Packaging management and control method fusing multivariable dynamic analysis

Abstract

The invention discloses a package management and control method fusing multivariable dynamic analysis, relates to the technical field of package dynamic management and control, and covers a complete process from data acquisition to protection strategy implementation. Firstly, multi-source sensors are arranged at packaging and transportation nodes, stress, acceleration and environmental parameters are collected in real time, and multi-dimensional original data covering the whole process is formed; then, carrying out time domain alignment and feature extraction on the data by utilizing denoising filtering, wavelet decomposition and environment coupling methods to obtain structured data of a unified coordinate system; and accurately identifying a packaging fatigue risk through a microcrack jump function and an accumulated impact measurement model, and generating a crack propagation trend and failure prediction. And finally, according to the risk change of the section, executing a sectional protection strategy, and dynamically adjusting and optimizing a protection scheme to ensure efficient management and control. The limitation of traditional packaging control is overcome through nonlinear modeling and real-time adjustment and optimization, and the method has a wide application prospect.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic packaging control, and in particular to a packaging control method integrating multivariate dynamic analysis. Background Art

[0002] With the diversification of modern logistics models and the continuous improvement of supply chain speed, the stability and safety of packaging during transportation and warehousing are increasingly becoming key factors affecting product quality and end-user experience. Different types of goods often need to go through complex environments such as multiple loading and unloading, sudden changes in temperature and humidity, high-frequency or low-frequency vibrations during long-distance transportation across regions and multiple stages. Especially in the distribution of goods that are susceptible to shock or vibration (such as precision instruments, electronic components or fragile items), if the cumulative stress on the packaging cannot be accurately identified and dynamically controlled, it is very easy to cause product damage, increase the return rate and even cause safety hazards due to packaging failure. In the face of this demand, existing technologies usually rely on single parameter monitoring or phased sampling methods, and it is difficult to identify the subtle differences in each link of the transportation process in a timely and accurate manner. In addition, the tolerance limits of packaging of different materials and specifications under transportation and storage conditions are not uniform, and the existing general packaging design or static protection solutions are difficult to meet the needs of complex and changing logistics scenarios.

[0003] In the Chinese invention patent with the authorization announcement number CN113065740B, a high-efficiency product packaging management and control system is disclosed, including: a collection domain creation module, an information processing module, a physical address acquisition module and a verification module; the collection domain creation module is used to create a spatial coordinate collection domain; the information processing module is used to obtain the layout distribution information and the first sequence information of the outer box, and obtain the first binding information according to the layout distribution information, the first sequence information and the spatial coordinate collection domain; the physical address acquisition module is used to obtain the second sequence information of the product, and obtain the physical address of the outer box corresponding to the product based on the second sequence information and the first binding information; the verification module is used to perform verification measures according to the physical address, obtain a configuration signal, and perform product packaging measures according to the configuration signal; the present invention can accurately locate the outer box position required by the product, thereby ensuring the correctness of the product packaging, and reducing its management and control costs and improving its management and control efficiency.

[0004] However, combining the existing technology and the above application scenarios; In practice, simply relying on the limited records of vibration amplitude or environmental parameters provided by existing technologies cannot effectively quantify the multiple stress superpositions that packaging suffers during the entire circulation process, nor can it capture the impact of high-frequency and intermittent small-amplitude impacts on early microcracks or fatigue phenomena in packaging materials. When various dynamic factors are coupled with each other and superimposed at different logistics stages, potential damage to the packaging structure or sealing parts often appears in advance, causing cracks that are difficult to detect with the naked eye to expand rapidly in subsequent transportation or storage links. Existing technologies lack the ability to perform real-time fusion and in-depth analysis of multi-source data, and lack targeted protection measures for different sections, so that packaging protection measures cannot be actively intervened in special scenarios such as increased vibration intensity, sudden changes in temperature and humidity, or frequent loading and unloading, which ultimately leads to a decline in product quality, an increase in rework rate, and an increase in corporate logistics costs. It can be seen that a technical means that can monitor and analyze the dynamics of multi-variable packaging and flexibly adjust the protection plan based on the prediction results is urgently needed to achieve high reliability and low-cost logistics control.

[0005] To this end, the present invention provides a packaging control method integrating multivariate dynamic analysis. Summary of the invention

[0006] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a packaging control method that integrates multivariate dynamic analysis. By deploying multi-source sensors at packaging and transportation nodes, stress, acceleration and environmental parameters are collected in real time to form multi-dimensional raw data covering the entire process; then, the data is aligned in the time domain and features are extracted using denoising filtering, wavelet decomposition and environmental coupling methods to obtain structured data in a unified coordinate system; the microcrack jump function and cumulative impact measurement model are used to accurately identify packaging fatigue risks, and crack propagation trends and failure predictions are generated. Finally, according to the changes in segment risks, a segmented protection strategy is implemented, and the protection plan is dynamically optimized to ensure efficient control. The limitations of traditional packaging control are overcome through nonlinear modeling and real-time optimization, thereby solving the technical problems recorded in the background technology.

[0007] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a packaging control method integrating multivariate dynamic analysis, including, when the initial logistics transportation process is started and the monitoring demand is confirmed, by deploying multi-source sensors at the packaging and transportation nodes to collect environmental parameters in real time, so as to obtain multi-dimensional raw data covering the entire process and establish a unified spatiotemporal label; After the multi-dimensional raw data stream is initially stored, the sensor output is aligned in the time domain and high-order features are extracted by using methods such as denoising filtering, wavelet decomposition and environmental coupling to obtain structured data with a unified coordinate system and covering multi-dimensional indicators. When abnormal mutation signs are detected in structured data, the microcrack jump function and high-order cumulative impact measurement model are used to finely identify and quantitatively evaluate the packaging fatigue risk, and generate the crack growth trend and potential failure time window of each sensor; When the analysis results show that the risk index of a certain logistics section has increased significantly, the segmented protection strategy is immediately executed and the dynamic tuning algorithm is triggered to differentiate and strengthen the packaging materials and buffer layout and make real-time corrections to maintain a high safety margin and closed-loop control of the entire process while minimizing resource investment.

[0008] Preferably, determine the area to be monitored and the key locations where impact or fatigue concentration may occur, and form a preliminary set of candidate coordinates for sensor deployment. ,in Indicates The spatial coordinates or installation plans of candidate locations are calculated; the layout of the candidate coordinate set is optimized, and the coverage and comprehensive effectiveness of the deployment are measured using the following formula to construct the solution coverage :

[0009] in: is the number of candidate sensors; represents the optimal distance metric between the sensor location π and the packaging target monitoring area R; is a custom attenuation coefficient; is the sensor coordinate set; By maximizing solution coverage Or if the threshold conditions are met, the final deployment plan is selected, a formal list of sensor network installation locations and installation methods is generated, and a sensor layout and deployment information parameter set is generated; Preferably, after the initial deployment of the sensor network is completed, the accelerometer, gyroscope and vibration sensor are calibrated, and the calibration parameter set is recorded as ; Deploy environmental sensing devices in the target area and record parameter sets , respectively representing temperature, humidity, air pressure and number of transfers / loading and unloading frequency; Register the calibrated sensor parameters and the environmental sensor list together into the calibration and environmental node configuration parameter set, and establish a corresponding relationship with the sensor layout and deployment information parameter set; Preferably, according to the coordinates and calibration information, real-time data collection is started at each stage of transportation or storage, and each sensor is sampled at a set frequency. Output time series data , each sensor synchronously outputs environmental data ; Construct preliminary time tags and geographic tags to form data objects ,in and Indicates time and space / node markings; Setting specific dynamic weight functions to represent time and space / node labeling; Setting a specific dynamic weight function The sensor data is preliminarily weighted by time decay to extract the potential impact of recent vibration shock on microcracks. The time window decay weighting function An example is as follows:

[0010] Where: Indicates the sensor Weighted results within a time window; For sensor The attenuation factor of To achieve the points cap, all real-time data are uploaded to the data management platform along with the preliminary weighted results; Preferably, all sensors The timing signal Mapping to a unified time scale , for each sensor’s timing signal Perform denoising and smoothing to obtain a preliminary denoised signal ; Output denoised and time-aligned data , and retains all time stamps in the corresponding metadata With sensor number ; Preferably, wavelet transform is used to denoise the output and align the data in the time domain. Perform multi-scale decomposition and define is the discrete wavelet transform operator:

[0011] in: Indicated in scale With pan Time-frequency coefficient under the condition is the selected wavelet basis function, different and Corresponding to different frequency bands or time parts; In order to quantify the distribution characteristics of vibration energy at different scales, the following characteristic energy spectrum is defined: , used to measure the packaging in a specific frequency band Cumulative impact strength within:

[0012] in: After wavelet transformation, the sensor In scale With pan The time-frequency coefficients on ; , Indicates the selected frequency band or scale interval set; Represents the absolute value of the waveform amplitude, is a custom amplitude index; Indicates the translation dimension The difference or increment of the above waveform amplitude: ; is the local mutation weight coefficient, Used to extract only the positive mutation part; is the outer layer nonlinear amplification index; The output high-order feature data can be formalized as , and retain the sensor number The corresponding relationship between Extract characteristic energy spectra in high, medium and low frequency intervals respectively , in order to locate the frequency band where the material is prone to fatigue, for each sensor generating a number of characteristic components; Preferably, combined with environmental sensor data , for each vibration feature To perform a coupled analysis:

[0013] in: It represents the environmental coupling index after fusion; It can be a linear or nonlinear combination function of one or more environmental variables. is the adjustment coefficient; Getting environmental coupling indicators Then, define the multi-dimensional indicator vector :

[0014] All sensors With all environment nodes With all environment nodes When the data is finally output to a unified data management structure, the corresponding relationship between sensors and environmental nodes is retained; Preferably, obtain each sensor The corresponding multi-dimensional indicator vector ,in The time scale is calibrated to a unified time scale, and all , and are sequentially spliced ​​into a feature trajectory sequence ; Defining the symptom function Compare the change rates of multi-dimensional indicators at adjacent or nearby moments:

[0015] Where: It is the time difference used to measure the difference between adjacent moments or adjacent logistics segments; represents the vector norm, is the nonlinear index; when When the preset dynamic threshold is exceeded, it is considered as a possible sign of microcracks, and the time and related sensor number are recorded. In the short-term risk list; output the initial signs of microcracks and the corresponding change range records ; Preferably, for the moment that has been marked as a sign of suspected microcracks , further analyze its historical data The cumulative impact degree is used to determine whether the crack may accelerate in the subsequent logistics stage. The local fatigue impact metric is defined as follows: :

[0016] Where: is the microcrack jump measure; is a partial energy index obtained by multi-scale wavelet transform, Indicates a specific frequency band or scale; It is a collection of indices for all scales or frequency bands of interest selected in the multiscale analysis; It is an environment variable function; For environment variables Functions that perform deformation or mapping; To calibrate the material sensitivity coefficient by experiment; is the nonlinear amplification index for microcrack signs; is the wavelet energy weight at each scale (or frequency band); : Nonlinear index of wavelet energy; is the environmental coupling adjustment coefficient; , is the time decay factor; Obtaining local fatigue impact measurements Finally, the impact measurement is converted into a risk factor for failure tendency by combining the fatigue curve or physical mechanism model of the packaging material. :

[0017] in: is the impact-failure mapping coefficient; When risk factors When the value is close to 1, it means that the microcracks are very likely to expand further to become visible or cause overall damage in the short term; when the value is low, it means that the packaging can still maintain structural integrity, but it needs to be monitored; the final output is the packaging damage risk factor sequence and compare it with the sensor number and time scale Make corresponding marks; Preferably, the packaging damage risk factor Integrate into a timing matrix And compare or regress with the actual failure cases of the material to obtain the overall failure probability function of the packaging; According to the microcrack risk factor to infer a subsequent moment Potential probability of damage :

[0018] in: and , is the model coefficient of material expansion rate; When the risk factor of package damage When it is large, even if the remaining time If it is not long, it is easy to fail; when the packaging is damaged, the risk factor When it is smaller, it will take longer or additional impacts to trigger the breakage; When analyzing different transport stages or storage conditions, the multidimensional indicator vector Risk factor for microcracks caused by medium energy Potential damage probability The indicators are ranked in ascending order to identify the vibration frequency bands, temperature and humidity levels, or loading and unloading operations that require the most attention; the identification results are combined with the potential damage probability The predicted value of Potential damage probability within , key impact factor list or ranking output; Preferably, based on the potential breakage probability of the output and packaging damage risk factors , combining the main nodes and transportation methods in the logistics route, dividing the overall logistics process into several sections, and assigning a section identifier to each section ; Set the time scale or interval Map it with the corresponding logistics section s to form a section-time correspondence table; Statistics or prediction of the time distribution of package damage risk in each segment s, mainly based on the package damage risk factor or potential damage probability , calculate the overall risk index of the segment :

[0019] in: is the time range corresponding to segment s; Select all sensors in the same time segment The biggest risk factor; It is a mapping function related to the environment or scenario, and finally outputs the overall risk index As a measure of risk level for each segment; Preferably, based on the segment Overall risk index , combined with key influencing factors, formulate a corresponding protection plan for each section s, including: In the overall risk index For sections that are higher than expected, add cushioning materials appropriately or strengthen the impact-resistant structure of the outer box; Allocate more manpower or automatic equipment at nodes with frequent loading and unloading to reduce the impact; add moisture-proof or thermal insulation layers in cold chain or high humidity sections; Before each segment, calibrate the sensor and environmental monitoring equipment The monitoring frequency should be appropriately increased, with a focus on high-risk sensor numbers , the new real-time data collected during this period is compared with the calculated package damage risk factor or potential damage probability Make a comparison to see whether it is consistent with the prediction or deviates from it; Refer to the following formula to make a preliminary assessment of the protection effect of this section and generate a protection effect assessment value :

[0020] Where: is the previously predicted risk factor, is the new risk factor actually observed in this section; Indicates in section Average all time slices or multiple time points; The number of key sensors active in this segment; Preferably, when the evaluation result protection effect evaluation value Continuously below the effect threshold Or when a negative value appears, it is determined that the current protection measures have not met expectations: If the predicted risk factors are monitored A sharp increase in a short period of time triggers a temporary tuning process; In high-risk sections, temporarily add stronger outer boxes, add more anti-seismic pads, or strengthen auxiliary means in the loading and unloading process to define the incremental tuning strength function :

[0021] Where: and , and To tune the sensitivity coefficient Used to capture the protection effect evaluation value When it is a negative value or less than zero, if it is a positive value, the item is recorded as zero; represents the amplification of environmental stimuli, A comprehensive metric function for representing environmental incentives; After executing the tuning measures, continue to collect and calculate new predicted risk factors in real time , if the incremental tuning intensity function is found after tuning Significant improvement or new risk factors gradually stabilize; Otherwise, continue to perform incremental tuning or switch to other protection solutions, and record the experience parameters during the tuning process in the database.

[0022] (III) Beneficial effects The present invention provides a packaging control method integrating multivariate dynamic analysis, which has the following beneficial effects: The present invention sets up multi-level sub-steps within the four major steps of monitoring-preprocessing-analysis-protection, and each performs refined processing on sensor deployment, data denoising, feature extraction, microcrack identification and risk prediction, and logistics segment protection and tuning, thereby constructing a complete cross-dimensional and cross-stage management and control system. Through the reasonable layout of multi-source sensors and high-order feature extraction based on wavelet transform, the scheme can deeply explore the hidden fatigue effects that may occur in complex logistics environments, and weaken noise interference through nonlinear filtering and outlier removal. In this process, for the potential damage of packaging materials caused by short-term high-amplitude impact or long-term cumulative vibration, the present invention defines a microcrack jump and cumulative impact measurement model, and comprehensively uses formulas such as integral attenuation and environmental index amplification to achieve sensitive capture of early signs of fatigue evolution. For special scenarios such as repeated loading and unloading, high humidity or extreme temperature involved in multi-stage transportation, the model can integrate historical and real-time monitoring in time series to accurately measure the probability of occurrence of packaging cracks and the subsequent expansion rate. At the same time, unified time and space tag management ensures the consistency of data across steps, avoids parameter confusion and semantic disconnection, and allows the output of each sub-step to be seamlessly connected to the next link.

[0023] In the protection link, the present invention allocates differentiated solutions according to the risk index of different transportation or storage sections. It can strengthen the outer box structure, add cushioning pads or optimize the loading and unloading process in high-risk sections, or adopt appropriate streamlining strategies in low-risk areas to achieve a reasonable balance between resources and safety. In addition, the protection strategy effect evaluation value is calculated by comparing the continuous monitoring and prediction results. Once the observed risk is higher than expected, the dynamic tuning mechanism will be triggered, and the plan will be revised based on the incremental tuning intensity formula to achieve a closed-loop control of "data-prediction-execution-feedback". Thanks to the high sensitivity of nonlinear modeling methods to extreme environmental shocks and the high efficiency of real-time tuning in correcting strategy deviations, the present invention not only overcomes the limitations of traditional packaging control that lack multi-source fusion and instant adjustment, but also provides scalable technical support for recyclable packaging, iterative material design and cross-industry applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The figure is a flow chart of the packaging control method integrating multivariate dynamic analysis according to the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 The present invention provides a packaging control method integrating multivariate dynamic analysis, comprising: Step 1: When the initial logistics and transportation process is started and the monitoring needs are confirmed, multi-source sensors are deployed at the packaging and transportation nodes to collect environmental parameters in real time, so as to obtain multi-dimensional raw data covering the entire process and establish a unified spatiotemporal tag; The step 1 includes the following contents: Step 101: Sensor deployment planning and layout optimization Based on the known packaging size, material properties and logistics route profile, determine the areas to be monitored and the key locations where impact or fatigue may occur, and form a preliminary set of candidate coordinates for sensor placement ,in Indicates The spatial coordinates or installation plans of candidate locations are calculated; the layout of the candidate coordinate set is optimized, and the coverage and comprehensive effectiveness of the deployment are measured using the following formula to construct the solution coverage :

[0027] in: is the number of candidate sensors; The optimal distance metric between the sensor position π and the target monitoring area R of the package (or transport carrier) (which can be customized according to the package shape and material distribution, such as surface fit, protective layer thickness, etc.); It is a custom attenuation coefficient used to adjust the impact of distance on deployment effect (it can be determined based on material sensitivity and deployment difficulty); is the sensor coordinate set; By maximizing solution coverage Or meet its threshold conditions, select the final deployment plan, so that the sensors can cover high-risk areas and avoid redundant or overly dense points in logistics. After completion, generate a formal list of sensor network installation locations and installation methods, including the coordinates or angles of each sensor on the package, and generate a sensor layout and deployment information parameter set; When in use, by The deployment significantly improves the probability of capturing potential impact accumulation points and effectively covers high-risk areas; reduces redundant deployment: using the solution coverage Optimization functions such as the use of sensors can be used to avoid repeated installation of sensors at non-critical locations on the packaging, reducing costs and improving monitoring efficiency. The sensor array can be flexibly configured according to the characteristics of different packaging materials, sizes and logistics routes, which is conducive to large-scale applications and improves adaptability.

[0028] Step 102: Basic calibration and environment monitoring node settings After completing the initial deployment of the sensor network, perform basic calibration on each accelerometer, gyroscope, and vibration sensor, and record the calibration parameter set such as zero bias, upper range limit, and sensitivity coefficient, which is recorded as , and stored in the underlying firmware; In order to obtain environmental data of logistics nodes, it is necessary to deploy environmental sensing equipment in key transfer links or target areas with large temperature and humidity gradients, and record parameter sets. , respectively representing temperature, humidity, air pressure and number of transfers / loading and unloading frequency, etc.; register the calibrated sensor parameters and the environmental sensor list together in the calibration and environmental node configuration parameter set, and establish a corresponding relationship with the sensor layout and deployment information parameter set to ensure that the sensor network at the same location can accurately associate its environmental nodes; When using, calibrate the zero bias and sensitivity coefficient of each sensor to ensure that the sensor is correct in the subsequent steps. The timing signal Environmental data The data can be accurately compared to ensure data consistency; the variables such as temperature, humidity, air pressure and loading and unloading times are uniformly collected and associated to provide multi-dimensional environmental input for subsequent algorithms; unified calibration information can maintain monitoring accuracy in different batches or multi-model packaging, reducing the workload of repeated configuration.

[0029] Step 103: Real-time data collection and tag management According to the confirmed coordinates and calibration information, real-time data collection is started at each stage of transportation or storage. Each sensor samples at the set frequency. Output time series data , each sensor synchronously outputs environmental data ; To prevent simple accumulation from making data difficult to manage, construct preliminary time tags and geographic tags (such as GPS or logistics link ID) to form data objects ,in and Represents time and space / node labels for alignment and fusion in subsequent steps; Set a specific dynamic weight function at this stage The sensor data is preliminarily weighted by time decay to extract the potential impact of recent vibration shock on microcracks. The time window decay weighting function An example is as follows:

[0030] Where: Indicates the sensor Weighted results within a time window; For sensor The attenuation factor (can be combined with the sensitivity recorded during calibration) to select), the larger the value, the faster the decay of earlier data; is the upper limit of the integral, indicating the length of time considered, and is used to focus on recent high-frequency shocks; all real-time data together with the preliminary weighted results are uploaded to the data management platform; When used, by time stamp With space marker Construct a complete data object to ensure accurate tracing of historical events in subsequent steps; time window weighting can be used in the collection stage , highlighting the impact of recent large-scale stress on material fatigue and improving the recognition of key impacts; at the same time, it can automatically adapt to changes in the network environment to ensure the continuity and security of data in multi-stage transportation or warehousing scenarios.

[0031] Step 2: After the multi-dimensional raw data stream is initially stored, the sensor output is aligned in the time domain and high-order features are extracted by using denoising filtering, wavelet decomposition and environmental coupling to obtain structured data with a unified coordinate system and covering multi-dimensional indicators; The step 2 includes the following contents: Step 201, time domain alignment and nonlinear denoising filtering; According to the data object generated in the first step First, synchronize the output of sensors in the same logistics node or the same transportation section; The timing signal Mapping to a unified time scale , so that any time The corresponding vibration stress readings and environmental readings can be found; If some data are missing or have duplicate marks, it is necessary to combine the sensor basic calibration information registered in the first step Interpolate or trim to keep data objects in strict one-to-one correspondence in the time dimension; For each sensor timing signal , denoising and smoothing are performed using morphological filtering or adaptive structural element method to obtain the signal after preliminary denoising ; Its core calculation can be expressed as:

[0032] in, is a nonlinear filtering operator (such as a combination of adaptive morphological opening and closing operations), Represents a set of filter structure elements or kernel functions; When performing this filtering, different sensors can be Adjustment to different layout positions For example, a stronger noise suppression strategy is selected at locations with high vibration intensity, while a more detailed structural element is used in areas with weak amplitude; the final output is a set of denoised and time-aligned data. , and retains all time stamps in the corresponding metadata With sensor number ; When using, To unify the time scale and ensure that all They can be integrated and compared with each other to reduce the probability of subsequent misjudgment; nonlinear filtering It can significantly reduce the impact of high-frequency noise, while retaining the waveform spikes that may cause microcracks relatively intact; it can reduce the interference of outliers and random jitter, provide a more reliable data basis for subsequent indicator calculations and fatigue analysis model outputs, and reduce the probability of subsequent misjudgment.

[0033] Step 202: Multi-scale band decomposition and high-order feature extraction The output is denoised and time-domain aligned using wavelet transform. Perform multi-scale decomposition and define is the discrete wavelet transform operator:

[0034] in: Indicated in scale With pan Time-frequency coefficient under the condition is the selected wavelet basis function, different and Corresponding to different frequency bands or time locals, thus achieving multi-scale decomposition; In order to quantify the distribution characteristics of vibration energy at different scales, the following characteristic energy spectrum is defined: , used to measure the packaging in a specific frequency band Cumulative impact strength within (or scale interval):

[0035] in: After wavelet transformation, the sensor In scale With pan The time-frequency coefficients on ; , Indicates the selected frequency band or scale interval set, which is the same as the previous The concept remains consistent; Represents the absolute value of the waveform amplitude, is a custom amplitude index ( will pay more attention to large amplitude impact); Indicates the translation dimension The difference or increment of the above waveform amplitude: , used to capture instantaneous mutations in amplitude; is the local mutation weight coefficient, which is used to amplify (or suppress) the impact of those sudden rising amplitude peaks on the cumulative impact; It is used to extract only the positive mutation part (i.e. the amplitude growth part), and record the negative value or no mutation as zero; is the outer layer nonlinear amplification index (which can be compared with Taking different values) can further enhance the sensitivity to large amplitude or mutation signals; When used, the amplitude mutation term is introduced on the basis of the traditional absolute value accumulation. , which can more carefully describe the energy concentration phenomenon of packaging materials under instantaneous impact, thereby providing more sensitive measurement indicators for subsequent fatigue analysis models in capturing early signs of microcracks. , , The combination can adapt to various packaging materials and scenarios with different fatigue sensitivities; The final output high-order feature data can be formalized as , and retain the sensor number The output will be integrated with the environmental information of the next step to form a multi-dimensional index; using wavelet transform Extract characteristic energy spectra in high, medium and low frequency intervals respectively , in order to locate the frequency band where the material is prone to fatigue;

[0036] Generate several feature components to facilitate the subsequent algorithm to flexibly select the most discriminative indicators and reduce information loss.

[0037] Step 203: Environmental coupling and multi-dimensional indicator system construction Incorporating environmental sensor data (such as temperature , , air pressure , Loading and unloading times For each vibration feature To perform a coupled analysis:

[0038] in: It represents the environmental coupling index after fusion; It can be a linear or nonlinear combination function of one or more environmental variables (for example, adding temperature and humidity according to a certain weight and then multiplying by the logarithm of air pressure). In specific implementation, it can be adjusted according to material properties; is the adjustment coefficient, which has a value greater than 0 and is used to control the amplification or attenuation effect of environmental variables on the vibration energy spectrum; Getting environmental coupling indicators After that, we can further define a set of multi-dimensional indicator vectors :

[0039] Each multidimensional indicator vector Both combine high-order vibration characteristics with external environmental conditions to reflect the packaging at all times. or the combined fatigue potential within a segment; With all environment nodes The generated multi-dimensional indicator vector When the data is finally output to a unified data management structure, the corresponding relationship between sensors and environmental nodes must be retained; When in use, by coupling environmental parameters such as temperature and humidity with the impact energy spectrum and integrating multiple environmental variables, it is possible to avoid the one-sidedness of asserting the degree of fatigue based solely on temperature or humidity and reduce single parameter deviation.

[0040] Step 3: When abnormal mutation signs are detected in the structured data, the microcrack jump function and high-order cumulative impact measurement model are used to finely identify and quantitatively evaluate the packaging fatigue risk, and generate the crack propagation trend and potential failure time window of each sensor; The step three includes the following contents: Step 301: Feature pattern recognition and microcrack sign detection Get each sensor The corresponding multi-dimensional indicator vector ,in The time scale is calibrated to a unified time scale, and all , and are sequentially concatenated into a sequence of feature trajectories ; In order to highlight that microcracks often show sudden changes in certain characteristics or local anomalies in the early stage, the following symptom function is defined: Compare the change rates of multi-dimensional indicators at adjacent or nearby moments:

[0041] Where: It is used to measure the time difference between adjacent moments or adjacent logistics segments (it can be set according to the segment length or refresh frequency of the transportation process); represents the vector norm (e.g. norm), which is used to synthesize the overall change range of multi-dimensional indicators; It is a nonlinear index used to amplify large changes, thereby highlighting the abnormality of indicators when potential cracks occur; when When the preset dynamic threshold is exceeded (which can be obtained by combining material fatigue curve, statistical priors or historical sample training), it is considered as a possible sign of microcracks, and the time and related sensor number are recorded. In the short-term risk list; output the initial signs of microcracks, such as , and the corresponding change amplitude records ; When using, use the symptom function By characterizing the jumps of characteristic vectors, it is possible to identify the signs of microcracks that may appear in the packaging at an early stage and complete early crack detection. Refined anomaly detection can be achieved through dynamic thresholds or statistical distributions, and false mutations caused by short-term noise can be filtered to reduce false alarms. The identified suspected microcracks are recorded in the risk control list at all times to facilitate subsequent focus in the risk measurement model and complete systematic alarms.

[0042] Step 302: Damage risk measurement based on fatigue analysis model For moments that have been marked as suspected signs of microcracks , further analyze its historical data The cumulative impact degree is used to determine whether the crack may accelerate in the subsequent logistics stage. The local fatigue impact metric is defined as follows: :

[0043] Where: is the microcrack jump measure; is a partial energy index obtained by multi-scale wavelet transform, Indicates a specific frequency band or scale; It is a collection of indices for all scales or frequency bands of interest selected in the multiscale analysis; It is the fusion result of environmental variable functions, such as temperature, humidity, air pressure, loading and unloading times, etc. For environment variables Functions that perform deformation or mapping; To calibrate the material sensitivity coefficient by experiment; is the nonlinear amplification index for microcrack signs; is the wavelet energy weight at each scale (or frequency band), which can be set according to the sensitivity of the packaging material to vibrations of different frequencies; : Nonlinear index of wavelet energy, if Then the large amplitude vibration energy can be amplified more strongly; is the environmental coupling adjustment coefficient, , used to control the reinforcing (or inhibiting) effects of external environmental variables; , is the time attenuation factor, indicating that the impact closer to the current moment is more influential; is the current time (or the time so far), and the integral upper limit represents the value between 0 and The accumulation of the whole process; : Integral variable, traversing the historical time series experienced by the package.

[0044] Traditional crack risk assessment methods often only consider a single dimension (such as the sum of acceleration amplitudes) or simple power weighting, which makes it difficult to simultaneously reflect the comprehensive impact of multi-scale vibration, environmental factors (temperature and humidity, loading and unloading times, etc.) and temporal cumulative effects on crack propagation. With the help of high-order nonlinear integration, the multi-scale wavelet energy spectrum, microcrack jump variable metric and environmental coupling index are integrated to solve the problem that single-dimensional or simple accumulation methods cannot effectively distinguish the microcrack generation and propagation states. Packaging materials often do not break immediately when microcracks appear in the early stage, but if they are subsequently subjected to frequent local impacts or extreme environments (such as high humidity, repeated loading and unloading), the cracks will rapidly deteriorate. This parameter targets the mechanism where recent impacts are more influential than long-term impacts, and uses the time attenuation factor to And the jump amplitude The nonlinear amplification can highlight the most active crack development period and identify potential deterioration risks in advance; Obtaining local fatigue impact measurements Finally, the impact measurement is converted into a risk factor for failure tendency by combining the fatigue curve or physical mechanism model of the packaging material. :

[0045] in: is the impact-failure mapping coefficient, the larger the value, the more vulnerable the material is to the cumulative impact; When risk factors If the value is close to 1, it means that the microcracks are very likely to expand further to become visible or cause overall damage in the short term; when the value is lower, it means that the packaging can still maintain structural integrity, but it needs to be monitored; The final output is the package damage risk factor sequence and compare it with the sensor number and time scale Mark accordingly. The larger the value, the more vulnerable the material is to cumulative impact. Emphasize the dominance of recent shocks and achieve accurate quantification of material fatigue; risk factors exist The range intuitively reflects the probability level of crack extension or damage, which facilitates quick decision-making on the business side and completes risk factor mapping.

[0046] Step 303: Prediction of packaging structure failure probability and identification of key factors Package damage risk factor Integrate into a timing matrix And compare or regress with the actual failure cases of the material (if they have been recorded historically or obtained through accelerated tests) to obtain the overall failure probability function of the packaging; according to the microcrack risk factor to infer a subsequent moment Potential probability of damage :

[0047] in: and , is the model coefficient of the material extension rate, which indicates the possibility of crack development over time based on the cumulative impact intensity; When the risk factor of package damage When it is large, even if the remaining time If it is not long, it is easy to fail; when the packaging is damaged, the risk factor When it is smaller, it will take longer or additional impacts to trigger the breakage; When analyzing different transportation stages or storage conditions, machine learning interpretability methods (such as feature importance analysis, weighted regression coefficients, etc.) can be used to analyze the multidimensional indicator vector Risk factor for microcracks caused by medium energy Potential damage probability The indicators are ranked in ascending order to identify the vibration frequency bands, temperature and humidity levels, or loading and unloading operations that require the most attention; the identification results are combined with the potential damage probability The predicted value of Potential damage probability within , key impact factor list or ranking output; Potential breakage probability during use It can break through the limitations of the current moment and provide quantitative results for potential damage in subsequent transportation or storage stages; use feature importance analysis of machine learning or regression models to accurately locate the high-frequency bands or high-humidity ranges that are most likely to induce cracks, thereby increasing interpretability; after identifying the key causes, more efficient differentiated protection can be implemented in the fourth step, reducing resource investment while enhancing reliability and implementing targeted protection recommendations.

[0048] Step 4: When the analysis results show that the risk index of a certain logistics section has increased significantly, the segmented protection strategy is immediately implemented and the dynamic tuning algorithm is triggered to perform differentiated reinforcement and real-time correction on packaging materials and buffer layout to maintain a high safety margin and close-loop control of the entire process while minimizing resource investment; The step 4 includes the following contents: Step 401: Logistics segment division and risk matching According to the potential damage probability of the output and packaging damage risk factors , combined with the main nodes and transportation methods in the logistics route (such as land transportation, sea transportation, air transportation, cold chain, etc.), the overall logistics process is divided into several sections (for example ), and assign a segment identifier to each segment ; Set the time scale or interval Mapped with the corresponding logistics sections s to form a section-time correspondence table to distinguish different environmental characteristics or impact modes; Statistics or prediction of the time distribution of package damage risk in each segment s, mainly based on the package damage risk factor or potential damage probability , calculate the overall risk index of the segment :

[0049] in: is the time range corresponding to segment s; Select all sensors in the same time segment 's maximum risk factor to capture the most vulnerable areas; is an environment- or scenario-dependent mapping function (depending on the mode of transport) used to convert the failure probability Further amplify or reduce the comprehensive risk of the segment; finally output the overall risk index As a measure of risk level for each segment; When using, the risk index constructed Weigh the overall risk of each section to make packaging protection more targeted, avoid excessive or insufficient one-size-fits-all measures, achieve precise resource allocation, and unify time and space mapping; when crossing multiple transportation modes and multiple sites, we can generate packaging damage risk factors and potential damage probability Data is seamlessly linked; protective measures can be simplified in low-risk sections, and padding can be strengthened or outer boxes can be upgraded in high-risk sections. Overall efficiency is improved accordingly, and efficiency and cost are balanced.

[0050] Step 402: Execution of protection strategy and real-time monitoring Segment-based Overall risk index , combined with key influencing factors (vibration frequency band, temperature and humidity levels, number of loading and unloading operations, etc.), formulate a corresponding protection plan for each section s, including: In the overall risk index For sections that are higher than expected, add cushioning materials appropriately or strengthen the impact-resistant structure of the outer box; Allocate more manpower or automatic equipment at nodes with frequent loading and unloading to reduce the impact; add moisture-proof or thermal insulation layers in cold chain or high humidity sections; Before each segment, calibrate the sensor and environmental monitoring equipment The monitoring frequency should be appropriately increased, with a focus on high-risk sensor numbers , upload the new real-time data collected during this period (including acceleration, temperature, humidity, air pressure, etc.) to the data management platform and compare it with the calculated package damage risk factor or potential damage probability Make a comparison to see whether it is consistent with the prediction or deviates from it; Refer to the following formula to make a preliminary assessment of the protection effect of this section and generate a protection effect assessment value :

[0051] Where: is the previously predicted risk factor, is the new risk factor actually observed in this segment (if obtained through short-term retraining or online analysis); Indicates in section Average all time slices or multiple time points; The number of key sensors active in this segment; like If a significant positive value is displayed, it means that the actual risk factor is lower than the predicted value and the protection strategy is effective. If a negative value or a value that is too low is displayed, it means that the actual risk may be higher than the predicted value and subsequent dynamic adjustment is required.

[0052] When used, generates a protection effect evaluation value It can measure and timely discover the deviation between actual observations and previous predictions, and provide early signals for responding to sudden anomalies; the sensor monitors at a higher frequency within the section, which is linked to the effectiveness of strategy execution. Once a crack expansion trend occurs, it can respond immediately and monitor the closed loop in real time: data is continuously accumulated: execution records and evaluation results are stored synchronously, and can be used as an experience library to input the next batch or new material upgrade.

[0053] Step 403: Dynamic tuning and adaptive feedback When the evaluation result is the protection effect evaluation value Continuously below the effect threshold Or when a negative value appears, it is determined that the current protection measures have not met expectations: If the predicted risk factors are monitored A sharp increase in a short period of time triggers a temporary tuning process; To improve the protection effect, you can temporarily add stronger outer boxes in high-risk sections, add more anti-seismic pads, or strengthen auxiliary means in the loading and unloading process, and define the incremental tuning strength function. :

[0054] Where: and , and To tune the sensitivity coefficient Used to capture the protection effect evaluation value When it is a negative value or less than zero, if it is a positive value, the item is recorded as zero; represents the amplification of environmental stimuli, A comprehensive metric function used to represent environmental incentives can be obtained by weighting variables such as temperature and humidity or frequent loading and unloading times; A larger value means that more significant tuning or additional investment in protection resources is required.

[0055] After implementing optimization measures (such as changing to a higher grade outer box material, increasing cushion thickness, improving loading and unloading operations, etc.), continue to collect and calculate new predicted risk factors in real time , if the incremental tuning intensity function is found after tuning If there is a significant improvement or the new risk factor gradually stabilizes, it means that the optimization has been effective; Otherwise, continue to perform incremental tuning or switch to other protection solutions, and use the experience parameters in the tuning process (such as different time periods) The corresponding protection effects) are recorded in the database to provide a reference for subsequent logistics route planning and packaging selection.

[0056] When used, incremental tuning strength The system is allowed to quickly add protective resources or change plans when actual risks arise, and quickly respond to risks beyond expectations; continuous monitoring and cyclic correction can effectively prevent microcracks from evolving from early local small defects to global damage, thereby improving the overall safety margin; the results of the optimization will continue to be included in the database, completing R&D iterations and multiple cycles of feedback, providing more experience basis for future packaging design or logistics solutions.

[0057] 1. How to obtain material fatigue curve Standardized fatigue test methods: Stress-Life (SN) Test: For common packaging materials such as paper packaging materials, plastic films or composite films, the SN curve can be measured on a constant load tester or a repeated bending instrument, that is, the number of fatigue cycles required for the material to fail (obvious cracks or fractures) at different stress / strain levels is recorded.

[0058] According to the test results, the SN curve is drawn, and the average life or distribution range under different stress levels is obtained through interpolation or regression algorithms. Accelerated fatigue test: For some polymer packaging or composite structures (such as multi-layer films with strong barrier properties, aluminum-plastic composite materials, etc.), vibration accumulation or repeated heat sealing and opening tests can be performed in a constant or controllable temperature and humidity environment to observe the fatigue evolution rate of the material at a specific step rate. Combined with real logistics scenarios, the effective life of the material is evaluated by the acceleration effect.

[0059] Material failure mechanism and microscopic detection: For the outer packaging of precision instruments or fragile items, the microstructural changes of the material during the crack initiation and propagation stages can be further observed through a microscope or scanning electron microscope (SEM) to provide micromechanical evidence for the fatigue model. In addition, the interface delamination or fiber fracture data of the material after being stressed under different temperature and humidity conditions can be collected to reduce the lifespan of the material under extreme environments in subsequent mathematical models. or Make corrections; Data mapping to the fatigue analysis model of this solution: The SN data or accelerated fatigue test results obtained can be converted into material fatigue curve functions by regression or curve fitting, and referenced in high-order cumulative impact metrics. If the jump metric in this solution and microcrack index In order to be closer to reality, it is necessary to combine these experimental data to correct the model parameters (including material sensitivity coefficient K, attenuation coefficient n, mapping coefficient s, etc.).

[0060] 2. Specific Hardware Implementation Selection and installation of multi-source sensors: Vibration and acceleration sensors: It is recommended to use three-axis accelerometers (such as MEMS sensors) and medium- and high-frequency vibration pickups (such as piezoelectric) to cover a wide range of vibration frequency bands (1Hz to several kHz). For the packaging of electronic precision instruments, the sensitivity and sampling frequency of the sensor can be appropriately increased; Environmental sensors: Temperature and humidity sensors should have certain waterproof and anti-interference capabilities: The pressure sensor can choose a high-precision MEMS barometer. If it involves loading and unloading frequency detection, a transfer counter (RFID access control counter, Bluetooth counter, etc.) can be added to the handling equipment or box, and uploaded synchronously with the timestamp; Installation method: The sensor can be attached to the key stress concentration area of ​​the packaging lining, or placed on the surface of the outer box; for high-value products, multiple sensors can be deployed inside and outside the box to form redundancy and backup for comparison and cross-verification. All sensors are connected to the wireless gateway or data recording module and have segmented or full-time sampling functions; 2. Data collection and preliminary transmission equipment Data logging module: A low-power microcontroller (MCU) or a small single-board computer can be used, with built-in Flash storage or SD card for caching when the network is disconnected.

[0061] Communication method: In case of long-distance transportation, data needs to be relayed to the cloud platform via 4G / 5G, LoRa or satellite communication; at storage nodes or ports, it can be switched to Wi-Fi or wired LAN for batch uploading.

[0062] Gateway and back-end data management: It is recommended to use edge gateways for basic data cleaning and segmentation packaging, and to attach time and geographic tags: If the logistics vehicle has its own GPS module, location information can be integrated to further enrich the multi-dimensional analysis of this solution. The back-end data management platform can use cloud databases or distributed storage to carry large-scale data from different sensors and different logistics routes, and connect to the various algorithm modules described in the second, third, and fourth steps of this solution.

[0063] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0066] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A packaging control method integrating multivariate dynamic analysis, characterized in that: include, When the initial logistics and transportation process is started and the monitoring needs are confirmed, multi-source sensors are deployed at the packaging and transportation nodes to collect environmental parameters in real time, so as to obtain multi-dimensional raw data covering the entire process and establish a unified space-time tag; After the multi-dimensional raw data stream is initially stored, the sensor output is aligned in the time domain and high-order features are extracted using denoising filtering, wavelet decomposition, and environmental coupling to obtain structured data with a unified coordinate system and covering multi-dimensional indicators. When abnormal mutation signs are detected in structured data, the microcrack jump function and high-order cumulative impact measurement model are used to finely identify and quantitatively evaluate the packaging fatigue risk, and generate the crack growth trend and potential failure time window of each sensor; When the analysis results show that the risk index of a certain logistics section has increased significantly, the segmented protection strategy is immediately executed and the dynamic tuning algorithm is triggered to differentiate and strengthen the packaging materials and buffer layout and make real-time corrections to maintain a high safety margin and closed-loop control of the entire process while minimizing resource investment.

2. A packaging control method integrating multivariate dynamic analysis according to claim 1, characterized in that: Determine the areas to be monitored and the key locations where impact or fatigue concentration may occur, form a preliminary set of candidate coordinates for sensor deployment, optimize the layout of the candidate coordinates, and construct a solution coverage to measure the coverage and comprehensive effectiveness of the deployment; By maximizing the solution coverage or meeting its threshold conditions, the final deployment solution is selected and a formal list of sensor network installation locations and installation methods is generated.

3. A packaging control method integrating multivariate dynamic analysis according to claim 2, characterized in that: Perform basic calibration of accelerometers, gyroscopes, and vibration sensors, and record calibration parameter sets; Environmental sensing equipment is deployed in the target area to collect and record parameter sets, and the calibrated sensor parameters are registered together with the environmental sensor list, and a corresponding relationship is established.

4. A packaging control method integrating multivariate dynamic analysis according to claim 3, characterized in that: According to the coordinates and calibration information, real-time data collection is started at each transportation or storage stage. Each sensor outputs time series data at the set sampling frequency, and each sensor synchronously outputs environmental data; Preliminary time tags and geographic tags are constructed, and specific dynamic weight functions are set to perform preliminary time decay weighting on the sensor data to extract the potential impact of recent vibration shocks on microcracks.

5. A packaging control method integrating multivariate dynamic analysis according to claim 4, characterized in that: After mapping all sensor timing signals to a unified time scale ， De-noise and smooth the time series signal of each sensor to obtain a preliminary de-noised signal; The output is denoised and time-aligned data, and all time stamps and sensor numbers are preserved in the corresponding metadata.

6. A packaging control method integrating multivariate dynamic analysis according to claim 5, characterized in that: Wavelet transform is used to perform multi-scale decomposition on the output denoised and time-domain aligned data; In order to quantify the distribution characteristics of vibration energy at different scales, the definition is used to measure the vibration energy distribution of the package in a specific frequency band. Characteristic energy spectrum of internal cumulative impact strength ; The output high-order feature data can be formalized as , and retain the sensor number The corresponding relationship.

7. A packaging control method integrating multivariate dynamic analysis according to claim 6, characterized in that: Combine environmental sensor data with characteristic energy spectrum Conduct coupling analysis and generate a multi-dimensional indicator vector after obtaining the environmental coupling index ; Set all sensors With all environment nodes With all environment nodes Finally, the data is exported to a unified data management structure.

8. The packaging control method integrating multivariate dynamic analysis according to claim 7 is characterized in that: Get each sensor The corresponding multi-dimensional indicator vector , all multi-dimensional index vectors , and are sequentially concatenated into a sequence of feature trajectories ; Defining the symptom function Compare the change rates of multi-dimensional indicators at adjacent or nearby moments. When the preset dynamic threshold is exceeded, it is considered as a possible sign of microcracks, and the time and related sensor number are recorded. In the list of short-term risks; Output the initial signs of micro cracks and the corresponding change amplitude records .

9. A packaging control method integrating multivariate dynamic analysis according to claim 8, characterized in that: For moments that have been marked as suspected signs of microcracks , analyze the cumulative impact of its history and define the local fatigue impact metric ; Obtaining local fatigue impact measurements Finally, the impact measurement is converted into a risk factor for failure tendency by combining the fatigue curve or physical mechanism model of the packaging material. ; Output package damage risk factor sequence and compare it with the sensor number and time scale Make corresponding marks.

10. A packaging control method integrating multivariate dynamic analysis according to claim 9, characterized in that: Package damage risk factor Integrate into a timing matrix And compare or regress with the actual failure cases of the material to obtain the overall failure probability function of the packaging; According to the microcrack risk factor to infer a subsequent moment Potential probability of damage ; For multi-dimensional index vector Risk factor for microcracks caused by medium energy Potential damage probability Sort the indicators by ascending order to identify the vibration frequency bands, temperature and humidity levels, or loading and unloading operations that require the most attention; The identification results are combined with the potential damage probability The predicted value of Potential damage probability within , key impact factor list or ranking output.

11. A packaging control method integrating multivariate dynamic analysis according to claim 10, characterized in that: Divide the overall logistics process into several sections and assign a section ID to each section ; Set the time scale or interval Corresponding logistics section Mapping to form a segment-time correspondence table; statistically or predicting the time distribution of package damage risk in each segment s, based on the package damage risk factor or potential damage probability , calculate the overall risk index of the segment , as a measure of the risk level of each segment.

12. A packaging control method integrating multivariate dynamic analysis according to claim 11, characterized in that: Segment-based Overall risk index , formulate the corresponding protection plan for each section s based on the key influencing factors, Included in the overall risk index Appropriately add cushioning materials or strengthen the impact-resistant structure of the outer box in sections with higher than expected loads; allocate more manpower or automatic equipment to reduce impact at nodes with frequent loading and unloading; add moisture-proof or thermal insulation layers in cold chain or high humidity sections; Before each segment, calibrate the sensor and environmental monitoring equipment Increase the monitoring frequency and focus on high-risk sensor numbers , the new real-time data collected during this period will be combined with the packaging damage risk factor or potential damage probability for comparison.

13. A packaging control method integrating multivariate dynamic analysis according to claim 12, characterized in that: Generate a protection effect evaluation value to conduct a preliminary evaluation of the protection effect of this section; when the protection effect evaluation value of the evaluation result is continuously lower than the effect threshold or a negative value appears, it is determined that the current protection measures have not met expectations: if the predicted risk factor is monitored to rise sharply in a short period of time, a temporary adjustment process is triggered; Temporarily add stronger outer boxes in high-risk sections, add more seismic pads, or strengthen auxiliary means in the loading and unloading process, and define the incremental tuning strength function; after executing the tuning measures, continue to collect and calculate new predicted risk factors in real time. If it is found that the incremental tuning strength function is significantly improved after the tuning or the new risk factors are gradually stabilized; otherwise, continue to perform incremental tuning or switch to other protection plans.

Images