Tinplate box production state data analysis method based on Internet of Things

Abstract

The invention provides a tinplate box production state data analysis method based on the Internet of Things, and the method comprises the steps: firstly collecting a multi-source real-time monitoring data set containing an equipment temperature monitoring sequence and the like through an Internet of Things sensor node disposed at the edge of production equipment, and then carrying out the cross-dimension standardization processing of the multi-source real-time monitoring data set, time domain synchronous alignment and dimension unified conversion are covered, a standardized monitoring data set is obtained, a state feature set containing thermal distribution features and the like is extracted from the standardized monitoring data set, then based on a preset abnormal state discrimination rule base, the state feature set and historical normal production feature templates are subjected to dynamic similarity matching, and normal production feature templates are obtained; and generating an equipment health state score and abnormal positioning identifier set, finally generating a production parameter optimization strategy set, and issuing the production parameter optimization strategy set to the equipment control terminal to execute a real-time regulation and control instruction, thereby realizing effective analysis and real-time regulation and control of the tinplate box production state.

Description

Technical Field

[0001] This application relates to the field of Internet of Things technology. Specifically, it relates to a method for analyzing the production status data of tinplate boxes based on the Internet of Things. Background Art

[0002] In the current tinplate box production field, with the expansion of production scale and the complication of production processes, accurately monitoring the operating status of production equipment and efficiently managing it have become key links to improve production quality and efficiency. However, there are many limitations in the existing production technologies in this regard.

[0003] On the one hand, most of the existing methods are based on simple threshold judgments or empirical rules, lacking systematicness and dynamics. These methods cannot comprehensively evaluate based on the historical operating conditions and real-time status of the equipment, making it difficult to accurately judge the health status of the equipment, and even more difficult to precisely locate the specific location and type of abnormalities. Once an abnormality occurs in the equipment, manual investigation and diagnosis are often required, which not only consumes a large amount of time and labor costs, but may also lead to production interruptions, affecting production efficiency and product quality.

[0004] On the other hand, existing production systems usually adopt fixed production parameter settings or adjust parameters according to simple feedback mechanisms. These methods cannot automatically generate targeted production parameter optimization strategies based on the real-time health status of the equipment and the results of abnormality location. When the operating status of the equipment changes, production parameters cannot be adjusted in a timely and effective manner to meet the actual operating requirements of the equipment, thus affecting the stability of production and the consistency of product quality. Summary of the Invention

[0005] In view of the above-mentioned problems, in combination with the first aspect of this application, embodiments of this application provide a method for analyzing the production status data of tinplate boxes based on the Internet of Things. The method includes:

[0006] Collecting a multi-source real-time monitoring data set through Internet of Things sensor nodes deployed at the edge of production equipment. The multi-source real-time monitoring data set includes equipment temperature monitoring sequences, stamping pressure monitoring waveforms, conveyor belt vibration spectra, and environmental humidity change curves;

[0007] Performing cross-dimensional standardization processing on the multi-source real-time monitoring data set to obtain a standardized monitoring data set. Among them, the cross-dimensional standardization processing includes time-domain synchronous alignment operations and dimension-unifying conversion operations;

[0008] Performing feature extraction on the standardized monitoring data set to obtain a state feature set of production equipment. The state feature set includes thermal distribution features, pressure fluctuation pattern features, mechanical resonance frequency point features, and environmental interference coupling features;

[0009] Based on a preset abnormal state discrimination rule library, perform dynamic similarity matching between the state feature set and the historical normal production feature template to generate a device health state score and an abnormal location identification set;

[0010] Generate a production parameter optimization strategy set according to the device health state score and the abnormal location identification set, and send the production parameter optimization strategy set to the device control terminal to execute real-time control instructions.

[0011] On the other hand, an embodiment of the present application also provides a production monitoring system for tinplate boxes, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor. The machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to run the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0012] Based on the above aspects, the embodiment of the present application realizes the full-process closed-loop control from multi-source heterogeneous data perception to device health state evaluation and then to autonomous optimization of production parameters by constructing a data analysis method for the production state of tinplate boxes based on the Internet of Things, significantly improving the intelligent level and operation efficiency of the production system. Specifically, by deploying Internet of Things sensor nodes at the edge of production equipment, comprehensive collection of multi-dimensional real-time monitoring data such as device temperature, stamping pressure, conveyor belt vibration, and environmental humidity is realized, effectively overcoming the problem of one-sided state perception caused by traditional single data source analysis and providing a rich data basis for accurately evaluating the operation state of the device. On this basis, cross-dimensional standardization processing technology is adopted, and through time-domain synchronous alignment and dimension-unifying conversion operations, the differences in time and space scales of different monitoring data are eliminated, ensuring the comparability and fusion of multi-source data in the feature extraction process, so as to be able to extract multi-dimensional coupling features such as thermal distribution, pressure fluctuation, mechanical resonance, and environmental interference, significantly improving the accuracy and integrity of state feature extraction. Further, based on a preset abnormal state discrimination rule library, dynamic similarity matching is performed between the real-time state features and the historical normal production feature template, which not only realizes the quantitative scoring of the device health state, but also can accurately locate the position and type of the abnormality, providing strong support for subsequent fault warning and maintenance. Finally, according to the device health state score and the abnormal location result, a targeted production parameter optimization strategy is automatically generated and sent to the device control terminal in real time to execute the control instruction, forming an intelligent closed-loop control system, effectively improving the adaptive ability and stability of the production process, reducing the risk of production interruption and quality fluctuation caused by device abnormalities, and at the same time reducing the manual intervention and trial-and-error costs. Description of the Drawings

[0013] Figure 1It is a schematic execution flowchart of the method for analyzing the production status data of tinplate boxes based on the Internet of Things provided by an embodiment of the present application.

[0014] Figure 2 It is a schematic hardware architecture diagram of the tinplate box production monitoring system provided by an embodiment of the present application. Detailed implementation manners

[0015] The present application will be specifically described below with reference to the accompanying drawings of the specification. Figure 1 It is a schematic flowchart of the method for analyzing the production status data of tinplate boxes based on the Internet of Things provided by an embodiment of the present application. The method for analyzing the production status data of tinplate boxes based on the Internet of Things will be introduced in detail below.

[0016] Step S110: Collect a multi-source real-time monitoring data set through the Internet of Things sensor nodes deployed at the edge of the production equipment. The multi-source real-time monitoring data set includes a device temperature monitoring sequence, a stamping pressure monitoring waveform, a conveyor belt vibration spectrum, and an environmental humidity change curve.

[0017] During the production process of tinplate boxes, in order to comprehensively and accurately grasp the operating status of the production equipment, a series of Internet of Things sensor nodes are reasonably deployed at the edge of the production equipment. These sensor nodes can capture various data information closely related to the production process in real time.

[0018] Specifically, the temperature sensor is responsible for collecting the device temperature monitoring sequence. Taking an actual production scenario as an example, the temperature sensor can be installed at key parts of the production equipment, such as the stamping die and the motor housing. Suppose the temperature sensor collects temperature data at a fixed time interval, for example, every 5 seconds. In a continuous operation period of 10 minutes, 120 temperature data points will be obtained. These data points are arranged in the order of collection time to form a device temperature monitoring sequence containing 120 values. Each value in the device temperature monitoring sequence represents the temperature of a specific part of the device at the corresponding moment. By analyzing the device temperature monitoring sequence, the change trend of the device temperature over time can be understood, and whether there are abnormalities such as overheating of the device can be judged.

[0019] The stamping pressure sensor is used to obtain the stamping pressure monitoring waveform. In the stamping process, the change of pressure is crucial for the forming quality of the tinplate box. The stamping pressure sensor continuously records the change of pressure over time during each stamping operation. For example, within a complete stamping cycle, the pressure gradually rises from the initial value to the peak value and then drops to the end value. Connecting the pressure change data recorded from multiple stamping operations forms a continuous stamping pressure monitoring waveform. This stamping pressure monitoring waveform can intuitively reflect the dynamic change of pressure during the stamping process. By analyzing the stamping pressure monitoring waveform, the working stability of the stamping equipment and the rationality of the stamping process can be evaluated.

[0020] The conveyor belt vibration sensor is used to collect the conveyor belt vibration spectrum. The conveyor belt generates vibrations during operation, and vibrations of different frequencies may reflect different operating states of the conveyor belt. The vibration sensor collects and analyzes the vibration signals of the conveyor belt to obtain the vibration energy distribution of the conveyor belt at different frequencies, that is, the conveyor belt vibration spectrum. For example, by analyzing the conveyor belt vibration spectrum, if it is found that the vibration energy at a specific frequency increases abnormally, it may mean that there are problems such as looseness and wear in the components corresponding to that frequency of the conveyor belt.

[0021] The environmental humidity sensor is responsible for monitoring the change of environmental humidity in the production workshop. Environmental humidity also has a certain impact on the production of tinplate boxes. For example, too high humidity may cause the tinplate to rust and affect the product quality. The environmental humidity sensor collects environmental humidity data at a set time interval, such as once every 10 seconds. Arranging these environmental humidity data in chronological order forms an environmental humidity change curve. By analyzing this environmental humidity change curve, the fluctuation of environmental humidity in the workshop over time can be understood, so as to take corresponding measures to control the environmental humidity.

[0022] Step S120: Perform cross-dimensional standardization processing on the multi-source real-time monitoring data set to obtain a standardized monitoring data set, where the cross-dimensional standardization processing includes a time domain synchronization alignment operation and a dimension unification conversion operation.

[0023] Since the different data in the multi-source real-time monitoring data set collected have different time scales and dimensions, it is necessary to perform cross-dimensional standardization processing on these data to ensure that different types of data can correspond in time and have a unified dimension, thus facilitating subsequent feature extraction and state analysis.

[0024] Step S121: Perform timestamp alignment processing on the equipment temperature monitoring sequence, extract the temperature gradient change rate at each sampling moment, and map the original temperature value to a normalized temperature range based on a preset industrial temperature measurement range.

[0025] First, perform timestamp alignment processing. Since the sampling times of different sensors may vary, in order to accurately correspond the device temperature monitoring sequence with other data in terms of time, it is necessary to uniformly adjust the timestamps of the temperature data. For example, taking the sampling time of the stamping pressure monitoring waveform as the reference, align the timestamps of the device temperature monitoring sequence. Assume that the sampling interval of the stamping pressure monitoring waveform is 5 seconds, while the sampling interval of the device temperature monitoring sequence is 3 seconds. Then, it is necessary to screen and interpolate the temperature data so that the timestamps of the temperature data match those of the stamping pressure data.

[0026] Next, extract the temperature gradient change rate at each sampling moment. The temperature gradient change rate reflects the rate of change of temperature over time. The specific calculation method is to calculate the difference between the temperature values at two adjacent sampling moments and divide it by the time interval. For example, if the temperature at the nth sampling moment is Tn and the temperature at the (n + 1)th sampling moment is Tn+1, and the time interval is Δt, then the temperature gradient change rate at the nth sampling moment is (Tn+1 - Tn) / Δt. Calculate this for each sampling moment in the device temperature monitoring sequence in turn to obtain the temperature gradient change rate at each sampling moment.

[0027] Finally, map the original temperature values to the normalized temperature range based on the preset industrial temperature measurement range. The preset industrial temperature measurement range is determined according to the normal operating temperature range of the production equipment. For example, assume that the normal operating temperature range of this production equipment is from 0°C to 100°C, then the industrial temperature measurement range is from 0°C to 100°C. The normalized temperature range is usually set between 0 and 1. The specific method to map the original temperature values to the normalized temperature range is to calculate their relative positions in the industrial temperature measurement range for each original temperature value T, that is, (T - Tmin) / (Tmax - Tmin), where Tmin is the minimum value of the industrial temperature measurement range (here it is 0°C) and Tmax is the maximum value of the industrial temperature measurement range (here it is 100°C). Through this mapping, the original temperature values are converted into normalized temperature values between 0 and 1, forming the normalized temperature range.

[0028] Step S122: Perform peak detection processing on the stamping pressure monitoring waveform, identify the pressure extreme points in each stamping cycle, and perform non-dimensional conversion on the pressure extreme points according to the rated pressure parameters of the stamping equipment to generate a standard pressure fluctuation sequence.

[0029] Peak detection processing of the stamping pressure monitoring waveform is to accurately identify the pressure extreme points within each stamping cycle. It can be achieved by using the method of local maximum detection. Specifically, traverse each data point on the stamping pressure monitoring waveform, compare the current data point with its adjacent data points. If the value of the current data point is greater than the values of its adjacent data points and meets certain peak conditions (such as the peak amplitude is greater than a certain threshold), then this data point is determined as a peak point. In this way, the pressure extreme points within each stamping cycle can be identified, including the pressure maximum and the pressure minimum.

[0030] Perform dimensionless conversion on the pressure extreme points according to the rated pressure parameters of the stamping equipment. The rated pressure parameters of the stamping equipment are the normal working pressure ranges specified during equipment design. For example, the rated pressure range of a certain stamping equipment is from 0 MPa to 20 MPa. For each identified pressure extreme point P, divide it by the maximum value Pmax of the rated pressure (here it is 20 MPa) to obtain the dimensionless pressure value P' = P / Pmax. Arrange all the pressure extreme points after dimensionless conversion in the order of the stamping cycle, and a standard pressure fluctuation sequence is generated. Each value in this standard pressure fluctuation sequence represents the proportional relationship of the pressure relative to the rated pressure within the corresponding stamping cycle, eliminating the influence of the rated pressure differences of different equipment and facilitating subsequent comparison and analysis.

[0031] Step S123: Perform frequency band decomposition processing on the vibration spectrum of the conveyor belt, extract the energy integral value within the preset mechanical resonance frequency band, and convert the energy integral value into a standard vibration intensity index based on the sensitivity coefficient of the vibration sensor.

[0032] Call a preset band-pass filter to segment the original vibration spectrum to obtain multiple sub-band energy distribution sequences. Among them, the cut-off frequencies of the band-pass filter are dynamically adjusted according to the inherent vibration characteristics of the conveyor belt material. The function of the band-pass filter is to only allow signals within a specific frequency range to pass through, thereby segmenting the original vibration spectrum into multiple sub-bands. The inherent vibration characteristics of the conveyor belt material will affect its vibration response at different frequencies. Therefore, it is necessary to dynamically adjust the cut-off frequencies of the band-pass filter according to the specific characteristics of the conveyor belt material. For example, for a conveyor belt made of a certain specific material, its inherent vibration frequencies are mainly concentrated between 50 Hz and 200 Hz. Then the cut-off frequencies of the band-pass filter can be set to 50 Hz and 200 Hz. In this way, the original vibration spectrum can be segmented into multiple sub-bands, each sub-band corresponding to a specific frequency range, and at the same time, the energy distribution sequence within each sub-band can be obtained.

[0033] Match the target resonance frequency band corresponding to the current production batch from the multiple sub-band energy distribution sequences, and the target resonance frequency band is obtained through the learning of historical vibration data. By analyzing and learning a large amount of historical vibration data, the target resonance frequency band of the conveyor belt under different production batches can be determined. For example, when producing a certain batch of tinplate boxes, by analyzing the vibration data during the production process of the previous same batch, it is found that the conveyor belt is prone to resonance in the frequency range of 100 Hz to 150 Hz, then this frequency range is the target resonance frequency band corresponding to the current production batch. Screen out the sub-band energy distribution sequences corresponding to the target resonance frequency band from the multiple sub-band energy distribution sequences.

[0034] Perform an integration operation on the energy distribution sequence within the target resonance frequency band to obtain an initial energy integral value, and perform speed compensation calibration on the initial energy integral value based on the real-time monitoring value of the conveyor belt running speed. Performing an integration operation on the energy distribution sequence within the target resonance frequency band means accumulating the energy values of each frequency point within this frequency band to obtain the initial energy integral value. Since the running speed of the conveyor belt will affect its vibration condition, it is necessary to perform compensation calibration on the initial energy integral value according to the real-time monitoring value of the conveyor belt running speed. For example, when the running speed of the conveyor belt increases, its vibration energy may increase accordingly, and at this time, it is necessary to make appropriate adjustments to the initial energy integral value. The specific compensation calibration method can be determined according to experimental data and empirical formulas.

[0035] Compare the calibrated energy integral value with a preset vibration safety threshold. If the calibrated energy integral value exceeds the vibration safety threshold, trigger a resonance frequency band recalibration operation to update the target resonance frequency band. The preset vibration safety threshold is determined according to the safe operation requirements of the production equipment. If the calibrated energy integral value exceeds this vibration safety threshold, it indicates that the vibration condition of the conveyor belt may be abnormal, and it is necessary to recalibrate the target resonance frequency band. The recalibration process includes re-analyzing and learning the historical vibration data, and combining the current production situation to determine the new target resonance frequency band.

[0036] The calibrated energy integral value is converted into a standard vibration intensity index based on the sensitivity coefficient of the vibration sensor. The sensitivity coefficient of the vibration sensor represents the response ability of the sensor to vibration signals. Dividing the calibrated energy integral value by the sensitivity coefficient of the vibration sensor can obtain the standard vibration intensity index. This standard vibration intensity index can more accurately reflect the vibration intensity of the conveyor belt, facilitating subsequent comprehensive analysis with other data.

[0037] Step S124: Perform a sliding window smoothing process on the environmental humidity change curve, calculate the humidity coefficient of variation within each window, and perform a ratio operation on the humidity coefficient of variation and the environmental reference humidity parameter to generate a standard humidity impact factor sequence.

[0038] The purpose of performing a sliding window smoothing process on the environmental humidity change curve is to reduce noise interference in the data and make the humidity data smoother and more stable. The specific method of the sliding window smoothing process is to select a window of a fixed size. For example, the window size is 5 data points, and then slide this window sequentially on the environmental humidity change curve. For the data within each window, calculate their average value as the smoothed humidity value at the center point of the window. Process the entire environmental humidity change curve sequentially to obtain the smoothed humidity curve.

[0039] Calculate the humidity coefficient of variation within each window. The humidity coefficient of variation reflects the degree of dispersion of the humidity data within the window. The calculation method is to first calculate the standard deviation of the humidity data within the window and then divide it by the average value of the humidity data within the window. For example, in a window with 5 humidity data values, namely H1, H2, H3, H4, and H5, first calculate their average value H_avg = (H1 + H2 + H3 + H4 + H5) / 5, then calculate the standard deviation σ, and finally obtain the humidity coefficient of variation CV = σ / H_avg. Calculate for each window sequentially to obtain the humidity coefficient of variation within each window.

[0040] Perform a ratio operation on the humidity coefficient of variation and the environmental reference humidity parameter. The environmental reference humidity parameter is determined according to the normal humidity requirements of the production environment. For example, the environmental reference humidity parameter of a certain production workshop is 60%. For the humidity coefficient of variation CV within each window, divide it by the environmental reference humidity parameter H_base (here it is 60%) to obtain the ratio CV' = CV / H_base. Arrange the ratios of all windows in chronological order to generate a standard humidity impact factor sequence. Each value in this standard humidity impact factor sequence represents the proportional relationship of the variation degree of the humidity within the corresponding window relative to the environmental reference humidity, and can reflect the impact degree of the environmental humidity change on the production process.

[0041] Step S125: Integrate the normalized temperature range, the standard pressure fluctuation sequence, the standard vibration intensity index, and the standard humidity impact factor sequence in the time dimension into the standardized monitoring data set.

[0042] After completing the standardization processing of the device temperature monitoring sequence, stamping pressure monitoring waveform, conveyor belt vibration spectrum, and ambient humidity change curve, a normalized temperature range, standard pressure fluctuation sequence, standard vibration intensity index, and standard humidity influence factor sequence are obtained. Next, it is necessary to integrate these standardized data according to the time dimension to form a unified standardized monitoring data set.

[0043] The specific approach is to use time as an index to combine the data at the same time points in the normalized temperature range, standard pressure fluctuation sequence, standard vibration intensity index, and standard humidity influence factor sequence. For example, at a specific time point t, there is a corresponding normalized temperature value T' in the normalized temperature range, a corresponding standard pressure value P' in the standard pressure fluctuation sequence, a corresponding standard vibration intensity value V' in the standard vibration intensity index, and a corresponding standard humidity influence factor value H' in the standard humidity influence factor sequence. These four values are combined to form a four-dimensional data vector [T', P', V', H']. Such combination operations are performed for all time points in sequence, and a standardized monitoring data set containing multiple four-dimensional data vectors is obtained. Each data vector in this standardized monitoring data set represents the comprehensive operating state information of the production equipment at the corresponding time point, providing a unified data basis for subsequent feature extraction and state analysis.

[0044] Step S130: Extract features from the standardized monitoring data set to obtain a set of state features of the production equipment, where the set of state features includes thermal distribution features, pressure fluctuation pattern features, mechanical resonance frequency point features, and environmental interference coupling features.

[0045] To gain an in-depth understanding of the operating state of the production equipment, it is necessary to extract key features from the standardized monitoring data set that can reflect the equipment state. These features will help identify whether there are abnormal conditions in the equipment and determine the specific type and location of the abnormal conditions.

[0046] Step S131: Perform spatial interpolation processing on the normalized temperature range in the standardized monitoring data set to generate a thermal distribution map of the equipment surface, and extract the maximum change direction of the temperature gradient and the coordinates of the high-temperature aggregation area from the thermal distribution map of the equipment surface.

[0047] Spatial interpolation of the normalized temperature range is to obtain more comprehensive temperature distribution information on the device surface. Since temperature sensors can usually only measure the temperatures at a limited number of points on the device surface, spatial interpolation is required to obtain the temperature distribution of the entire device surface. Common spatial interpolation methods include linear interpolation, spline interpolation, etc. For example, using the linear interpolation method, for two points A and B with known temperature values on the device surface and an unknown point C between them, the temperature value of point C can be obtained through linear calculation based on the temperature values of A and B and the relative positions of point C with respect to points A and B. By performing interpolation calculations on all unknown points on the device surface in turn, a thermal distribution map of the device surface can be generated.

[0048] Extract the direction of the maximum temperature gradient change from the thermal distribution map of the device surface. The temperature gradient represents the rate of change of temperature in space, and the direction of the maximum temperature gradient change reflects the direction in which the temperature changes fastest. The specific calculation method is that on the thermal distribution map of the device surface, for each point, calculate the rate of change of temperature in different directions, and select the direction with the largest rate of change of temperature as the direction of the maximum temperature gradient change at that point. By calculating all points on the entire device surface, the distribution of the direction of the maximum temperature gradient change on the device surface can be obtained.

[0049] At the same time, identify the coordinates of the high-temperature aggregation areas from the thermal distribution map of the device surface. The high-temperature aggregation areas refer to the areas on the device surface where the temperature is relatively high and concentrated, and abnormal situations such as device overheating may exist in these areas. A temperature threshold can be set to mark the areas on the device surface where the temperature is higher than the threshold as high-temperature areas. Then, through methods such as clustering analysis, adjacent high-temperature points are merged into high-temperature aggregation areas, and the central point coordinates of each high-temperature aggregation area are determined, and these coordinates are the coordinates of the high-temperature aggregation areas.

[0050] Step S132: Perform time-frequency joint analysis on the standard pressure fluctuation sequence, extract the slope feature in the pressure rising stage, the stability index in the pressure holding stage, and the decay rate in the pressure releasing stage, and construct a pressure fluctuation pattern coding vector.

[0051] Performing time-frequency joint analysis on the standard pressure fluctuation sequence is to comprehensively understand the change characteristics of pressure in time and frequency. There are many time-frequency joint analysis methods, such as short-time Fourier transform, wavelet transform, etc. Taking wavelet transform as an example, the standard pressure fluctuation sequence is wavelet decomposed to obtain the coefficients of different frequency components at different time points. By analyzing these coefficients, the distribution of pressure in different time and frequency can be obtained.

[0052] Extract the slope characteristics during the pressure rising stage. First, identify the starting pressure point, peak pressure point, and ending pressure point within the pressure fluctuation cycle. The starting pressure point refers to the point where the pressure begins to rise, the peak pressure point is the point where the pressure rises to the maximum value, and the ending pressure point is the point where the pressure drops to the lowest value. Calculate the time interval from the starting pressure point to the peak pressure point as the duration of the rising stage. Perform linear fitting on the pressure sampling points within the rising stage to obtain an initial slope estimate. The method of linear fitting is to use the least squares method to find a straight line that minimizes the sum of the squared errors between the line and the pressure sampling points within the rising stage. At the same time, calculate the root mean square error of the fitting residuals to evaluate the linearity. The fitting residual refers to the difference between the actual pressure sampling point and the corresponding point on the linear fitting line, and the root mean square error is the square root of the average of the sum of the squares of these differences. When the root mean square error exceeds the preset linearity threshold, it indicates that the linear fitting effect is poor. In this case, use the piecewise polynomial fitting method to recalculate the dynamic slope change curve during the pressure rising stage. Piecewise polynomial fitting divides the rising stage into several small segments and performs polynomial fitting on each small segment separately. Extract the maximum slope value, average slope value, and slope coefficient of variation of the dynamic slope change curve, and combine the three into slope characteristics.

[0053] Extract the stability index during the pressure holding stage. The pressure holding stage refers to the stage where the pressure remains relatively stable after reaching the peak. The stability index can be measured by calculating the standard deviation of the pressure values within this stage. The smaller the standard deviation, the more stable the pressure is during the holding stage.

[0054] Extract the decay rate during the pressure release stage. The pressure release stage refers to the stage where the pressure drops from the peak to the ending value. The decay rate can be obtained by calculating the downward slope of the pressure values within this stage. Specifically, perform linear fitting on the pressure sampling points within the pressure release stage to obtain the downward slope, and the absolute value of this slope is the decay rate of the pressure release stage.

[0055] Combine the slope characteristics during the pressure rising stage, the stability index during the pressure holding stage, and the decay rate during the pressure release stage to construct a pressure fluctuation pattern coding vector. Each element in this pressure fluctuation pattern coding vector represents a feature of the pressure fluctuation pattern. By analyzing this pressure fluctuation pattern coding vector, different pressure fluctuation patterns can be identified.

[0056] Step S133: Perform wavelet packet decomposition on the standard vibration intensity index, extract the proportion of low-frequency energy related to mechanical looseness and the number of high-frequency energy mutation points related to bearing wear, and generate a mechanical resonance frequency point feature matrix.

[0057] Perform wavelet packet decomposition on the standard vibration intensity index. Wavelet packet decomposition is a more refined time-frequency analysis method than wavelet decomposition, which can divide the signal more finely on different frequency sub-bands. During specific operation, select an appropriate wavelet basis function, such as the Daubechies wavelet basis, and perform multi-level wavelet packet decomposition on the standard vibration intensity index sequence. Each level of decomposition will further decompose the signal of the previous level into two sub-band signals, namely low-frequency and high-frequency signals. After multi-level decomposition, multiple sub-band signals with different frequency ranges can be obtained.

[0058] Extract the proportion of low-frequency energy related to mechanical looseness. Mechanical looseness usually causes obvious changes in vibration energy in the low-frequency band. Among the multiple sub-band signals obtained by wavelet packet decomposition, determine the range of the low-frequency sub-band. For example, consider the sub-band with a frequency lower than 100 Hz as the low-frequency sub-band related to mechanical looseness. Calculate the total energy of these low-frequency sub-band signals. The calculation method of energy is to accumulate the squared values of each data point in the sub-band signal. At the same time, calculate the total energy of all sub-band signals, that is, accumulate the squared values of the data points of all sub-band signals. Divide the total energy of the low-frequency sub-band signals by the total energy of all sub-band signals, and the obtained ratio is the proportion of low-frequency energy related to mechanical looseness. For example, assume that the total energy of the low-frequency sub-band signals is E_low and the total energy of all sub-band signals is E_total, then the proportion of low-frequency energy is E_low / E_total.

[0059] Extract the number of high-frequency energy mutation points related to bearing wear. Bearing wear often causes mutations in vibration energy in the high-frequency band. Determine the range of the high-frequency sub-band related to bearing wear. For example, consider the sub-band with a frequency higher than 1000 Hz as the high-frequency sub-band. Analyze these high-frequency sub-band signals and detect the energy mutation points. The method for detecting energy mutation points can be to set an energy change threshold, that is, calculate the energy difference between adjacent data points. If this difference exceeds the preset energy change threshold, then this point is considered an energy mutation point. Traverse all data points in the high-frequency sub-band signal and count the number of energy mutation points.

[0060] Generate a mechanical resonance frequency point feature matrix. Use the proportion of low-frequency energy related to mechanical looseness and the number of high-frequency energy mutation points related to bearing wear as the elements of the matrix. Assume that the above analysis is performed on the standard vibration intensity index for multiple different time periods, and multiple values of the proportion of low-frequency energy and the number of high-frequency energy mutation points are obtained. Arrange these values in chronological order to form a two-dimensional matrix. Each row of the matrix corresponds to a time period. The first column element is the proportion of low-frequency energy in this time period, and the second column element is the number of high-frequency energy mutation points in this time period. This two-dimensional matrix is the mechanical resonance frequency point feature matrix, which can comprehensively reflect the vibration characteristics related to mechanical looseness and bearing wear in different time periods.

[0061] Step S134: Conduct a lag correlation analysis on the sequence of standard humidity influence factors, calculate the time-delay correlation coefficient between the environmental humidity change and the equipment temperature fluctuation, and identify the duration of the impact of humidity mutation events on temperature stability.

[0062] Conduct a lag correlation analysis on the sequence of standard humidity influence factors to explore the relationship between environmental humidity change and equipment temperature fluctuation. First, it is necessary to obtain the equipment temperature fluctuation sequence, which can be extracted from the normalized temperature range and reflects the change of equipment temperature over time. Then, set a series of lag times, for example, from 0 to 100 time steps. For each lag time k, shift the sequence of standard humidity influence factors backward by k time steps and calculate the correlation with the equipment temperature fluctuation sequence. The correlation calculation can use the method of Pearson correlation coefficient, which measures the linear correlation between two sequences by calculating the ratio of the covariance of the two sequences to the product of their standard deviations.

[0063] For each lag time k, a correlation coefficient is calculated. These correlation coefficients reflect the strength of the correlation between environmental humidity change and equipment temperature fluctuation at different lag times. Among these correlation coefficients, find the correlation coefficient with the largest absolute value. The corresponding lag time is the time delay, and this maximum correlation coefficient is the time-delay correlation coefficient. For example, when the lag time k = 20, the calculated absolute value of the correlation coefficient is the largest, which is 0.8. Then the time delay is 20 time steps, and the time-delay correlation coefficient is 0.8.

[0064] Identify the duration of the impact of humidity mutation events on temperature stability. Humidity mutation events can be determined by setting a humidity change threshold. When the difference between a data point in the sequence of standard humidity influence factors and the previous data point exceeds the preset humidity change threshold, it is considered that a humidity mutation event has occurred. For each humidity mutation event, observe the change of the equipment temperature fluctuation sequence after the event. Set a temperature stability threshold. When the fluctuation amplitude of the equipment temperature fluctuation sequence continuously exceeds the temperature stability threshold within a certain period after the humidity mutation event, it is considered that this period is the time period when the humidity mutation event affects temperature stability. Record the start time and end time of this period, and calculate the difference between the two to obtain the duration of the impact of the humidity mutation event on temperature stability. For example, a certain humidity mutation event occurs at time t1, and the equipment temperature fluctuation continuously exceeds the temperature stability threshold from t1 to t2. Then the duration of the impact of this humidity mutation event on temperature stability is t2 - t1.

[0065] Step S135: Integrate the maximum change direction of the temperature gradient, the pressure fluctuation mode coding vector, the mechanical resonance frequency point feature matrix, and the time-delay correlation coefficient into the state feature set.

[0066] After extracting the features of each data in the standardized monitoring data set, the maximum change direction of the temperature gradient, the encoded vector of the pressure fluctuation pattern, the characteristic matrix of the mechanical resonance frequency points, and the time-delay correlation coefficient are obtained. Next, these features are integrated to form the state feature set of the production equipment.

[0067] The specific approach is as follows: represent the maximum change direction of the temperature gradient as a vector, and the elements of this vector respectively correspond to the components in the length direction, width direction, and height direction of the equipment. The encoded vector of the pressure fluctuation pattern itself is a vector, which contains information such as the slope feature in the pressure rising stage, the stability index in the pressure holding stage, and the decay rate in the pressure releasing stage. The characteristic matrix of the mechanical resonance frequency points is a two-dimensional matrix, which reflects the vibration characteristics related to mechanical looseness and bearing wear in different time periods. The time-delay correlation coefficient is a scalar value, which reflects the correlation between the change of environmental humidity and the temperature fluctuation of the equipment.

[0068] Concatenate the maximum change direction vector of the temperature gradient, the encoded vector of the pressure fluctuation pattern, each row vector of the characteristic matrix of the mechanical resonance frequency points, and the time-delay correlation coefficient in a set order. For example, first place the maximum change direction vector of the temperature gradient at the front, then sequentially concatenate the encoded vector of the pressure fluctuation pattern and each row vector of the characteristic matrix of the mechanical resonance frequency points, and finally add the time-delay correlation coefficient as a single element to the end of the vector. Through such a concatenation operation, a high-dimensional vector is formed, and this vector is the state feature set of the production equipment. This set comprehensively combines the thermal distribution characteristics, pressure fluctuation pattern characteristics, mechanical resonance frequency point characteristics, and environmental interference coupling characteristics of the equipment, and can comprehensively reflect the operating state of the production equipment.

[0069] Step S140: Based on a preset abnormal state discrimination rule base, perform dynamic similarity matching between the state feature set and the historical normal production feature template to generate a device health state score and an abnormal location identification set.

[0070] In order to evaluate the health state of the production equipment and locate possible abnormal positions, it is necessary to perform dynamic similarity matching between the extracted state feature set and the historical normal production feature template, and generate a device health state score and an abnormal location identification set according to the preset abnormal state discrimination rule base.

[0071] Step S141: Retrieve a reference feature set with the same current production batch number from the historical normal production feature template, and the reference feature set includes a historical thermal distribution benchmark, a pressure fluctuation pattern benchmark, a mechanical resonance frequency point benchmark, and a humidity influence benchmark.

[0072] The historical normal production feature template is a set of feature data accumulated during past normal production processes, which contains reference features of different production batches. When performing similarity matching, first retrieve from the historical normal production feature template the set of reference features with the same production batch number as the current production batch. This set of reference features is a comprehensive feature set, where the historical thermal distribution benchmark is the temperature distribution feature on the equipment surface during normal production of this production batch, such as the standard value of the maximum change direction of the temperature gradient, the standard coordinates of the high-temperature aggregation area, etc.; the pressure fluctuation pattern benchmark is the pressure fluctuation feature during normal production, such as the standard slope feature during the pressure rising stage, the standard stability index during the pressure holding stage, and the standard decay rate during the pressure release stage; the mechanical resonance frequency point benchmark is the vibration feature related to mechanical looseness and bearing wear during normal production, such as the standard value of the low-frequency energy ratio and the standard value of the number of high-frequency energy mutation points; the humidity influence benchmark is the correlation standard between environmental humidity change and equipment temperature fluctuation during normal production, such as the standard value of the time-delay correlation coefficient. Retrieving the set of reference features corresponding to the current production batch provides an accurate comparison benchmark for subsequent similarity matching.

[0073] Step S142: Calculate the cosine value of the direction angle between the maximum change direction of the temperature gradient and the historical thermal distribution benchmark as the thermal anomaly index.

[0074] Represent the maximum change direction of the temperature gradient in the current production cycle as a three-dimensional direction vector, where the three dimensions correspond to the length direction, width direction, and height direction of the equipment respectively. Extract the standard temperature gradient direction vector of the same production batch from the historical thermal distribution benchmark. Calculate the dot product of these two vectors. The calculation method of the dot product is to multiply the elements of the two vectors corresponding to the same dimension and then add them together. Then, calculate the modulus lengths of the two vectors respectively. The modulus length of a vector is the square root of the sum of the squares of the elements of the vector. Divide the dot product by the product of the modulus lengths of the two vectors, and the resulting value is the cosine value of the direction angle. For example, if the current maximum change direction vector of the temperature gradient is A = (a1, a2, a3) and the standard temperature gradient direction vector is B = (b1, b2, b3), then the dot product is A·B = a1*b1 + a2*b2 + a3*b3, the modulus length of vector A is |A| = √(a1² + a2² + a3 2 ), the modulus length of vector B is |B| = √(b1² + b2² + b3 2 ), and the cosine value of the direction angle is cosθ = (A·B) / (|A|*|B|). This cosine value of the direction angle is used as the thermal anomaly index. The closer its value is to 1, the closer the current maximum change direction of the temperature gradient is to the historical benchmark, and the more normal the thermal state is; the closer its value is to -1, the greater the direction difference between the two, and the thermal state may be abnormal.

[0075] When the cosine value of the direction included angle is lower than a preset direction consistency threshold, a warning for abnormal thermal distribution is triggered and the coordinates of the abnormal area are recorded. The preset direction consistency threshold is determined according to the normal operation requirements and experience of the production equipment. For example, it is set to 0.8. If the calculated cosine value of the direction included angle is lower than 0.8, it is considered that the direction of the maximum change in the current temperature gradient is quite different from the historical benchmark, and a warning for abnormal thermal distribution is triggered. At the same time, the coordinates of the high-temperature aggregation area are recorded from the thermal distribution map of the equipment surface, and these coordinates are the coordinates of the abnormal area, which is convenient for further investigation and handling of abnormal situations in the future.

[0076] The weight coefficient of the thermal anomaly index is dynamically adjusted according to the difference between the cosine value of the direction included angle and the direction consistency threshold. When the difference between the cosine value of the direction included angle and the direction consistency threshold is large, it indicates a high degree of abnormality in the thermal state. At this time, the weight coefficient of the thermal anomaly index is increased to highlight the impact of the thermal anomaly on the equipment health status score; when the difference is small, it indicates a relatively low degree of abnormality in the thermal state, and the weight coefficient of the thermal anomaly index is appropriately reduced. For example, a weight adjustment function is set to calculate the new weight coefficient according to the size of the difference, and the adjusted weight coefficient is applied to the subsequent calculation of the equipment health status score.

[0077] Step S143: Perform dynamic time warping matching on the pressure fluctuation pattern coding vector and the pressure fluctuation pattern benchmark to obtain a pressure pattern deviation score.

[0078] Dynamic time warping (DTW) is a method for comparing the similarity of two time series. It can find the optimal matching path between them without requiring the two series to have the same length. The pressure fluctuation pattern coding vector and the pressure fluctuation pattern benchmark are subjected to dynamic time warping matching. First, a distance matrix is constructed, and the elements of the matrix represent the distances between each element in the pressure fluctuation pattern coding vector and the corresponding element in the pressure fluctuation pattern benchmark. The distance can be calculated using methods such as Euclidean distance. For example, for two elements x and y, the Euclidean distance is d = √((x - y)²). Then, through the method of dynamic programming, an optimal path is found in the distance matrix so that the sum of the element distances along this path is the smallest. The sum of the distances corresponding to this optimal path is the dynamic time warping distance. The dynamic time warping distance is normalized, for example, by dividing it by a preset maximum distance value, to obtain a pressure pattern deviation score. The larger the score value, the greater the deviation degree of the current pressure fluctuation pattern from the benchmark pattern, and the pressure pattern may be abnormal; the smaller the score value, the closer the two are, and the more normal the pressure pattern is.

[0079] Step S144: Perform singular value decomposition on the mechanical resonance frequency point feature matrix and the mechanical resonance frequency point reference, and extract the maximum singular value ratio as the mechanical state degradation index.

[0080] Singular value decomposition (SVD) is a method of decomposing a matrix into the product of three matrices, which can reveal the internal structure and characteristics of the matrix. Perform singular value decomposition on the mechanical resonance frequency point feature matrix and the mechanical resonance frequency point reference respectively. Specifically, for the mechanical resonance frequency point feature matrix M and the mechanical resonance frequency point reference matrix N, through singular value decomposition, we can get M = U1 * Σ1 * V1^T and N = U2 * Σ2 * V2^T, where U1 and U2 are orthogonal matrices, Σ1 and Σ2 are diagonal matrices, and the elements on the diagonal are singular values, and V1^T and V2^T are the transposed matrices of V1 and V2.

[0081] Extract the maximum singular values in Σ1 and Σ2, denoted as σ1_max and σ2_max respectively. Calculate the maximum singular value ratio, that is, σ1_max / σ2_max. This maximum singular value ratio is used as the mechanical state degradation index, which reflects the degree of difference between the current mechanical resonance frequency point feature and the historical reference. The closer the ratio is to 1, the more similar the current mechanical state is to the historical normal state, and the better the mechanical state; the greater the deviation of the ratio from 1, the more likely the mechanical state has degraded, and the greater the possibility of problems such as mechanical looseness and bearing wear.

[0082] Step S145: Perform sliding window correlation analysis on the time-delay correlation coefficient and the humidity influence reference, and calculate the change rate of humidity interference intensity.

[0083] Set the size of a sliding window, for example, the window size is 10 time steps. Arrange the time-delay correlation coefficient sequence and the humidity influence reference sequence in chronological order, and slide the sliding window on these two sequences in turn. In each window, calculate the correlation between the time-delay correlation coefficient sequence and the humidity influence reference sequence. The correlation calculation can use the method of Pearson correlation coefficient. After obtaining the correlation coefficient in each window, calculate the difference between the correlation coefficients of adjacent windows, and divide these differences by the time interval of the window to get the change rate of humidity interference intensity. For example, the correlation coefficient in the i-th window is ri, the correlation coefficient in the i + 1-th window is ri+1, and the time interval of the window is Δt, then the change rate of humidity interference intensity is (ri+1 - ri) / Δt. The change rate of humidity interference intensity reflects the change of the interference intensity of environmental humidity change on the equipment temperature fluctuation over time. The greater the change rate, the more unstable the humidity interference situation, and the greater the possible impact on the equipment operation.

[0084] Step S146: Generate the equipment health status score based on the weighted combination of the thermal anomaly index, the pressure pattern deviation score, the mechanical state degradation index, and the humidity interference intensity change rate.

[0085] Set weight coefficients for the thermal anomaly index, the pressure pattern deviation score, the mechanical state degradation index, and the humidity interference intensity change rate respectively. These weight coefficients are determined according to the importance of each characteristic to the equipment health status. For example, set the weight of the thermal anomaly index as w1 = 0.3, the weight of the pressure pattern deviation score as w2 = 0.2, the weight of the mechanical state degradation index as w3 = 0.3, and the weight of the humidity interference intensity change rate as w4 = 0.2. Multiply each characteristic value by its corresponding weight coefficient, and then add these products together to obtain the equipment health status score. That is, equipment health status score = w1 * thermal anomaly index + w2 * pressure pattern deviation score + w3 * mechanical state degradation index + w4 * humidity interference intensity change rate. Through this weighted combination method, multiple factors such as the thermal distribution, pressure fluctuation, mechanical resonance, and humidity interference of the equipment are comprehensively considered, and a score value that comprehensively reflects the equipment health status is obtained. The higher the score value, the better the equipment health status; the lower the score value, it indicates that the equipment may have abnormal conditions and further attention and handling are required.

[0086] Meanwhile, generate a set of anomaly location identifiers based on the comparison results of each characteristic value with the corresponding reference value. For example, if the thermal anomaly index is lower than the direction consistency threshold, mark the thermal distribution as abnormal; if the pressure pattern deviation score exceeds the preset pressure anomaly threshold, mark the pressure fluctuation pattern as abnormal; if the mechanical state degradation index deviates significantly, mark the mechanical resonance frequency point as abnormal; if the humidity interference intensity change rate exceeds the preset humidity interference threshold, mark the humidity impact as abnormal. Combine these anomaly marks together to form a set of anomaly location identifiers, which can clearly indicate the specific aspects where the equipment may have abnormalities and provide accurate location information for subsequent production parameter optimization.

[0087] Step S150: Generate a set of production parameter optimization strategies based on the equipment health status score and the set of anomaly location identifiers, and send the set of production parameter optimization strategies to the equipment control terminal to execute real-time control instructions.

[0088] After obtaining the equipment health status score and the set of anomaly location identifiers, it is necessary to generate a corresponding set of production parameter optimization strategies based on this information and send these strategies to the equipment control terminal to achieve real-time control of the production process, ensure the normal operation of the production equipment and product quality.

[0089] Step S151: When the equipment health status score is lower than the first health threshold, generate a stamping pressure reduction strategy, which includes a pressure peak reduction ratio and a holding time adjustment plan.

[0090] The first health threshold is a scoring boundary set according to the normal operation requirements and experience of the production equipment. For example, it is set to 70 points. When the equipment health status score is lower than 70 points, it indicates that the overall health status of the equipment is not good, and there may be problems such as abnormal pressure fluctuations. At this time, a stamping pressure reduction strategy needs to be generated.

[0091] Determine the pressure peak reduction ratio. By analyzing the pressure pattern deviation score and historical production data, evaluate the impact of the current stamping pressure on the equipment health status. For example, if the pressure pattern deviation score is high, it indicates that the current stamping pressure fluctuates greatly, which may cause a greater burden on the equipment, and the pressure peak needs to be appropriately reduced. According to the evaluation results, determine the pressure peak reduction ratio. For example, reduce it by 10%. That is, if the current stamping pressure peak is P, the adjusted pressure peak is P*(1 - 10%).

[0092] Formulate a holding time adjustment plan. The holding time refers to the length of time when the pressure remains at the peak during the stamping process. Analyze the stability index during the pressure holding stage and the actual operation of the equipment to determine the adjustment direction and amplitude of the holding time. If the stability index during the pressure holding stage is low, it indicates that the pressure fluctuates greatly during the holding stage, and the holding time may need to be appropriately shortened. For example, adjust the holding time from the original t seconds to t*(1 - 5%) seconds. Combine the pressure peak reduction ratio and the holding time adjustment plan to form a stamping pressure reduction strategy.

[0093] Step S152: When the mechanical state degradation index exceeds the preset mechanical wear threshold, generate a vibration suppression strategy, which includes conveyor belt tension adjustment parameters and lubricant replenishment cycle.

[0094] The preset mechanical wear threshold is a boundary value determined according to the mechanical performance and service life of the production equipment. For example, it is set to 1.2. When the mechanical state degradation index exceeds 1.2, it indicates that the mechanical state of the equipment has significantly degraded, and there may be problems such as mechanical looseness and bearing wear, resulting in increased vibration. At this time, a vibration suppression strategy needs to be generated.

[0095] First, determine the conveyor belt tension adjustment parameters. Insufficient conveyor belt tension may cause problems such as slipping and vibration during operation, while excessive tension may increase the wear of the conveyor belt and transmission components. By analyzing information such as the proportion of low-frequency energy and the number of high-frequency energy mutation points in the mechanical resonance frequency point characteristic matrix, evaluate the relationship between the vibration condition of the conveyor belt and the tension. If the proportion of low-frequency energy is too high, it may indicate insufficient conveyor belt tension and appropriate tension needs to be increased; if the number of high-frequency energy mutation points is too large, it may indicate excessive tension or other abnormal conditions, and adjustments are required.

[0096] Based on historical data and experimental results, establish a tension adjustment model. For example, when the proportion of low-frequency energy exceeds the set threshold, for each increase in the proportion of low-frequency energy by a set ratio, the corresponding tension adjustment amount is increased. Assume that for each 5% increase in the proportion of low-frequency energy, the conveyor belt tension is increased by 10N. By analyzing the current mechanical resonance frequency point characteristic matrix, calculate the tension value that needs to be adjusted to obtain the conveyor belt tension adjustment parameters.

[0097] Next, determine the lubricant replenishment cycle. Wear of mechanical components will increase friction, which in turn generates more vibration. Lubricants can reduce the friction between mechanical components, reduce wear and vibration. Analyze factors such as the mechanical resonance frequency point characteristic matrix, the operating time of the equipment, and the load condition to evaluate the wear degree and lubrication requirements of mechanical components.

[0098] Based on historical data and the equipment operation manual, establish a lubricant replenishment cycle model. For example, when the mechanical state degradation index exceeds the set threshold, for each increase in the mechanical state degradation index by a set value, the set lubricant replenishment cycle is shortened accordingly. Assume that for each 0.1 increase in the mechanical state degradation index, the lubricant replenishment cycle is shortened from the original 30 days to 25 days. By analyzing the current mechanical state degradation index, calculate the adjusted lubricant replenishment cycle to obtain the adjustment plan for the lubricant replenishment cycle.

[0099] Combine the conveyor belt tension adjustment parameters and the lubricant replenishment cycle adjustment plan to form a vibration suppression strategy.

[0100] Step S153: When the thermal anomaly index continuously exceeds the preset temperature rise threshold, generate an optimization strategy for the cooling system, where the optimization strategy for the cooling system includes the fan speed increase gradient and the coolant flow adjustment curve.

[0101] The preset temperature rise threshold is a limit value set according to the normal operating temperature range and heat dissipation requirements of the production equipment, for example, set to 0.8. When the thermal anomaly index continuously exceeds 0.8 multiple times, it indicates that there is a continuous abnormality in the thermal state of the equipment, and overheating may occur. At this time, an optimization strategy for the cooling system needs to be generated.

[0102] Determine the basic rotational speed increase amount according to the difference between the thermal anomaly index and the temperature rise threshold, and calculate the dynamic compensation coefficient based on the current load rate of the equipment. First, calculate the difference between the thermal anomaly index and the temperature rise threshold. For example, if the current thermal anomaly index is 0.9 and the temperature rise threshold is 0.8, the difference is 0.1. According to historical data and experimental results, establish a relationship model between the basic rotational speed increase amount and the difference. For example, for every 0.01 increase in the difference, the basic rotational speed increase amount increases by 100 revolutions per minute. Then, for a difference of 0.1, the basic rotational speed increase amount is 1000 revolutions per minute.

[0103] The current load rate of the equipment reflects the working intensity of the equipment. The higher the load rate, the more heat the equipment generates and the stronger the cooling capacity required. Calculate the current load rate of the equipment by monitoring parameters such as the current and power of the equipment. For example, if the rated power of the equipment is P0 and the current actual power is P1, then the current load rate of the equipment is P1 / P0. According to historical data and experimental results, establish a relationship model between the dynamic compensation coefficient and the current load rate of the equipment. For example, when the current load rate of the equipment is between 50% - 70%, the dynamic compensation coefficient is 1.2; when the current load rate of the equipment is between 70% - 90%, the dynamic compensation coefficient is 1.5. Determine the dynamic compensation coefficient according to the current load rate of the equipment.

[0104] Multiply the basic rotational speed increase amount by the dynamic compensation coefficient to obtain the actual rotational speed increase gradient, and limit the rotational speed increase speed not to exceed the maximum acceleration of the motor. Multiply the previously calculated basic rotational speed increase amount of 1000 revolutions per minute by the dynamic compensation coefficient of 1.5 to obtain an actual rotational speed increase gradient of 1500 revolutions per minute. At the same time, to prevent the motor from being damaged due to too fast a rotational speed increase, it is necessary to limit the rotational speed increase speed not to exceed the maximum acceleration of the motor. Assume that the maximum acceleration of the motor is 2000 revolutions per minute². According to the startup time of the motor and the actual rotational speed increase gradient, reasonably adjust the time interval of the rotational speed increase to ensure that the rotational speed increase speed is within the range of the maximum acceleration of the motor.

[0105] Determine the coolant priority supply area according to the direction of the maximum change in the temperature gradient, and generate a zoning flow rate control instruction. The direction of the maximum change in the temperature gradient reflects the direction in which the surface temperature of the equipment changes the fastest. Along this direction, there are often areas with higher temperatures that need to be cooled preferentially. Determine the direction of the maximum change in the temperature gradient by analyzing the thermal distribution map of the equipment surface. For example, if the direction of the maximum change in the temperature gradient points to a specific corner of the equipment, then the area where this corner is located is determined as the coolant priority supply area.

[0106] Generate a partitioned flow rate regulation command according to the coolant priority supply area. For example, divide the cooling system into multiple areas. For the coolant priority supply area, increase the coolant flow rate in this area; for other areas, appropriately adjust the coolant flow rate according to the temperature distribution. The specific flow rate adjustment values can be calculated based on the temperature distribution on the surface of the device and the cooling requirements.

[0107] Calculate the coolant demand density distribution based on the coordinates of the high-temperature aggregation area, and fit to obtain the coolant flow rate adjustment curve. By analyzing the thermal distribution map of the device surface, determine the coordinates of the high-temperature aggregation area. Calculate the coolant demand density of each area according to factors such as the size and temperature of the high-temperature aggregation area. For example, the higher the temperature and the larger the area of the high-temperature aggregation area, the higher the coolant demand density in this area.

[0108] Arrange the coolant demand densities of each area in a set order to obtain the coolant demand density distribution. Then use a fitting method, such as polynomial fitting, to fit the coolant flow rate adjustment curve according to the coolant demand density distribution. This curve indicates how the coolant flow rate should be adjusted at different positions and times to meet the cooling requirements of the device.

[0109] Set the cooperative control timing sequence of the rotational speed increase gradient and the flow rate adjustment curve to ensure the phase synchronization of the fan acceleration and the coolant supply increment. To improve the efficiency of the cooling system, it is necessary to ensure the temporal synchronization of the fan acceleration and the coolant supply increment. According to the actual rotational speed increase gradient and the coolant flow rate adjustment curve, formulate the cooperative control timing sequence. For example, when the fan starts to accelerate, start increasing the coolant flow rate according to the coolant flow rate adjustment curve, and ensure that when the fan reaches the maximum rotational speed, the coolant flow rate also reaches the corresponding maximum value. Through this cooperative control, the cooling system can more effectively reduce the temperature of the device and solve the thermal anomaly problem.

[0110] Step S154: When the change rate of the humidity interference intensity exceeds the environmental adaptation threshold, generate a humidity compensation strategy, and the humidity compensation strategy includes the sealed cabin air pressure adjustment parameter and the desiccant replacement frequency.

[0111] The environmental adaptation threshold is a boundary value set according to the adaptability of the production equipment to environmental humidity changes, for example, set to 0.05. When the change rate of the humidity interference intensity exceeds 0.05, it indicates that the change in environmental humidity has a greater interference on the device and may affect the normal operation of the device. At this time, it is necessary to generate a humidity compensation strategy.

[0112] Determine the air pressure adjustment parameters for the sealed cabin. The sealed cabin can, to a certain extent, isolate the influence of the external environmental humidity. By adjusting the air pressure inside the sealed cabin, the humidity inside the cabin can be controlled. Analyze the change rate of the humidity interference intensity and the environmental humidity change curve to evaluate the degree and trend of the current humidity's impact on the equipment. If the change rate of the humidity interference intensity continues to increase, it indicates that the interference of the environmental humidity change on the equipment is intensifying, and it is necessary to appropriately increase the air pressure inside the sealed cabin to reduce the entry of external humidity.

[0113] Based on historical data and experimental results, establish a relationship model between the air pressure adjustment parameters of the sealed cabin and the change rate of the humidity interference intensity. For example, for every 0.01 increase in the change rate of the humidity interference intensity, increase the air pressure inside the sealed cabin by 100 Pascals. Through the analysis of the current change rate of the humidity interference intensity, calculate the value of the air pressure of the sealed cabin that needs to be adjusted to obtain the air pressure adjustment parameters of the sealed cabin.

[0114] Determine the desiccant replacement frequency. The desiccant can absorb the moisture inside the sealed cabin and reduce the humidity inside the cabin. Analyze the change rate of the humidity interference intensity and the humidity change situation inside the sealed cabin to evaluate the moisture absorption effect and service life of the desiccant. If the change rate of the humidity interference intensity is large, it indicates that the moisture absorption speed of the desiccant may not be able to keep up with the humidity change, and it is necessary to shorten the desiccant replacement frequency.

[0115] Based on historical data and the performance parameters of the desiccant, establish a relationship model between the desiccant replacement frequency and the change rate of the humidity interference intensity. For example, for every 0.01 increase in the change rate of the humidity interference intensity, adjust the desiccant replacement frequency from once a week to once every three days. Through the analysis of the current change rate of the humidity interference intensity, calculate the adjusted desiccant replacement frequency to obtain the adjustment plan for the desiccant replacement frequency.

[0116] Combine the air pressure adjustment parameters of the sealed cabin and the adjustment plan for the desiccant replacement frequency to form a humidity compensation strategy.

[0117] Step S155: Sort the stamping pressure reduction strategy, vibration suppression strategy, cooling system optimization strategy, and humidity compensation strategy by priority and integrate them into the production parameter optimization strategy set.

[0118] Rank the priorities of the stamping pressure reduction strategy, vibration suppression strategy, cooling system optimization strategy, and humidity compensation strategy according to the impact degree and urgency of each strategy on the equipment health status. Generally speaking, if there is an overheating problem with the equipment, the cooling system optimization strategy has the highest priority because overheating may cause equipment damage or even lead to safety accidents; if there is an abnormal mechanical vibration problem with the equipment, the vibration suppression strategy has the second highest priority because excessive vibration will affect the stability and service life of the equipment; if there is an abnormal pressure fluctuation in the equipment, the stamping pressure reduction strategy has the next highest priority; if the environmental humidity has a greater interference on the equipment, the humidity compensation strategy has a relatively lower priority.

[0119] For example, set the priority of the cooling system optimization strategy to 1, the priority of the vibration suppression strategy to 2, the priority of the stamping pressure reduction strategy to 3, and the priority of the humidity compensation strategy to 4. Arrange each strategy in order from highest to lowest priority and integrate them into a set of production parameter optimization strategies. This set of production parameter optimization strategies includes optimization strategies for different abnormal situations of the equipment and can comprehensively adjust production parameters to ensure the normal operation of the equipment.

[0120] Step S156: Send the set of production parameter optimization strategies to the equipment control terminal to execute real-time control instructions.

[0121] Convert the stamping pressure reduction strategy into a hydraulic system control signal, and the hydraulic system control signal includes pressure sensor calibration parameters and servo valve opening adjustment steps. The pressure peak reduction ratio and the holding pressure time adjustment scheme in the stamping pressure reduction strategy need to be implemented through the hydraulic system. Convert the pressure peak reduction ratio into pressure sensor calibration parameters, for example, adjust the measurement range of the pressure sensor accordingly so that it can accurately measure the adjusted pressure value. Convert the holding pressure time adjustment scheme into servo valve opening adjustment steps, for example, determine the adjustment amplitude and time interval of the servo valve opening according to the shortening or lengthening of the holding pressure time. Combine these parameters together to form a hydraulic system control signal.

[0122] Convert the vibration suppression strategy into a mechanical drive system control instruction, and the mechanical drive system control instruction includes the set value of the tension roller displacement and the trigger condition of the automatic lubrication device. The conveyor belt tension adjustment parameter and the lubricant replenishment cycle in the vibration suppression strategy need to be implemented through the mechanical drive system. Convert the conveyor belt tension adjustment parameter into the set value of the tension roller displacement, for example, calculate the distance that the tension roller needs to move according to the required increase or decrease in tension. Convert the lubricant replenishment cycle into the trigger condition of the automatic lubrication device, for example, determine the trigger time interval of the automatic lubrication device according to the shortened or lengthened lubricant replenishment cycle. Combine these parameters together to form a mechanical drive system control instruction.

[0123] Convert the cooling system optimization strategy into PID parameter adjustment instructions for the temperature control module. The PID parameter adjustment instructions include a proportional coefficient correction amount and an integral time constant update value. The fan speed increase gradient and coolant flow adjustment curve in the cooling system optimization strategy need to be implemented through the temperature control module. Convert the fan speed increase gradient and coolant flow adjustment curve into PID parameter adjustment instructions, for example, calculate the proportional coefficient correction amount and the integral time constant update value according to the changes in the speed increase gradient and flow adjustment curve. By adjusting the PID parameters, the temperature control module can more precisely control the fan speed and coolant flow, achieving effective regulation of the equipment temperature.

[0124] Convert the humidity compensation strategy into an operation sequence for the environmental control system. The operation sequence for the environmental control system includes a timing diagram for the opening and closing of air valves and the triggering frequency of the desiccant delivery mechanism. The sealed cabin air pressure adjustment parameter and desiccant replacement frequency in the humidity compensation strategy need to be implemented through the environmental control system. Convert the sealed cabin air pressure adjustment parameter into a timing diagram for the opening and closing of air valves, for example, determine the opening and closing times of the air valves according to the required increase or decrease in the sealed cabin air pressure. Convert the desiccant replacement frequency into the triggering frequency of the desiccant delivery mechanism, for example, determine the triggering time interval of the desiccant delivery mechanism according to the shortened or extended desiccant replacement frequency. Combine these parameters to form an operation sequence for the environmental control system.

[0125] Encapsulate the control signals, control instructions, adjustment instructions, and operation sequences into real-time data packets through an industrial bus protocol, and send them to each device control terminal according to a preset priority queue, and receive the execution status feedback for policy effectiveness verification. The industrial bus protocol is a standard protocol for communication between devices in an industrial automation system, such as the Modbus protocol, Profibus protocol, etc. Encapsulate the hydraulic system control signal, mechanical drive system control instruction, PID parameter adjustment instruction of the temperature control module, and the operation sequence of the environmental control system according to the format of the industrial bus protocol to form real-time data packets.

[0126] According to the previously set policy priorities, send the real-time data packets to each device control terminal in the order of the priority queue. After receiving the data packets, each device control terminal executes the corresponding regulation instructions. At the same time, the device control terminal will send back the execution status feedback information. By analyzing this feedback information, verify the effectiveness of the production parameter optimization strategy. If it is found that the policy execution effect is not good, it is necessary to re-evaluate and adjust the policy to ensure that the equipment can return to the normal operating state.

[0127] Figure 2FIG. 0 shows a hardware structure diagram of a tinplate box production monitoring system 100 provided by an embodiment of the present application for implementing the above-mentioned method for analyzing the production status data of tinplate boxes based on the Internet of Things, as Figure 2 shown, the tinplate box production monitoring system 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

[0128] In a possible design, the tinplate box production monitoring system 100 may be a single server or a server group. The server group may be centralized or distributed (for example, the tinplate box production monitoring system 100 may be a distributed system). In some embodiments, the tinplate box production monitoring system 100 may be local or remote. For example, the tinplate box production monitoring system 100 may access information and / or data stored in the machine-readable storage medium 120 via a network. Again, for example, the tinplate box production monitoring system 100 may be directly connected to the machine-readable storage medium 120 to access the stored information and / or data. In some embodiments, the tinplate box production monitoring system 100 may be implemented on the tinplate box production monitoring system. By way of example only, the tinplate box production monitoring system may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any aggregation thereof.

[0129] The machine-readable storage medium 120 may store data and / or instructions. In some embodiments, the machine-readable storage medium 120 may store data obtained from an external terminal. In some embodiments, the machine-readable storage medium 120 may store data and / or instructions used by the tinplate box production monitoring system 100 to execute or use to complete the exemplary methods described in the present application.

[0130] In a specific implementation process, one or more processors 110 execute computer-executable instructions stored in the machine-readable storage medium 120, so that the processors 110 can execute the method for analyzing the production status data of tinplate boxes based on the Internet of Things in the above method embodiments. The processors 110, the machine-readable storage medium 120, and the communication unit 140 are connected through the bus 130, and the processors 110 may be used to control the transceiver actions of the communication unit 140.

[0131] For the specific implementation process of the processor 110, reference may be made to the various method embodiments executed by the above-mentioned tinplate box production monitoring system 100. The implementation principles and technical effects are similar, and will not be elaborated herein in this embodiment.

[0132] In addition, an embodiment of the present application further provides a readable storage medium, in which computer-executable instructions are set. When a processor runs the computer-executable instructions, the above-mentioned method for analyzing the production status data of tinplate boxes based on the Internet of Things is implemented.

[0133] It should be noted that, in order to simplify the description of the disclosure of the present application and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawing or description thereof. Similarly, it should be noted that, in order to simplify the description of the disclosure of the present application and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawing or description thereof.

Claims

1. A method for analyzing the production status data of tinplate boxes based on the Internet of Things, characterized in that, The method includes: Collecting a multi-source real-time monitoring data set through Internet of Things sensor nodes deployed at the edge of production equipment, where the multi-source real-time monitoring data set includes a device temperature monitoring sequence, a stamping pressure monitoring waveform, a conveyor belt vibration spectrum, and an environmental humidity change curve; Performing cross-dimensional standardization processing on the multi-source real-time monitoring data set to obtain a standardized monitoring data set, where the cross-dimensional standardization processing includes a time domain synchronization alignment operation and a dimension unification conversion operation; Performing feature extraction on the standardized monitoring data set to obtain a state feature set of the production equipment, where the state feature set includes a thermal distribution feature, a pressure fluctuation pattern feature, a mechanical resonance frequency point feature, and an environmental interference coupling feature; Based on a preset abnormal state discrimination rule library, dynamically matching the state feature set with a historical normal production feature template to generate a device health state score and an abnormal location identification set; Generating a production parameter optimization strategy set according to the device health state score and the abnormal location identification set, and sending the production parameter optimization strategy set to a device control terminal to execute real-time regulation instructions.

2. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 1, wherein The performing cross-dimensional standardization processing on the multi-source real-time monitoring data set to obtain a standardized monitoring data set includes: Performing timestamp alignment processing on the device temperature monitoring sequence, extracting the temperature gradient change rate at each sampling moment, and mapping the original temperature value to a normalized temperature range based on a preset industrial temperature measurement range; Performing peak detection processing on the stamping pressure monitoring waveform, identifying the pressure extreme points in each stamping cycle, and performing dimensionless conversion on the pressure extreme points according to the rated pressure parameters of the stamping equipment to generate a standard pressure fluctuation sequence; Performing frequency band decomposition processing on the conveyor belt vibration spectrum, extracting the energy integral value within a preset mechanical resonance frequency band, and converting the energy integral value into a standard vibration intensity index based on the sensitivity coefficient of the vibration sensor; Performing sliding window smoothing processing on the environmental humidity change curve, calculating the humidity variation coefficient within each window, and performing a ratio operation on the humidity variation coefficient and an environmental reference humidity parameter to generate a standard humidity influence factor sequence; Integrating the normalized temperature range, the standard pressure fluctuation sequence, the standard vibration intensity index, and the standard humidity influence factor sequence in the time dimension into the standardized monitoring data set.

3. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 2, characterized in that, The performing frequency band decomposition processing on the conveyor belt vibration spectrum, extracting the energy integral value within a preset mechanical resonance frequency band includes: Invoking a preset band-pass filter to perform frequency band segmentation on the original vibration spectrum to obtain multiple sub-band energy distribution sequences, where the cut-off frequency of the band-pass filter is dynamically adjusted according to the inherent vibration characteristics of the conveyor belt material; Matching a target resonance frequency band corresponding to the current production batch from the multiple sub-band energy distribution sequences, where the target resonance frequency band is obtained through learning of historical vibration data; Performing integral operation on the energy distribution sequence within the target resonance frequency band to obtain an initial energy integral value, and performing speed compensation calibration on the initial energy integral value based on the real-time monitoring value of the conveyor belt running speed; Compare the calibrated energy integral value with a preset vibration safety threshold. If the calibrated energy integral value exceeds the vibration safety threshold, trigger a resonance frequency band recalibration operation to update the target resonance frequency band.

4. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 2, wherein Perform feature extraction on the standardized monitoring data set to obtain a state feature set of the production equipment, including: Perform spatial interpolation processing on the normalized temperature range in the standardized monitoring data set to generate a thermal distribution map of the equipment surface, and extract the direction of the maximum change in temperature gradient and the coordinates of the high-temperature aggregation area from the thermal distribution map of the equipment surface; Perform time-frequency joint analysis on the standard pressure fluctuation sequence, extract the slope feature in the pressure rising stage, the stability index in the pressure holding stage, and the decay rate in the pressure releasing stage, and construct a pressure fluctuation mode coding vector; Perform wavelet packet decomposition on the standard vibration intensity index, extract the low-frequency energy ratio related to mechanical looseness and the number of high-frequency energy mutation points related to bearing wear, and generate a mechanical resonance frequency point feature matrix; Perform lag correlation analysis on the standard humidity influence factor sequence, calculate the time-delay correlation coefficient between the ambient humidity change and the equipment temperature fluctuation, and identify the duration of the influence of the humidity mutation event on the temperature stability; Integrate the direction of the maximum change in temperature gradient, the pressure fluctuation mode coding vector, the mechanical resonance frequency point feature matrix, and the time-delay correlation coefficient into the state feature set.

5. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 4, characterized in that, Perform time-frequency joint analysis on the standard pressure fluctuation sequence, and extract the slope feature in the pressure rising stage, including: Identify the starting pressure point, peak pressure point, and ending pressure point within the pressure fluctuation period, and calculate the time interval from the starting pressure point to the peak pressure point as the rising stage duration; Perform linear fitting on the pressure sampling points in the rising stage to obtain an initial slope estimate value, and calculate the root mean square error of the fitting residuals to evaluate the linearity; When the root mean square error exceeds a preset linearity threshold, use the piecewise polynomial fitting method to recalculate the dynamic slope change curve of the pressure rising stage; Extract the maximum slope value, average slope value, and slope variation coefficient of the dynamic slope change curve, and combine the three as the slope feature.

6. The method for analyzing tinplate box production status data based on the Internet of Things according to claim 4, characterized in that: Based on a preset abnormal state discrimination rule library, perform dynamic similarity matching between the state feature set and the historical normal production feature template, including: Retrieve a reference feature set with the same current production batch number from the historical normal production feature template, and the reference feature set includes a historical thermal distribution benchmark, a pressure fluctuation mode benchmark, a mechanical resonance frequency point benchmark, and a humidity influence benchmark; Calculate the cosine value of the direction angle between the direction of the maximum change in temperature gradient and the historical thermal distribution benchmark as the thermal anomaly index; Perform dynamic time warping matching between the pressure fluctuation mode coding vector and the pressure fluctuation mode benchmark to obtain a pressure mode deviation score; Perform singular value decomposition on the mechanical resonance frequency point feature matrix and the mechanical resonance frequency point benchmark, and extract the maximum singular value ratio as the mechanical state degradation index; Perform sliding window correlation analysis on the time-delay correlation coefficient and the humidity influence benchmark, and calculate the humidity interference intensity change rate; Generate the equipment health status score based on the weighted combination of the thermal anomaly index, the pressure mode deviation score, the mechanical state degradation index, and the humidity interference intensity change rate.

7. The method for analyzing tinplate box production status data based on the Internet of Things according to claim 6, characterized in that: The calculation of the cosine value of the direction angle between the maximum change direction of the temperature gradient and the historical thermal distribution reference includes: Represent the maximum change direction of the temperature gradient in the current production cycle as a three-dimensional direction vector, where the three dimensions correspond to the length direction, width direction, and height direction of the equipment respectively; Extract the standard temperature gradient direction vector of the same production batch from the historical thermal distribution reference; Calculate the dot product of the three-dimensional direction vector and the standard temperature gradient direction vector, and divide it by the product of their moduli to obtain the cosine value of the direction angle; When the cosine value of the direction angle is lower than the preset direction consistency threshold, trigger an alarm for abnormal thermal distribution and record the coordinates of the abnormal area; Dynamically adjust the weight coefficient of the thermal anomaly index according to the difference between the cosine value of the direction angle and the direction consistency threshold.

8. The method for analyzing tinplate box production status data based on the Internet of Things according to claim 6, characterized in that: The generation of the production parameter optimization strategy set based on the equipment health status score and the abnormal location identification set includes: When the equipment health status score is lower than the first health threshold, generate a stamping pressure reduction strategy, which includes the reduction ratio of the pressure peak and the adjustment plan for the holding pressure time; When the mechanical state degradation index exceeds the preset mechanical wear threshold, generate a vibration suppression strategy, which includes the adjustment parameters of the conveyor belt tension and the lubricant replenishment cycle; When the thermal anomaly index continuously exceeds the preset temperature rise threshold, generate a cooling system optimization strategy, which includes the fan speed increase gradient and the coolant flow adjustment curve; When the humidity interference intensity change rate exceeds the environmental adaptation threshold, generate a humidity compensation strategy, which includes the adjustment parameters of the sealed cabin air pressure and the desiccant replacement frequency; Sort the stamping pressure reduction strategy, vibration suppression strategy, cooling system optimization strategy, and humidity compensation strategy by priority and integrate them into the production parameter optimization strategy set.

9. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 8, wherein The generation of the cooling system optimization strategy when the thermal anomaly index continuously exceeds the preset temperature rise threshold, and the cooling system optimization strategy includes the fan speed increase gradient and the coolant flow adjustment curve, includes: Determine the basic speed increase amount according to the difference between the thermal anomaly index and the temperature rise threshold, and calculate the dynamic compensation coefficient based on the current load rate of the equipment; Multiply the basic speed increase amount by the dynamic compensation coefficient to obtain the actual speed increase gradient, and limit the speed increase speed not to exceed the maximum acceleration of the motor; Determine the priority supply area of the coolant according to the maximum change direction of the temperature gradient, and generate a zoning flow control instruction; Calculate the coolant demand density distribution based on the coordinates of the high-temperature aggregation area, and fit to obtain the coolant flow adjustment curve; Set the coordinated control timing of the speed increase gradient and the flow adjustment curve to ensure the phase synchronization of the fan acceleration and the coolant supply increment.

10. The method for analyzing the production status data of tinplate boxes based on the Internet of Things according to claim 8, characterized in that, The issuance of the production parameter optimization strategy set to the equipment control terminal to execute real-time control instructions includes: Converting the stamping pressure reduction strategy into a hydraulic system control signal, wherein the hydraulic system control signal includes pressure sensor calibration parameters and a servo valve opening adjustment step; Converting the vibration suppression strategy into a mechanical transmission system control instruction, wherein the mechanical transmission system control instruction includes a tension roller displacement setting value and an automatic lubrication device triggering condition; Converting the cooling system optimization strategy into a PID parameter adjustment instruction for a temperature control module, wherein the PID parameter adjustment instruction includes a proportional coefficient correction amount and an integral time constant update value; Converting the humidity compensation strategy into an environmental control system operation sequence, wherein the environmental control system operation sequence includes a gas valve opening and closing timing diagram and a desiccant delivery mechanism triggering frequency; The control signals, control instructions, adjustment instructions and operation sequences are encapsulated into real-time data packets through the industrial bus protocol, and sent to each device control terminal according to the preset priority queue, and the execution status feedback is received to verify the effectiveness of the strategy.

Images