Method for identifying abnormality of structural monitoring sensor in logistics sorting production line, processing device and logistics sorting system

Abstract

The application discloses a structure monitoring sensor anomaly identification method, a processing device and a logistics sorting system in a logistics sorting production line, relates to the technical field of the logistics sorting production line, and solves the technical problem that the state anomaly of the structure monitoring sensor cannot be accurately identified without stopping the sorting production line device. The method comprises the following steps: when a non-aliasing sorting task is executed, task information of the sorting task is acquired; the sorting task is executed, and actual response characteristics of a first structure monitoring sensor bound with a structure section passing through a collection time window are acquired; reference response characteristics corresponding to the structure section are queried from a running correlation mapping table; based on the correlation between the actual response characteristics and the reference response characteristics, a binding score of the structure section is determined; and based on the position relationship between the structure section with the highest binding score and the structure section bound with the first structure monitoring sensor, and the deviation between the actual response characteristics and the corresponding reference response characteristics, the state of the first structure monitoring sensor is determined.

Description

Technical Field

[0001] This invention relates to the field of logistics sorting production line technology, and in particular to a method, processing equipment and logistics sorting system for identifying abnormalities in structural monitoring sensors in a logistics sorting production line. Background Technology

[0002] Logistics sorting lines are used to automatically identify and mechanically divert incoming packages to their corresponding slots / chutes based on their destination information. Structural monitoring sensors are typically deployed along the main line of the logistics sorting line, including belt conveyors, narrow-belt sorters and their supports (containing electric rollers), sorting execution units, and slots / chutes, to detect vibration, impact, strain, displacement (or tilt angle), etc., within their respective structural sections. Currently, the deployment of existing structural monitoring sensors usually involves construction personnel recording the sensor numbers and their installation locations, then manually establishing a mapping relationship between sensor numbers and installation locations in a host computer. This mapping relationship, combined with the sensor output monitoring signals, enables fatigue warnings, impact source tracing, and equipment health management for the sorting line equipment.

[0003] Structural monitoring sensors are typically mounted on the surface of production line machinery using threaded or bolted connections, adhesive bonding, or magnetic mounting. During continuous operation of a logistics sorting line, factors such as package drop impacts, roller rotation vibrations, and conveyor belt movement generate continuous dynamic loads, causing the connection between the structural monitoring sensors and the mechanical structure to loosen or shift. In such cases, the monitoring signals output by the sensors cannot accurately reflect the vibration, impact, strain, and displacement of the target monitored area, affecting the accuracy of subsequent structural fatigue warnings, impact tracing, and equipment health management. Because the package transport paths for sorting tasks in different compartments of a logistics sorting line may differ, and not all tasks follow a fixed path, the vibration, impact, and strain signals detected by a structural monitoring sensor in one structural section may be transmitted from other structural sections performing other tasks. This results in a wide range of normal signal output from the sensors. Therefore, the magnitude of the structural monitoring sensor's output signal alone cannot accurately identify whether its condition is abnormal. Therefore, in actual production, after the sorting production line has been running for a period of time, it is necessary to periodically stop the machine and tap or perform single-point actions to check whether the structural monitoring sensors are loose or displaced. However, this will reduce the number of packages sorted on the production line and increase operating costs.

[0004] In the process of realizing this invention, the inventors discovered at least the following problems in the prior art: It is impossible to accurately identify abnormal status of structural monitoring sensors without shutting down the sorting production line equipment. Summary of the Invention

[0005] The purpose of this invention is to provide a method, processing equipment, and logistics sorting system for identifying abnormalities in structural monitoring sensors in a logistics sorting production line, thereby solving the technical problem in the prior art that it is impossible to accurately identify abnormalities in the state of structural monitoring sensors without stopping the sorting production line equipment. The various technical effects of the preferred solutions among the many technical solutions provided by this invention are detailed below.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The present invention provides a method for identifying structural monitoring sensor anomalies in a logistics sorting production line. When performing a non-overlapping sorting task, the method performs the following steps: acquiring task information for the sorting task, including the target grid and the planned start and end times; querying a runtime association mapping table using the target grid to find all structural sections traversed by the sorting task in the logistics sorting production line; determining the collection time window for the sorting task based on the planned start and end times; wherein the runtime association mapping table stores structural sections traversed by sorting tasks at different target grids, structural monitoring sensors bound to the traversed structural sections, and reference response features corresponding to each structural monitoring sensor, the reference response features including reference response arrival time, reference response amplitude peak value, frequency band energy mean vector, reference duration, and reference signal time series; executing the sorting task and acquiring the structural sections traversed by the sorting task within the collection time window. The bound first The actual response characteristics of the individual structural monitoring sensors; This indicates the index of the structural segment traversed by the sorting task. For structural sections The bound structure monitoring sensor index, , All values ​​are positive integers. The actual response characteristics include response arrival time, peak response amplitude, frequency band energy vector, duration, and signal time series. The associated mapping table is used to query the data bound to the first... Similar structural monitoring sensors to individual structural monitoring sensors Each structural segment was extracted. The reference response characteristics of the monitoring sensors of the same type of structure respectively bound to each structural segment; It is a positive integer; based on the first The actual response characteristics of the structural monitoring sensor are similar to those of the first... The correlation of the first baseline response feature is used to determine the first... The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score, ; It is a positive integer; based on the structural segment with the highest binding score and the first... The positional relationship of the structural segments to which the structural monitoring sensors are attached, and the relationship between the actual response characteristics and the first... The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of a structural monitoring sensor is described as loose, displaced, or normal.

[0007] Preferably, the determination of the first The status of the structure monitoring sensor includes: based on the first The actual response characteristics of the structural monitoring sensor are similar to those of the first... The correlation of the first baseline response feature is used to determine the first... The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score, ; It is a positive integer; if the structural segment with the highest binding score is the first... The structural segment to which the structural monitoring sensor is attached, then based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose; if the structural segment with the highest binding score is associated with the first... If the structural segments to which the structural monitoring sensors are attached are adjacent, then the first one is determined. The status of the structural monitoring sensor is shifted.

[0008] Preferred, the first The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score is: ;in, As a structural constraint indicator, if the structural section Satisfy the first The structural constraints of the structural segments to which the structural monitoring sensors are bound, then ,otherwise ;in, This indicates the temporal correlation calculated based on the envelope of the stated signal time series and the envelope of the reference signal time series. Indicates the weight of time relevance; To ensure amplitude consistency based on the ratio of the peak value of the response amplitude to the peak value of the reference response amplitude, Indicates the magnitude consistency weight; The cosine similarity between the frequency band energy vector and the frequency band energy mean vector is represented. Indicates the spectral similarity weight; This indicates the propagation consistency calculated based on the deviation between the response arrival time and the reference response arrival time, and the deviation between the duration and the reference duration. This represents the propagation consistency weight.

[0009] Preferred structural segments Satisfy the first Structural constraints of structural segments bound to structural monitoring sensors are represented as follows: structural segment In the Within a preset neighborhood of the structural segment to which each structural monitoring sensor is attached.

[0010] Preferably, the step based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose, including: based on the first The spectral deviation is calculated by the cosine similarity between the frequency band energy vector of a structural monitoring sensor and the mean frequency band energy vector in its corresponding reference response feature. If the spectral deviation is greater than a spectral deviation threshold, then the first sensor is determined to be... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of the first structural monitoring sensor is normal; or, based on the first... The amplitude deviation is calculated by the ratio of the peak value of the response amplitude of each structural monitoring sensor to the peak value of the reference response amplitude in its corresponding reference response characteristic. If the amplitude deviation is greater than the amplitude deviation threshold, then the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of the first structural monitoring sensor is normal; or, if the first... If the deviation between the arrival time of the response of a structural monitoring sensor and the arrival time of the reference response in its corresponding reference response feature is greater than the time delay deviation threshold, then the sensor is determined to be the first one. The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of the structural monitoring sensor is normal; or, if based on the first... If the temporal correlation between the envelope of the signal time series of a structural monitoring sensor and the envelope of the corresponding reference signal time series in the reference response features is less than the temporal correlation threshold, then the sensor is determined to be the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of all structural monitoring sensors is normal.

[0011] Preferably, the structural monitoring sensors include at least one of the following: acceleration sensors, strain sensors, tilt sensors, and displacement sensors.

[0012] Preferably, the collection time window for determining the sorting task based on the start and end times of the planned actions is... ,in, This indicates the start time in the planned action's start and end times. Indicates the duration of noise retention before the action. This indicates the end time in the start and end times of the planned action. Indicates the duration of structural decay retention after the action.

[0013] Preferably, the process of constructing the runtime association mapping table includes: initializing the runtime association mapping table; determining all structural segments traversed by the sorting task with each grid as the target grid according to the structural topology diagram of the logistics sorting production line; traversing the grids of the logistics sorting production line and performing the following steps: currently traversing to the grid Get multiple grids The execution information for the successful, non-overlapping sorting task at the target compartment includes the start and end times of the actual actions and all structural segments traversed. Represents the grid index, which is a positive integer; based on the first... The start and end times of the actual actions that have successfully executed the sorting task are used to determine the data collection time window, based on which the data collection time window is the first... Each structural segment that has successfully completed a sorting task is divided into a reference time interval; Indicates the index of successfully executed tasks; obtains the signal time series collected by all structural monitoring sensors on the logistics sorting production line within the collection time window; based on the first... Extracting the time series signal from the first structural monitoring sensor The response arrival time and response peak time of each structural monitoring sensor; statistical analysis of the first... The arrival and peak response times of each structural monitoring sensor fall within the structural sections they pass through. The number of times the reference time interval is calculated, and the number of times is used to calculate the first time interval. Each structural monitoring sensor is located in the structural section it passes through. The recurrence rate of falling into the first place; if the first place Each structural monitoring sensor is located in the structural section it passes through. If the recurrence rate of the fall-in is greater than the fall-in recurrence rate threshold, then the first... Each structural monitoring sensor and the structural sections it passes through Binding, and based on the first A structural monitoring sensor fell into the structural section it was passing through. Time series extraction of signal at time 1 The reference response characteristics corresponding to each structural monitoring sensor; the grid All structural sections that have successfully executed the sorting task with grid j as the target grid, all structural monitoring sensors bound to each structural section, and the baseline response characteristics corresponding to each structural monitoring sensor are associated and stored in the operation association mapping table.

[0014] The present invention also provides a processing device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors are configured to execute the one or more computer programs stored in the memory to cause the one or more processors to perform the structural monitoring sensor anomaly identification method in a logistics sorting production line as described in the present invention.

[0015] This invention also provides a logistics sorting system, comprising: a host computer; a logistics sorting production line, wherein one or more structural monitoring nodes are deployed on all or part of the structural sections of the logistics sorting production line, each structural monitoring node including a processor, a sensing communication unit connected and communicating with the processor, and one or more structural monitoring sensors; a gateway, connected and communicating with the host computer and the sensing communication unit respectively, wherein the structural monitoring nodes upload signal time series to the host computer through the sensing communication unit and the gateway; one or more end-side control nodes, which obtain task instructions issued by the host computer through the gateway, and control one or more sorting execution units of the logistics sorting production line to work based on the task instructions; the host computer executes the steps of the structural monitoring sensor anomaly identification method in the logistics sorting production line of this invention to obtain the status of the structural monitoring sensors.

[0016] Implementing one of the above-described technical solutions of the present invention has the following advantages or beneficial effects: The non-overlapping sorting tasks in the actual operation of the logistics sorting production line are directly used as test incentive tasks to avoid interference from other sorting tasks in the logistics sorting production line. During the execution of the sorting task, the status of the structural monitoring sensors bound to the structural sections through which the sorting task passes is identified in parallel without interrupting the operation of the logistics sorting production line. The abnormal status of the structural monitoring sensors can be accurately identified without stopping the sorting production line equipment. During the structural monitoring sensor status identification process, the actual response characteristics of the structural monitoring sensors associated with the structural sections traversed by the sorting task are mapped to similar sensors in the operation association mapping table. Cross-comparison of the baseline response characteristics of each structural segment is performed, not limited to the baseline response characteristics of the structural segment bound to the structural monitoring sensor. This expands the search range to accurately identify and distinguish between the two abnormal states of displacement and loosening of the structural monitoring sensor. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart illustrating the method for identifying structural monitoring sensors anomalies in a logistics sorting production line according to Embodiment 1 of the present invention. Figure 2 This is a partial schematic diagram of a logistics sorting production line in one example of the present invention; Figure 3 This is a schematic diagram of the process of determining the state of the structure monitoring sensor in Embodiment 1 of the present invention; Figure 4 This is a schematic diagram of the acquisition time window in Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of the process of constructing the association mapping table in Embodiment 1 of the present invention; Figure 6 This is a hierarchical structure diagram of the running association mapping table in Embodiment 1 of the present invention; Figure 7 This is a control block diagram of the logistics sorting system in Embodiment 3 of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the present invention clearer, various exemplary embodiments described below will be referenced to the accompanying drawings, which form part of the exemplary embodiments, illustrating various exemplary embodiments that may be used to implement the present invention. Unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. It should be understood that they are merely examples of processes, methods, and apparatuses consistent with some aspects of the present invention disclosed as detailed in the appended claims, and other embodiments may be used, or structural and functional modifications may be made to the embodiments listed herein without departing from the scope and spirit of the present invention.

[0019] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," etc., indicate the orientation or positional relationship based on the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the referred element must have a specific orientation, or be constructed and operated in a specific orientation. The terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. The term "multiple" means two or more. The terms "connected" and "linked" should be interpreted broadly, for example, they can be fixed connections, detachable connections, integral connections, mechanical connections, electrical connections, communication connections, direct connections, indirect connections through an intermediate medium, and can be the internal connection of two elements or the interaction relationship between two elements. The term "and / or" includes any and all combinations of one or more of the related listed items. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0020] To illustrate the technical solution described in this invention, specific embodiments are described below, showing only the parts related to the embodiments of this invention.

[0021] Example 1: Actual logistics sorting production line such as Figure 2 As shown, the system includes a main feeder belt conveyor, a narrow-belt sorter and its support structure (containing electric rollers), grids / chutes, grid supports, branch conveyor lines, and the steel structure supporting the aforementioned equipment or mechanisms. The main feeder belt conveyor and the steel structure are connected by supports and beams. The narrow-belt sorter and its support structure includes roller seats, electric rollers on the roller seats, and drive assemblies for the electric rollers. The grid supports are used to connect the diversion gates, swing wheels, flaps, or chutes to the steel structure.

[0022] Based on the structural design diagram of the logistics sorting production line, the production line is divided into multiple structural sections. A structural section refers to a structural unit within the logistics sorting production line that is relatively independent in mechanical structure and has identifiable boundaries along the vibration / impact transmission path. The specific division rules are as follows: Structural components on the logistics sorting production line that can be independently disassembled, maintained, or replaced can be considered as a structural section. For example, a section of the main conveyor belt, an independent installation structure of the narrow belt sorter and its support, the mounting bracket of a sorting execution unit, and the support bracket and its associated crossbeams of a slot (chute) can all be considered as independent structural sections.

[0023] Alternatively, the structural sections can be divided based on the integrity of the vibration transmission path. Specifically, structural components with continuous vibration transmission paths and consistent signal transmission characteristics can be divided into the same structural section using the connection surface of the structural components as the boundary. Structural components whose signal transmission characteristics change significantly after crossing the connection surface can be divided into different structural sections.

[0024] In this embodiment, the structural segments are numbered and used as graph nodes. The entrance and each compartment of the logistics sorting line are also set as graph nodes. An edge is created between any two actually connected graph nodes to form the structural topology of the logistics sorting line. The logistics sorting line has multiple compartments. When any compartment is chosen as the target compartment, a definite transport path can be quickly obtained through the structural topology of the logistics sorting line. Packages sequentially pass through the structural segments along this transport path to reach the target compartment.

[0025] In this embodiment, one or more structural monitoring sensors are deployed on all or part of the structural sections. Figure 2 (Not illustrated). Structural monitoring sensors include at least one of the following: accelerometers, strain sensors, tilt sensors, and displacement sensors. Because the impact loads on structural sections vary at different locations, different types of structural monitoring sensors can be installed in different structural sections, or more than one type can be installed in the same structural section. Accelerometers are not limited to triaxial MEMS (Micro-Electro-Mechanical Systems) accelerometers or piezoelectric accelerometers. Strain sensors are not limited to resistance strain gauges or fiber optic strain sensors. Triaxial MEMS accelerometers are generally installed in structural sections located at grids, grid supports, roller seats, and main conveyor belts. Piezoelectric accelerometers are generally installed in structural sections at grids or drop points with high impact frequencies. Strain sensors are generally installed in structural sections located on beams, supports, and steel structures. Displacement sensors and tilt sensors are generally installed in structural sections at the connection points of covered supports, or in structural sections located on main conveyor belts or steel structures.

[0026] Structural monitoring sensors are typically mounted on the surfaces of mechanical structures in production lines using threaded or bolted connections, adhesive bonding, or magnetic mounting. During the continuous operation of logistics sorting lines, factors such as package drop impacts, roller rotation vibrations, and conveyor belt movement generate continuous dynamic loads, leading to loosening or displacement of the connection between the structural monitoring sensors and the mechanical structure surfaces. This affects the accuracy of fatigue warnings, impact tracing, and equipment health management for sorting line equipment. Loosening refers to a state where the structural monitoring sensor, under dynamic load impacts at its installation position, experiences a decrease in connection preload, resulting in microscopic relative movement or reduced contact stiffness with its mounting surface. During this relative movement, the spatial coordinates of the structural monitoring sensor do not move across the boundary of the structural section, but only within a small range within the structural section. In a loose state, the acquired signal exhibits distortion characteristics such as high-frequency attenuation and amplitude fluctuations. Displacement refers to a state where the sensor deviates from its original installation position due to dynamic loads and crosses into an adjacent structural section. In a displaced state, its response arrival time, frequency band energy distribution, and other response characteristics show a high degree of consistency with the adjacent structural section.

[0027] In this embodiment, a non-overlapping sorting task refers to a sorting task in which the physical effects such as vibration and impact generated on the corresponding conveyor path are caused solely by the sorting task itself and are not superimposed or interfered with by the physical effects of other sorting tasks when the sorting task is executed within the planned start and end time.

[0028] like Figure 1 As shown, this embodiment provides a method for identifying structural monitoring sensor anomalies in a logistics sorting production line. The executing entity of this method is not limited to the host computer in the logistics sorting system, but can be any one of a physical server, computer equipment, cloud server, industrial control computer, programmable logic controller (PLC), or embedded processor, or a combination of the above devices. The method is as follows: When performing a non-overlapping sorting task, execute: Step A1: Obtain the task information for the sorting task, which includes the target compartment and the start and end times of the planned action.

[0029] In this embodiment, each sorting task has a target slot. To avoid interference, the planned start and end times for sorting tasks with the same target slot are different. The execution entity of this method is not limited to obtaining task information from a management platform or reading task information from its internally stored task list. Preferably, the task information may also include the address of the execution unit that implements the sorting task. The planned start and end times include the start time. and end time .

[0030] Step A2 involves retrieving all structural segments traversed by the sorting task along the logistics sorting line from the runtime association mapping table using the target grid. The data collection time window for the sorting task is determined based on the planned start and end times. The runtime association mapping table stores the structural segments traversed by sorting tasks at different target grids, the structural monitoring sensors bound to these segments, and the baseline response characteristics for each sensor. These baseline response characteristics include the baseline response arrival time, peak baseline response amplitude, average frequency band energy vector, baseline duration, and baseline signal time series.

[0031] Understandably, the association mapping table uses a multi-tree structure, with each tree corresponding to a target cell. Figure 6 It displays the tree structure corresponding to a specific target cell, in order to Figure 6 In a sorting task whose endpoint is the target compartment, the sorting task passes through a total of [number] [locations]. Each structural segment The value is a positive integer. Each structural segment along the route is equipped with more than one structural monitoring sensor. The number of structural monitoring sensors equipped in each structural segment can be the same or different, and the types of structural monitoring sensors equipped in the same structural segment can be the same or different, such as... Figure 6 As shown, each structural monitoring sensor bound to a structural segment corresponds to a baseline response characteristic. The association mapping table can be stored in the memory of the execution entity of this method. Running the association mapping table allows for pre-deployment manual testing of sensor response signals during structural monitoring sensor deployment, calculation of baseline response characteristics for each structural monitoring sensor based on the response signals, and integration with the structural topology construction of the logistics sorting production line.

[0032] Preferably, the data collection time window for the sorting task is determined based on the start and end times of the planned actions. ,like Figure 3 As shown, where, Indicates the start time in the planned start and end times of the action. Indicates the duration of noise retention before the action. Indicates the end time in the planned action's start and end times. This indicates the duration of structural decay retention after the action. Extending the time before and after the planned action start and end times, a data acquisition time window is obtained. Preserve background noise before the action, with a value ranging from 0.2s to 1s; utilize Preserving the structural decay process, with values ​​ranging from 0.5s to 3s, helps to extract accurate actual response characteristics.

[0033] Step A3: Execute the sorting task and obtain the structural segments traversed by the sorting task within the collection time window. The bound first The actual response characteristics of the individual structural monitoring sensors; This indicates the index of the structural segment traversed by the sorting task. For structural sections The bound structure monitoring sensor index, , All are positive integers.

[0034] In this embodiment, the execution entity of the present invention controls the actions of the execution units on the logistics sorting production line according to the task information to complete the sorting task. During the execution of the sorting task, according to the operation association mapping table, such as... Figure 4 As shown, all structural sections traversed by the executing entity from the sorting task (assuming a total of...) Each structural segment The structure monitoring sensors are bound together to collect their output signal time series, and the actual response characteristics of each structure monitoring sensor are extracted based on the signal time series. Specifically, the strain sensor outputs a strain time series, the acceleration sensor outputs an acceleration time series, the displacement sensor outputs a displacement time series, and the tilt sensor outputs a tilt time series.

[0035] Preferred, the first The actual response characteristics of a structural monitoring sensor include response arrival time, peak response amplitude, frequency band energy vector, duration, and signal time series.

[0036] Specifically, the response arrival time is based on the start time. Using the zero point as a reference, the signal time series envelope is calculated within the acquisition time window. The time point when the envelope first exceeds the background noise threshold (the sum of the background mean and three times the background standard deviation) is marked, and the starting time is subtracted. The response arrival time is obtained. The peak response amplitude is obtained by traversing the signal time series within the acquisition time window and taking the amplitude value with the largest absolute value. The frequency band energy vector is obtained as follows: a Fast Fourier Transform is performed on the signal time series within the acquisition time window, dividing the spectrum into several continuous frequency bands according to the frequency range. The sum of squares or the mean energy of the spectral amplitudes in each frequency band is calculated and used as the energy value of that frequency band. The energy values ​​of all frequency bands are arranged into a vector. Within the acquisition time window, the duration is obtained by calculating the difference between the start and end points, starting from the response arrival time and ending at the moment when the envelope of the signal time series last falls below the background noise threshold.

[0037] Step A4, query the associated mapping table to find the bound first... Similar structural monitoring sensors to individual structural monitoring sensors The structural section (including the first) (The structure segment currently bound to each structure monitoring sensor) and extract it. The baseline response characteristics of the same type of structural monitoring sensors bound to each structural segment; It is a positive integer.

[0038] Step A5, based on the first The actual response characteristics of the structural monitoring sensor are similar to those of the first... The correlation of the first baseline response feature is used to determine the first... The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score, ; It is a positive integer.

[0039] Step A6, based on the structural segment with the highest binding score and the... The positional relationship of the structural segments to which the structural monitoring sensors are attached, and the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of a structural monitoring sensor is described as loose, displaced, or normal.

[0040] Step A5, the first The actual response characteristics of each structural monitoring sensor are respectively compared with... The first baseline response feature is compared, and the second baseline response feature is determined based on the comparison results. The status of the structure monitoring sensor is indicated as loose, displaced, or normal.

[0041] Step A3 obtains all structural segments traversed by the sorting task (assuming they are...). After identifying the actual response characteristics of the structural monitoring sensors bound to each structural segment, the corresponding tree structure is retrieved from the runtime association mapping table using the target node of the sorting task, and the sorting task path is extracted. The baseline response characteristics of all structural monitoring sensors attached to a structural segment are used (equivalent to extracting all leaf nodes of a tree). The baseline response characteristics of structural monitoring sensors belonging to the same type are grouped together. Based on the measured actual response characteristics of a specific type of monitoring structural sensor and comparing them with the baseline response characteristics within the corresponding group, steps A5 and A6 are executed to determine the state of a specific type of monitoring structural sensor. For example, if a structural segment with an accelerometer attached has... indivual, This includes the first The structural segment currently bound to each structural monitoring sensor will The reference response features corresponding to the accelerometers bound to each structural segment are extracted and grouped into one group. Based on the measured actual response features of each accelerometer, they are compared with the corresponding group. The reference response feature executes steps A5 and A6 to determine the state of the accelerometer. In this embodiment, the first... The actual response characteristics of the structural monitoring sensor are similar to those of the first... The greater the correlation of each baseline response feature, the higher the corresponding binding score.

[0042] Further preferred, the first The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score is: ; in, As a structural constraint indicator, if the structural section Satisfy the first The structural constraints of the structural segments to which the structural monitoring sensors are bound, then ,otherwise ; in, This indicates the temporal correlation calculated based on the envelope of the signal time series and the envelope of the reference signal time series. Indicates the weight of time relevance; To ensure amplitude consistency based on the ratio of the peak response amplitude to the peak reference response amplitude, Indicates the magnitude consistency weight; The cosine similarity between the frequency band energy vector and the frequency band energy mean vector is denoted as spectral similarity. Indicates the spectral similarity weight; This represents the propagation consistency calculated based on the deviations of the response arrival time from the baseline response arrival time and the duration from the baseline duration. This represents the propagation consistency weight. , , , The value range of is [0,1], and satisfies The specific values ​​of the four weights can be set based on user experience.

[0043] In this embodiment, the time correlation is not limited to using existing normalized cross-correlation (NCC) to calculate the time correlation based on the envelope of the signal time series and the envelope of the reference signal time series. , Calculate the ratio of the peak response amplitude to the peak reference response amplitude, and normalize this ratio to obtain amplitude consistency. The absolute value of the difference between the response arrival time and the baseline response arrival time is calculated, and the absolute value of the difference between the duration and the baseline duration is calculated. These two absolute values ​​are then added together and normalized to obtain propagation consistency. .

[0044] Time correlation in the binding score calculation process Amplitude consistency Spectral similarity Consistency of propagation The correlation between the actual response characteristics and the baseline response characteristics of the structural segment is evaluated from four dimensions: time-domain morphology, energy amplitude, spectral distribution, and propagation path. Loosening and displacement exhibit distinct characteristics across these four dimensions. When the structural monitoring sensor indicates loosening, its response waveform morphology, response arrival time, and propagation path remain essentially unchanged, with minimal time correlation. Consistency of propagation The difference compared to the normal state is not significant, but the spectral similarity is... and amplitude consistency Compared to the normal state, there is a significant deviation; when the structural monitoring sensor is in a displaced state, its response waveform, arrival delay, and frequency band energy distribution will highly match the reference response characteristics of adjacent structural segments, exhibiting strong time correlation. Amplitude consistency Spectral similarity Consistency of propagation All four dimensions deviate significantly from the normal state. This results in a high accuracy in the final calculated binding score, which can serve as an important assessment indicator to distinguish between the three states of loosening, displacement, and normality.

[0045] In addition, during the binding score calculation process, settings were configured. As a structural constraint indicator, the search scope is limited to structural segments that satisfy the structural constraints, so that a structural segment that does not satisfy the structural constraints will not be bound even if it has a high binding score.

[0046] Further preferred structural sections Satisfy the first Structural constraints of structural segments bound to structural monitoring sensors are represented as follows: structural segment In the The structural monitoring sensor is attached to a predefined neighborhood of the structural segment. Specifically, the neighborhood refers to the area within the structural segment. Centered on the periphery, it spreads outwards to the surrounding structural sections. The range is formed by a structural segment with a direct hardware connection. Each determination only needs to calculate the binding score of a finite number of structural segments within a preset neighborhood, instead of traversing all structural segments of the logistics sorting production line, thus reducing algorithm complexity and computational resource consumption.

[0047] In this embodiment, preferably, please refer to Figure 3 Step A6 is as follows: If the structural segment with the highest binding score is the first The structural segment to which the structural monitoring sensor is attached, then based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose; if the structural segment with the highest binding score is associated with the first... If the structural segments to which the structural monitoring sensors are attached are adjacent, then the first one is determined. The state of the structural monitoring sensor is shifted. If the structural segment with the highest binding score is associated with the first... If the structural monitoring sensors are attached to structural sections that are not adjacent, it is possible that the structural monitoring sensors have been manually relocated, causing them to report warning information to the management platform or the smart terminals of relevant personnel.

[0048] In this embodiment, more preferably, in step A6, based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose, including: Based on the The spectral deviation is calculated by the cosine similarity between the frequency band energy vector of a structural monitoring sensor and the mean frequency band energy vector in its corresponding reference response characteristics. If the spectrum deviation If it is greater than the spectral deviation threshold, then determine the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of the structural monitoring sensors is normal. Specifically, the spectral deviation... , Indicates the first The cosine similarity between the frequency band energy vector of a structural monitoring sensor and the mean frequency band energy vector in its corresponding reference response characteristics.

[0049] Or, based on the first The amplitude deviation is calculated by the ratio of the peak amplitude of the response of each structural monitoring sensor to the peak amplitude of the corresponding reference response characteristic. If the amplitude deviation If it exceeds the amplitude deviation threshold, then determine the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of each structural monitoring sensor is normal; amplitude deviation. , Indicates the first The ratio of the peak value of the response amplitude of a structural monitoring sensor to the peak value of the reference response amplitude in its corresponding reference response characteristic.

[0050] Or, if the first The deviation between the arrival time of the response of a structural monitoring sensor and the arrival time of the reference response in its corresponding reference response characteristic. If the time delay deviation is greater than the threshold, then determine the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of all structural monitoring sensors is normal.

[0051] Or, if based on the first If the temporal correlation between the envelope of the signal time series of a structural monitoring sensor and the envelope of the corresponding reference signal time series in the reference response features is less than the temporal correlation threshold, then the sensor is determined to be the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of all structural monitoring sensors is normal.

[0052] The above four determination methods identify looseness from four independent physical dimensions: spectrum distribution, amplitude attenuation, propagation delay, and waveform distortion. In practical applications, they can be flexibly selected or combined. Since the effects of the above four determination methods vary when looseness occurs in different installation methods (threaded connection, adhesive, magnetic base) and different structural parts, it is preferable to use the four determination methods in parallel to ensure that no matter what physical form the looseness takes, it can be effectively captured by at least one determination method.

[0053] In this preferred embodiment of Example 1, the association mapping table is constructed automatically online. Please see [link to example]. Figure 5 As shown, the process of building the association mapping table includes: Step B1: Initialize the running association mapping table; specifically, initialize it as a multi-tree structure, with each tree structure having 4 levels and each node in the tree structure being empty.

[0054] Step B2: Based on the structural topology diagram of the logistics sorting production line, determine all structural sections that the sorting task will pass through with each grid as the target grid.

[0055] Step B3: Traverse the sorting grids of the logistics sorting line and perform the following steps: Step B31, currently traversing to the grid. , obtain multiple ( (each) in a grid The execution information for the target grid is the non-overlapping sorting task that has been successfully executed. The execution information includes the start and end times of the actual actions and all structural segments traversed. The grid index is a positive integer; assuming the logistics sorting production line has... Each compartment, then . It is a positive integer, generally greater than or equal to 20.

[0056] Step B32, based on the first The collection time window is determined by the start and end times of the actual actions that have been successfully executed in the sorting task. Similarly, the start and end times of the actual actions and the noise retention time before the actions are combined. and the retention time of structural decay after the action The data acquisition time window is expanded. Based on the data acquisition time window being the [number]th [timeframe]... Each structural segment that has successfully completed a sorting task is divided into a reference time interval; The index, which is a positive integer, indicates the successful execution of the task.

[0057] In this preferred embodiment, a finite element model of the structural section of the logistics sorting production line can be established, and a grid-like structure can be applied to the finite element model. Transient dynamic simulations are performed on the simulated excitation of the target grid to obtain the reference time intervals for each structural segment along the route.

[0058] Step B33: Obtain the time series of signals collected by all structural monitoring sensors on the logistics sorting production line within the collection time window.

[0059] Step B34, based on the first Extracting the time series signal from the first structural monitoring sensor The response arrival time and response peak time of each structural monitoring sensor.

[0060] Step B35, statistic of the first The arrival and peak response times of each structural monitoring sensor fall within the structural sections they pass through. Number of reference time intervals Based on the number Calculate the first Each structural monitoring sensor is located in the structural section it passes through. The recurrence rate of falling into the field ; It is an integer greater than or equal to 0.

[0061] Step B36, if the first The recurrence rate of a structural monitoring sensor falling into structural section m along its path. If the value is greater than the recurrence rate threshold, then the first... Each structural monitoring sensor and the structural sections it passes through Binding, and based on the first A structural monitoring sensor fell into the structural section it was passing through. Time series extraction of signal at time 1 The reference response characteristics corresponding to the structural monitoring sensor. If the first... If the recurrence rate of a structural monitoring sensor falling into structural segment m along its path is not greater than the recurrence rate threshold, then the first structural monitoring sensor will not be included. Each structural monitoring sensor and the structural sections it passes through Binding.

[0062] Specifically, based on sequence A structural monitoring sensor fell into the structural section it was passing through. The signal time series, i.e. based on Extracting the time series of the signal. The baseline response characteristics corresponding to each structural monitoring sensor are determined first. Then, the actual response characteristics of each signal time series are calculated to obtain... The median of the actual response characteristics of the nth signal time series is used to obtain the nth signal time series. The reference response characteristics corresponding to each structural monitoring sensor. The first signal time series is fitted into a single signal time series using the least squares method, and this single time series is used as the first signal time series. The reference signal time series in the reference response characteristics corresponding to each structural monitoring sensor. The mean frequency band energy vector is obtained by taking the mean of the frequency band energy vector in the actual response characteristics of a signal time series.

[0063] Step B37, place the grid The following information is stored in the operation association mapping table: all structural segments that have successfully completed the sorting task with grid j as the target grid, all structural monitoring sensors bound to each structural segment, and the baseline response characteristics corresponding to each structural monitoring sensor. Specifically, the above information is filled into the nodes of the tree structure corresponding to grid j.

[0064] The aforementioned automatic construction process of the association mapping table pre-divides reference time intervals for each structural segment encountered. It then statistically judges the recurrence rate of all structural monitoring sensors whose response arrival and peak response times in multiple successfully executed sorting tasks fall within the reference interval of that structural segment. Only when the recurrence rate exceeds a threshold is the structural monitoring sensor bound to the structural segment. This achieves automatic calibration of structural monitoring sensor locations without downtime, changing the traditional deployment method of manually recording numbers and installation locations and manually entering them into the host computer, thus avoiding incorrect binding due to manual input. Simultaneously, the baseline response features are extracted based on the signal time series from multiple encounters with the same structural segment, providing a reliable comparison benchmark for subsequent sensor status identification. The grid, all structural segments encountered in the task, the sensors bound to each segment, and their baseline response features are associated and stored in a four-layer tree structure with the grid as the root node. This enables rapid retrieval by grid dimension. During actual online identification, it can quickly locate the relevant structural segments and the corresponding baseline response features of the structural monitoring sensors based on the target grid of the current task, improving query efficiency.

[0065] Example 2: The present invention also provides a processing device embodiment, including one or more processors and a memory; wherein the memory is used to store one or more computer programs, and the one or more processors are used to execute the one or more computer programs stored in the memory, so that the processors execute the features / steps of the above-described embodiment of the method for identifying abnormalities of structural monitoring sensors in a logistics sorting production line.

[0066] Example 3: The present invention also provides an embodiment of a logistics sorting system, such as... Figure 7 As shown, the system includes: Host computer; Logistics sorting production line ( Figure 7 (Not shown in the figure) One or more structural monitoring nodes are deployed on all or part of the structural sections of the logistics sorting production line. Each structural monitoring node includes a processor, a sensing communication unit connected to the processor, and one or more structural monitoring sensors. It is assumed that a total of N structural monitoring nodes are deployed on the logistics sorting production line, where N is a positive integer.

[0067] The gateway connects to the host computer and the sensor communication unit respectively. The structural monitoring node uploads the signal time series to the host computer through the sensor communication unit and the gateway. One or more end-side control nodes obtain task instructions from the host computer through a gateway, and control one or more sorting execution units on the logistics sorting production line to work based on the task instructions; the logistics sorting production line has N1 sorting execution units, where N1 is a positive integer. The end-side control nodes and sorting execution units communicate via the RS485 (recommended standard 485) communication protocol.

[0068] The host computer executes the steps of the abnormal identification method for structural monitoring sensors in the logistics sorting production line provided in Example 1 to obtain the status of the structural monitoring sensors.

[0069] The aforementioned logistics sorting system uses a gateway to enable data transmission and communication between the host computer, structural monitoring nodes, and end-side control nodes. While the end-side control nodes execute sorting tasks, the structural monitoring nodes simultaneously collect the structural response signals caused by these actions. The host computer aggregates the actions and response signals of the same task, enabling the identification of abnormal states of the structural monitoring sensors to utilize normal sorting tasks as known excitation sources for online detection without downtime. At the same time, the sensor communication unit and the end-side control nodes in the system architecture are independent of each other, ensuring that the abnormal state identification process does not interfere with the normal and continuous operation of the production line.

[0070] The embodiment is merely a specific example and does not indicate that this is the only way to implement the present invention.

[0071] The above description is merely a preferred embodiment of the present invention. Those skilled in the art will understand that various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the present invention. Furthermore, under the teachings of the present invention, these features and embodiments can be modified to adapt to specific situations and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of the present invention.

Claims

1. A method for identifying anomalies in structural monitoring sensors in a logistics sorting production line, characterized in that, When performing a non-overlapping sorting task, execute: Obtain the task information for the sorting task, including the target compartment and the planned start and end times of the action; Using the target grid, all structural sections that the sorting task passes through in the logistics sorting production line are retrieved from the operation association mapping table; the collection time window of the sorting task is determined based on the start and end times of the planned actions; wherein, the operation association mapping table stores the structural sections that the sorting task passes through for different target grids, the structural monitoring sensors bound to the structural sections that pass through, and the reference response characteristics corresponding to each structural monitoring sensor, the reference response characteristics including the reference response arrival time, the reference response amplitude peak value, the frequency band energy mean vector, the reference duration, and the reference signal time series; Execute the sorting task and obtain the structural segments traversed by the sorting task within the collection time window. The bound first The actual response characteristics of the individual structural monitoring sensors; This indicates the index of the structural segment traversed by the sorting task. For structural sections The bound structure monitoring sensor index, , All are positive integers, and the actual response characteristics include response arrival time, peak response amplitude, frequency band energy vector, duration, and signal time series; Query the runtime association mapping table to find the one bound to the first... Similar structural monitoring sensors to individual structural monitoring sensors Each structural segment was extracted. The reference response characteristics of the monitoring sensors of the same type of structure respectively bound to each structural segment; It is a positive integer; Based on the The actual response characteristics of the structural monitoring sensor are similar to those of the first... The correlation of the first baseline response feature is used to determine the first... The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score, ; It is a positive integer; Based on the structural segment with the highest binding score and the first The positional relationship of the structural segments to which the structural monitoring sensors are attached, and the relationship between the actual response characteristics and the first... The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of a structural monitoring sensor is described as loose, displaced, or normal.

2. The method for identifying structural monitoring sensors in a logistics sorting production line according to claim 1, characterized in that, The determination of the first The status of the structure monitoring sensors includes: If the structural segment with the highest binding score is the first The structural segment to which the structural monitoring sensor is attached, then based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose; If the highest-scoring structural segment is bound to the first... If the structural segments to which the structural monitoring sensors are attached are adjacent, then the first one is determined. The status of the structural monitoring sensor is shifted.

3. The method for identifying structural monitoring sensors in a logistics sorting production line according to claim 1, characterized in that, No. The structural monitoring sensor and the first The structural segment to which the structural monitoring sensor is bound corresponding to each benchmark response characteristic The binding score is: ; in, As a structural constraint indicator, if the structural section Satisfy the first The structural constraints of the structural segments to which the structural monitoring sensors are bound, then ,otherwise ; in, This indicates the temporal correlation calculated based on the envelope of the stated signal time series and the envelope of the reference signal time series. Indicates the weight of time relevance; To ensure amplitude consistency based on the ratio of the peak value of the response amplitude to the peak value of the reference response amplitude, Indicates the magnitude consistency weight; The cosine similarity between the frequency band energy vector and the frequency band energy mean vector is represented. Indicates the spectral similarity weight; This indicates the propagation consistency calculated based on the deviation between the response arrival time and the reference response arrival time, and the deviation between the duration and the reference duration. This represents the propagation consistency weight.

4. The method for identifying structural monitoring sensor anomalies in a logistics sorting production line according to claim 3, characterized in that, Structural Sections Satisfy the first Structural constraints of structural segments bound to structural monitoring sensors are represented as follows: Structural Sections In the Within a preset neighborhood of the structural segment to which each structural monitoring sensor is attached.

5. The method for identifying structural monitoring sensors in a logistics sorting production line according to claim 2, characterized in that, The based on the actual response characteristics and the first The deviation of the reference response characteristics corresponding to the first structural monitoring sensor is used to determine the first... The status of each structural monitoring sensor is either normal or loose, including: Based on the The spectral deviation is calculated by the cosine similarity between the frequency band energy vector of a structural monitoring sensor and the mean frequency band energy vector in its corresponding reference response feature. If the spectral deviation is greater than a spectral deviation threshold, then the first sensor is determined to be... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of each structural monitoring sensor is normal; Or, based on the first The amplitude deviation is calculated by the ratio of the peak value of the response amplitude of each structural monitoring sensor to the peak value of the reference response amplitude in its corresponding reference response characteristic. If the amplitude deviation is greater than the amplitude deviation threshold, then the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of each structural monitoring sensor is normal; Or, if the first If the deviation between the arrival time of the response of a structural monitoring sensor and the arrival time of the reference response in its corresponding reference response feature is greater than the time delay deviation threshold, then the sensor is determined to be the first one. The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of each structural monitoring sensor is normal; Or, if based on the first If the temporal correlation between the envelope of the signal time series of a structural monitoring sensor and the envelope of the corresponding reference signal time series in the reference response features is less than the temporal correlation threshold, then the sensor is determined to be the first... The status of the first structural monitoring sensor is loose; otherwise, determine the first... The status of all structural monitoring sensors is normal.

6. The method for identifying structural monitoring sensor anomalies in a logistics sorting production line according to any one of claims 1-5, characterized in that, The types of structural monitoring sensors include at least one of the following: acceleration sensors, strain sensors, tilt sensors, and displacement sensors.

7. The method for identifying structural monitoring sensor anomalies in a logistics sorting production line according to claim 1, characterized in that, The collection time window for the sorting task is determined based on the start and end times of the planned actions. ,in, This indicates the start time in the planned action's start and end times. Indicates the duration of noise retention before the action. This indicates the end time in the start and end times of the planned action. Indicates the duration of structural decay retention after the action.

8. The method for identifying structural monitoring sensors in a logistics sorting production line according to claim 1, characterized in that, The process of constructing the association mapping table includes: Initialize the runtime association mapping table; Based on the structural topology diagram of the logistics sorting production line, determine all structural sections that the sorting task will pass through with each grid as the target grid. Traverse the sorting grids of the logistics sorting line and perform the following steps: Currently traversing to the grid Get multiple grids The execution information for the successful, non-overlapping sorting task at the target compartment includes the start and end times of the actual actions and all structural segments traversed. Represents the grid index, which is a positive integer; Based on the The start and end times of the actual actions that have successfully executed the sorting task are used to determine the data collection time window, based on which the data collection time window is the first... Each structural segment that has successfully completed a sorting task is divided into a reference time interval; An index indicating that a task has been successfully executed; Obtain the time series of signals collected by all structural monitoring sensors on the logistics sorting production line within the acquisition time window; Based on the Extracting the time series signal from the first structural monitoring sensor The response arrival time and response peak time of each structural monitoring sensor; Statistics The arrival and peak response times of each structural monitoring sensor fall within the structural sections they pass through. The number of times the reference time interval is calculated, and the number of times is used to calculate the first time interval. Each structural monitoring sensor is located in the structural section it passes through. The recurrence rate of occurrence; If the first Each structural monitoring sensor is located in the structural section it passes through. If the recurrence rate of the fall-in is greater than the fall-in recurrence rate threshold, then the first... Each structural monitoring sensor and the structural sections it passes through Binding, and based on the first A structural monitoring sensor fell into the structural section it was passing through. Time series extraction of signal at time 1 The baseline response characteristics corresponding to each structural monitoring sensor; Grid , with grid All structural sections that have been successfully processed by the target grid, all structural monitoring sensors bound to each structural section, and the baseline response characteristics of each structural monitoring sensor are associated and stored in the operation association mapping table.

9. A processing device, characterized in that, include: One or more processors; A memory for storing one or more computer programs, and one or more processors for executing the one or more computer programs stored in the memory to cause the one or more processors to perform the structural monitoring sensor anomaly identification method in a logistics sorting production line as described in any one of claims 1-8.

10. A logistics sorting system, characterized in that, include: Host computer; A logistics sorting production line, wherein one or more structural monitoring nodes are deployed on all or part of the structural sections of the logistics sorting production line, and the structural monitoring node includes a processor, a sensing communication unit connected and communicating with the processor, and one or more structural monitoring sensors. The gateway is connected to the host computer and the sensor communication unit for communication, respectively. The structure monitoring node uploads the signal time series to the host computer through the sensor communication unit and the gateway. One or more end-side control nodes obtain task instructions issued by the host computer through the gateway, and control one or more sorting execution units of the logistics sorting production line to work based on the task instructions; The host computer executes the steps of the abnormal identification method for structural monitoring sensors in the logistics sorting production line according to any one of claims 1-8 to obtain the status of the structural monitoring sensors.

Images