A Smart Monitoring System for Dynamic Environmental Parameters of a Marine Biopharmaceutical Production Line

Abstract

This invention provides an intelligent monitoring system for dynamic environmental parameters in a marine biopharmaceutical production line, belonging to the field of computer data processing technology. By employing a closed-loop monitoring method centered on dynamic environmental state consensus and integrating multi-model collaborative early warning and adaptive selection of control strategies, it achieves highly reliable perception of production environment parameters, proactive risk warning, and intelligent and stable control. This invention solves the fundamental problem of multi-source heterogeneous data conflict and drift by constructing a closed-loop monitoring architecture centered on dynamic environmental state consensus and integrating multi-model early warning and adaptive control. It avoids the defects of unreliable decision-making basis caused by single sensor failure or data inconsistency, providing accurate data input for the entire control and regulation system and improving the system's perception reliability.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to an intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line. Background Technology

[0002] Marine biopharmaceutical production, such as the fermentation and culture of marine microorganisms or cells to prepare active substances, is a highly complex and precise biochemical process. The success of this process, as well as the yield and quality of the product, largely depends on the precise control of various dynamic parameters within the production environment. These parameters include temperature, pH, dissolved oxygen, nutrient concentration, and metabolite concentration. To ensure production stability and batch-to-batch consistency, production lines are typically equipped with comprehensive automated monitoring and control systems.

[0003] Existing monitoring and control systems typically involve installing multiple environmental parameter sensors of different types on key equipment such as reactors to collect data in real time. Then, they use classical control algorithms such as proportional-integral-derivative to adjust actuators, such as heaters, feed pumps, and venting valves, to maintain the stability of environmental parameters.

[0004] Existing technologies have several inherent technical defects in practical applications. During long-term operation, various sensors are affected by factors such as aging and media contamination, and their measurement data inevitably experience slow drift or sudden inaccuracies. When multiple sensors provide conflicting readings, existing systems lack an effective arbitration mechanism to determine the true operating conditions, leaving room for improvement. Summary of the Invention

[0005] This invention provides an intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line. By adopting a closed-loop monitoring method that takes dynamic environmental state consensus as its core and integrates multi-model collaborative early warning and adaptive selection of control strategies, it can achieve highly reliable perception of production environment parameters, forward-looking risk warning, and intelligent and stable control.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a dynamic environmental parameter intelligent monitoring system for a marine biopharmaceutical production line is provided, comprising: The multi-source data acquisition module is configured to acquire real-time raw data collected by multiple environmental parameter sensors in the production line, as well as process models describing the theoretical relationships between parameters, as the basis for constructing a multi-source dataset. The consensus generation engine is configured to calculate the dynamic confidence weights of each data source through real-time consistency game based on the real-time raw data and the process model, and to fuse and generate a dynamic environmental state consensus that represents the current real state of the environment, and to evaluate the reliability of the current consensus to generate the overall confidence level of the system. The intelligent early warning center includes a time-series prediction unit and a pattern recognition unit. It is configured to input the dynamic environmental state consensus into the time-series prediction model and the pattern recognition model respectively, generate predicted risk signals and pattern anomaly signals, and perform fusion and mutual verification on the predicted risk signals and the pattern anomaly signals to generate graded early warning instructions. The pattern recognition unit is also configured to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals, and feed the sensor performance evaluation signals back to the dynamic confidence weight calculation process of the consensus generation engine for correction. An adaptive controller is configured to receive the dynamic environment state consensus, the hierarchical early warning instructions, and the overall system confidence level provided by the consensus generation engine, and adaptively select a control strategy and generate consensus-driven control instructions. The consensus generation engine, the intelligent early warning center, and the adaptive controller form a closed-loop linkage through the dynamic environmental state consensus and the sensor performance evaluation signal.

[0007] Optionally, the consensus generation engine is specifically configured to calculate the dynamic confidence weights of each data source and generate a dynamic environment state consensus as follows: The theoretical predictions based on the current operating parameters are obtained from the process model and used together with the real-time raw data as the data source. Calculate the real-time deviation between each data source and all other data sources and theoretical predictions; The dynamic confidence weight is calculated by combining the historical consistency performance of each data source with the real-time deviation. The readings from all data sources are weighted and fused according to the dynamic confidence weight to generate the dynamic environment state consensus.

[0008] Optionally, the tiered early warning instructions include comprehensive early warning instructions, intermediate early warning instructions, and low-level early warning instructions; the intelligent early warning center is specifically configured to perform fusion and mutual verification and generate tiered early warning instructions as follows: The predicted risk signal is quantified as the deviation of future parameter trajectory, and the pattern anomaly signal is quantified as the deviation of the current overall state; When both the deviation of the future parameter trajectory and the deviation of the current overall state exceed their respective critical thresholds, the highest level of comprehensive early warning instruction is generated; When only the deviation of the future parameter trajectory exceeds the warning threshold, a medium-level early warning instruction suggesting continuous observation is generated; When only the deviation of the current overall state exceeds the warning threshold, a low-level warning instruction is generated to trigger targeted diagnosis.

[0009] Optionally, it also includes a model self-update module, configured as follows: When the internal consistency of the consensus in the dynamic environment state remains above a stable threshold, the current time period is determined to be a high-quality learning window. The consensus sequence of dynamic environment states generated during the high-quality learning window is used to construct incremental training samples; The incremental training samples are used to perform online incremental updates of the temporal prediction model in the temporal prediction unit and the pattern recognition model in the pattern recognition unit.

[0010] Optionally, the consensus generation engine is further configured to: calculate the dynamic confidence weights. Receive the sensor performance evaluation signal fed back from the pattern recognition unit; Based on the fault mode information contained in the sensor performance evaluation signal, a penalty factor is introduced into the calculation of the real-time deviation of a specific sensor. By utilizing the real-time deviation after introducing the penalty factor, the dynamic confidence weight of the specific sensor is reduced more quickly.

[0011] Optionally, when selecting a control strategy and generating consensus-driven control commands, the adaptive controller is specifically configured as follows: Strategy selection is based on the overall confidence level of the system, specifically the evaluation value calculated based on the uniformity and stability of the distribution of the dynamic confidence weights. When the overall confidence level of the system is higher than the first confidence threshold, a fine-grained control strategy aimed at optimizing production efficiency is selected, and a first control command is generated. When the overall confidence level of the system is between the first confidence threshold and the second confidence threshold, a robust control strategy with parameter stability as the objective is selected, and a second control command is generated. When the overall confidence level of the system is lower than the second confidence threshold, a conservative control strategy with the goal of ensuring safety is selected, and a third control command is generated.

[0012] Optionally, it also includes a forward-looking maintenance module, configured as follows: The dynamic confidence weights of each environmental parameter sensor are continuously recorded to form a dynamic confidence weight change curve; Analyze the dynamic confidence weight change curve to identify whether there is a weight decay trend that conforms to the characteristics of performance degradation; When the weight decay trend is detected, a predictive maintenance work order is generated before the sensor readings exceed the physical tolerance range.

[0013] Optionally, the execution of the robust control strategy creates a safe buffer period for the system; the system is configured to: During the safety buffer period, the adaptive controller triggers an enhanced diagnostic process for environmental parameter sensors whose dynamic confidence weights are below the diagnostic threshold. In the enhanced diagnostic process, the pattern recognition unit is used first to confirm the fault mode of the target sensor.

[0014] Optionally, the model self-update module works in conjunction with the forward-looking maintenance module, specifically configured as follows: The model self-updating module adds a verification condition to the conditions for determining the high-quality learning window, namely, querying the forward-looking maintenance module to confirm that no predictive maintenance work order has been generated in the past health check cycle; In the step of constructing the incremental training samples, the model self-updating module labels and downweights the data contributed by the sensors that have generated the predictive maintenance work orders.

[0015] Secondly, a method for intelligent monitoring of dynamic environmental parameters in a marine biopharmaceutical production line is provided, including the following steps: Acquire real-time raw data collected by multiple environmental parameter sensors in the production line and process models describing the theoretical relationships between parameters as the basis for constructing a multi-source dataset; Based on the real-time raw data and the process model, the dynamic confidence weights of each data source are calculated through real-time consistency game theory, and then fused to generate a dynamic environmental state consensus that represents the true state of the current environment. The dynamic environment state consensus is input into the time series prediction model and the pattern recognition model to generate prediction risk signals and pattern anomaly signals, respectively. The predicted risk signal and the pattern anomaly signal are fused and cross-verified to generate a graded early warning instruction; Based on the dynamic environment state consensus and the hierarchical early warning instructions, and combined with the overall system confidence level generated by assessing the reliability of the current consensus, the control strategy is adaptively selected and consensus-driven control instructions are generated. The pattern recognition model is also used to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals. The sensor performance evaluation signals are fed back to the calculation process of the dynamic confidence weights for correction.

[0016] Thirdly, an electronic device is provided, comprising: a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the electronic device to perform the intelligent monitoring system for dynamic environmental parameters of the marine biopharmaceutical production line described in the first aspect.

[0017] In one possible design, the electronic device described in the third aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the electronic device described in the third aspect and other electronic devices.

[0018] In the embodiments of the present invention, the electronic device described in the third aspect may be a terminal, or a chip (system) or other component or assembly disposed in the terminal, or a system containing the terminal.

[0019] Fourthly, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer causes the computer to perform the intelligent monitoring system for dynamic environmental parameters of the marine biopharmaceutical production line described in the first aspect.

[0020] In summary, the above methods and systems have the following technical effects: This invention addresses the fundamental problems of conflict and drift in multi-source heterogeneous data by constructing a closed-loop monitoring architecture centered on dynamic environmental state consensus and integrating multi-model early warning and adaptive control. It avoids the unreliability of decision-making bases caused by single sensor failures or data inconsistencies, providing accurate data input for the entire control and regulation system and improving the system's perception reliability. By combining a dual early warning mechanism of time-series trend prediction and overall pattern recognition, it achieves a shift from passive threshold alarms to proactive risk prediction, identifying potential deterioration trends of single parameters and complex anomalies composed of small changes in multiple parameters in advance. This significantly improves the foresight and accuracy of early warnings, avoiding production losses due to alarm lag. Based on a quantitative assessment of the current data's reliability, it executes refined optimization control when the data is highly reliable and automatically switches to robust safety control when data uncertainty exists, ensuring the system makes reasonable adjustment responses and enhancing the intelligence and operational robustness of the entire production process control. Attached Figure Description

[0021] Figure 1 A flowchart illustrating the intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line provided in this embodiment of the invention. Detailed Implementation

[0022] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0023] In this embodiment of the invention, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In specific implementation, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a correlation between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0024] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be elaborated upon here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In specific implementation, the required indication method can be selected according to specific needs. This embodiment of the invention does not limit the selected indication method; therefore, the indication methods involved in this embodiment of the invention should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0025] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this embodiment of the invention. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0026] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This embodiment of the invention does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or electronic device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or electronic device. The type of memory can be any form of storage medium, and this embodiment of the invention does not limit this.

[0027] In the embodiments of this invention, the “protocol” may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to the intelligent monitoring system for dynamic environmental parameters of future marine biopharmaceutical production lines. The embodiments of this invention do not specifically limit this.

[0028] In this embodiment of the invention, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0029] In the description of the embodiments of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this invention, words such as "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0030] The network architecture and business scenarios described in the embodiments of this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0031] Figure 1 This is a system structure block diagram provided in an embodiment of the present invention. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line includes: The multi-source data acquisition module is configured to acquire real-time raw data collected by multiple environmental parameter sensors in the production line, as well as process models describing the theoretical relationships between parameters, as the basis for constructing a multi-source dataset. The consensus generation engine is configured to calculate the dynamic confidence weights of each data source through real-time consistency game based on the real-time raw data and the process model, and to fuse and generate a dynamic environmental state consensus that represents the current real state of the environment, and to evaluate the reliability of the current consensus to generate the overall confidence level of the system. The intelligent early warning center includes a time-series prediction unit and a pattern recognition unit. It is configured to input the dynamic environmental state consensus into the time-series prediction model and the pattern recognition model respectively, generate predicted risk signals and pattern anomaly signals, and perform fusion and mutual verification on the predicted risk signals and the pattern anomaly signals to generate graded early warning instructions. The pattern recognition unit is also configured to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals, and feed the sensor performance evaluation signals back to the dynamic confidence weight calculation process of the consensus generation engine for correction. An adaptive controller is configured to receive the dynamic environment state consensus, the hierarchical early warning instructions, and the overall system confidence level provided by the consensus generation engine, and adaptively select a control strategy and generate consensus-driven control instructions. The consensus generation engine, the intelligent early warning center, and the adaptive controller form a closed-loop linkage through the dynamic environmental state consensus and the sensor performance evaluation signal.

[0032] Optionally, the consensus generation engine is specifically configured to calculate the dynamic confidence weights of each data source and generate a dynamic environment state consensus as follows: The theoretical predictions based on the current operating parameters are obtained from the process model and used together with the real-time raw data as the data source. Calculate the real-time deviation between each data source and all other data sources and theoretical predictions; The dynamic confidence weight is calculated by combining the historical consistency performance of each data source with the real-time deviation. The readings from all data sources are weighted and fused according to the dynamic confidence weight to generate the dynamic environment state consensus.

[0033] In one specific embodiment, for generating consensus on dynamic environmental states, the system first acquires real-time sensor readings in batches from the SCADA system and combines them with current operating parameters to input a multivariate nonlinear process model to obtain theoretically predicted values. Then, it calculates the comprehensive deviation, which integrates the current normalized difference and the historical root mean square error of the data source extracted from the historical performance database. Next, it calculates the instantaneous confidence weight based on the following formula: ; Where: W represents the final calculated instantaneous confidence weight; H is the historical consistency performance factor, ranging from 0 to 1, with a higher value indicating more stable and reliable long-term performance of the data source; k is the sensitivity coefficient, used to adjust the suppression strength of the overall deviation on weight decay, and is a positive value, generally ranging from 0.5 to 2.0; D is the overall deviation, reflecting the degree of deviation of the data source from the group, and is a weighted fusion of readings from all data sources.

[0034] Wherein, C is the consensus value of the dynamic environment state finally generated by this environmental parameter; The instantaneous confidence weight corresponding to data source i; The real-time raw reading or theoretical estimate of this parameter provided to data source i; This means summing all relevant data sources and outputting a set of smooth and highly reliable dynamic environment state consensus values ​​through the above calculation, which serve as the data input for all subsequent intelligent analysis and control modules; Optionally, the tiered early warning instructions include comprehensive early warning instructions, intermediate early warning instructions, and low-level early warning instructions; the intelligent early warning center is specifically configured to perform fusion and mutual verification and generate tiered early warning instructions as follows: The predicted risk signal is quantified as the deviation of future parameter trajectory, and the pattern anomaly signal is quantified as the deviation of the current overall state; When both the deviation of the future parameter trajectory and the deviation of the current overall state exceed their respective critical thresholds, the highest level of comprehensive early warning instruction is generated; When only the deviation of the future parameter trajectory exceeds the warning threshold, a medium-level early warning instruction suggesting continuous observation is generated; When only the deviation of the current overall state exceeds the warning threshold, a low-level warning instruction is generated to trigger targeted diagnosis.

[0035] In the early warning mutual verification step, the system quantifies the future parameter trajectory output by the time series prediction model into a dimensionless future parameter trajectory deviation, which is the ratio of the predicted trajectory to the width of the safe operation range; and quantifies the output of the pattern recognition model into the current overall state deviation, which takes a value of 0-1.

[0036] The judgment logic is as follows: if both are greater than the critical threshold, such as 0.8, the highest level comprehensive early warning instruction that triggers emergency intervention is generated; if only the deviation of the future parameter trajectory is greater than the warning threshold, such as 0.6, the intermediate early warning instruction that suggests continuous observation is generated; if only the deviation of the current overall state is greater than its warning threshold, the low-level early warning instruction that triggers diagnosis is generated.

[0037] Optionally, it also includes a model self-update module, configured as follows: When the internal consistency of the consensus in the dynamic environment state remains above a stable threshold, the current time period is determined to be a high-quality learning window. The consensus sequence of dynamic environment states generated during the high-quality learning window is used to construct incremental training samples; The incremental training samples are used to perform online incremental updates of the temporal prediction model in the temporal prediction unit and the pattern recognition model in the pattern recognition unit.

[0038] Optionally, the consensus generation engine is further configured to: calculate the dynamic confidence weights. Receive the sensor performance evaluation signal fed back from the pattern recognition unit; Based on the fault mode information contained in the sensor performance evaluation signal, a penalty factor is introduced into the calculation of the real-time deviation of a specific sensor. By utilizing the real-time deviation after introducing the penalty factor, the dynamic confidence weight of the specific sensor is reduced more quickly.

[0039] Optionally, when selecting a control strategy and generating consensus-driven control commands, the adaptive controller is specifically configured as follows: Strategy selection is based on the overall confidence level of the system, specifically the evaluation value calculated based on the uniformity and stability of the distribution of the dynamic confidence weights. When the overall confidence level of the system is higher than the first confidence threshold, a fine-grained control strategy aimed at optimizing production efficiency is selected, and a first control command is generated. When the overall confidence level of the system is between the first confidence threshold and the second confidence threshold, a robust control strategy with parameter stability as the objective is selected, and a second control command is generated. When the overall confidence level of the system is lower than the second confidence threshold, a conservative control strategy with the goal of ensuring safety is selected, and a third control command is generated.

[0040] In the adaptive control stage, the overall confidence level of the system is calculated based on the uniformity of the weight distribution and stability, using the following formula: ; in: The value represents the final calculated overall confidence level of the system, and its range is normalized to between 0 and 1. E is an index characterizing the uniformity of the weight distribution, which is obtained by calculating the normalized information entropy of the instantaneous confidence weight vectors of all data sources. V is an index characterizing the stability of the weights, which is obtained by calculating the reciprocal of the Euclidean distance between the current weight vector and the weight vector of the previous period. a and b are preset weighting coefficients, satisfying The value is used to balance the importance of uniformity and stability in the overall confidence level assessment, and its typical value is 0.5.

[0041] when If no high-level warning is received, the system determines that the current perception state is highly reliable and activates a fine-grained control strategy aimed at optimizing production efficiency, such as Model Predictive Control (MPC). when When a medium or low-level warning command is received, the system switches to a conservative and robust control strategy, such as PID control, to quickly suppress fluctuations and maintain parameter stability. when When the highest-level comprehensive early warning instruction is received, a conservative control strategy with safety as a safety net is implemented, forcing the actuator to be set within a set of predefined, absolutely safe parameter ranges to prevent the situation from deteriorating.

[0042] Optionally, it also includes a forward-looking maintenance module, configured as follows: The dynamic confidence weights of each environmental parameter sensor are continuously recorded to form a dynamic confidence weight change curve; Analyze the dynamic confidence weight change curve to identify whether there is a weight decay trend that conforms to the characteristics of performance degradation; When the weight decay trend is detected, a predictive maintenance work order is generated before the sensor readings exceed the physical tolerance range.

[0043] For proactive maintenance, the system maintenance module performs a sliding window linear regression analysis on historical weighted data from the most recent 24 hours every hour. When the calculated slope value is negative for several consecutive periods, for example, within the range of -0.001 to -0.005, and the statistical significance p-value is <0.05, it is determined to meet the "slow linear decay" trend. If the real-time reading of the sensor is still within the physical tolerance range set by the factory, the system automatically sends a predictive maintenance work order containing sensor identification and decay mode to the computerized maintenance management system.

[0044] Optionally, the execution of the robust control strategy creates a safe buffer period for the system; the system is configured to: During the safety buffer period, the adaptive controller triggers an enhanced diagnostic process for environmental parameter sensors whose dynamic confidence weights are below the diagnostic threshold. In the enhanced diagnostic process, the pattern recognition unit is used first to confirm the fault mode of the target sensor.

[0045] Optionally, the model self-update module works in conjunction with the forward-looking maintenance module, specifically configured as follows: The model self-updating module adds a verification condition to the conditions for determining the high-quality learning window, namely, querying the forward-looking maintenance module to confirm that no predictive maintenance work order has been generated in the past health check cycle; In the step of constructing the incremental training samples, the model self-updating module labels and downweights the data contributed by the sensors that have generated the predictive maintenance work orders.

[0046] The system provided by the embodiments of the present invention has been described in detail above. The following describes in detail a method for intelligent monitoring of dynamic environmental parameters in a marine biopharmaceutical production line for implementing the system provided by the embodiments of the present invention, including the following steps: Acquire real-time raw data collected by multiple environmental parameter sensors in the production line and process models describing the theoretical relationships between parameters as the basis for constructing a multi-source dataset; Based on the real-time raw data and the process model, the dynamic confidence weights of each data source are calculated through real-time consistency game theory, and then fused to generate a dynamic environmental state consensus that represents the true state of the current environment. The dynamic environment state consensus is input into the time series prediction model and the pattern recognition model to generate prediction risk signals and pattern anomaly signals, respectively. The predicted risk signal and the pattern anomaly signal are fused and cross-verified to generate a graded early warning instruction; Based on the dynamic environment state consensus and the hierarchical early warning instructions, and combined with the overall system confidence level generated by assessing the reliability of the current consensus, the control strategy is adaptively selected and consensus-driven control instructions are generated. The pattern recognition model is also used to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals. The sensor performance evaluation signals are fed back to the calculation process of the dynamic confidence weights for correction.

[0047] In specific implementation, the time series prediction model can adopt a long short-term memory network (LSTM) or an autoregressive integral moving average model (ARIMA) to effectively extract historical time series features of environmental parameters and output future trajectory deviation; the pattern recognition model can adopt an isolation forest algorithm or an autoencoder to efficiently identify latent anomalies in multidimensional parameters that deviate from normal spatial distribution and abnormal group behavior of sensors.

[0048] The electronic device provided in this embodiment of the invention, exemplarily, can be a network device, or a chip (system) or other component or assembly that can be disposed in a network device. The electronic device may include a processor. Optionally, the electronic device may also include a memory and / or a transceiver. The processor is coupled to the memory and transceiver, for example, by means of a communication bus connection.

[0049] The following is a detailed introduction to the various components of the electronic device: In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0050] Alternatively, the processor can perform various functions of the electronic device, such as the methods described above, by running or executing software programs stored in memory and by calling data stored in memory.

[0051] In a specific implementation, as one example, the processor may include one or more CPUs, such as CPU0 and CPU1.

[0052] In a specific implementation, as one example, the electronic device may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0053] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0054] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device; the embodiments of the present invention do not specifically limit this.

[0055] A transceiver is used for communication with other electronic devices. For example, if the electronic device is a terminal, the transceiver can be used to communicate with a network device or with another terminal device. Similarly, if the electronic device is a network device, the transceiver can be used to communicate with a terminal or with another network device.

[0056] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0057] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device. This embodiment of the invention does not specifically limit this.

[0058] It is understood that the structure of the electronic device in this embodiment does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components, or combine certain components, or have different component arrangements.

[0059] Furthermore, the technical effects of the electronic device can be referred to the technical effects of the method described in the above method embodiments, and will not be repeated here.

[0060] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0061] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0062] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0063] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0064] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0065] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0066] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0067] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0070] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0071] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0072] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent monitoring system for dynamic environmental parameters in a marine biopharmaceutical production line, characterized in that, include: The multi-source data acquisition module is configured to acquire real-time raw data collected by multiple environmental parameter sensors in the production line, as well as process models describing the theoretical relationships between parameters, as the basis for constructing a multi-source dataset. The consensus generation engine is configured to calculate the dynamic confidence weights of each data source through real-time consistency game based on the real-time raw data and the process model, and to fuse and generate a dynamic environmental state consensus that represents the current real state of the environment, and to evaluate the reliability of the current consensus to generate the overall confidence level of the system. The intelligent early warning center includes a time-series prediction unit and a pattern recognition unit. It is configured to input the dynamic environmental state consensus into the time-series prediction model and the pattern recognition model respectively, generate predicted risk signals and pattern anomaly signals, and perform fusion and mutual verification on the predicted risk signals and the pattern anomaly signals to generate graded early warning instructions. The pattern recognition unit is also configured to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals, and feed the sensor performance evaluation signals back to the dynamic confidence weight calculation process of the consensus generation engine for correction. An adaptive controller is configured to receive the dynamic environment state consensus, the hierarchical early warning instructions, and the overall system confidence level provided by the consensus generation engine, and adaptively select a control strategy and generate consensus-driven control instructions. The consensus generation engine, the intelligent early warning center, and the adaptive controller form a closed-loop linkage through the dynamic environmental state consensus and the sensor performance evaluation signal.

2. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 1, characterized in that, The consensus generation engine is specifically configured as follows when calculating the dynamic confidence weights of each data source and generating a dynamic environment state consensus: The theoretical predictions based on the current operating parameters are obtained from the process model and used together with the real-time raw data as the data source. Calculate the real-time deviation between each data source and all other data sources and theoretical predictions; The dynamic confidence weight is calculated by combining the historical consistency performance of each data source with the real-time deviation. The readings from all data sources are weighted and fused according to the dynamic confidence weight to generate the dynamic environment state consensus.

3. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 1, characterized in that, The tiered early warning instructions include comprehensive early warning instructions, intermediate early warning instructions, and low-level early warning instructions; the intelligent early warning center is specifically configured as follows when performing fusion and mutual verification and generating tiered early warning instructions: The predicted risk signal is quantified as the deviation of future parameter trajectory, and the pattern anomaly signal is quantified as the deviation of the current overall state; When both the deviation of the future parameter trajectory and the deviation of the current overall state exceed their respective critical thresholds, the highest level of comprehensive early warning instruction is generated; When only the deviation of the future parameter trajectory exceeds the warning threshold, a medium-level early warning instruction suggesting continuous observation is generated; When only the deviation of the current overall state exceeds the warning threshold, a low-level warning instruction is generated to trigger targeted diagnosis.

4. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 1, characterized in that, It also includes a model self-update module, configured as follows: When the internal consistency of the consensus in the dynamic environment state remains above a stable threshold, the current time period is determined to be a high-quality learning window. The consensus sequence of dynamic environment states generated during the high-quality learning window is used to construct incremental training samples; The incremental training samples are used to perform online incremental updates of the temporal prediction model in the temporal prediction unit and the pattern recognition model in the pattern recognition unit.

5. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 2, characterized in that, The consensus generation engine is further configured to: Receive the sensor performance evaluation signal fed back from the pattern recognition unit; Based on the fault mode information contained in the sensor performance evaluation signal, a penalty factor is introduced into the calculation of the real-time deviation of a specific sensor. By utilizing the real-time deviation after introducing the penalty factor, the dynamic confidence weight of the specific sensor is reduced more quickly.

6. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 1, characterized in that, When selecting a control strategy and generating consensus-driven control commands, the adaptive controller is specifically configured as follows: Strategy selection is based on the overall confidence level of the system, specifically the evaluation value calculated based on the uniformity and stability of the distribution of the dynamic confidence weights. When the overall confidence level of the system is higher than the first confidence threshold, a fine-grained control strategy aimed at optimizing production efficiency is selected, and a first control command is generated. When the overall confidence level of the system is between the first confidence threshold and the second confidence threshold, a robust control strategy with parameter stability as the objective is selected, and a second control command is generated. When the overall confidence level of the system is lower than the second confidence threshold, a conservative control strategy with the goal of ensuring safety is selected, and a third control command is generated.

7. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 1, characterized in that, It also includes a forward-looking maintenance module, configured as follows: The dynamic confidence weights of each environmental parameter sensor are continuously recorded to form a dynamic confidence weight change curve; Analyze the dynamic confidence weight change curve to identify whether there is a weight decay trend that conforms to the characteristics of performance degradation; When the weight decay trend is detected, a predictive maintenance work order is generated before the sensor readings exceed the physical tolerance range.

8. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 6, characterized in that, The execution of the robust control strategy creates a safe buffer period for the system; the system is configured as follows: During the safety buffer period, the adaptive controller triggers an enhanced diagnostic process for environmental parameter sensors whose dynamic confidence weights are below the diagnostic threshold. In the enhanced diagnostic process, the pattern recognition unit is used first to confirm the fault mode of the target sensor.

9. The intelligent monitoring system for dynamic environmental parameters of a marine biopharmaceutical production line according to claim 7, characterized in that, The model self-update module and the forward-looking maintenance module work together, specifically configured as follows: The model self-updating module adds a verification condition to the conditions for determining the high-quality learning window, namely, querying the forward-looking maintenance module to confirm that no predictive maintenance work order has been generated in the past health check cycle; In the step of constructing the incremental training samples, the model self-updating module labels and downweights the data contributed by the sensors that have generated the predictive maintenance work orders.

10. A method for intelligent monitoring of dynamic environmental parameters in a marine biopharmaceutical production line, applied to the intelligent monitoring system for dynamic environmental parameters in a marine biopharmaceutical production line as described in any one of claims 1-9, characterized in that, include: Acquire real-time raw data collected by multiple environmental parameter sensors in the production line and process models describing the theoretical relationships between parameters as the basis for constructing a multi-source dataset; Based on the real-time raw data and the process model, the dynamic confidence weights of each data source are calculated through real-time consistency game theory, and then fused to generate a dynamic environmental state consensus that represents the true state of the current environment. The dynamic environment state consensus is input into the time series prediction model and the pattern recognition model to generate prediction risk signals and pattern anomaly signals, respectively. The predicted risk signal and the pattern anomaly signal are fused and cross-verified to generate a graded early warning instruction; Based on the dynamic environment state consensus and the hierarchical early warning instructions, and combined with the overall system confidence level generated by assessing the reliability of the current consensus, the control strategy is adaptively selected and consensus-driven control instructions are generated. The pattern recognition model is also used to identify abnormal group behavior of the environmental parameter sensors and generate sensor performance evaluation signals. The sensor performance evaluation signals are fed back to the calculation process of the dynamic confidence weights for correction.

Images