A carton conveying equipment operation state self-diagnosis and early warning method

Abstract

The application discloses a kind of carton conveying equipment operating state self-diagnosis and early warning method, belong to industrial automation control technical field.It includes acquisition vibration spectrum, current ripple fluctuation rate, equipment operating parameter, vibration wave conduction timing, laser scanning;Vibration current composite sensing data and carton deformation characteristics are generated;Establish equipment dynamic health record;Composite sensing data and health record are carried out abnormal separation first diagnosis result;Based on the result, vibration wave timing and deformation characteristics are fused to perform fault tracing, and output secondary positioning information;According to positioning information, generate maintenance decision instruction, output early warning containing fault component identification and maintenance measures.The application adopts multi-source data fusion and intelligent diagnosis algorithm, combined with dynamic health record, can realize the accurate positioning of equipment anomaly, improve equipment reliability and maintenance efficiency.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control technology, and in particular to a method for self-diagnosis and early warning of the operating status of a carton conveying equipment. Background Technology

[0002] Carton conveying equipment is an indispensable key component of automated production lines and logistics warehousing systems. Its main function is to achieve continuous, efficient, and stable transport of materials such as cartons. In the context of modern industry and intelligent manufacturing, this type of equipment is usually integrated into complex flexible manufacturing systems, and its operational reliability directly affects the efficiency and cost of the entire production or logistics process. Therefore, real-time monitoring of the operational status and fault early warning of carton conveying equipment is an important technical support for ensuring the smooth operation of production lines and achieving predictive maintenance.

[0003] Existing methods for monitoring the condition of carton conveying equipment often rely on the detection of a single physical quantity. For example, they might monitor the mechanical vibration of key components such as bearings and motors by installing vibration sensors, or determine whether the load is abnormal by monitoring the current of the drive motor. While some systems may collect multiple signals simultaneously, these signals are typically analyzed independently at the data processing level, failing to achieve deep information fusion. When a certain indicator exceeds a preset threshold, the system issues an alarm, requiring maintenance personnel to rely on their personal experience to determine the specific cause and location of the fault.

[0004] The aforementioned existing technologies have significant shortcomings in practical applications. First, single-signal monitoring has limited ability to identify complex faults; many early signs of faults are the result of the coupling of multiple physical quantities, which a single signal cannot effectively capture. Second, independent signal analysis methods ignore the inherent correlation between different physical phenomena, easily leading to false alarms or missed alarms, and are not very accurate in locating the source of faults, often only providing a vague fault area. Furthermore, traditional alarm methods can only inform that equipment is abnormal, but cannot provide specific fault diagnosis conclusions or maintenance guidance, heavily relying on the professional skills and experience of maintenance personnel, resulting in low troubleshooting efficiency and increased unplanned downtime. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a self-diagnosis and early warning method for the operating status of carton conveying equipment. By employing multi-source data fusion and intelligent diagnostic algorithms, combined with dynamic health records, it can achieve precise location of equipment anomalies, thereby improving equipment reliability and maintenance efficiency.

[0006] The above objectives can be achieved through the following approach:

[0007] A self-diagnosis and early warning method for the operating status of a carton conveying equipment includes collecting vibration spectrum, current ripple fluctuation rate, equipment operating parameters, vibration wave propagation time sequence, and laser scanning; generating composite vibration-current sensing data and carton deformation characteristics; establishing a dynamic health record for the equipment; performing anomaly separation on the composite sensing data and health record to obtain a primary diagnostic result; performing fault tracing based on the result by fusing vibration wave time sequence and deformation characteristics, and outputting secondary location information; generating maintenance decision instructions based on the location information, and outputting an early warning containing faulty component identification and maintenance measures.

[0008] Optionally, generating composite sensing data based on the vibration spectrum data and current ripple fluctuation rate data includes: performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector; and extracting the energy gradient change features in the time-domain synchronization feature vector to generate composite sensing data.

[0009] Optionally, the step of performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector includes: obtaining a time-domain vibration sequence based on the vibration spectrum data; performing time-domain waveform normalization processing on the current ripple fluctuation rate data to obtain a current fluctuation time series; and performing time-domain alignment processing on the time-domain vibration sequence and the current fluctuation time series to generate a time-domain synchronization feature vector.

[0010] Optionally, the fault tracing analysis includes: acquiring the transmission threshold and vibration peak time series data of the vibration sensor; calculating a first difference in propagation delay based on the vibration peak time series data; and determining that the positioning motor bearing fails when the first difference in propagation delay exceeds the transmission threshold.

[0011] Optionally, generating carton deformation features based on the laser scanning data includes: performing dynamic displacement compensation and geometric contour extraction on the laser scanning data to obtain a calibrated three-dimensional edge coordinate set; and performing decoupling calculation of deformation physical quantities on the three-dimensional edge coordinate set to generate carton deformation features.

[0012] Optionally, establishing a dynamic health record for the equipment includes: acquiring current harmonic amplitude ratio data from the equipment operating parameters; monitoring the current harmonic amplitude ratio data to obtain a time-varying degradation offset; and establishing a dynamic health record for the equipment based on the time-varying degradation offset.

[0013] Optionally, generating maintenance decision instructions based on the secondary positioning information includes: performing fault topology modeling on the secondary positioning information to obtain a fault positioning topology map; performing maintenance strategy matching and optimization on the fault positioning topology map to generate maintenance decision instructions.

[0014] Optionally, the step of outputting a warning signal containing the faulty component identifier and maintenance measures based on the maintenance decision instruction includes: parsing the maintenance decision instruction to obtain the optimized strategy parameters of the faulty component maintenance measures; performing adaptive signal encapsulation processing on the optimized strategy parameters of the faulty component maintenance measures; and outputting a warning signal containing the faulty component identifier and maintenance measures.

[0015] Optionally, the step of performing maintenance strategy matching and optimization on the fault location topology map to generate maintenance decision instructions includes: performing node correlation analysis and maintenance path weight calculation on the fault location topology map to obtain a path weight matrix; and performing dynamic strategy matching and maintainability index optimization based on the path weight matrix to generate maintenance decision instructions.

[0016] Based on the same inventive concept, this invention also provides a self-diagnosis and early warning system for the operating status of a carton conveying equipment. The system includes: a multi-source signal acquisition module for acquiring vibration spectrum data, current ripple fluctuation rate data, equipment operating parameters, vibration wave propagation time series data, and laser scanning data; a composite sensing generation module for generating composite sensing data based on the vibration spectrum data and current ripple fluctuation rate data; a deformation feature extraction module for generating carton deformation features based on the laser scanning data; a health record modeling module for establishing a dynamic health record for the equipment based on the equipment operating parameters; an anomaly diagnosis module for performing anomaly separation processing on the composite sensing data and the dynamic health record to generate a primary diagnostic result; a fault tracing module for performing fault tracing analysis on the vibration wave propagation time series data and the carton deformation features based on the primary diagnostic result to generate secondary positioning information; a maintenance decision module for generating maintenance decision instructions based on the secondary positioning information; and an early warning output module for outputting an early warning signal containing faulty component identification and maintenance measures based on the maintenance decision instructions.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] This invention generates composite sensing data by fusing vibration spectrum data and current ripple fluctuation rate data, enabling collaborative monitoring of equipment status from both mechanical and electrical dimensions. This multi-physical quantity fusion approach can capture early fault signs that are difficult to detect with a single signal, such as mechanical vibrations caused by electrical system anomalies, thereby improving the sensitivity and foresight of fault diagnosis and providing effective early warnings in the early stages of fault occurrence.

[0019] This invention innovatively introduces vibration wave propagation time-series data and carton deformation characteristics for fault source analysis. By measuring the propagation delay of vibration signals among key components of the equipment, combined with laser scanning analysis of the deformation patterns of the conveyed material itself, dual verification and precise location of the fault source are achieved. This method can clearly distinguish faults in different components, such as motor bearing failure and loose tension wheel bolts, improving the accuracy and reliability of fault diagnosis.

[0020] This invention establishes a complete intelligent process from fault location to maintenance decision-making. After accurately locating the fault, the system can automatically perform fault topology modeling and maintenance strategy optimization, generating maintenance decision instructions that include specific faulty component identifiers and optimized maintenance measures. This transforms early warning information from simple alarm signals into directly executable intelligent maintenance plans, improving maintenance efficiency and reducing equipment downtime.

[0021] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a self-diagnosis and early warning method for the operating status of a carton conveying equipment according to an embodiment of the present invention.

[0024] Figure 2 This is a vibration wave propagation timing data diagram according to an embodiment of the present invention.

[0025] Figure 3 This is a comparison diagram of the theoretical deformation of a cardboard box under load according to an embodiment of the present invention.

[0026] Figure 4 This is a dynamic health record diagram of the device according to an embodiment of the present invention.

[0027] Figure 5 This is a dynamic health record degradation curve of the device according to an embodiment of the present invention.

[0028] Figure 6 This is a schematic diagram of the structure of a self-diagnosis and early warning system for the operating status of a carton conveying equipment according to an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Reference Figure 1 One embodiment of the present invention proposes a self-diagnosis and early warning method for the operating status of a carton conveying equipment. By using multi-source data fusion and intelligent diagnostic algorithms, combined with dynamic health records, it can achieve accurate location of equipment anomalies and improve equipment reliability and maintenance efficiency.

[0031] The method described in this embodiment specifically includes:

[0032] Acquire vibration spectrum data, current ripple fluctuation rate data, equipment operating parameters, vibration wave propagation time sequence data, and laser scanning data;

[0033] Based on the vibration spectrum data and current ripple fluctuation rate data, composite sensing data is generated.

[0034] Based on the laser scanning data, the deformation characteristics of the carton are generated;

[0035] Based on the equipment operating parameters, establish a dynamic health record for the equipment;

[0036] The composite sensor data and the device's dynamic health record are subjected to anomaly separation processing to generate a primary diagnostic result;

[0037] Based on the primary diagnostic results, fault source analysis is performed on the vibration wave propagation time series data and the carton deformation characteristics to generate secondary positioning information;

[0038] Based on the secondary positioning information, a maintenance decision instruction is generated;

[0039] Based on the maintenance decision command, an early warning signal containing the faulty component identification and maintenance measures is output.

[0040] Specifically, firstly, the mechanical vibration, drive current, macroscopic operating parameters, vibration wave propagation time sequence, and three-dimensional morphological data of the transported object are collected synchronously. The vibration wave propagation time sequence data includes, for example, data on the mechanical vibration, drive current, macroscopic operating parameters, vibration wave propagation time sequence, and the three-dimensional morphological data of the transported object. Figure 2As shown, this system achieves comprehensive perception of equipment status. Its core lies in the deep fusion of vibration spectra and current ripple, reflecting subtle internal dynamics of the equipment, to generate composite sensor data that is more sensitive to early faults. Simultaneously, a dynamically changing health baseline—the equipment's dynamic health record—is established by continuously monitoring equipment operating parameters, serving as a basis for distinguishing between normal aging and abnormal degradation. The diagnostic process employs a tiered strategy. Level 1 diagnosis compares the composite sensor data with the health record to quickly determine the presence or absence of abnormalities. This is achieved through dynamic statistical thresholds. Every second, the system extracts the most recent 30 time-varying degradation offset samples from the equipment's dynamic health record and calculates their mean. with standard deviation If the current energy gradient value of the composite sensing data exceeds... If the fault is detected, it is classified as a Level 1 anomaly. Once the anomaly is confirmed, Level 2 diagnosis is initiated, namely fault source analysis. This analysis innovatively combines the time delay characteristics of vibration wave propagation in the equipment structure with the physical deformation characteristics of the cardboard box obtained by laser scanning, achieving precise spatial location of the fault source. Finally, based on the precise location information, the system intelligently generates maintenance decision instructions containing specific component identification and optimized maintenance steps through fault topology modeling and maintenance strategy optimization, and encapsulates them as early warning signals for output, forming a complete technical closed loop from state perception, anomaly detection, fault location to maintenance decision-making.

[0041] Optionally, generating composite sensing data based on the vibration spectrum data and current ripple fluctuation rate data includes:

[0042] The vibration spectrum data and the current ripple fluctuation rate data are time-domain aligned to generate a time-domain synchronization feature vector.

[0043] Extract the energy gradient change features from the time-domain synchronization feature vector to generate composite sensing data.

[0044] Specifically, the first step is to perform time-domain alignment processing to generate a time-domain synchronized feature vector. This step requires acquiring vibration spectrum data and current ripple fluctuation rate data. The vibration spectrum data is first processed into a time-domain vibration sequence, which typically involves analyzing the acquired raw vibration time-domain signal or using inverse transformation to obtain time-series data characterizing the mechanical vibration state of the equipment. Simultaneously, the acquired current ripple fluctuation rate data undergoes time-domain waveform normalization processing to obtain the current fluctuation time series. Normalization aims to eliminate amplitude differences caused by power supply voltage fluctuations or different base loads, focusing the data on the shape of the fluctuation rather than its absolute magnitude, thereby enhancing the comparability of data under different operating conditions. After completing the above preprocessing, the time-domain vibration sequence and the current fluctuation time series are precisely aligned on the time axis, ensuring that the vibration value at each time point corresponds to the current fluctuation value at the same moment. This constructs a two-dimensional time-domain synchronized feature vector sequence, where each vector contains mechanical and electrical state information at the same instant. After obtaining the time-domain synchronized feature vector, the energy gradient change characteristics are further extracted, which serve as the final generated composite sensing data. Energy gradient change characteristics can sensitively capture the instantaneous changes in equipment state or the emergence of anomalies. The calculation of this characteristic first defines the instantaneous energy of the time-domain synchronization feature vector at any given moment. The instantaneous energy characterizes the combined intensity of mechanical vibration and current fluctuations at that moment. Subsequently, the gradient of this instantaneous energy over time is calculated, i.e., the rate of change of energy with time. In discrete sampling systems, the energy gradient can be approximated by calculating the difference between the instantaneous energies of two adjacent sampling moments. Its calculation method can be expressed as:

[0045] ,

[0046] in, Representative at The energy gradient change characteristics at any given time are the composite sensing data we are looking for. for The instantaneous energy at time t is calculated from the time-domain synchronization feature vector at that time, which contains... The vibrational components and current fluctuation components at any given moment. Instantaneous energy. It is calculated using the following formula:

[0047] ,

[0048] in for The amplitude of the vibration component at any given moment; for The amplitude of the current fluctuation component at any given moment; For current fluctuations within a time window The mean within; Let be the weighting coefficient for vibration and current energy, and satisfy . The method for determining this is as follows: the initial value is set based on the proportion of historical equipment failure types: when the proportion of mechanical failures exceeds 60%, =0.6、 =0.4; when the proportion of electrical faults is higher, =0.4、 =0.6. Dynamic optimization: Under high load. Increase by 0.1, run at low speed Increase by 0.1, during the break-in period of new equipment. = =0.5. Self-learning calibration: If the mechanical fault false alarm rate exceeds 5% after every 10 accumulated fault records, then... Increase by 0.05; if the electrical fault false alarm rate exceeds 5%, then... Increase by 0.05; For the integration time window, the value is 10. 50ms; This represents the instantaneous energy at the previous sampling moment. By calculating this energy gradient, the method no longer focuses on the absolute values ​​of vibration or current in isolation, but rather on the dynamic trend of the combined energy of the two. A drastic change in the energy gradient, whether a positive surge or a negative drop, strongly indicates that an abnormal transition in the equipment's operating state may have occurred, such as component impact, sudden load changes, or loose connections.

[0049] Optionally, the step of performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector includes:

[0050] Based on the vibration spectrum data, a time-domain vibration sequence is obtained;

[0051] The current ripple fluctuation rate data is subjected to time-domain waveform normalization processing to obtain the current fluctuation time series.

[0052] The time-domain vibration sequence and the current fluctuation time series are time-domain aligned to generate a time-domain synchronization feature vector.

[0053] Specifically, the first step is to generate a time-domain vibration sequence based on the acquired vibration spectrum data. Vibration spectrum data describes the distribution of equipment vibration energy in the frequency domain. To use it for time-series analysis, signal processing techniques such as inverse Fourier transform are needed to restore it to a time-sampled vibration amplitude sequence, which is the time-domain vibration sequence. It intuitively reflects the mechanical vibration state of the equipment at each moment. Simultaneously, time-domain waveform normalization is performed on the acquired current ripple volatility data to generate a current fluctuation time series. Current ripple volatility data is a time series characterizing the severity of high-frequency disturbances in the motor drive current. To eliminate the interference caused by differences in the absolute value of the current when the equipment is operating under different loads, normalization must be performed to focus on the shape of the fluctuation rather than its magnitude. An effective normalization method is minimum-maximum normalization, which is calculated as follows:

[0054] ,

[0055] In this formula, After normalization The timing value of current fluctuation at any given moment. Is The original current ripple fluctuation rate data collected at any time. and These represent the maximum and minimum values ​​of the raw current ripple fluctuation rate data within a specific monitoring period. Through this processing, the raw current data is mapped to a fixed interval, resulting in a current fluctuation time series with a consistent shape but independent of the absolute load. Finally, the time-domain vibration sequence obtained after the above processing is... and current fluctuation timing Time-domain alignment is performed. This step aims to resolve minor discrepancies that may exist in the timestamps of data acquisition from different sensors, ensuring that each data point is synchronous in time. This can be achieved by calibrating the timestamps of the two sequences, or by resampling them to a common time reference, ensuring that at any given sampling time... We each have a precisely corresponding vibration value. and current fluctuation value Combining these two values ​​generates the time-domain synchronization feature vector. Each element of this vector sequence synchronously encapsulates the mechanical and electrical state characteristics of the device at that instant.

[0056] Optionally, the fault tracing analysis includes:

[0057] Acquire the conduction threshold and vibration peak time series data of the vibration sensor;

[0058] Based on the vibration peak time series data, the first difference in propagation delay is calculated;

[0059] When the first difference in propagation delay exceeds the conduction threshold, the positioning motor bearing fails.

[0060] Specifically, this method requires obtaining two key data points. The first is the conduction threshold of the vibration sensor, which is a key parameter that is either preset or obtained through experimental calibration.

[0061] The conduction threshold was calibrated experimentally as follows: Sample collection must cover three operating conditions: no load, 50% load, and full load. At least 90 hours of data must be collected under normal conditions, and simulated data for five failure stages must be included under fault conditions. Sensor installation positions are strictly limited to: the near-end sensor ≤ 5cm from the bearing center, and the far-end sensor 1.5±0.2m horizontally from the near-end sensor. Threshold calculation employs a double-safety mechanism, using normal data... The system employs a rule (covering 99.7% of normal fluctuations) and adjusts it based on the minimum failure threshold of fault data. To adapt to equipment aging characteristics, automatic calibration is triggered every 300 hours of operation or after maintenance, dynamically updating the threshold through a sliding window algorithm to ensure accuracy in long-term use. This threshold is determined based on the equipment's mechanical structure, material properties, and sensor layout. It represents a time delay criterion that distinguishes whether a fault originates from the motor area or other areas when vibration waves propagate between two specific sensors on the equipment. This threshold is determined based on the equipment's mechanical structure, material properties, and sensor layout. The second is vibration peak time series data, collected by multiple vibration sensors deployed at different locations on the equipment, particularly at and near the motor and other critical components along the transmission path. By processing the raw vibration signals, impact signals generated by faults such as bearing defects are identified, and the peak values ​​of these impact signals are accurately recorded at the time they arrive at each sensor, forming a time series containing multiple timestamps. Next, the calculation and location phase begins. When the primary diagnostics issue an abnormal signal, the system analyzes the most recently collected vibration peak time series data. This method utilizes the peak arrival times of at least two sensors (e.g., one close to the motor, and the other located somewhere on the conveyor frame) for calculation. Based on this time-series data, the first difference in propagation delay is calculated as follows:

[0062] ,

[0063] in, This is the first difference in propagation delay. The time it takes for the vibration peak to reach the sensor closest to the motor. The propagation delay difference is the time it takes for the same vibration peak to reach another sensor at a predetermined location. This difference essentially reflects the time difference required for the fault shock wave to propagate from its source to these two different sensors. A second propagation delay difference can be calculated in a similar manner using data from another pair of sensors (e.g., a motor sensor and a drive end sensor), used to assist in locating or eliminating faults at other locations. Finally, a decision is made. The calculated propagation delay difference is then used... The propagation delay is compared to a conduction threshold. When the first difference in propagation delay exceeds this threshold, the system determines that the fault source is a motor bearing failure. The physical basis of this logic is that if the fault occurs at the motor bearing, the vibration wave is first captured by a sensor near the motor, then propagates along a fixed structural path before being captured by a sensor at a distance, resulting in a specific time delay. The magnitude of this time delay is strongly correlated with the fault source being at the motor. The conduction threshold is a critical value set based on this correlation. If the fault occurs at another location, the propagation path of the vibration wave will change, causing the calculated propagation delay difference to fall within the threshold range or exhibit a different distinguishable pattern.

[0064] Optionally, generating the carton deformation features based on the laser scanning data includes:

[0065] Dynamic displacement compensation and geometric contour extraction are performed on the laser scanning data to obtain a calibrated three-dimensional edge coordinate set;

[0066] The deformation physical quantities of the three-dimensional edge coordinate set are decoupled and calculated to generate the deformation characteristics of the carton.

[0067] Specifically, the first step involves processing the raw laser scan data, acquired by a laser scanner deployed on the conveyor line. This data is represented as a set of point clouds describing the spatial position of the cardboard box surface. Since the cardboard box is dynamic during transport while the scanner is fixed, the raw point cloud data will exhibit motion blur or distortion. Therefore, the first step must be dynamic displacement compensation. This compensation calculates the displacement of each point relative to a fixed reference coordinate system at the instant of scanning by acquiring the real-time speed of the conveyor belt and combining it with the timestamp of each point cloud data point. This displacement is then subtracted from the point's coordinates. This operation transforms the moving cardboard box into a virtual stationary object at the data level, eliminating motion blur and laying the foundation for accurate geometric analysis. After compensation, geometric contour extraction is performed. In this step, the system analyzes the compensated dense point cloud data to identify and extract the key geometric elements that constitute the basic framework of the cardboard box, namely edges and vertices. This is typically achieved through algorithms, such as detecting areas in the point cloud where the normal vector or curvature changes abruptly to locate edges, and then determining vertices by calculating the intersections of the edge lines. Through this process, the complex and disordered surface point cloud is refined into a set of ordered three-dimensional coordinate points that represent the macroscopic structure of the cardboard box, i.e., the calibrated three-dimensional edge coordinate set. After obtaining this coordinate set, the method enters its core step: decoupling the calculation of deformation physical quantities on this coordinate set to generate the final cardboard box deformation characteristics. The theoretical deformation of the cardboard box under load is compared to... Figure 3 As shown. The essence of decoupling calculation is to decompose the overall, complex morphological changes of a cardboard box into a series of independent or weakly correlated basic physical deformation components. This calculation compares the measured three-dimensional edge coordinate set with a standard, ideal cardboard box geometric model. Through comparison, multiple dimensions of deformation physical quantities can be calculated. For example, by calculating the deviation between the measured angles between the edges and the ideal 90-degree angle, the shear or twist amount of the box can be obtained; by calculating the change in the length of the relative edges, the compression or stretching amount of the box can be obtained; by measuring the degree of deviation of the center point of the box surface from the plane formed by the vertices, the bulging or indentation amount of the box surface can be obtained. These calculated, decoupled physical quantities, such as angular deviation values, edge length change rates, and surface curvature, together constitute a multi-dimensional vector or set, which is the deformation characteristic of the cardboard box.

[0068] Optionally, establishing a dynamic health record for the device includes:

[0069] Obtain the current harmonic amplitude ratio data from the operating parameters of the device;

[0070] The time-varying degradation offset is obtained by monitoring the current harmonic amplitude ratio data.

[0071] A dynamic health record for the device is established based on the time-varying degradation offset.

[0072] Specifically, the first step is to obtain the current harmonic amplitude ratio data from the equipment's operating parameters. Current harmonics refer to the components in the motor's operating current whose frequencies are integer multiples of the fundamental frequency, excluding the fundamental frequency. As the motor and its drive system, especially the insulation system, undergo gradual degradation over time due to aging and wear, its nonlinear characteristics intensify, leading to increased distortion of the current waveform. Consequently, the amplitude of specific harmonics will change slowly and continuously. The current harmonic amplitude ratio data is the ratio of the amplitude of a specific harmonic to the amplitude of the fundamental frequency. This ratio effectively eliminates the influence of overall current fluctuations caused by load variations, reflecting more purely the changes in the equipment's inherent electrical characteristics. This data is obtained through frequency domain analysis techniques such as Fourier transform on the real-time acquired motor current signal. After obtaining the current harmonic amplitude ratio data, the core of the method lies in long-term monitoring and calculating the time-varying degradation offset. This step requires collecting current harmonic amplitude ratio data for a period of time when the equipment is in a clearly healthy state (e.g., after new equipment commissioning or major overhaul), and calculating its stable value as a health benchmark value. Subsequently, during continuous operation of the equipment, the system periodically collects this data and compares it with a preset health benchmark value. The time-varying degradation offset is the difference between the current harmonic amplitude ratio at the current moment and the health benchmark value. Its calculation method can be expressed as:

[0073] ,

[0074] In this formula, Representative at The time-varying degradation offset calculated at each moment. It is a specific measurement taken at time t. The amplitude ratio data of the (second) harmonics. This is the ratio of the reference amplitude of that harmonic under healthy conditions. This offset... It is not a static value, but a sequence that changes over time, quantifying the cumulative degradation of the equipment's electrical performance since its healthy state. Finally, based on this series of continuously or discretely acquired time-varying degradation offsets, a dynamic health profile of the equipment is established, as shown in the figure below. Figure 4 As shown, this file is not a simple status label, but a dataset containing timestamps and corresponding degradation offsets. It plots a degradation trajectory curve of the device's health status along a time axis. This dynamic health file records the entire process of the device from healthy to potential failure, visually demonstrating the trend and rate of degradation. The device's dynamic health file degradation is as follows: Figure 5 As shown.

[0075] Optionally, generating maintenance decision instructions based on the secondary positioning information includes:

[0076] Fault topology modeling is performed on the secondary location information to obtain the fault location topology map;

[0077] The fault location topology map is used to match and optimize maintenance strategies, and maintenance decision instructions are generated.

[0078] Specifically, the system first performs fault topology modeling on the secondary location information obtained from fault tracing analysis. The secondary location information identifies the specific faulty component, such as "motor bearing failure." Fault topology modeling doesn't simply record this name; instead, it places the faulty component within the system structure diagram of the entire carton conveying equipment. This structure diagram is a pre-built digital model, a topology graph where nodes represent physical components of the equipment (such as motors, bearings, drive shafts, tensioners, conveyor belts, etc.), and edges represent the physical connections or functional dependencies between these components. When the secondary location information is input, the system highlights the corresponding faulty node and its directly associated nodes in the topology graph, generating a clear fault location topology graph showing the fault location and its context within the system. After obtaining this fault location topology graph, the system then performs maintenance strategy matching and optimization. Maintenance strategy matching involves the system accessing a pre-built maintenance knowledge base, which pre-associates one or more sets of standard maintenance operating procedures for each component node in the topology graph. For example, for the "motor bearing" node, the associated strategies might include "lubrication," "replacement," or "tightening check." The system first matches all possible maintenance strategies from the knowledge base based on the nature of the fault (determined jointly by primary diagnostic results and secondary location information). However, matching alone is insufficient; optimization is key. The optimization process is based on the fault location topology map. The system analyzes the correlation between nodes in the map and calculates the weights of different maintenance paths. This means the system evaluates the sequence of disassembly and installation steps necessary to execute a particular maintenance strategy, comprehensively considering the time, tooling, spare parts costs, and impact on other parts of the equipment. Through this topology-based path analysis and weight calculation, the system can compare the overall cost and benefit of different maintenance strategies and select the optimal maintenance path. For example, for replacing a bearing, the system will determine a sequence with the fewest disassembly parts and the shortest operation time. The results of this selection and optimization are ultimately integrated into a structured instruction—the maintenance decision instruction.

[0079] Optionally, the step of outputting a warning signal containing the faulty component identification and maintenance measures based on the maintenance decision instruction includes:

[0080] The maintenance decision command is parsed to obtain the optimized strategy parameters for maintenance measures of the faulty component;

[0081] The optimization strategy parameters for the maintenance measures of the faulty component are subjected to adaptive signal encapsulation processing, and an early warning signal containing the faulty component identification and maintenance measures is output.

[0082] Specifically, the first step is to parse the maintenance decision instructions generated in the previous stage. A maintenance decision instruction is a structured data packet containing the optimal maintenance path and strategy. Parsing this instruction involves disassembling and extracting information from this data packet to obtain a series of optimized strategy parameters for specific maintenance measures of the faulty components. These parameters are the core elements guiding actual maintenance work. For example, they clearly indicate the unique identifier or number of the faulty component, recommend specific maintenance measures such as "replacement" or "lubrication," the model and specifications of the required spare parts, the detailed sequence of steps for performing the measure, and the estimated working hours and necessary safety precautions. After parsing and obtaining these optimized strategy parameters, the system then performs adaptive signal encapsulation processing. This is a crucial conversion step, the core of which is "adaptive." This means that the system does not generate a single, fixed alarm format, but rather organizes and packages these optimized strategy parameters in the most appropriate form according to the preset output target or receiver type. For example, if the receiving end of the warning signal is a human-machine interface for on-site operators, the encapsulation process will convert the parameters into visual graphic information, which may include highlighting the location of the faulty component on the 3D model of the equipment and displaying the maintenance steps in a list format. If the receiving end is an enterprise-level computerized maintenance management system, the encapsulation process will encode these parameters into data packets conforming to a specific communication protocol, such as XML or JSON format, in order to automatically create maintenance work orders, request spare parts, and dispatch personnel. If the receiving end is a basic audible and visual alarm device, the encapsulation process will generate a simple drive signal to activate an alarm light of a specific color and associate it with a pre-recorded voice broadcast. The final output of this encapsulation process is a warning signal that includes the identification of the faulty component and maintenance measures.

[0083] Optionally, the step of performing maintenance strategy matching and optimization on the fault location topology map to generate maintenance decision instructions includes:

[0084] Node correlation analysis and maintenance path weight calculation are performed on the fault location topology to obtain the path weight matrix;

[0085] Based on the path weight matrix, dynamic strategy matching and maintainability index optimization are performed to generate maintenance decision instructions.

[0086] Specifically, the first step is to perform node correlation analysis and maintenance path weight calculation on the fault location topology. In this topology, nodes represent equipment components, and edges represent the connections between components. Node correlation analysis identifies and quantifies these connections; for example, to repair the target faulty node, which preceding nodes need to be disassembled first? These preceding nodes have a strong correlation with the target node. The maintenance path refers to the sequence of nodes traversed from the equipment's intact state to the completion of the target node's repair. The weight calculation for this path aims to concretize the abstract maintenance difficulty into numerical values. The weight of each operation step (i.e., an edge in the path) is determined by multiple factors, and its calculation method can be expressed as follows:

[0087] ,

[0088] In this formula, Represents operation To operation The comprehensive path weight of this maintenance step. These are pre-defined importance coefficients, representing the relative importance of time, cost, and risk in the decision-making process. The importance coefficients are adjusted using the Analytic Hierarchy Process (AHP) combined with dynamic scenarios. Specifically, the initial values ​​are calculated using the AHP method. By constructing a judgment matrix for time, cost, and risk, the initial weight ratios of the three factors are obtained. Dynamic adjustments are made based on equipment operating hours: efficiency is prioritized during peak production periods. The value is 0.4 0.5, The value is 0.2. 0.3; Cost control should be prioritized during equipment downtime. The value is 0.4 0.5, α takes the value 0.2 0.3; Risk weight Always maintain 0.2 0.3 to ensure operational safety. Based on historical data, a quarterly adjustment of ±0.05 is made if the actual impact of a factor deviates from its weight by more than 10%. , and These are the normalized values ​​of the estimated time, related costs, and operational risks required to complete this step. These raw data are obtained by querying equipment databases and maintenance knowledge bases, and are normalized to eliminate the influence of dimensions, allowing for weighted summation within a unified framework. By performing this calculation for each step on all possible maintenance paths, a path weight matrix can be constructed, which comprehensively depicts the overall "cost" of performing different maintenance operations. After obtaining the path weight matrix, the system performs dynamic strategy matching and maintainability index optimization based on this matrix. The maintainability index is a comprehensive indicator for evaluating the quality of a maintenance plan, defined as a quantitative value combining the total path weight, the scope of fault impact, and the correlation of components. The calculation formula is:

[0089]

[0090] in, The total weight of the path. This is the fault impact range coefficient (0-1, the larger the impact, the closer the value is to 1). This is a component correlation correction coefficient (0.1-0.3, with a larger value for higher correlation). and These represent the number of normally functioning components after maintenance and the total number of components in the equipment, respectively. The maintainability index is inversely proportional to the total path weight; the lower the total weight, the smaller the impact of the fault, and the higher the component correlation, the higher the maintainability index and the better the solution. Dynamic strategy matching refers to the system calling all feasible maintenance strategies (such as "replace," "repair," and "adjust") from the knowledge base for the faulty node, and using the path weight matrix to calculate the optimal execution path for each strategy, i.e., the path with the minimum total weight. This is a typical graph theory shortest path optimization problem. The maintainability index is a comprehensive indicator for evaluating the quality of a maintenance solution. It is usually inversely proportional to the total path weight; that is, the lower the total weight, the higher the maintainability index and the better the solution. The optimization process involves using an algorithm (such as Dijkstra's algorithm or A* algorithm) to traverse all possible strategies and their optimal paths to find the combination that maximizes the maintainability index. This finally selected strategy with the highest maintainability index and its execution path constitute the final maintenance decision instruction.

[0091] Based on the same inventive concept, such as Figure 6 As shown, the present invention also provides a self-diagnosis and early warning system for the operating status of a carton conveying equipment, the system comprising:

[0092] The multi-source signal acquisition module is used to acquire vibration spectrum data, current ripple fluctuation rate data, equipment operating parameters, vibration wave propagation time sequence data, and laser scanning data;

[0093] The composite sensing generation module is used to generate composite sensing data based on the vibration spectrum data and current ripple fluctuation rate data.

[0094] The deformation feature extraction module is used to generate carton deformation features based on the laser scanning data;

[0095] The health record modeling module is used to establish a dynamic health record for the equipment based on its operating parameters.

[0096] An anomaly diagnosis module is used to perform anomaly separation processing on the composite sensor data and the device dynamic health record to generate a first-level diagnostic result.

[0097] The fault tracing module is used to perform fault tracing analysis on the vibration wave propagation time series data and the carton deformation characteristics based on the primary diagnostic results, and generate secondary positioning information;

[0098] The maintenance decision module is used to generate maintenance decision instructions based on the secondary positioning information.

[0099] The early warning output module is used to output an early warning signal containing the faulty component identification and maintenance measures based on the maintenance decision command.

[0100] To verify the feasibility of this invention in practice, it was applied to a large automated logistics center. This logistics center has dozens of high-speed cardboard box conveyor lines for sorting and transferring packages. Traditional maintenance methods rely on periodic inspections and reactive repairs. When hidden faults such as roller jamming or bearing wear occur, it is difficult to quickly locate them, often leading to unplanned downtime of the conveyor lines and affecting overall sorting efficiency. This logistics center hopes to use the method of this invention to achieve real-time self-diagnosis and predictive maintenance of the cardboard box conveyor equipment's operating status.

[0101] In this embodiment, the logistics center deploys the system of the present invention on a critical conveyor line. The system uses a multi-source signal acquisition module to install vibration sensors and current sensors on the drive motor, critical bearing locations, and frame of the conveyor line. A laser scanner is installed above the end of the conveyor line to continuously acquire vibration spectrum data, current ripple fluctuation rate data, vibration wave propagation time sequence data, laser scan data, and equipment operating parameters including the motor current harmonic amplitude ratio.

[0102] The system first generates composite sensing data that is highly sensitive to combined mechanical and electrical disturbances by using time-domain alignment and energy gradient change feature extraction, based on acquired vibration spectrum data and current ripple fluctuation data. Simultaneously, based on long-term monitored current harmonic amplitude ratio data, a unique dynamic health record for the conveyor line is established, recording its performance degradation offset from initial installation to several months of operation.

[0103] At 15:20 on August 15, 2023, the system's anomaly diagnosis module detected continuous small-amplitude spike pulses in the composite sensor data. This feature deviated significantly from the normal operating mode in the equipment's dynamic health record, and a primary diagnostic result was generated, indicating an early potential fault in the equipment. Upon receiving the primary diagnostic result, the fault tracing module was activated. This module analyzed the vibration wave propagation time-series data and calculated the first difference in propagation delay from the sensor near the motor to the sensor in the middle of the frame to be 3.5ms. This value exceeded the preset 2.0ms propagation threshold, initially pointing the fault source to the drive motor. At the same time, the deformation feature extraction module analyzed the laser scan data of the cardboard boxes passing through this section and found slight, regular scratches on the bottom of multiple cardboard boxes. After decoupling the deformation physical quantities, this feature highly matched the small high-frequency vibration model caused by early wear of the motor bearing. Combining the two pieces of information, the system generated secondary location information: early wear of the output bearing of drive motor A03.

[0104] Subsequently, based on the secondary positioning information, the maintenance decision module constructed a fault location topology map including motor A03, the coupling, the gearbox, and its base. While matching the standard bearing replacement maintenance strategy, the system, through node correlation analysis and querying the equipment's dynamic health record, discovered that the coupling associated with the bearing had reached 85% of its wear life. To avoid a second downtime in the short term, the system optimized the maintainability index and generated a maintenance decision instruction to "replace the motor A03 bearing and coupling in one go." Finally, the early warning output module encapsulated this instruction as an early warning signal containing "Faulty Component Identifier: Motor A03 - Bearing," "Maintenance Measures: Replacement," and "Recommended Collaborative Maintenance: Replace Coupling," and sent it to the maintenance team's mobile terminals, automatically generating a parts requisition form in the spare parts system. Following the precise instructions, the maintenance personnel completed the work during the nighttime maintenance window in just 45 minutes, avoiding a potential daytime production interruption.

[0105] Data shows that, through the system of this invention, the logistics center achieved accurate prediction and efficient maintenance of conveyor line faults. Compared with the traditional method of relying on manual experience for troubleshooting, this invention reduces fault location time from an average of 2-3 hours to less than 5 minutes, with a diagnostic accuracy rate of over 98%. Through predictive maintenance, the average monthly unplanned downtime of the pilot conveyor line was reduced by 70%, and spare parts costs were reduced by approximately 15% by avoiding misdiagnosis and replacement of faulty components.

[0106] Table 1 Comparison of Fault Diagnosis Efficiency of Carton Conveying Equipment

[0107]

[0108] Table 2 Comparison of Equipment Maintenance and Operation Efficiency Data

[0109]

[0110] Table 3. Example Data Table for Diagnosis and Decision-Making of Specific Fault Events (Wear of Bearing A03 in Motor)

[0111]

[0112] As can be seen from the data in Tables 1 to 3 above, the present invention has achieved significant technical effects in the practical application of carton conveying equipment. Table 1 clearly demonstrates the significant advantage of the present invention in fault diagnosis efficiency, especially in reducing the minute-level fault location time by more than 97% and providing early warning, fundamentally changing the maintenance mode. The data in Table 2 proves that the improvement in diagnostic efficiency directly translates into considerable economic and operational benefits. The significant reduction in unplanned downtime and maintenance costs directly improve the operational efficiency of the logistics center. Table 3 records in detail the entire process of a real fault from detection to decision-making, showcasing the logical rigor and data-driven characteristics of the present invention. Through multi-dimensional information mutual verification, the accuracy of location and the optimization of decision-making are ensured, fully demonstrating the advanced nature and practicality of the present invention in realizing intelligent equipment maintenance.

[0113] It should be noted that the electrical connections between the various units described above do not necessarily represent direct or indirect connections. Any indirect connection method can be applied to the embodiments of the present invention as long as it achieves the purpose of the present invention. The above descriptions are merely exemplary embodiments of the present invention and should not be construed as limiting the scope of the present invention.

[0114] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. A method for self-diagnosis and early warning of the operating status of a carton conveying equipment, characterized in that, The method includes: Acquire vibration spectrum data, current ripple fluctuation rate data, equipment operating parameters, vibration wave propagation time sequence data, and laser scanning data; Based on the vibration spectrum data and current ripple fluctuation rate data, composite sensing data is generated, including: performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector; extracting the energy gradient change features in the time-domain synchronization feature vector to generate composite sensing data; The energy gradient change characteristics are calculated as follows: ， in, Representative at The characteristics of the energy gradient change at any given time, i.e., the composite sensing data to be sought. for The instantaneous energy at time t is calculated from the time-domain synchronization feature vector at that time, which contains... The vibrational components and current fluctuation components at any given moment, instantaneous energy It is calculated using the following formula: ， in for The amplitude of the vibration component at any given moment; for The amplitude of the current fluctuation component at any given moment; For current fluctuations within a time window The mean within; Let be the weighting coefficient for vibration and current energy, and satisfy . , For the integration time window, This is the instantaneous energy at the previous sampling time; Based on the laser scanning data, the deformation characteristics of the carton are generated; Based on the equipment operating parameters, a dynamic health record for the equipment is established, wherein establishing the dynamic health record for the equipment includes: acquiring current harmonic amplitude ratio data from the equipment operating parameters; monitoring the current harmonic amplitude ratio data to obtain a time-varying degradation offset; and establishing a dynamic health record for the equipment based on the time-varying degradation offset. The time-varying degradation offset is calculated as follows: ， In this formula, Representative at The time-varying degradation offset calculated at each moment. Is Time measured The amplitude ratio data of the second harmonic. This is the ratio of the baseline amplitude of that harmonic under healthy conditions; The composite sensor data and the device's dynamic health record are subjected to anomaly separation processing to generate a primary diagnostic result; Based on the primary diagnostic results, a fault source analysis is performed on the vibration wave propagation time series data and the carton deformation characteristics to generate secondary positioning information. The fault source analysis includes: acquiring the transmission threshold and vibration peak time series data of the vibration sensor; calculating the first difference in propagation delay based on the vibration peak time series data; and determining that the positioning motor bearing fails when the first difference in propagation delay exceeds the transmission threshold. The calculation method for the first difference in propagation delay is as follows: ， in, This is the first difference in propagation delay. The time it takes for the vibration peak to reach the sensor closest to the motor. The time it takes for the same vibration peak to reach another predetermined sensor position; Based on the secondary positioning information, a maintenance decision instruction is generated; Based on the maintenance decision command, an early warning signal containing the faulty component identification and maintenance measures is output.

2. The self-diagnosis and early warning method for the operating status of a carton conveying equipment according to claim 1, characterized in that, The step of performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector includes: Based on the vibration spectrum data, a time-domain vibration sequence is obtained; The current ripple fluctuation rate data is subjected to time-domain waveform normalization processing to obtain the current fluctuation time series. The time-domain vibration sequence and the current fluctuation time series are time-domain aligned to generate a time-domain synchronization feature vector.

3. The self-diagnosis and early warning method for the operating status of a carton conveying equipment according to claim 1, characterized in that, The generation of carton deformation features based on the laser scanning data includes: Dynamic displacement compensation and geometric contour extraction are performed on the laser scanning data to obtain a calibrated three-dimensional edge coordinate set; The deformation physical quantities of the three-dimensional edge coordinate set are decoupled and calculated to generate the deformation characteristics of the carton.

4. The self-diagnosis and early warning method for the operating status of a carton conveying equipment according to claim 1, characterized in that, The step of generating maintenance decision instructions based on the secondary positioning information includes: Fault topology modeling is performed on the secondary location information to obtain the fault location topology map; The fault location topology map is used to match and optimize maintenance strategies, and maintenance decision instructions are generated.

5. The self-diagnosis and early warning method for the operating status of a carton conveying equipment according to claim 1, characterized in that, The output of a warning signal containing faulty component identification and maintenance measures based on the maintenance decision instruction includes: The maintenance decision command is parsed to obtain the optimized strategy parameters for maintenance measures of the faulty component; The optimization strategy parameters for the maintenance measures of the faulty component are subjected to adaptive signal encapsulation processing, and an early warning signal containing the faulty component identification and maintenance measures is output.

6. The self-diagnosis and early warning method for the operating status of a carton conveying equipment according to claim 4, characterized in that, The step of performing maintenance strategy matching and optimization on the fault location topology map to generate maintenance decision instructions includes: Node correlation analysis and maintenance path weight calculation are performed on the fault location topology to obtain the path weight matrix; Based on the path weight matrix, dynamic strategy matching and maintainability index optimization are performed to generate maintenance decision instructions.

7. A self-diagnosis and early warning system for the operating status of a carton conveying equipment, applied to a self-diagnosis and early warning method for the operating status of a carton conveying equipment as described in any one of claims 1-6, characterized in that, The system includes: The multi-source signal acquisition module is used to acquire vibration spectrum data, current ripple fluctuation rate data, equipment operating parameters, vibration wave propagation time sequence data, and laser scanning data. The composite sensing generation module is used to generate composite sensing data based on the vibration spectrum data and the current ripple fluctuation rate data, including: performing time-domain alignment processing on the vibration spectrum data and the current ripple fluctuation rate data to generate a time-domain synchronization feature vector; and extracting the energy gradient change features in the time-domain synchronization feature vector to generate composite sensing data. The energy gradient change characteristics are calculated as follows: ， in, Representative at The characteristics of the energy gradient change at any given time, i.e., the composite sensing data to be sought. for The instantaneous energy at time t is calculated from the time-domain synchronization feature vector at that time, which contains... The vibrational components and current fluctuation components at any given moment, instantaneous energy It is calculated using the following formula: ， in for The amplitude of the vibration component at any given moment; for The amplitude of the current fluctuation component at any given moment; For current fluctuations within a time window The mean within; Let be the weighting coefficient for vibration and current energy, and satisfy . , For the integration time window, This is the instantaneous energy at the previous sampling time; The deformation feature extraction module is used to generate carton deformation features based on the laser scanning data; A health record modeling module is used to establish a dynamic health record for the equipment based on the equipment operating parameters. The establishment of the dynamic health record includes: acquiring current harmonic amplitude ratio data from the equipment operating parameters; monitoring the current harmonic amplitude ratio data to obtain a time-varying degradation offset; and establishing a dynamic health record for the equipment based on the time-varying degradation offset. The time-varying degradation offset is calculated as follows: ， In this formula, Representative at The time-varying degradation offset calculated at each moment. Is Time measured The amplitude ratio data of the second harmonic. This is the ratio of the baseline amplitude of that harmonic under healthy conditions; An anomaly diagnosis module is used to perform anomaly separation processing on the composite sensor data and the device dynamic health record to generate a first-level diagnostic result. The fault tracing module is used to perform fault tracing analysis on the vibration wave propagation time series data and the carton deformation characteristics based on the primary diagnostic results, and generate secondary positioning information. The fault tracing analysis includes: acquiring the transmission threshold and vibration peak time series data of the vibration sensor; calculating the first difference in propagation delay based on the vibration peak time series data; and determining that the positioning motor bearing fails when the first difference in propagation delay exceeds the transmission threshold. The calculation method for the first difference in propagation delay is as follows: ， in, This is the first difference in propagation delay. The time it takes for the vibration peak to reach the sensor closest to the motor. The time it takes for the same vibration peak to reach another predetermined sensor position; The maintenance decision module is used to generate maintenance decision instructions based on the secondary positioning information. The early warning output module is used to output an early warning signal containing the faulty component identification and maintenance measures based on the maintenance decision command.

Images