame to obtain spectrum energy distribution and main frequency component information; (6) The time domain feature quantity is fused with the spectrum energy distribution and the main frequency component information to generate the belt machine state feature data with a timestamp.

[0029] Specifically, the noise and interference signals in the multi-source operation data are eliminated by an adaptive filtering algorithm to obtain a pure data stream. The adaptive filtering algorithm is a signal processing method that can dynamically adjust the filtering parameters according to the signal characteristics. The specific implementation adopts the minimum mean square error (LMS) adaptive filter. The filter has a good suppression effect on the sudden interference in the temperature data of the strapping machine motor, the high-frequency jitter in the tension control parameters, the random fluctuation in the displacement data of the strapping robot arm, the environmental noise in the vibration signal of the cutting device, and the optical interference in the measurement of the strap deformation rate. The filtering process estimates the noise characteristics in the signal, and then automatically adjusts the filter coefficient according to the characteristic difference between the noise and the useful signal to achieve accurate noise elimination. For different types of sensor data, the filter parameters are automatically adjusted. For example, for slowly changing signals such as motor temperature, a narrower passband is used; for rapidly changing signals such as robot arm displacement, a wider passband is used to ensure that the filtered data not only removes interference but also retains the effective information of the original signal. The pure data stream is divided into data segments according to a sliding window method with a width of 5 seconds and a 50% overlap rate to form segmented processing data. Sliding window is a technology that divides continuous time series data into multiple overlapping segments. A window width of 5 seconds means that each data segment contains 5 seconds of continuous data, and a 50% overlap rate means that two adjacent windows share half of the data points. The selection of 5 seconds as the window width is based on the working cycle characteristics of the strapping machine. Generally, a single strapping operation cycle is between 3-8 seconds, and a 5-second window can fully capture most of the operating characteristics; and a 50% overlap rate ensures the continuity of the data and avoids the problem of information loss at the window boundary. In specific implementation, if the sensor sampling frequency is 100Hz, each 5-second window contains 500 data points, and 250 data points are shared between adjacent windows. This division method not only ensures the locality of data analysis, but also maintains the continuity of the signal, which is suitable for capturing the state change characteristics of the strapping machine during operation.

[0030] The time synchronization mechanism adds precise time tags to the segmented processed data to construct a time-aligned data frame. The time synchronization mechanism solves the inconsistency problem of multi-source heterogeneous sensor data in the time dimension. The Network Time Protocol (NTP) is used to ensure that all sensor nodes are clock synchronized, and the error is controlled at the millisecond level; then the divided data segments are time-stamped, and the start time and end time of each window are recorded; through time interpolation and resampling technology, sensor data with different sampling rates are aligned to a unified time scale. For example, the sampling rate of the motor temperature sensor is 1Hz, while the sampling rate of the vibration sensor is 1000Hz. The time synchronization mechanism will linearly interpolate the motor temperature data to create a temperature estimate consistent with the time point of the vibration data, ensuring the precise correspondence between different types of data in the data frame in time. The time domain feature quantities including mean, peak, root mean square value, kurtosis and skewness are extracted from the time-aligned data frame through the time domain analysis method. The time domain feature quantity is a statistical indicator that reflects the time distribution characteristics of the signal, which is of great significance for the fault diagnosis of the belting machine. The mean value calculates the average value of all sampling points in the data segment, reflecting the concentration trend of the signal; the peak value extracts the maximum absolute value in the data segment, reflecting the extreme value characteristics of the signal; the root mean square value calculates the mean of the sum of squares of the data points and then takes the square root, reflecting the energy level of the signal; the kurtosis measures the sharpness of the data distribution, and the kurtosis value under normal working conditions is usually close to 3, and it will deviate significantly under abnormal conditions; the skewness measures the asymmetry of the data distribution, reflecting the tilt characteristics of the signal waveform. These time domain feature quantities together constitute the feature vector that describes the statistical characteristics of the data segment, which can effectively distinguish different working conditions and failure modes of the strapping machine.

[0031] The time-aligned data frame is transformed into the frequency domain to obtain the spectrum energy distribution and main frequency component information. Frequency domain analysis converts the time domain signal into a frequency domain representation through fast Fourier transform (FFT) to reveal the frequency composition of the signal. For the banding machine, different components will show different spectrum characteristics under normal working and fault conditions. For example, the motor bearing fault will produce abnormal resonance peaks at a specific frequency. The frequency domain conversion applies the Hanning window function to the data segment to reduce spectrum leakage, and then performs FFT operation to obtain the complex spectrum. The power spectral density (PSD) is calculated to obtain the distribution of signal energy at each frequency. The total energy, the energy ratio of each frequency band, the main frequency point and its amplitude are extracted from the PSD. These features are particularly important for identifying the periodic faults and harmonic characteristics of the banding machine. The time domain feature quantity is fused with the spectrum energy distribution and the main frequency component information to generate the banding machine state feature data with timestamp. Feature fusion is the process of integrating features of different dimensions and scales into a unified representation. The feature-level fusion strategy is used to splice the time domain feature vector and the frequency domain feature vector into a high-dimensional feature vector. At the same time, feature normalization is performed to ensure that the weights of features of different dimensions are balanced during the fusion process. The fused feature data retains the timestamp information of the original window, which is convenient for subsequent timing analysis and fault tracing. The generated state feature data of the belting machine is a multidimensional time series data set, and each record contains a complete state feature description of the belting machine within a time window.

[0032] For example, when the strapping machine is performing the bundling task, the vibration sensor detects that the cutting device has abnormal vibration. The original vibration signal is mixed with environmental noise. After processing by the adaptive filtering algorithm, the 50Hz power supply interference and random white noise are successfully filtered out, and the vibration characteristics of the equipment itself are retained. The filtered 5-second data is divided into sliding windows, and a new data segment is formed every 2.5 seconds, and adjacent data segments share half of the data. Add an accurate time stamp to each data segment, such as "2024-10-15 14:30:25.500-14:30:30.500". Through time domain analysis and calculation, the mean value of the vibration signal is close to 0, the peak value is 2.8g, the root mean square value is 0.9g, the kurtosis value is 4.2 (higher than the normal value of 3, indicating the presence of impact components), and the skewness is 0.3 (slightly right-biased). FFT analysis of the data segment shows that there is an obvious frequency peak at 150Hz, and the energy is 3 times the fundamental frequency, which is significantly different from the spectrum characteristics under normal conditions. After fusing these time domain features with frequency domain features, a state feature vector containing 25 feature quantities is formed, along with the precise timestamp of the time window. By comparing with historical data, this feature combination highly matches the failure mode of cutting tool wear.

[0033] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Construct a normal operation benchmark parameter library of the belt conveyor from historical data, which includes the standard characteristic distribution boundary values ​​under various working conditions; (2) Calculate the difference between the state characteristic data of the strapping machine and the corresponding data in the normal operation benchmark parameter library of the strapping machine to obtain the characteristic deviation matrix; (3) The anomaly weight coefficient is set according to the degree of deviation of each parameter in the characteristic deviation matrix to generate a comprehensive anomaly index; (4) Using the threshold comparison method to determine whether the comprehensive abnormality index exceeds the preset warning threshold, forming an abnormal state indicator of the banding machine; (5) Perform similarity matching on the feature deviation matrix according to the typical fault feature template of the strapping machine to identify the target fault category; (6) The abnormal state identification of the strapping machine and the target fault category are combined to form the abnormal state identification of the strapping machine and the fault type determination result.

[0034] Specifically, a normal operating benchmark parameter library of the strapping machine is constructed from historical data, which contains the standard characteristic distribution boundary values ​​under various working conditions. The normal operating benchmark parameter library is a set of characteristic data of the normal operating state of the strapping machine under different working conditions, which is constructed by data collection and statistical analysis of the strapping machine that has been operating stably for a long time. The specific construction process includes: collecting data of the strapping machine that has been operating without fault for at least 30 consecutive days; classifying the data according to different working loads (light load, medium load, heavy load), different types of binding materials (plastic straps, metal straps) and different operating speeds (low speed, medium speed, high speed) and other working condition dimensions; calculating the statistical distribution characteristics of each characteristic parameter (such as motor temperature, vibration spectrum, tension parameters, etc.) under each type of working condition, including mean, standard deviation, maximum value, minimum value; determining the normal fluctuation range of each characteristic parameter according to the 3σ principle to form the standard characteristic distribution boundary value. The obtained benchmark parameter library is a multidimensional lookup table that can quickly locate the corresponding normal parameter range according to the current working condition. The difference between the state characteristic data of the strapping machine and the corresponding data in the normal operating benchmark parameter library of the strapping machine is calculated to obtain the characteristic deviation matrix. The feature deviation matrix is ​​a quantitative representation of the degree to which the current operating state of the strapping machine deviates from the normal state. The difference calculation retrieves the corresponding standard feature distribution boundary value from the benchmark parameter library according to the current working conditions of the strapping machine (such as the type of strap being processed, the current load, etc.); then calculates the normalized deviation between the current feature data and the standard value, that is, the actual value of each feature parameter minus the corresponding standard mean, and then divides it by the standard deviation to obtain the standardized deviation value; the standardized deviation values ​​of all feature parameters are organized into a matrix form, with rows representing different time windows and columns representing different feature parameters. The feature deviation matrix intuitively reflects the degree to which each parameter deviates from the normal state at each time point, providing a basis for anomaly detection.

[0035] The abnormal weight coefficient is set according to the degree of deviation of each parameter in the characteristic deviation matrix to generate a comprehensive abnormality index. Different characteristic parameters contribute differently to fault identification, so different weights need to be assigned. The abnormal weight coefficient setting specifies a basic weight for each characteristic parameter based on expert experience, reflecting its importance to fault indication; then an adaptive mechanism is introduced to dynamically adjust the weight according to the sensitivity of each parameter in the historical fault data; combined with the nonlinear mapping of the current deviation degree, parameters with severe deviations are given higher weights. The comprehensive abnormality index is the weighted sum of each element in the characteristic deviation matrix multiplied by the corresponding abnormal weight coefficient. It is a scalar between 0 and 1. The closer the value is to 1, the more severe the abnormality.

[0036] Determine whether the comprehensive abnormality index exceeds the preset warning threshold and form an abnormal state identification of the belt machine. Threshold comparison is a binary classification decision method. It determines whether the current state is normal or abnormal based on the size relationship between the comprehensive abnormality index and the preset threshold. The setting of the warning threshold adopts a graded strategy, including three levels: attention level (0.6), warning level (0.75) and danger level (0.85). When comparing the thresholds, the calculated comprehensive abnormality index is compared with these preset thresholds one by one to determine the warning level of the current state; if the comprehensive abnormality index is lower than the minimum threshold, it is judged to be a normal state; if it exceeds a certain threshold, an abnormal state identification of the corresponding level is formed, including information such as abnormality level, occurrence time, and parameters involved.

[0037] According to the typical fault feature template of the strapping machine, the feature deviation matrix is ​​matched for similarity to identify the target fault category. The fault feature template is a set of feature deviation patterns of various known faults, which is obtained through learning from historical fault cases. The similarity matching adopts the cosine similarity calculation method to calculate the similarity between the current feature deviation matrix and each fault template. The formula is as follows:

[0038] in, represents the fault similarity, represents the deviation value of the jth feature in the i-th time window in the feature deviation matrix, represents the corresponding feature deviation value in the k-th fault template, Indicates the number of time windows, represents the number of characteristic parameters, represents the weight coefficient of the pth key feature, A flag indicating whether feature j is a key indicator feature in fault type k (1 for yes, 0 for no), Represents the total number of key features. Not only the similarity of the overall deviation pattern is considered, but also the key indicative features of the fault type are particularly emphasized, which improves the accuracy of identification. After the similarity calculation is completed, the fault type with the highest similarity and exceeding the threshold of 0.8 is selected as the target fault category. If all similarities are lower than the threshold, it is marked as "unknown fault type". The abnormal state identification of the strapping machine is combined with the target fault category to form the abnormal state identification of the strapping machine and the fault type determination result. This is the process of integrating the results of the two subtasks of anomaly detection and fault classification into output. The combination method adopts a structured data format, which includes the following fields: abnormal state identification (normal / caution / warning / danger), abnormal occurrence time, abnormal duration, target fault category, similarity score, main abnormal parameters involved and their deviation values, and recommended processing priority.

[0039] For example, during the operation of a certain strapping machine, the data processing unit receives the preprocessed state feature data. By comparing with the normal operation benchmark parameter library, it is found that the current working condition is "medium load, plastic strap, medium speed", and the standard parameter boundary value under this working condition is extracted from the library. Then the difference between the current feature and the standard value is calculated to obtain the feature deviation matrix. Among them, the motor temperature deviation is +2.3σ (indicating that it exceeds the normal average value by 2.3 standard deviations), the energy deviation of the cutting device vibration spectrum at 150Hz is +4.1σ, the noise characteristic deviation is +2.8σ, and the tension control parameter and the strap deformation rate deviation are both within 1σ. According to the preset weight coefficients (vibration spectrum 0.35, noise characteristics 0.25, motor temperature 0.2, tension parameter 0.1, deformation rate 0.1), the comprehensive abnormality index is calculated to be 0.82, which exceeds the warning level threshold of 0.75. Then, the feature deviation matrix is ​​matched with each template in the fault feature template library for similarity matching calculation, and the similarity with the "cutting tool wear" template is 0.91, which is much higher than other fault types (such as "motor bearing fault" 0.43, "tension control imbalance" 0.38, etc.). The judgment result is: warning level abnormal state, occurrence time 2024-10-15 14:35:22, duration 8 minutes, target fault category is cutting tool wear, similarity 0.91, main abnormal parameters are 150Hz vibration spectrum (+4.1σ) and noise characteristics (+2.8σ), recommended processing priority is medium, it is recommended to arrange maintenance within 24 hours.

[0040] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Using the structural knowledge of the strapping machine, a component association graph of the strapping machine is constructed, which includes the physical connections and functional dependencies between the components. (2) Mark the abnormal component nodes in the belt machine component association map according to the fault type determination result; (3) Using the causal propagation algorithm, the abnormal signal transmission path is traced back in the belting machine component association map, and the probability value of each related component as the root cause of the fault is calculated; (4) Determine the target faulty component and its impact range by sorting the probability values, and generate the fault cause location result; (5) Based on the development patterns of similar historical fault cases, the fault cause location results are extrapolated in time series to construct a fault severity change curve; (6) Combine the fault severity change curve with the equipment safety threshold to predict the fault development time window and potential risk level, and form a predicted value for the fault development trend.

[0041] Specifically, the structural knowledge of the strapping machine is used to construct a component association graph of the strapping machine, which contains the physical connection and functional dependency between components. The component association graph is a network model that describes the internal structure and functional relationship of the strapping machine. It is represented by a directed graph, in which nodes represent the physical components of the strapping machine (such as motors, transmission shafts, tension controllers, cutting devices, etc.), and edges represent the relationship between components. The relationship types include physical connection relationships (such as component A is directly connected to component B) and functional dependency relationships (such as the function of component C depends on the normal operation of component D). The graph construction process includes: analyzing the structural drawings of the strapping machine, identifying all key components and setting them as nodes; determining the physical connection relationship between components and establishing connection edges; analyzing the working mechanism between components, determining the functional dependency relationship, and establishing dependency edges; assigning a transfer coefficient to each edge, indicating the attenuation degree of the fault signal transmitted from one component to another. The formed component association graph contains about 30 nodes and 60 directed edges, which fully describes the structural topology and functional hierarchy inside the strapping machine. According to the fault type judgment result, the abnormal component nodes are marked in the component association graph of the strapping machine. The process of mapping the fault type determination results to the component association map. According to the correspondence table between fault types and components, determine the components directly related to the current fault type, and mark these component nodes as abnormal nodes in the map. When marking, assign an initial abnormal strength value to each abnormal node, which is determined based on the similarity score of the fault type determination and the association between the component and the fault type. For example, for the "cutting tool wear" fault type, the cutting tool node is marked as abnormal and assigned an initial abnormal strength value of 0.91 based on the previously obtained 0.91 similarity.

[0042] The causal propagation algorithm is used to reversely trace the abnormal signal transmission path in the associated graph of the belting machine components, and the probability value of each related component as the root cause of the fault is calculated. The causal propagation algorithm is a calculation method for analyzing signal transmission and influence range in a network structure. In this scheme, an improved belief propagation algorithm is used. Starting from the marked abnormal node, the algorithm propagates backward along the edges in the graph to calculate the probability that the upstream node associated with the abnormal node is the root cause of the fault; then considering the convergence effect of multiple paths, for components with multiple downstream abnormal nodes, the probability of failure is higher; through multiple rounds of iterative calculations, it stops when the probability value change of each node is less than the threshold or reaches the maximum number of iterations. In the specific calculation, the failure probability of each node is affected by the weighted influence of all its downstream abnormal nodes, and the weight is determined by the transmission coefficient and path length of the connecting edge.

[0043] The target faulty component and its impact range are determined by sorting the probability values, and the fault cause location results are generated. In this step, the fault probability values ​​of each component calculated by the causal propagation algorithm are sorted in descending order to identify the most likely root cause of the fault. According to the sorting results, the component with the highest probability value is selected as the target faulty component; at the same time, the impact range of the component is determined based on the graph structure, including all downstream components that may be affected by the fault. The generated fault cause location results contain the target faulty component information, fault probability values, impact range list, and causal chain description between the fault and the observed anomaly. Based on the development laws in historical similar fault cases, the fault cause location results are extrapolated in time series to construct a fault severity change curve. In this step, similar fault cases recorded in the historical fault database are used to analyze the time laws of fault development. Retrieve historical cases that match the current target fault component and fault type from the database; then extract the data points of the fault severity changes over time in these cases; then use nonlinear regression methods to fit the mathematical model of fault development, commonly used models include exponential growth model, Weibull model or polynomial model; substitute the current fault severity value into the model, perform time series extrapolation calculation, predict the change trend of fault severity in the future, and form a fault severity change curve. This curve uses time as the horizontal axis and fault severity as the vertical axis to intuitively show the development speed and trend of the fault.

[0044] Combined with the fault severity change curve and the equipment safety threshold, the fault development time window and potential risk level are predicted to form a fault development trend prediction value. The equipment safety threshold refers to the safe operating limit of each component of the belting machine at different severities. Exceeding this limit will lead to equipment performance degradation, functional failure or safety accidents. The prediction process marks different levels of safety threshold lines on the fault severity change curve; then calculates the intersection of the curve and each threshold line to obtain the estimated time for the fault to develop to each severity; then comprehensively evaluates the potential risk level based on time urgency and consequence severity; and forms a fault development trend prediction value that includes the fault development time window, potential risk level, estimated impact and recommended processing time limit.

[0045] For example, a certain belt machine was detected with a "cutting tool wear" fault, with a similarity of 0.91. The cutting tool node was marked as abnormal in the component association map, with an initial abnormal strength of 0.91. The causal propagation algorithm was used to trace back and calculate the fault probability values ​​of all related components: the cutting tool itself was 0.91, the tool drive motor was 0.75, the control circuit was 0.45, the transmission shaft was 0.68, and the connecting bolt was 0.72. After sorting, the cutting tool was determined to be the most likely source of the fault, and its impact range included cutting quality, cutting noise, and the end treatment effect of the belt. 15 similar cases of tool wear were retrieved from the historical database, and the change law of fault severity over time in these cases was analyzed, and it was found to conform to the exponential growth model. According to the initial severity of the current fault and the historical development law, the fault severity change curve in the next 7 days was predicted. The equipment safety threshold is divided into three levels: attention level (0.6), warning level (0.8) and danger level (0.95). By comparing the safety threshold with the change curve, it is predicted that the fault will reach the warning level in 3 days and the danger level in 7 days. If not handled, it will lead to cutting failure and possible safety risks. The predicted value of the fault development trend is: Faulty component - cutting tool, current severity - 0.5, expected to reach the warning level in 3 days, reach the danger level in 7 days, it is recommended to arrange to replace the tool within 3 days, potential risk level - medium, expected impact - reduction in the quality of the strap cutting and possible cutting failure. This prediction result provides a clear time window and priority basis for maintenance decisions.

[0046] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Extract historical maintenance cases that match the fault cause location results from the belt machine maintenance database to build a basic set of maintenance knowledge; (2) Predict the fault development trend based on the maintenance knowledge base set, obtain the fault development trend prediction value, and calculate the fault risk index according to the fault development trend prediction value; (3) The failure risk index is weighted and combined with the production task priority, spare parts inventory status, and technician availability to generate a maintenance urgency index; (4) Classify maintenance tasks by maintenance urgency index and determine the maintenance operation level; (5) Extract the corresponding standard maintenance process based on the maintenance knowledge base set and maintenance operation level to form a maintenance plan; (6) Combine the predicted value of fault development trend with the production plan to determine the optimal maintenance time window and generate operation time recommendations.

[0047] Specifically, historical maintenance cases matching the fault cause location results are extracted from the belt machine maintenance database to construct a maintenance knowledge base set. The maintenance database is a structured data warehouse that records historical fault maintenance experience, containing information such as fault type, maintenance method, required resources, and maintenance effect. The extraction process uses case reasoning technology to retrieve similar historical cases based on the characteristic parameters of the current fault (faulty component, fault type, fault severity, operating environment, etc.). The similarity calculation comprehensively considers the matching degree of fault components, fault type matching degree, fault symptom similarity, and operating environment similarity, and uses the weighted summation method to obtain the comprehensive similarity. Historical cases with similarity exceeding the preset threshold (generally 0.75) are selected to form a maintenance knowledge base set. Each case in the base set contains key information such as fault description, maintenance method, required tools and spare parts, maintenance time, and maintenance effect evaluation. The fault development trend is predicted based on the maintenance knowledge base set to obtain the fault development trend prediction value, and the fault risk index is calculated according to the fault development trend prediction value. The fault development trend prediction is based on the time series data of fault development in historical cases. A mathematical model is established through regression analysis to predict the development trajectory of the current fault. The prediction model adopts a hybrid prediction method, and its calculation formula is as follows:

[0048] in, represents the failure risk index, represents the fault development rate in the i-th historical case, Indicates the current time. represents the time of the i-th historical case, represents the time decay coefficient, n represents the number of historical cases, Indicates the current fault severity. Indicates the maximum fault severity, It indicates the time required for the predicted fault to develop to a critical state. represents the time urgency coefficient, , , Represents the weight coefficient of each factor and satisfies + + = 1. This formula takes into account the weighted average of the historical case development rate (taking into account time decay), the current fault severity, and the time urgency of the fault development, and generates a risk index value between 0 and 1. The larger the value, the higher the risk.

[0049] The failure risk index is combined with the production task priority, spare parts inventory status and technician availability to generate the maintenance urgency index. The production task priority reflects the importance of the current strapping machine in the production plan, which is usually provided by the production management system and is divided into five levels (from 1 to 5). The spare parts inventory status indicates the inventory of parts required for maintenance, including information such as inventory quantity and procurement cycle. The technician availability describes the current workload and schedulability of personnel with corresponding maintenance skills. The weighted combination adopts a multi-factor evaluation model to consider the degree of influence of each factor on the maintenance decision and generate a comprehensive maintenance urgency index. The index is a value between 0 and 100, which intuitively reflects the urgency of the maintenance task. The maintenance tasks are graded by the maintenance urgency index to determine the maintenance operation level. The maintenance operation level is a classification of the urgency and handling methods of the maintenance task, which is generally divided into four levels: level 1 (emergency maintenance), level 2 (planned maintenance), level 3 (observation maintenance) and level 4 (routine maintenance). The grading process adopts a threshold segmentation method to determine the corresponding maintenance operation level according to the numerical range of the maintenance urgency index. Generally speaking, index values ​​of 90-100 correspond to level 1 maintenance, 70-89 correspond to level 2 maintenance, 50-69 correspond to level 3 maintenance, and 0-49 correspond to level 4 maintenance. Maintenance operations at different levels have different response time requirements and resource allocation strategies. According to the maintenance knowledge base set and the maintenance operation level, the corresponding standard maintenance process is extracted to form a maintenance plan. The standard maintenance process is a preset operating procedure for a specific fault type and maintenance level, which includes maintenance steps, required tools and spare parts, safety precautions, etc. The extraction process selects the maintenance case that best matches the current fault type from the maintenance knowledge base set; then selects the corresponding processing flow template according to the maintenance operation level; and then integrates the specific maintenance steps in the historical cases and the current maintenance requirements to form a customized maintenance plan. The generated maintenance plan is a structured document that describes in detail all the operating steps and resource requirements from preparation to completion acceptance.

[0050] Combine the fault development trend prediction value with the production plan arrangement to determine the best maintenance time window and generate operation time recommendations. The best maintenance time window is the time period with the least impact on production under the premise of ensuring the safe operation of the equipment. The determination process calculates the time point when the fault develops to each danger level based on the fault development trend prediction value, and determines the latest execution time of maintenance; then obtains the recent production task arrangement of the belting machine from the production plan management system, identifies the production idle period or low-load period; comprehensively considers the time required for maintenance operation, the available time period of technicians and the time when spare parts arrive, and selects the time period with the least impact on production within the safe time limit as the recommended maintenance time window. The generated operation time recommendation includes the recommended start time, estimated completion time, production impact assessment and scheduling recommendation.

[0051] For example, a certain strapping machine was diagnosed with a cutting tool wear fault, and the cause of the fault was determined to be severe wear of the cutting tool itself. Relevant cases were retrieved from the maintenance database, and 15 similar cutting tool wear cases were found, of which 12 cases had a similarity of more than 0.8, including key information such as maintenance methods, required spare parts, and average maintenance time, forming a basic set of maintenance knowledge. Based on the data of these historical cases, the above formula was used to calculate the failure risk index of 0.78. Currently, the strapping machine is responsible for the production of high-value products, and the production task priority is 4 (out of 5); the inventory of cutting tool spare parts required for maintenance is sufficient (10 pieces in stock, with an average daily consumption of 0.5 pieces); and the workload of technicians with corresponding maintenance skills is moderate in the next three days. Combining these factors, the maintenance urgency index is calculated to be 82, corresponding to the second-level maintenance operation level (planned maintenance). The standard maintenance process for cutting tool replacement is extracted from the maintenance knowledge base, forming a maintenance plan with 6 main steps including equipment shutdown, safety lock, removal of old tool, installation of new tool, adjustment of cutting parameters, and test verification, which is expected to take 2 hours to complete. According to the prediction of fault development, the cutting tool will reach the warning level in 3 days and the danger level in 7 days; the production plan is checked and it is found that there will be a 4-hour production switching gap the day after tomorrow. Taking all factors into consideration, the operation time recommendation is generated as follows: it is recommended to perform maintenance during the production switching gap (10:00-14:00) the day after tomorrow morning. The maintenance time is expected to be 2 hours, and the impact on production is controllable. It is recommended to notify the production department in advance to prepare for the connection.

[0052] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) Collect the performance indicator data of the belting machine after the maintenance plan is implemented through the sensor network, and build a post-maintenance operation effect evaluation report; (2) Compare and analyze the post-maintenance operation effect evaluation report with the pre-maintenance status and calculate the maintenance effect improvement metric; (3) Compare the fault cause location results with the fault sources found during actual maintenance, and record the fault diagnosis accuracy evaluation data; (4) According to the deviation in the fault diagnosis accuracy evaluation data, adjust the characteristic threshold of the corresponding fault mode in the fault feature library of the strapping machine; (5) Update the timing parameters in the prediction algorithm based on the difference between the predicted value of the fault development trend and the actual fault development trajectory; (6) The maintenance effect improvement measurement value and the associated data of the maintenance plan are integrated and written into the maintenance knowledge parameter library to form an updated belt machine fault feature library and maintenance knowledge parameters.

[0053] Specifically, the sensor network is used to collect the performance index data of the strapping machine after the maintenance plan is implemented, and a post-maintenance operation effect evaluation report is constructed. The post-maintenance data collection uses the same sensor network as the initial monitoring process, including motor temperature sensors, tension sensors, acceleration sensors, vibration sensors, and optical sensors. Data collection starts immediately after the maintenance is completed and lasts for at least 24 hours to ensure that various working conditions of the strapping machine are covered. The collected raw data undergoes the same filtering, segmentation, and feature extraction processes as the initial monitoring to form a standardized performance index data set. The performance indicators include key parameters such as motor temperature stability, tension control accuracy, robot arm movement smoothness, cutting vibration spectrum characteristics, and strap deformation consistency. These indicator data are organized in a unified format to form a structured post-maintenance operation effect evaluation report, which contains the numerical values, time series change trends, and statistical characteristics of each performance indicator. The post-maintenance operation effect evaluation report is compared and analyzed with the state before maintenance, and the maintenance effect improvement metric is calculated. The comparative analysis uses the parameter difference method to compare each performance indicator before and after maintenance one by one, and calculate the relative change and absolute change. The relative change indicates the percentage of improvement in the indicator, and the absolute change indicates the actual change in the indicator. For each performance indicator, a standardized improvement index is calculated to unify the indicators of various dimensions into the range of 0-1. Then, the improvement index of each indicator is weighted and averaged according to its importance to form a comprehensive maintenance effect improvement measurement value. This measurement value intuitively reflects the degree of improvement of the overall performance of the belting machine by the maintenance activities. The value range is 0-1, and the closer the value is to 1, the more significant the improvement effect is.

[0054] Compare the fault cause location results with the fault sources found in actual maintenance, and record the fault diagnosis accuracy evaluation data. Maintenance personnel will find the actual fault source during the implementation of the maintenance plan. These findings are recorded in detail through the maintenance record form, including the faulty component, fault type, fault severity and possible fault causes. The accuracy of the diagnosis is evaluated by comparing the fault cause location results given by the automatic diagnosis system with the fault source actually found by the maintenance personnel. The evaluation indicators include: target fault component matching (the consistency between the fault component automatically diagnosed and the actual fault component), fault type matching (the consistency between the fault type automatically diagnosed and the actual fault type) and fault severity estimation deviation (the difference between the predicted severity and the actual severity). These matching and deviation values ​​constitute the fault diagnosis accuracy evaluation data. According to the deviation in the fault diagnosis accuracy evaluation data, adjust the feature threshold of the corresponding fault mode in the fault feature library of the strapping machine. The fault feature library is a set of feature templates for fault identification, and each fault mode has a corresponding feature threshold setting. The adjustment process adopts an incremental learning strategy to fine-tune the feature threshold according to the deviation of the current diagnosis. In the case of misdiagnosis, analyze the key characteristic parameters that lead to misdiagnosis and adjust their weights and threshold ranges appropriately; in the case of missed diagnosis, enhance the sensitivity of relevant characteristic parameters and expand the coverage of characteristic thresholds; in the case of correct diagnosis but biased severity estimation, correct the coefficients in the severity assessment model. The adjusted characteristic thresholds will be immediately updated to the fault feature library for the next fault diagnosis.

[0055] According to the difference between the predicted value of the fault development trend and the actual fault development trajectory, the timing parameters in the prediction algorithm are updated. The fault development trend prediction algorithm contains multiple timing parameters, such as development rate coefficient, environmental impact factor, load adjustment coefficient, etc. The prediction deviation is calculated by comparing the predicted fault development trend with the actual fault development observed during the maintenance process. Deviation analysis includes: development speed deviation (difference between predicted speed and actual speed), inflection point time deviation (time difference between predicted inflection point and actual inflection point) and severity deviation (difference between predicted severity and actual severity). According to these deviations, the gradient descent method is used to iteratively optimize the timing parameters in the prediction algorithm to reduce the prediction error. The optimization process will take into account the historical correction records to avoid excessive adjustments caused by a single sample, ensuring that the stability and accuracy of the prediction model are gradually improved. The maintenance effect improvement metric and the associated data of the maintenance plan are integrated and written into the maintenance knowledge parameter library to form an updated belt machine fault feature library and maintenance knowledge parameters. The maintenance knowledge parameter library is a structured database that stores maintenance experience and best practices to guide future maintenance decisions. The integration process associates the key information of the current maintenance case (fault type, maintenance method, resources used, maintenance time, etc.) with the maintenance effect improvement metric to form a complete maintenance record; then, the effectiveness level of the maintenance plan is marked according to the maintenance effect; then, the integrated data is written into the maintenance knowledge parameter library in a predetermined format; and the statistical indicators in the maintenance knowledge parameter library are updated, such as the average maintenance time and average maintenance effect of various types of faults. At the same time, the adjusted fault feature threshold and the optimized prediction algorithm parameters are updated to the fault feature library and the prediction model respectively, forming a complete knowledge update cycle.

[0056] For example, after a certain strapping machine completed the replacement of the cutting tool, the sensor network immediately began to collect performance data. The motor temperature sensor showed that the temperature dropped from the continuous high temperature (85°C) before the maintenance to the normal range (70°C); the abnormal peak at 150Hz in the vibration spectrum of the cutting process recorded by the vibration sensor disappeared, and the vibration amplitude decreased; the noise sensor detected that the cutting noise dropped from 78dB to the standard level of 65dB; the quality parameters of the strap cut measured by the optical sensor returned to normal. After these data were standardized, a post-maintenance operation effect evaluation report was formed. Compared with the state before maintenance, the analysis showed that the motor temperature dropped by 15°C (improvement degree 0.88), the vibration spectrum abnormality was eliminated (improvement degree 0.95), and the noise level was reduced by 13dB (improvement degree 0.90). The comprehensive calculation showed that the maintenance effect improvement metric value was 0.92, indicating that the maintenance was very successful. The actual findings of the maintenance personnel confirmed that the severe wear of the cutting tool was the root cause of the fault, which was completely consistent with the "cutting tool wear" result given by the automatic diagnosis system. The target fault component matching degree was 1.0 and the fault type matching degree was 1.0. However, in terms of fault severity, the severity estimated by the automatic system was 0.75, while the actual severity found was 0.85, with an underestimation deviation of 0.1. Based on this, the characteristic threshold of the cutting tool wear mode in the fault feature library was adjusted, especially the mapping relationship between the energy and fault severity at 150Hz of the vibration spectrum was enhanced, and the severity assessment model was corrected. At the same time, by comparing the predicted fault development trend with the actual observation results, it was found that the development speed predicted by the system was 15% slower than the actual one. Based on this, the development rate coefficient in the prediction algorithm was updated from the original 0.085 to 0.098, making the prediction closer to reality. The complete information of this maintenance (including fault diagnosis, maintenance method, resources used, maintenance time of 2 hours, and maintenance effect improvement measure of 0.92, etc.) was written into the maintenance knowledge parameter library, and statistical indicators such as the average maintenance effect and average maintenance time of cutting tool replacement were updated.

[0057] The above describes the strapping machine fault monitoring method based on the Internet of Things in the embodiment of the present application. The following describes the strapping machine fault monitoring system based on the Internet of Things in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the strapping machine fault monitoring system based on the Internet of Things includes: The extraction module is used to collect the operating data of each key part of the strapping machine through the sensor network, and obtain multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate; A segmentation module, used for filtering and segmenting the data according to the multi-source operation data to obtain the state characteristic data of the strapping machine with a timestamp; A comparison module, used for analyzing and comparing the running state of the strapping machine based on the state characteristic data of the strapping machine, and obtaining the abnormal state identification and fault type determination result of the strapping machine; A positioning module is used to establish a component association map of the strapping machine according to the abnormal state identification and fault type determination result of the strapping machine, and obtain the fault cause positioning result and the fault development trend prediction value; A calculation module, for calculating the maintenance priority according to the fault cause location result and the fault development trend prediction value in combination with the belt machine maintenance database, and obtaining a maintenance plan and operation time recommendation; The prediction module is used to record the actual maintenance results and the prediction deviation according to the operation effect of the strapping machine after the maintenance plan is implemented, and obtain the updated strapping machine fault feature library and maintenance knowledge parameters.

[0058] Through the collaboration of the above components, Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0059] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0060] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0061] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0064] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring faults of a strapping machine based on the Internet of Things, characterized in that: The Internet of Things-based strapping machine fault monitoring method includes: The sensor network is used to collect the operating data of key parts of the strapping machine, and obtains multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate; According to the multi-source operation data, filtering and segmenting the data to obtain the state characteristic data of the strapping machine with a timestamp; Based on the state characteristic data of the strapping machine, the running state of the strapping machine is analyzed and compared to obtain the abnormal state identification and fault type determination result of the strapping machine; According to the abnormal state identification and fault type determination results of the strapping machine, a component association map of the strapping machine is established to obtain the fault cause location result and the fault development trend prediction value; According to the fault cause location result and the fault development trend prediction value, the maintenance priority is calculated in combination with the belt machine maintenance database to obtain the maintenance plan and operation time recommendation; According to the running effect of the strapping machine after the implementation of the maintenance plan, the actual maintenance result and the predicted deviation are recorded to obtain an updated strapping machine fault feature library and maintenance knowledge parameters.

2. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1 is characterized in that: The sensor network is used to collect the operating data of each key part of the strapping machine, and obtains multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate, including: Install temperature sensors and current sensors on the motor drive device of the strapping machine to collect the motor surface temperature and current waveform to obtain the motor temperature data; Arrange tension sensors and displacement sensors in the tension control mechanism of the strapping machine to record the tension change of the strapping machine and the displacement of the control rod to form tension control parameters; The binding robot arm of the strapping machine is equipped with an acceleration sensor and an angle sensor to measure the movement state and working angle of the robot arm and generate the displacement data of the binding robot arm; Install vibration sensors and sound sensors on the cutting device of the strapping machine to monitor the vibration frequency and noise characteristics during the cutting process and generate the operating status of the cutting device; The deformation of the strap during the bundling process is measured by an optical sensor, the degree of deformation of the strap due to stress is calculated, and the deformation rate of the strap is obtained; The motor temperature data, tension control parameters, binding robot arm displacement data, cutting device operating status and strap deformation rate are transmitted to the data processing unit through an industrial-grade wireless communication network to form multi-source operating data with corresponding time stamps.

3. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1 is characterized in that: The filtering and segmenting of the data according to the multi-source operation data to obtain the state characteristic data of the strapping machine with a timestamp includes: The noise and interference signals in the multi-source operation data are removed by an adaptive filtering algorithm to obtain a pure data stream; Divide the clean data stream into data segments in a sliding window manner with a width of 5 seconds and an overlap rate of 50% to form segmented processing data; Adding precise time stamps to the segmented processed data by a time synchronization mechanism to construct a time-aligned data frame; Extracting time domain feature quantities including mean, peak, root mean square value, kurtosis and skewness from the time-aligned data frame by a time domain analysis method; Performing frequency domain conversion on the time-aligned data frame to obtain spectrum energy distribution and main frequency component information; The time domain feature quantity is fused with the spectrum energy distribution and the main frequency component information to generate the state feature data of the strapping machine with a timestamp.

4. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1, characterized in that: The method of analyzing and comparing the running state of the strapping machine based on the state characteristic data of the strapping machine to obtain the abnormal state identification and fault type determination result of the strapping machine includes: Construct a normal operating benchmark parameter library of the belt machine from historical data, including the standard characteristic distribution boundary values ​​under various working conditions; Calculate the difference between the state characteristic data of the strapping machine and the corresponding data in the normal operation reference parameter library of the strapping machine to obtain a characteristic deviation matrix; The anomaly weight coefficient is set according to the degree of deviation of each parameter in the characteristic deviation matrix to generate a comprehensive anomaly index; By using a threshold comparison method, it is determined whether the comprehensive abnormality index exceeds a preset warning threshold, thereby forming an abnormal state mark of the strapping machine; Perform similarity matching on the characteristic deviation matrix according to the typical fault characteristic template of the strapping machine to identify the target fault category; The abnormal state identification of the strapping machine and the target fault category are combined to form the abnormal state identification of the strapping machine and the fault type determination result.

5. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1, characterized in that: The method of establishing a component association map of the strapping machine according to the abnormal state identification and fault type determination result of the strapping machine to obtain the fault cause location result and the fault development trend prediction value includes: Using the structural knowledge of the strapping machine, a component association graph of the strapping machine is constructed, which includes the physical connections and functional dependencies between the components. Mark abnormal component nodes in the belt machine component association graph according to the fault type determination result; By using a causal propagation algorithm, the abnormal signal transmission path is reversely traced in the belting machine component association map, and the probability value of each related component as the root cause of the fault is calculated; Determine the target faulty components and their impact range by sorting the probability values, and generate the fault cause location results; Based on the development rules of similar historical fault cases, the fault cause location results are extrapolated in time series to construct a fault severity change curve; By combining the fault severity change curve with the equipment safety threshold, the fault development time window and potential risk level are predicted to form a fault development trend prediction value.

6. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1, characterized in that: The maintenance priority is calculated based on the fault cause location result and the fault development trend prediction value in combination with the belt machine maintenance database to obtain the maintenance plan and operation time recommendation, including: Extract historical maintenance cases matching the fault cause location results from the belt machine maintenance database to build a maintenance knowledge base; Predicting the fault development trend according to the maintenance knowledge base set to obtain a fault development trend prediction value, and calculating a fault risk index according to the fault development trend prediction value; The failure risk index is weighted and combined with the production task priority, spare parts inventory status and technician availability to generate a maintenance urgency index; Classifying maintenance tasks according to the maintenance urgency index to determine the maintenance operation level; Extracting corresponding standard maintenance procedures according to the maintenance knowledge base set and the maintenance operation level to form a maintenance plan; Combine the fault development trend prediction value with the production plan to determine the best maintenance time window and generate operation time recommendations.

7. The method for monitoring faults of a strapping machine based on the Internet of Things according to claim 1, characterized in that: According to the running effect of the strapping machine after the maintenance plan is implemented, the actual maintenance result and the predicted deviation are recorded to obtain the updated strapping machine fault feature library and maintenance knowledge parameters, including: The performance index data of the belting machine after the maintenance plan is implemented is collected through the sensor network, and a post-maintenance operation effect evaluation report is constructed; Compare and analyze the post-maintenance operation effect evaluation report with the pre-maintenance status to calculate the maintenance effect improvement metric value; Compare the fault cause location result with the fault source found during actual maintenance, and record the fault diagnosis accuracy evaluation data; According to the deviation in the fault diagnosis accuracy evaluation data, adjusting the characteristic threshold of the corresponding fault mode in the belting machine fault characteristic library; According to the difference between the predicted value of the fault development trend and the actual fault development trajectory, updating the timing parameters in the prediction algorithm; The maintenance effect improvement metric value and the associated data of the maintenance plan are integrated and written into the maintenance knowledge parameter library to form an updated belt machine fault feature library and maintenance knowledge parameters.

8. A strapping machine fault monitoring system based on the Internet of Things, used to implement the strapping machine fault monitoring method based on the Internet of Things as described in any one of claims 1 to 7, characterized in that: The strapping machine fault monitoring system based on the Internet of Things includes: The extraction module is used to collect the operating data of each key part of the strapping machine through the sensor network, and obtain multi-source operating data including motor temperature data, tension control parameters, strapping robot arm displacement data, cutting device operating status and strap deformation rate; A segmentation module, used for filtering and segmenting the data according to the multi-source operation data to obtain the state characteristic data of the strapping machine with a timestamp; A comparison module, used for analyzing and comparing the running state of the strapping machine based on the state characteristic data of the strapping machine, and obtaining the abnormal state identification and fault type determination result of the strapping machine; A positioning module is used to establish a component association map of the strapping machine according to the abnormal state identification and fault type determination result of the strapping machine, and obtain the fault cause positioning result and the fault development trend prediction value; A calculation module, for calculating the maintenance priority according to the fault cause location result and the fault development trend prediction value in combination with the belt machine maintenance database, and obtaining a maintenance plan and operation time recommendation; The prediction module is used to record the actual maintenance results and the prediction deviation according to the operation effect of the strapping machine after the maintenance plan is implemented, and obtain the updated strapping machine fault feature library and maintenance knowledge parameters.

9. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, it implements the strapping machine fault monitoring method based on the Internet of Things described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the method for monitoring faults of a strapping machine based on the Internet of Things as claimed in any one of claims 1 to 7.

Images