Real-time monitoring and processing system for inner packaging production data

Abstract

The present invention relates to the field of condition monitoring technology, specifically a real-time monitoring and processing system for inner packaging production data. The system includes an operating status acquisition module, a performance deviation assessment module, an abnormal behavior identification module, a task scheduling optimization module, and a load balancing optimization module. In the present invention, through the coordinated collection of operating data such as temperature fluctuations, pressure changes, and flow rate stability, dynamic aggregation of operating status and immediate perception of high-frequency changes are achieved. With the help of a cross-discrimination strategy of distribution uniformity and response time, non-representative data segments are eliminated, and the accuracy of performance anomaly identification is improved. Through the time-coupled analysis of gradient trajectory and offset, abnormal behavior segments are locked in advance, and forward identification of trend instability is achieved. The intervention window is dynamically screened to ensure the effectiveness and synchronization of the response. Based on a real-time matching mechanism between load and demand, task priority and processing channel allocation are optimized, and intervention efficiency and scheduling adaptability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of condition monitoring, and in particular to a real-time monitoring and processing system for inner packaging production data. Background Art

[0002] The field of condition monitoring technology involves real-time detection, data collection, analysis, and management of equipment operating status. Core issues include the continuous acquisition of operating parameters, the recording and analysis of key data, the prediction of state change trends, and the identification and early warning of abnormal conditions. Widely used in industries such as industrial manufacturing, power systems, and transportation, these systems achieve comprehensive monitoring and management of equipment lifecycle status through technical means. Among these, traditional real-time monitoring and processing systems for inner packaging production data centrally collect and manage the large amounts of real-time data generated during the inner packaging production process. The technical issues addressed are the rapid aggregation, unified encoding, and structured processing of multiple sensor data types, such as temperature, pressure, flow rate, position, and speed, during the automated production of inner packaging. Traditional real-time monitoring and processing systems for inner packaging production data utilize serial connections between data collectors and industrial computers, acquiring multi-sensor data via the CAN bus or RS485 protocol. These systems then rely on a PLC centralized control system to perform preliminary data standardization and coordinate the execution of command response mechanisms.

[0003] The existing technology in the production of inner packaging is based on a model in which data collectors and industrial computers are connected in series. The operating status data mostly relies on linear transmission paths and unified control instructions to complete scheduling and processing. When the number of sensors increases or the complexity of equipment operation increases, the data is prone to return delays or format dislocations, resulting in a decrease in real-time monitoring capabilities. Especially in the scenario where multiple source parameters suddenly change at the same time, it is difficult to make refined judgments, and the processing strategy is also difficult to cover high-frequency abnormal conditions. In addition, since the scheduling mechanism is fixedly dependent on the PLC centralized processing process, there is a problem of allocation lag in resource utilization. When the processing tasks are intensive, there is a queue accumulation phenomenon in the task response, which affects the overall smoothness and emergency response capabilities of the system. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a real-time monitoring and processing system for inner packaging production data.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: the real-time monitoring and processing system for inner packaging production data includes:

[0006] The operating status acquisition module uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment to monitor the temperature fluctuation amplitude, pressure change rate, and flow rate stability during equipment operation and generate an equipment operating status set;

[0007] The performance deviation evaluation module collects temperature distribution uniformity and pressure response time data based on the equipment operation status set, identifies the matching between the uniformity interval and the response time interval, filters the data segments that deviate from the standard range, and generates a performance deviation monitoring interval;

[0008] The abnormal behavior identification module calls the performance deviation monitoring interval, extracts the pressure change trajectory of the corresponding time period in the pressure detection component, analyzes the time correlation between the gradient characteristics of the pressure change trajectory and the temperature distribution offset, filters the abnormal behavior fragments, and obtains the device abnormal behavior identification set;

[0009] The task scheduling optimization module detects the communication delay index and instruction execution interval index between the production equipment end and the control center end based on the equipment abnormal behavior identification set, selects the low-latency time period as the intervention window, synchronously maps the time period corresponding to the abnormal behavior with the intervention window, and generates a task scheduling mapping table.

[0010] As a further solution of the present invention, the equipment operation status set includes temperature fluctuation level, pressure change trend, and flow rate stability index; the performance deviation monitoring interval includes uniformity fluctuation range, response time change range, and data deviation segment; the equipment abnormal behavior identification set includes abnormal behavior trajectory, abnormal response mode, and abnormal behavior type; the task scheduling mapping table includes abnormal time node, intervention window, and synchronization association information.

[0011] As a further solution of the present invention, the operating status acquisition module includes:

[0012] The parameter monitoring submodule uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment. It uses the temperature monitoring component to detect temperature fluctuation data and the pressure detection component to detect pressure change data. It calculates the temperature fluctuation amplitude, pressure change rate, and flow rate stability per unit time, compares them with the baseline values, and generates component parameter offsets.

[0013] The state classification submodule calls the component parameter offset, classifies the components according to the temperature fluctuation amplitude, pressure change rate and flow rate stability, and sets the temperature distribution, pressure response and flow rate stability state interval, and marks the corresponding state of the data to obtain a state feedback data set;

[0014] The instruction generation submodule calls the state feedback data set, and according to the temperature distribution, pressure response and flow rate stable state type, screens the equipment execution resource allocation, task adjustment and recording control actions in the corresponding state, identifies the corresponding control instructions based on the action threshold associated with the differentiated state, and generates the equipment operation state set.

[0015] As a further solution of the present invention, the performance deviation evaluation module includes:

[0016] The uniformity identification submodule analyzes the temperature distribution uniformity change rate and uniformity fluctuation amplitude based on the equipment operation status set, selects data segments with low change rate and fluctuation amplitude less than the uniformity stability threshold, and obtains the uniformity stability interval;

[0017] The response time analysis submodule calls the uniformity stability interval, identifies the response time change rate through the synchronously collected pressure response time data, obtains the difference in response time change, filters the data segments below the response time consistency threshold, and generates the response time consistency interval;

[0018] The performance deviation screening submodule calls the response time consistency interval, and screens data segments that deviate from the stability threshold and the consistency threshold according to the uniformity fluctuation amplitude and the response time consistency, to generate a performance deviation monitoring interval.

[0019] As a further solution of the present invention, the abnormal behavior identification module includes:

[0020] The trajectory extraction submodule calls the performance deviation monitoring interval, extracts the pressure detection component data, extracts the pressure change points and operation change values ​​according to the timestamps, and organizes them into a synchronous data structure to generate a synchronous pressure trajectory set;

[0021] The time series association calculation submodule calls the synchronized pressure trajectory set, calculates the normalized index value of the pressure trajectory offset by identifying the pressure trajectory gradient characteristics of the temperature distribution change sequence and the normalized change rate of the temperature distribution offset, compensates for the impact of operational changes by superimposing offset terms, and filters time segments above the abnormal offset threshold to generate a device-associated offset set;

[0022] The abnormal behavior collection submodule calls the device-associated offset set, combines the trajectory gradient frequency and the operation mutation amplitude, filters the behavior segments that exceed the abnormal threshold, and obtains the device abnormal behavior identification set.

[0023] As a further solution of the present invention, the task scheduling optimization module includes:

[0024] The communication delay detection submodule detects the communication delay index and instruction execution interval index between the production equipment end and the control center end based on the device abnormal behavior identification set, records the communication transmission delay and instruction execution response time respectively, and generates a communication delay data set;

[0025] The low-latency screening submodule calls the communication delay data set, extracts communication delay and instruction execution interval indicators, screens time periods that meet low-latency requirements, identifies signal sending and receiving delays and instruction execution sending and receiving intervals within each period, counts the total number of detections, calculates the intervention time period score, screens low-scoring time intervals based on the score value, and generates a screening time interval list;

[0026] The time period mapping submodule matches the time period corresponding to the abnormal behavior based on the screening time interval list, analyzes the time synchronization mapping relationship, and generates a task scheduling mapping table.

[0027] As a further solution of the present invention, the system further includes:

[0028] The load balancing optimization module calls the task scheduling mapping table, collects the current device load occupancy and abnormal behavior processing requirements, analyzes the ratio between processing requirements and available load capacity, adjusts task priority sorting rules, selects the optimal processing channel and execution time period, and generates a device load balancing tuning table;

[0029] The device load balancing tuning table includes task priority setting, processing channel selection, and execution time arrangement.

[0030] As a further solution of the present invention, the load balancing optimization module includes:

[0031] The load demand collection submodule calls the task scheduling mapping table to collect the real-time task type, processing demand and device load occupancy of the device, detects the load proportion of the task type, and generates the device load demand offset rate based on the load reference rate;

[0032] The dynamic priority adjustment submodule detects tasks whose demand deviation rate exceeds a threshold based on the device load demand deviation rate, processing urgency, and load demand intensity, and reorders tasks based on urgency and deviation amplitude to determine load distribution priorities and obtain a multi-function device task priority sequence;

[0033] The task control allocation submodule extracts the channel parameters and time period parameters in the task scheduling mapping table according to the multi-function device task priority sequence, screens the channels whose load capacity and time period resources meet the requirements, allocates tasks to the optimal processing channel and execution time period, and generates a device load balancing tuning table.

[0034] Compared with the prior art, the advantages and positive effects of the present invention are:

[0035] In the present invention, through the multi-dimensional collaborative collection mechanism of operating data such as temperature fluctuations, pressure changes and flow rate stability, dynamic aggregation of operating status and instant perception of high-frequency changes can be achieved. Through the cross-discrimination method of distribution uniformity and response time, unrepresentative data segments can be effectively screened out, and the accuracy of identifying performance anomalies can be enhanced. Through the time coupling analysis mechanism between trajectory gradient characteristics and offsets, abnormal behavior segments can be locked in advance to achieve forward identification of trend instability phenomena. Combined with the actual fluctuations of communication delays and command responses, the optimal intervention window can be dynamically screened to ensure the effectiveness and synchronization of intervention responses. In conjunction with the real-time evaluation strategy of the matching relationship between processing load and demand, the dynamic regulation of task execution priority and the reasonable allocation of resource channels can be completed, thereby improving the efficiency of fault intervention and the adaptability of resource scheduling, and optimizing overall operation stability and processing continuity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a system flow chart of the present invention;

[0037] Figure 2 This is a flow chart of the operating status acquisition module in the present invention;

[0038] Figure 3 This is a flow chart of the performance deviation evaluation module in the present invention;

[0039] Figure 4 This is a flow chart of the abnormal behavior identification module in the present invention;

[0040] Figure 5 This is a flow chart of the task scheduling optimization module in the present invention;

[0041] Figure 6 This is a flow chart of the load balancing optimization module in the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0043] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0044] See also Figure 1 The real-time monitoring and processing system for inner packaging production data includes:

[0045] The operating status acquisition module uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment to monitor the temperature fluctuation amplitude, pressure change rate, and flow rate stability during equipment operation and generate an equipment operating status set;

[0046] The performance deviation assessment module collects temperature distribution uniformity and pressure response time data based on the equipment operating status set, identifies the matching between the uniformity interval and the response time interval, filters the data segments that deviate from the standard range, and generates the performance deviation monitoring interval;

[0047] The abnormal behavior identification module calls the performance deviation monitoring interval, extracts the pressure change trajectory of the corresponding time period in the pressure detection component, analyzes the temporal correlation between the gradient characteristics of the pressure change trajectory and the temperature distribution offset, filters the abnormal behavior segments, and obtains the device abnormal behavior identification set;

[0048] The task scheduling optimization module detects the communication delay and instruction execution interval between the production equipment and the control center based on the device abnormal behavior identification set, selects the low-latency time period as the intervention window, and synchronously maps the time period corresponding to the abnormal behavior with the intervention window to generate a task scheduling mapping table.

[0049] The load balancing optimization module calls the task scheduling mapping table, collects the current equipment load occupancy and abnormal behavior processing requirements, analyzes the ratio between processing requirements and available load capacity, adjusts task priority sorting rules, selects the optimal processing channel and execution period, and generates a device load balancing tuning table.

[0050] The equipment operation status set includes temperature fluctuation level, pressure change trend, and flow rate stability index; the performance deviation monitoring interval includes uniformity fluctuation range, response time change range, and data deviation segment; the equipment abnormal behavior identification set includes abnormal behavior trajectory, abnormal response mode, and abnormal behavior type; the task scheduling mapping table includes abnormal time node, intervention window, and synchronization correlation information; the equipment load balancing tuning table includes task priority setting, processing channel selection, and execution time schedule.

[0051] See also Figure 2 , the running status acquisition module includes:

[0052] The parameter monitoring submodule uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment. It uses the temperature monitoring component to detect temperature fluctuation data and the pressure detection component to detect pressure change data. It calculates the temperature fluctuation amplitude, pressure change rate, and flow rate stability per unit time, compares them with the baseline values, and generates component parameter offsets.

[0053] Based on the data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment, the temperature monitoring component detects the temperature fluctuation data of the equipment in real time during the operation of the production equipment. For example, on the plastic packaging equipment, the temperature sensor collects temperature data every 1 second and records it as , the pressure detection component detects the pressure change data of the device in real time. For example, the pressure sensor collects pressure data every 1 second and records it as , the flow rate analysis component detects the flow rate data of the device in real time. For example, the flow meter collects flow rate data every 1 second and records it as , calculate the temperature fluctuation amplitude per unit time, specifically the absolute value of the temperature difference between the current time point and the previous time point. For example, if the temperature changes from 200.0℃ to 200.5℃ at a certain moment, the temperature fluctuation amplitude is |200.5-200.0|=0.5℃. Calculate the pressure change rate per unit time, specifically the absolute value of the pressure difference between the current time point and the previous time point divided by the time interval. For example, if the pressure changes from 5.0MPa to 5.2MPa at a certain moment, and the time interval is 1 second, the pressure change rate is |5.2-5.0| / 1=0.2MPa / s. Calculate the flow velocity stability per unit time, specifically The calculation method is the absolute value of the difference between the flow rate at the current time point and the flow rate at the previous time point. For example, if the flow rate changes from 100mL / s to 100.2mL / s at a certain moment, the flow rate stability is |100.2-100.0|=0.2mL / s. The calculation result is then compared with the preset reference value. For example, the calculated temperature fluctuation amplitude of 0.5℃ is compared with the temperature fluctuation reference value of 0.3℃, the pressure change rate of 0.2MPa / s is compared with the pressure change reference value of 0.1MPa / s, and the flow rate stability of 0.2mL / s is compared with the flow rate stability reference value of 0.1mL / s, thereby generating the component parameter offset.

[0054] The state classification submodule calls the component parameter offset and classifies the components according to the temperature fluctuation amplitude, pressure change rate and flow rate stability, according to the set temperature distribution, pressure response and flow rate stability state interval, and marks the corresponding state of the data to obtain the state feedback data set;

[0055] The component parameter offset is used as input. For example, the temperature fluctuation offset is 0.5°C, the pressure change rate offset is 0.2 MPa / s, and the flow rate stability offset is 0.2 mL / s. The offset is classified according to the preset temperature distribution, pressure response, and flow rate stability state interval. The temperature distribution state interval is set as: normal (temperature fluctuation amplitude ≤ 0.3°C), slight fluctuation (0.3°C < temperature fluctuation amplitude ≤ 0.8°C), and significant fluctuation (temperature fluctuation amplitude > 0.8°C). The pressure response state interval is set as: stable (pressure change rate ≤ 0.1 MPa / s), moderate change (0.1 MPa / s < pressure change rate ≤ 0.3 MPa / s), and drastic change (pressure change rate > The flow rate stability state interval is set as follows: stable (flow rate stability ≤ 0.1 mL / s), slightly unstable (0.1 mL / s < flow rate stability ≤ 0.5 mL / s), and severely unstable (flow rate stability > 0.5 mL / s). For example, the current temperature fluctuation amplitude is 0.5°C, which is classified as "slight fluctuation", the pressure change rate is 0.2 MPa / s, which is classified as "medium change", and the flow rate stability is 0.2 mL / s, which is classified as "slightly unstable". The corresponding state of the data is marked, for example, 0.5°C is marked as "slight temperature fluctuation", 0.2 MPa / s is marked as "medium pressure change", and 0.2 mL / s is marked as "slightly unstable flow rate", and a state feedback data set is obtained.

[0056] The instruction generation submodule calls the state feedback data set and selects the equipment to perform resource allocation, task adjustment, and record control actions in the corresponding state based on temperature distribution, pressure response, and flow rate stability state type. It then identifies the corresponding control instructions based on the action threshold associated with the differentiated state and generates the equipment operation state set.

[0057] Call the status feedback data set. For example, the current device status is "slight temperature fluctuation", "medium pressure change", "slight flow rate instability". According to the temperature distribution, pressure response and flow rate stability state type, filter the resource allocation, task adjustment and recording control actions that the device should perform in the corresponding state. For example, when the "slight temperature fluctuation" state is detected, filter the resource allocation action of "adjusting heating power". When the "medium pressure change" state is detected, filter the task adjustment action of "adjusting pump speed". When the "slight flow rate instability" state is detected, filter the recording control action of "recording abnormal log". Identify the corresponding control instructions based on the action threshold associated with the differentiated state. For example, for the "adjusting heating power" action, set the action threshold to a heating power adjustment range of no more than 5%. For the "adjusting pump speed" action, set the action threshold to a pump speed adjustment range of no more than 10%. For the "recording abnormal log" action, set The action threshold is set to trigger recording at a minimum frequency of once per minute. The threshold is set with reference to the historical operating data of the inner packaging production equipment and expert experience. For example, by analyzing the historical operating data of the equipment under different fluctuation levels, it was found that when the temperature fluctuation amplitude exceeds 0.3°C, appropriate adjustment of the heating power can effectively suppress the fluctuation, and when the power adjustment amplitude is within 5%, the impact on product quality is minimal. After multiple experimental verifications, it is reasonable and effective to set the threshold of the heating power adjustment amplitude to 5%. The equipment operation status set is generated based on the threshold. For example, if the current temperature fluctuation amplitude is 0.5°C, the control instruction of "adjusting the heating power to 98% of the current power" is identified. If the pressure change rate is 0.2 MPa / s, the control instruction of "reducing the pump speed by 5%" is identified. If the flow rate stability is 0.2 mL / s, the control instruction of "immediately recording the flow rate abnormality log" is identified.

[0058] See also Figure 3 ,The performance deviation assessment module includes:

[0059] The uniformity identification submodule analyzes the temperature distribution uniformity change rate and uniformity fluctuation amplitude based on the equipment operation status set, selects data segments with low change rate and fluctuation amplitude less than the uniformity stability threshold, and obtains the uniformity stability interval;

[0060] Based on the equipment operation status set, for example, the status set includes the current temperature, pressure, flow rate and other parameters of the equipment, the temperature distribution uniformity change rate and uniformity fluctuation amplitude are analyzed. For example, by comparing the reading differences of multiple temperature sensors at different positions inside the equipment, the change rate is calculated. If the temperature of each point of the equipment changes from 0 to 1 in 3 seconds, the change rate of the temperature distribution uniformity is calculated. ℃、 ℃、 ℃ becomes ℃、 ℃、 ℃, the change rate of each point is 0.1℃ / s, and the uniformity fluctuation amplitude refers to the difference between the maximum and minimum temperature of each measuring point inside the equipment within a period of time. For example, at a certain moment, the internal temperature of the equipment measuring point A is 199.5℃, measuring point B is 200.0℃, and measuring point C is 200.5℃, then the uniformity fluctuation amplitude is 200.5-199.5=1.0℃. Filter out the data segments with low change rate and fluctuation amplitude less than the uniformity stability threshold. Here, "low change rate" is defined as a change rate less than 0.2℃ / s. For example, when the change rate is 0.1℃ / s, the "low change rate" condition is met, and the "uniformity stability threshold" is set to 0. .8℃, this is based on data analysis and experimental verification of historical stable production batches. For example, through statistical analysis of the production data of 20 batches of qualified products, it was found that the temperature uniformity fluctuation amplitude was kept below 0.8℃, and the product quality was stable within this range. Through experimental verification, the threshold was set to 0.8℃. When the fluctuation amplitude was 0.7℃, the condition of "fluctuation amplitude less than uniformity stability threshold" was met. The data segments that met both conditions were identified and obtained. For example, if the temperature distribution uniformity change rate was 0.15℃ / s and the uniformity fluctuation amplitude was 0.6℃ within a certain time period, then this time period was screened out to obtain the uniformity stability interval.

[0061] The response time analysis submodule uses the uniformity stability interval to identify the response time change rate through the synchronously collected pressure response time data, calculate the difference in response time changes, filter out data segments below the response time consistency threshold, and generate the response time consistency interval;

[0062] The uniformity stability interval is taken as input, for example, the obtained stability interval is the time period ,Through the synchronously collected pressure response time data, the response time change rate is identified, for example, in the time period The pressure response time data is collected every 1 second and recorded as The response time change rate is calculated as the absolute value of the difference between the response time at the current time point and the response time at the previous time point. For example, if the response time changes from 0.5 seconds to 0.6 seconds at a certain moment, the change rate is |0.6-0.5|=0.1 seconds. The variability of the response time change is calculated as the standard deviation of all response time change rates within a period of time. For example, the standard deviation of the response time change rate data collected above [0.1, 0.05, 0.02, ...] is calculated, and the data segment below the response time consistency threshold is filtered out. The "response time consistency threshold" here is set to 0.08 seconds. This threshold is obtained by statistically analyzing a large amount of device response time data under normal operating conditions and verified through multiple experiments. For example, the pressure response time under normal operation is monitored for 500 times, and the average and standard deviation of the change rate are calculated. The threshold is set to the average plus 1.5 times the standard deviation to ensure that most normal data is covered. For example, if the calculated variability of the response time change is 0.07 seconds, then the data segment meets the condition and the response time consistency interval is generated.

[0063] The performance deviation screening submodule calls the response time consistency interval and filters the data segments that deviate from the stability threshold and consistency threshold based on the uniformity fluctuation amplitude and response time consistency to generate the performance deviation monitoring interval;

[0064] Take the response time consistency interval as input, for example, the response time consistency interval is the time period ,According to the uniformity fluctuation amplitude and response time consistency, ,the data segments that deviate from the stability threshold and ,the consistency threshold are filtered, for example, in the time period Within the data segment, the uniformity fluctuation range exceeds 0.8°C (stability threshold), or the response time consistency is lower than 0.08 seconds (consistency threshold). For example, if the uniformity fluctuation range of a data segment is 1.2°C, which exceeds the stability threshold of 0.8°C, then the data segment is identified as a deviation. If the response time consistency of a data segment is 0.05 seconds, which is lower than the consistency threshold of 0.08 seconds, then the data segment is also identified as a deviation. The data segments that meet both the deviation conditions are screened out to generate a performance deviation monitoring interval.

[0065] See also Figure 4 ,The abnormal behavior recognition module includes:

[0066] The trajectory extraction submodule calls the performance deviation monitoring interval, extracts the pressure detection component data, extracts the pressure change points and operation change values ​​according to the timestamp, and organizes them into a synchronous data structure to generate a synchronous pressure trajectory set;

[0067] The performance deviation monitoring interval is taken as input, for example, the performance deviation monitoring interval is the time period , extract the pressure detection component data within the time period, for example, extract the pressure detection component data within the time period from the pressure sensor database All pressure data points recorded in , extract the pressure change point and operation change value corresponding to each pressure data point according to the timestamp, for example, for the pressure data point (Time stamp is , pressure value is 5.5MPa), extract it in The pressure value at the moment of the operation is combined with the equipment operation record at the same time stamp. For example, the operation record is displayed in The valve opening is adjusted once at the time, and the operation change value is +10%. The data is organized into a synchronous data structure, and the pressure change value is mapped to the corresponding operation change value and time stamp. For example, a structured data pair is formed: [( , , operation change value 1), ( , , operation change value 2), ...], generating a set of synchronized pressure trajectories.

[0068] The time series correlation calculation submodule calls the synchronized pressure trajectory set, identifies the pressure trajectory gradient characteristics of the temperature distribution change sequence and the normalized change rate of the temperature distribution offset, and uses the formula:

[0069] ;

[0070] Calculate the normalized index value of the pressure trajectory offset, compensate for the impact of operational changes by superimposing offset terms, filter time segments above the abnormal offset threshold, and generate a device-associated offset set;

[0071] in, Represents the normalized index value of the pressure trajectory offset, Represents the temperature change sequence The pressure trajectory change value corresponding to the temperature gradient of the point, Represents the temperature change sequence The pressure weight factor of each point, represents the mean of the current temperature distribution, Indicates the The mean temperature distribution of the temperature sampling points, Indicates the normalized rate of change of the current temperature distribution offset, represents the total number of temperature sampling points involved in gradient identification within the sequence;

[0072] Calling the synchronized pressure trajectory set, for example, the synchronized pressure trajectory set contains a series of pressure change points and operation change values ​​with timestamps, by identifying the pressure trajectory gradient characteristics of the temperature distribution change sequence and the normalized change rate of the temperature distribution offset. Here, the temperature distribution change sequence refers to a series of continuous temperature measurement values, and its pressure trajectory gradient characteristic is the degree of influence of temperature change on pressure change. By calculating the pressure change value corresponding to each temperature sampling point For example, when the temperature changes from 200℃ to 201℃, the pressure changes from 5.0MPa to 5.1MPa, then the pressure trajectory change value corresponding to the temperature gradient is is 0.1MPa / ℃, and the normalized change rate of temperature distribution offset is Indicates the relative change between the current temperature distribution and the temperature distribution at the previous moment. For example, if the current temperature average is 200°C and the previous temperature average was 199.5°C, then , the parameter is used to calculate the normalized index value of the pressure trajectory offset by the following formula:

[0073] ,in, Represents the normalized index value of the pressure trajectory offset, which measures the degree of deviation of the pressure trajectory from the ideal state. The larger the value, the more abnormal the pressure behavior. Represents the temperature change sequence The pressure trajectory change value corresponding to the temperature gradient of each point quantifies the immediate impact of temperature change on pressure. Represents the temperature change sequence The pressure weight factor of each point is used to adjust the contribution of different temperature points to the total pressure deviation. For example, the temperature change in the key area has a higher weight. Indicates the mean of the current temperature distribution, for example, the average value of multiple temperature sensor readings inside the current device, as a representative of the current overall temperature state. Indicates the The mean value of the temperature distribution of the temperature sampling points is used to compare with the current mean value. Comparison is performed to identify instantaneous shifts in temperature distribution, Indicates the normalized rate of change of the current temperature distribution offset, which is used to measure the severity of the temperature distribution change. Through normalization, it makes it comparable under different equipment and working conditions. Indicates the total number of temperature sampling points involved in gradient identification in the sequence, ranging from 5 to 15. In this embodiment, it is set to , summation symbol Express The pressure trajectory change value corresponding to the temperature gradient at each sampling point Its pressure weight factor The purpose is to comprehensively consider the influence of multiple temperature points on the pressure trajectory. " means to subtract a term from the accumulated result. , used to compensate for pressure changes caused by instantaneous offsets in temperature distribution, square root symbol and the absolute value symbol It ensures the non-negativity of the compensation term and reflects the degree of deviation. The division sign " " means dividing the numerator (the absolute value of the difference between the accumulated result and the compensation term) by the denominator , 1 is added to the denominator to avoid division by zero, and to use Normalize the offset to reduce the temperature change rate The direct impact on the final result makes the result more robust, for example, when When the temperature gradient corresponds to the pressure trajectory change value MPa / ℃, MPa / ℃, MPa / ℃, pressure weighting factor 、 、 , the mean of the current temperature distribution ℃, the mean temperature distribution of the previous temperature sampling point ℃, the normalized change rate of the current temperature distribution offset ,So:

[0074] ;

[0075] ;

[0076] ;

[0077] The benefit of the formula is that by introducing the pressure trajectory change value corresponding to the temperature gradient and pressure weighting factor , can more precisely capture the instantaneous effect of temperature change on pressure, and at the same time Compensate for the instantaneous offset of temperature distribution and normalize the rate of change Normalization is performed so that the calculated pressure trajectory offset This method can more accurately reflect the true degree of equipment abnormality under complex operating conditions and reduce false alarms. The results show that the normalized pressure trajectory offset index value is 0.6145. This value is a measure of the degree of pressure trajectory abnormality. By superimposing the effects of operational changes, for example, if the synchronized pressure trace records an operation that increases valve opening by 10%, resulting in a pressure increase of 0.5 MPa, this 0.5 MPa is added as a compensation term to the calculated P to eliminate the interference of operational changes on the pressure trajectory offset, thereby more accurately identifying pressure anomalies caused by non-operational factors. Time segments above the abnormal offset threshold are screened. The "abnormal offset threshold" here is set to 0.5. This is achieved by analyzing large amounts of historical data and comparing it with equipment failure cases. For example, when the P value exceeds 0.5, the probability of abnormal equipment behavior increases significantly. Using 0.5 as a threshold can effectively identify potential anomalies. If the calculated pressure trajectory offset normalized index value P is 0.6145, which is higher than the abnormal offset threshold of 0.5, the time segment is screened out to generate the device-associated offset set.

[0078] The abnormal behavior collection submodule calls the device-associated offset set, combines the trajectory gradient frequency and the operation mutation amplitude, filters the behavior segments that exceed the abnormal threshold, and obtains the device abnormal behavior identification set;

[0079] The device-associated offset set is called. For example, the device-associated offset set contains a series of time segments exceeding the abnormal offset threshold. The trajectory gradient frequency and operational mutation amplitude are combined to screen for behavioral segments exceeding the abnormal threshold. For example, if the frequency of pressure trajectory gradients in a certain time segment exceeds three times within 10 seconds, and the operational mutation amplitude (for example, valve opening changes by more than 20% within 1 second) exceeds a preset threshold of 15%, the behavior segment is considered to exceed the abnormal threshold. The setting of the "abnormal threshold" here comprehensively considers the inherent characteristics of the equipment, production process requirements, and historical failure data. For example, through monitoring of long-term equipment operation data, it is found that when the trajectory gradient frequency exceeds two times within 10 seconds and the operational mutation amplitude exceeds 10%, the risk of equipment failure increases significantly. After repeated experiments and actual verification, the thresholds are set to three times and 15%, respectively. For example, if the trajectory gradient frequency of a time segment in the device-associated offset set is four times / 10 seconds and the operational mutation amplitude is 25%, the segment is screened as abnormal behavior, resulting in the device abnormal behavior identification set.

[0080] See also Figure 5 , the task scheduling optimization module includes:

[0081] The communication delay detection submodule detects the communication delay index and instruction execution interval index between the production equipment and the control center based on the equipment abnormal behavior identification set, records the communication transmission delay and instruction execution response time respectively, and generates a communication delay data set;

[0082] Based on the device abnormal behavior identification set, for example, the abnormal behavior identification set indicates that the device has abnormal behavior in a specific time period, the communication delay index and the instruction execution interval index between the production device and the control center are detected. For example, during the time period when the abnormal behavior is identified, the time difference from the production device sending the data packet to the control center receiving the data packet is recorded as the communication transmission delay. For example, the production device Send a data packet at every moment, the control center When the data packet is received at time , the communication transmission delay is milliseconds, and simultaneously record the time from when the control center issues a command to when the production equipment executes the command and returns a confirmation message, as the command execution response time. For example, the control center Instructions are issued at all times, and production equipment is The instruction execution is completed and confirmation is returned at the moment, then the instruction execution response time is milliseconds, respectively record the communication transmission delay and instruction execution response time to generate a communication delay dataset.

[0083] The low-latency screening submodule calls the communication delay dataset and uses the formula:

[0084] ;

[0085] Identify communication delay and instruction execution interval indicators, screen time periods that meet low latency requirements, identify signal sending and receiving delays and instruction execution sending and receiving intervals within each period, calculate the total number of detections, calculate the intervention time period score, screen low-scoring time intervals based on the score value, and generate a list of screened time intervals;

[0086] in, represents the communication delay and instruction execution interval indicators, Represents the total number of communication and instruction interactions during this time period. Represents the first Communication delay time, Represents the average value of all communication delays within this time period. Represents the first The interval between instruction executions, Represents the first The time difference between the secondary command response and the communication trigger;

[0087] Call the communication delay dataset, for example, the communication delay dataset contains multiple sets of communication transmission delays and instruction execution response time , identify the communication delay and instruction execution interval indicators through the following formula, and filter the time period that meets the low latency requirement: ,in, Represents the communication delay and instruction execution interval indicators. The smaller the indicator value, the better the communication delay and instruction execution interval performance. Represents the total number of communication and command interactions within the time period. For example, within a 5-minute time period, there are 100 data interactions. Represents the first For example, the 50th communication delay is 25 milliseconds. Represents the average value of all communication delays in this time period. The average value is obtained, for example, the average communication delay is 22 milliseconds, Represents the first The interval between instruction executions is 60 milliseconds. For example, the interval between the 50th instruction execution is 60 milliseconds. Represents the first The time difference between the command response and the communication trigger. For example, after the control center sends a command, the time difference between the actual response of the command and the communication trigger on the device side is very small. It is used to accurately measure the degree of synchronization between the actual execution of the command and the communication event. The summation symbol Express In the communication and instruction interaction, the specific items of each interaction Perform accumulation, the numerator of the accumulated term Indicates the combined effect of communication delay and instruction execution efficiency. Communication delay Directly affects the response speed, and The total time taken to execute the instruction is taken into account, minus sign " In the denominator It is used to calculate the absolute deviation of a single communication delay from the average delay. Adding 1 is to avoid division by zero and increase the stability of the denominator, so that there is a smoother penalty for delays that deviate from the average value. The absolute value symbol Ensure the final indicator It is a non-negative value, indicating that it is a magnitude of a performance indicator, not a directionality;

[0088] The formula is beneficial in that by introducing the average communication delay Delay in single communication Normalization is performed so that the indicator can more comprehensively evaluate the overall stability and consistency of communication delay, while taking into account the instruction execution interval. The time difference between command response and communication trigger , so that the indicator can more accurately reflect the response performance of the device in actual operation. For example, assuming that in a certain period of time, the total number of interactions , communication delay time Milliseconds, instruction execution interval Milliseconds, the time difference between command response and communication trigger milliseconds, first calculate the average communication delay millisecond;

[0089] for ;

[0090] for ;

[0091] for ;

[0092] ;

[0093] ;

[0094] The results show that the communication delay and instruction execution interval indicators For 80.201, filter the time period that meets the low latency requirement. Here, "low latency requirement" is defined as The value is lower than 100. This threshold is verified by experiments based on the real-time control requirements of production equipment and historical stable operation data. For example, by testing under various network loads and equipment operation modes, it is found that when When the value is lower than 100, the equipment control response is timely, and the production efficiency and product quality are maintained at a high level. When the value is 80.201, the "low latency requirement" is met. The signal sending and receiving delays and the instruction execution sending and receiving intervals within each segment are identified, and the total number of detections is counted. The intervention time period score is calculated. For example, for each time period that meets the low latency requirement, the signal sending delay is recorded as 2 milliseconds, the signal receiving delay is 3 milliseconds, the instruction execution sending interval is 5 milliseconds, and the instruction execution receiving interval is 10 milliseconds. The total number of detections within the time period is counted as 1000. Based on the data, the intervention time period score is calculated. For example, the score calculation formula is: Score = (Signal Sending Delay + Signal Receiving Delay + Instruction Execution Sending Interval + Instruction Execution Receiving Interval) / Total Number of Detections × 100. Substituting the data into the calculation: Score = (2 + 3 + 5 + 10) / 1000 × 100 = 20 / 1000 × 100 = 2. Low-scoring time intervals are filtered based on the score value. Here, "low score" is defined as a score value less than 5. For example, when the score value is 2, the "low score" condition is met, and a list of filtered time intervals is generated.

[0095] The time period mapping submodule filters the time interval list, matches the time period corresponding to the abnormal behavior, analyzes the time synchronization mapping relationship, and generates a task scheduling mapping table;

[0096] Based on the screening time interval list, for example, the screening time interval list contains multiple time periods that meet the low latency requirement, match the time period corresponding to the abnormal behavior, for example, compare each time period in the screening time interval list with the abnormal behavior time period in the previously identified device abnormal behavior identification set, for example, there is a time period in the screening time interval list If there is an abnormal behavior time period in the abnormal behavior identification set , and there is overlap between these two time periods, for example and If there is an intersection, the abnormal behavior is considered to be associated with the low-latency time period, and the time synchronization mapping relationship is analyzed. For example, the specific time points of the overlapping parts are further analyzed to determine the specific time of the low-latency time period when the abnormal behavior occurs. For example, if the abnormal behavior occurs at Moment (at inside), and Also falls Inside, then and Establish a mapping relationship and generate a task scheduling mapping table.

[0097] See also Figure 6 , the load balancing optimization module includes:

[0098] The load demand collection submodule calls the task scheduling mapping table to collect the device's real-time task type, processing requirements, and device load occupancy, detects the load proportion of the task type, and generates the device load demand offset rate based on the load benchmark rate;

[0099] The task scheduling mapping table is called. For example, the task scheduling mapping table indicates abnormal behavior and corresponding low-latency time intervals within a specific time period. The real-time task type, processing requirements, and device load occupancy of the device are collected. For example, during a certain time period, the device is executing the "injection molding" task type with a processing requirement of producing 100 parts per minute. The current device load occupancy is 80%. The load proportion of the task type is detected. For example, the current "injection molding" task accounts for 60% of the total load. According to the preset load base rate, the "load base rate" here is set to 70%. This value is set based on the device's rated maximum load capacity and long-term stable operation historical data. For example, by evaluating the energy consumption, wear, and production efficiency of the device under different loads, it is found that when the load rate is maintained at around 70%, the device operating efficiency is the highest and the failure rate is the lowest. Therefore, 70% is set as the base rate. For example, if the current device load occupancy is 80% and the load base rate is 70%, the device load demand offset rate is (80% - 70%) / 70% ≈ 14.3%, which is the device load demand offset rate.

[0100] The dynamic priority adjustment submodule detects tasks whose demand deviation rate exceeds the threshold based on the equipment load demand deviation rate, processing urgency and load demand intensity, and reorders them according to the urgency and deviation amplitude to determine the load distribution priority and obtain the multi-functional equipment task priority sequence;

[0101] Based on the equipment load demand deviation rate (for example, the current equipment load demand deviation rate is 14.3%), tasks with a demand deviation rate exceeding a threshold are detected based on processing urgency and load demand intensity. The "threshold" here is set to 10%. This threshold is determined by analyzing historical production data and identifying when the load deviation rate exceeds this value, equipment performance begins to decline significantly or production tasks cannot be completed on time. Experimental verification shows that setting the threshold at 10% can effectively warn of potential load issues. For example, if the current task's demand deviation rate is 14.3%, exceeding the threshold of 10%, the task is identified as having a demand deviation rate exceeding the threshold. The load distribution priority is determined by reordering the task based on urgency and deviation magnitude. For example, if there are two tasks A and B, task A has high urgency and a deviation magnitude of 15%, while task B has medium urgency and a deviation magnitude of 12%, then task A has higher priority than task B. The priority sorting rule is: the task with higher urgency takes precedence; if the urgency is the same, the task with larger deviation magnitude takes precedence, thus obtaining a priority sequence for multifunctional equipment tasks.

[0102] The task control allocation submodule extracts the channel parameters and time period parameters in the task scheduling mapping table according to the multi-function device task priority sequence, selects the channels whose load capacity and time period resources meet the requirements, allocates tasks to the optimal processing channel and execution time period, and generates a device load balancing tuning table;

[0103] According to the priority sequence of the multi-function device tasks, for example, the priority sequence is: Task A (priority 1), Task B (priority 2), Task C (priority 3), extract the channel parameters and time period parameters in the task scheduling mapping table. For example, for Task A, the channels that can be assigned are "Channel 1" and "Channel 2" extracted from the task scheduling mapping table, and the executable time period is , filter the channels whose load capacity and time period resources meet the requirements. For example, if the current load capacity of "channel 1" is 90%, The resource idle rate within the time period is 85%, and the processing demand of Task A requires 50% load capacity and 60% resource idle rate, then "Channel 1" meets the demand. If the load capacity of "Channel 2" is 40% and the resource idle rate is 50%, then "Channel 2" does not meet the demand of Task A. Assign tasks to the optimal processing channel and execution time period. The "optimal" here is based on a comprehensive consideration of load balancing and resource utilization. For example, under the premise of meeting the task requirements, select the channel and time period that can make the overall load of the device more balanced and the resource utilization higher. For example, if "Channel 1" meets the requirements of Task A and after allocating it to "Channel 1", the overall device load rate is 75%, which can make the load rate closer to the benchmark value of 70% than allocating it to the channel that meets the requirements. Then assigning Task A to "Channel 1" is more effective. Generate a device load balancing tuning table for each time period.

[0104] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. Real-time monitoring and processing system for inner packaging production data, characterized by: The system comprises: The operating status acquisition module uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment to monitor the temperature fluctuation amplitude, pressure change rate, and flow rate stability during equipment operation and generate an equipment operating status set; The performance deviation evaluation module collects temperature distribution uniformity and pressure response time data based on the equipment operation status set, identifies the matching between the uniformity interval and the response time interval, filters the data segments that deviate from the standard range, and generates a performance deviation monitoring interval; The performance deviation assessment module includes: The uniformity identification submodule analyzes the temperature distribution uniformity change rate and uniformity fluctuation amplitude based on the equipment operation status set, selects data segments with low change rate and fluctuation amplitude less than the uniformity stability threshold, and obtains the uniformity stability interval; The response time analysis submodule calls the uniformity stability interval, identifies the response time change rate through the synchronously collected pressure response time data, obtains the difference in response time change, filters the data segments below the response time consistency threshold, and generates the response time consistency interval; The performance deviation screening submodule calls the response time consistency interval, and screens the data segments that deviate from the stability threshold and the consistency threshold according to the uniformity fluctuation amplitude and the response time consistency, thereby generating a performance deviation monitoring interval; The abnormal behavior identification module calls the performance deviation monitoring interval, extracts the pressure change trajectory of the corresponding time period in the pressure detection component, analyzes the time correlation between the gradient characteristics of the pressure change trajectory and the temperature distribution offset, filters the abnormal behavior fragments, and obtains the device abnormal behavior identification set; The task scheduling optimization module detects the communication delay index and instruction execution interval index between the production equipment end and the control center end based on the equipment abnormal behavior identification set, selects the low-latency time period as the intervention window, synchronously maps the time period corresponding to the abnormal behavior with the intervention window, and generates a task scheduling mapping table.

2. The real-time monitoring and processing system for inner packaging production data according to claim 1, characterized in that: The equipment operation status set includes temperature fluctuation level, pressure change trend, and flow rate stability index; the performance deviation monitoring interval includes uniformity fluctuation range, response time change range, and data deviation segment; the equipment abnormal behavior identification set includes abnormal behavior trajectory, abnormal response mode, and abnormal behavior type; the task scheduling mapping table includes abnormal time node, intervention window, and synchronization association information.

3. The real-time monitoring and processing system for inner packaging production data according to claim 1, characterized in that: The operating status acquisition module includes: The parameter monitoring submodule uses data from the temperature monitoring component, pressure detection component, and flow rate analysis component in the inner packaging production equipment. It uses the temperature monitoring component to detect temperature fluctuation data and the pressure detection component to detect pressure change data. It calculates the temperature fluctuation amplitude, pressure change rate, and flow rate stability per unit time, compares them with the baseline values, and generates component parameter offsets. The state classification submodule calls the component parameter offset, classifies the components according to the temperature fluctuation amplitude, pressure change rate and flow rate stability, and sets the temperature distribution, pressure response and flow rate stability state interval, and marks the corresponding state of the data to obtain a state feedback data set; The instruction generation submodule calls the state feedback data set, and according to the temperature distribution, pressure response and flow rate stable state type, screens the equipment execution resource allocation, task adjustment and recording control actions in the corresponding state, identifies the corresponding control instructions based on the action threshold associated with the differentiated state, and generates the equipment operation state set.

4. The real-time monitoring and processing system for inner packaging production data according to claim 1, characterized in that: The abnormal behavior identification module includes: The trajectory extraction submodule calls the performance deviation monitoring interval, extracts the pressure detection component data, extracts the pressure change points and operation change values ​​according to the timestamps, and organizes them into a synchronous data structure to generate a synchronous pressure trajectory set; The time series association calculation submodule calls the synchronized pressure trajectory set, calculates the normalized index value of the pressure trajectory offset by identifying the pressure trajectory gradient characteristics of the temperature distribution change sequence and the normalized change rate of the temperature distribution offset, compensates for the impact of operational changes by superimposing offset terms, and filters time segments above the abnormal offset threshold to generate a device-associated offset set; The abnormal behavior collection submodule calls the device-associated offset set, combines the trajectory gradient frequency and the operation mutation amplitude, filters the behavior segments that exceed the abnormal threshold, and obtains the device abnormal behavior identification set.

5. The real-time monitoring and processing system for inner packaging production data according to claim 4, characterized in that: The task scheduling optimization module includes: The communication delay detection submodule detects the communication delay index and instruction execution interval index between the production equipment end and the control center end based on the device abnormal behavior identification set, records the communication transmission delay and instruction execution response time respectively, and generates a communication delay data set; The low-latency screening submodule calls the communication delay data set, identifies the communication delay and instruction execution interval indicators, screens the time periods that meet the low-latency requirements, identifies the signal sending and receiving delays and the instruction execution sending and receiving intervals in each period, and counts the total number of detections, calculates the intervention time period score, screens the low-scoring time intervals according to the score value, and generates a screening time interval list; The time period mapping submodule matches the time period corresponding to the abnormal behavior based on the screening time interval list, analyzes the time synchronization mapping relationship, and generates a task scheduling mapping table.

6. The real-time monitoring and processing system for inner packaging production data according to claim 1, characterized in that: The system also includes: The load balancing optimization module calls the task scheduling mapping table, collects the current device load occupancy and abnormal behavior processing requirements, analyzes the ratio between processing requirements and available load capacity, adjusts task priority sorting rules, selects the optimal processing channel and execution time period, and generates a device load balancing tuning table; The device load balancing tuning table includes task priority setting, processing channel selection, and execution time arrangement.

7. The real-time monitoring and processing system for inner packaging production data according to claim 6, characterized in that: The load balancing optimization module includes: The load demand collection submodule calls the task scheduling mapping table to collect the real-time task type, processing demand and device load occupancy of the device, detects the load proportion of the task type, and generates the device load demand offset rate based on the load reference rate; The dynamic priority adjustment submodule detects tasks whose demand deviation rate exceeds a threshold based on the device load demand deviation rate, processing urgency, and load demand intensity, and reorders tasks based on urgency and deviation amplitude to determine load distribution priorities and obtain a multi-function device task priority sequence; The task control allocation submodule extracts the channel parameters and time period parameters in the task scheduling mapping table according to the multi-function device task priority sequence, screens the channels whose load capacity and time period resources meet the requirements, allocates tasks to the optimal processing channel and execution time period, and generates a device load balancing tuning table.

Images