Intelligent control method and system for corrosion-resistant mass flow sensor

Abstract

The invention belongs to the technical field of computer technology and industrial automation control, and particularly relates to an intelligent control method and system for a corrosion-resistant mass flow sensor, and the method comprises the steps: obtaining an original electric signal of the sensor, a fluid corrosion grade and a temperature parameter in real time through a data collection interface; performing multi-level software processing including wavelet transform adaptive filtering, baseline drift compensation and feature vector extraction on the original signal to generate standardized flow data; the standardized data, the corrosion scene parameters and the historical performance data are input into a self-adaptive control engine, a flow control instruction is dynamically generated, and a sensor health state evaluation report is output; and executing the control instruction to drive an execution mechanism, and implementing a predictive maintenance strategy based on the health report. According to the invention, the long-term measurement precision and control stability of the sensor in a corrosive environment are effectively improved, and intelligent self-adaptive control and predictive maintenance of flow are realized.

Description

Technical Field

[0001] This invention belongs to the field of computer technology and industrial automation control technology, specifically relating to an intelligent control method and system for a corrosion-resistant mass flow sensor. Background Technology

[0002] In the field of industrial sensor control based on electro-digital data processing (G06F), existing solutions have significant shortcomings in signal processing, intelligent control, and predictive maintenance when dealing with corrosive fluid media. This makes it difficult to guarantee the long-term accuracy and reliability of the sensors, resulting in the following deficiencies: 1. Lacking intelligent compensation mechanisms, conventional digital filtering algorithms (such as mean filtering and Kalman filtering) can suppress random noise, but they are difficult to effectively distinguish and compensate for signal drift caused by corrosive media, which is time-varying and nonlinear.

[0003] 2. The control strategy has poor adaptability. The control model parameters are fixed and cannot be adaptively adjusted according to changes in fluid corrosivity and the health status of the sensor itself. It is difficult to maintain optimal control performance in complex and ever-changing industrial environments.

[0004] 3. The maintenance methods are outdated, usually adopting a passive mode of periodic inspection or repair after failure. This cannot achieve early warning and predictive maintenance of sensor performance degradation, which may lead to unplanned downtime and increase operational risks. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an intelligent control method and system for a corrosion-resistant mass flow sensor, which can overcome the problems of decreased measurement accuracy and unreliable control caused by signal drift and performance degradation of the corrosion-resistant mass flow sensor in a long-term corrosive environment.

[0006] To address the aforementioned technical problems, the first aspect of this invention discloses an intelligent control method for a corrosion-resistant mass flow sensor, comprising the following steps: S1. The raw electrical signal output by the corrosion-resistant sensor is acquired in real time through the data acquisition interface, and the fluid corrosion level and temperature parameters provided by the environmental monitoring module are acquired simultaneously. S2. Perform multi-level software signal processing on the original electrical signal, including adaptive filtering based on wavelet transform, baseline drift compensation combined with corrosion level signal, and flow feature vector extraction, to generate high-fidelity standardized flow data. S3. Input the standardized flow data, along with the preset corrosion scenario parameters and sensor historical performance data, into the adaptive control engine. The software algorithm dynamically generates flow control commands and simultaneously outputs a sensor health status assessment report. S4. Execute the flow control command, drive the actuator of the quality flow controller through the communication interface, and implement predictive maintenance strategy based on the health status assessment report.

[0007] As an optional implementation, in the first aspect of the present invention, step S1 includes: The conveyor belt is controlled to perform intermittent stepping motion, so that the cardboard boxes equipped with sensors enter the processing station in sequence, and then corrosive fluid or media is input into the sensors; Establish a multi-channel data acquisition task to receive data streams from multiple sensors in parallel, and attach a high-precision timestamp and environmental parameter label to each data packet; Run a data integrity verification algorithm, use cyclic redundancy check codes to verify the integrity of data packets, and initiate an automatic retransmission mechanism for data packets that fail verification.

[0008] As an optional implementation, in the first aspect of the present invention, the signal processing in step S2 specifically includes: The signal preprocessing layer applies an adaptive threshold denoising algorithm based on wavelet transform to filter out high-frequency noise introduced by corrosive fluid turbulence or medium inhomogeneity. The drift compensation layer calls a pre-trained drift compensation model, which takes historical flow data, ambient temperature and corrosion level as input and outputs a compensation signal to offset the baseline drift caused by the sensor's long-term exposure to the corrosive environment. The feature extraction layer uses dynamic sliding window technology to calculate the feature values ​​of the flow curve in real time on the processed signal and encodes them into feature vectors.

[0009] As an optional implementation, in the first aspect of the invention, the adaptive control engine in step S3 operates in the following manner: Run a lightweight control model on the local edge node to handle regular requests and achieve low-latency control; Key data is regularly encrypted and uploaded to the cloud platform. The big data analytics capabilities of the cloud platform are used to optimize control model parameters, and the updated model increments are distributed locally.

[0010] As an optional implementation, in the first aspect of the present invention, the adaptive control engine is trained using a deep reinforcement learning algorithm. Its state space is defined as the current flow value, the target flow value, environmental parameters, and sensor health index, the action space is the control command, and the reward function integrates the control accuracy, response speed, and sensor power consumption index.

[0011] As an optional implementation, in the first aspect of the present invention, the sensor health status assessment report generation process in step S3 includes: Based on the feature vector and sensor operating parameters, a real-time health score is calculated using a health assessment algorithm. When the health score falls below a preset threshold, an early warning message is automatically generated, indicating potential performance degradation risks and suggesting maintenance measures.

[0012] As an optional implementation, in the first aspect of the invention, the predictive maintenance strategy in step S4 includes: Power consumption optimization involves dynamically adjusting the software power supply strategy of the sensor chip, switching to a low-power mode when the flow rate is stable, and instantly resuming full-power operation when a sudden change in flow rate is detected. Virtual performance testing involves building a digital twin model of the sensor system in a software environment and injecting simulated corrosion and aging data to predict performance degradation curves.

[0013] As an optional implementation, in the first aspect of the present invention, the method further includes blockchain-based data security technology to generate tamper-proof audit logs for each data acquisition and control command execution, ensuring the traceability of traffic metering data and control processes.

[0014] A second aspect of this invention discloses an intelligent control system for a corrosion-resistant mass flow sensor, used to implement the intelligent control method for a corrosion-resistant mass flow sensor described in any of the above embodiments, the system comprising: The data acquisition module is used to acquire raw electrical signals and environmental parameters in real time. The feature extraction module is used to perform multi-level software signal processing on the raw electrical signal to generate standardized flow data. The adaptive control engine module is used to generate control commands and health status reports based on standardized flow data, environmental parameters, and historical data. The control module is used to execute control commands and implement predictive maintenance strategies.

[0015] A third aspect of this invention discloses another intelligent control system for a corrosion-resistant mass flow sensor, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent control method for a corrosion-resistant mass flow sensor disclosed in the first aspect of the present invention.

[0016] The fourth aspect of this invention discloses a computer-readable storage medium storing computer instructions, which, when invoked by a processor, are used to execute an intelligent control method for a corrosion-resistant mass flow sensor disclosed in the first aspect of this invention.

[0017] Compared with the prior art, the beneficial effects of the present invention are: 1. By introducing a signal drift compensation algorithm based on a machine learning model, the sensor baseline drift caused by corrosive environments can be actively identified and offset at the software level, significantly improving long-term measurement accuracy and control stability under harsh working conditions, and reducing the extreme dependence on the corrosion resistance of hardware materials.

[0018] 2. The adaptive control engine, built using advanced algorithms such as deep reinforcement learning, can dynamically adjust the control strategy based on real-time flow data, environmental parameters, and sensor health status, enabling the system to maintain rapid response and optimal control performance in various fluid environments ranging from mild to highly corrosive.

[0019] 3. An innovative software-based predictive maintenance strategy based on digital twins and health assessment algorithms is proposed. The system can assess sensor health scores in real time and provide early warnings of performance degradation risks, such as adhesive layer aging and decreased chip sensitivity. This transforms passive maintenance into proactive intervention, significantly reducing unplanned downtime and lowering maintenance costs.

[0020] 4. By dynamically managing the power consumption mode of the sensor chip through software algorithms, the overall energy consumption of the system is effectively reduced while ensuring detection accuracy. This is especially suitable for industrial applications that require long-term continuous operation and extends the service life of the equipment. Attached Figure Description

[0021] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, wherein: Figure 1 This is a schematic flowchart of an intelligent control method for a corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent control system for a corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an intelligent control system for another corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] This invention discloses an intelligent control method and system for a corrosion-resistant mass flow sensor. By introducing a signal drift compensation algorithm based on a machine learning model, it can actively identify and offset the sensor baseline drift caused by the corrosive environment at the software level, significantly improving the long-term measurement accuracy and control stability under harsh working conditions, and reducing the extreme dependence on the corrosion resistance of hardware materials.

[0026] Example 1 Please see Figure 1 , Figure 1 This is a schematic flowchart illustrating an intelligent control method for a corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention. Wherein, Figure 1 The described intelligent control method for a corrosion-resistant mass flow sensor is applied to a data processing chip, processing terminal, or processing server, and the processing server can be a local server or a cloud server; this embodiment of the invention is not limited thereto. Figure 1 As shown, the intelligent control method for this corrosion-resistant mass flow sensor may include the following operations: S1. The raw electrical signal output by the corrosion-resistant sensor is acquired in real time through the data acquisition interface, and the fluid corrosion level and temperature parameters provided by the environmental monitoring module are acquired simultaneously.

[0027] Specifically, this step lays a precise data foundation for subsequent intelligent processing and control by synchronously acquiring raw electrical signals from sensors and environmental parameters. Real-time acquisition of raw electrical signals ensures the integrity and timeliness of flow rate change information, while the synchronous acquisition of corrosion level and temperature parameters constitutes a multimodal dataset. This comprehensive data acquisition method enables the system to analyze flow signals within specific operating conditions, providing crucial environmental context information for subsequent signal compensation and adaptive control.

[0028] It is evident that the core of associating environmental parameters with electrical signals lies in achieving deep perception of the sensor's operating status. The system can dynamically adjust the parameters of the signal processing algorithm and the decision weights of the control strategy based on real-time corrosion levels and temperature changes. This data-driven approach can effectively identify the coupled influence of environmental factors on the sensor output, thereby providing a quantitative basis for accurately compensating for signal drift caused by temperature fluctuations and media corrosion, and improving the overall system's perception accuracy and control robustness under complex operating conditions.

[0029] S2. Perform multi-level software signal processing on the original electrical signal, including adaptive filtering based on wavelet transform, baseline drift compensation combined with corrosion level signal, and flow feature vector extraction, to generate high-fidelity standardized flow data.

[0030] Specifically, this multi-level software signal processing workflow effectively improves the quality and usability of the original signal. Wavelet transform-based adaptive filtering can accurately remove non-stationary noise from the signal, preserving the true characteristics of flow rate changes. Combined with a baseline drift compensation algorithm for corrosiveness level signals, it dynamically corrects measurement benchmark deviations caused by medium corrosion by modeling the correlation between environmental parameters and signal drift. These processes collectively ensure the high fidelity of the signal source used in subsequent analyses.

[0031] As can be seen, by extracting the flow feature vector, the system transforms continuous time-domain signals into standardized data containing key information. This standardized data format not only eliminates individual differences and environmental interference between different sensors, but also provides a unified and reliable input for the upstream adaptive control engine.

[0032] S3. Standardized flow data, along with preset corrosion scenario parameters and historical sensor performance data, are input into the adaptive control engine. The engine dynamically generates flow control commands through software algorithms and simultaneously outputs a sensor health status assessment report.

[0033] Specifically, this step integrates real-time flow data, preset corrosion scenario parameters, and historical sensor performance data through an adaptive control engine, enabling precise flow control decisions and simultaneous assessment of sensor health. This multi-source information integration method allows control commands to dynamically adapt to the characteristic changes of different corrosive fluids, while also tracing the sensor's own state decay trend based on historical performance data, thereby maintaining the stability of the control loop under complex operating conditions.

[0034] As can be seen, by synchronously generating control commands and health status assessment reports through software algorithms, the system not only performs real-time flow regulation but also provides quantitative data for predictive maintenance. This mechanism effectively combines control functions with status monitoring, optimizing current control actions and providing data support for early warning of sensor performance degradation and long-term reliable system operation.

[0035] S4. Execute flow control commands, drive the actuator of the quality flow controller through the communication interface, and implement predictive maintenance strategies based on the health status assessment report.

[0036] Specifically, the execution process realizes a closed-loop linkage between control commands and maintenance strategies. The control commands precisely drive the actuators through the communication interface to complete the real-time adjustment of fluid flow, ensuring the consistency between the system response and the set target. At the same time, based on the performance degradation trend indicated by the health status assessment report, the system proactively triggers the corresponding maintenance plan, transforming maintenance actions from passive response to proactive intervention.

[0037] It is evident that predictive maintenance strategies based on health status can rationally schedule maintenance timing and resources, and carry out targeted maintenance before sensor performance completely fails, thereby avoiding unplanned downtime. The aforementioned integrated execution and maintenance mechanism not only ensures the continuity of process control but also improves the overall utilization rate and operational reliability of the equipment.

[0038] As an optional embodiment, step S1 in the above steps includes: The conveyor belt is controlled to perform intermittent stepping motion, so that the cardboard boxes equipped with sensors enter the processing station in sequence, and then corrosive fluid or media is input into the sensors; Establish a multi-channel data acquisition task to receive data streams from multiple sensors in parallel, and attach a high-precision timestamp and environmental parameter label to each data packet; Run a data integrity verification algorithm, use cyclic redundancy check codes to verify the integrity of data packets, and initiate an automatic retransmission mechanism for data packets that fail verification.

[0039] In this embodiment of the invention, the control method achieves precise synchronization of the production process by coordinating the intermittent movement of the conveyor belt with the data acquisition task. The stepping movement of the conveyor belt causes the cardboard boxes equipped with sensors to enter the processing station in sequence at a predetermined rhythm, providing a stable time window for each station to input corrosive fluids or media into the sensors. On this basis, the system receives multi-sensor data streams in parallel and establishes an accurate spatiotemporal correlation framework for subsequent analysis by adding high-precision timestamps and environmental parameters, effectively avoiding data misalignment and confusion.

[0040] As can be seen, by introducing cyclic redundancy check codes and automatic retransmission mechanisms, the system has built a reliable data transmission channel. The data integrity verification algorithm can instantly identify erroneous data packets generated during transmission and trigger the retransmission process, ensuring the integrity and accuracy of the collected data.

[0041] As an optional embodiment, the signal processing in step S2 of the above steps specifically includes: The signal preprocessing layer applies an adaptive threshold denoising algorithm based on wavelet transform to filter out high-frequency noise introduced by corrosive fluid turbulence or medium inhomogeneity. The drift compensation layer calls a pre-trained drift compensation model, which takes historical flow data, ambient temperature and corrosion level as input and outputs a compensation signal to offset the baseline drift caused by the sensor's long-term exposure to the corrosive environment. The feature extraction layer uses dynamic sliding window technology to calculate the feature values ​​of the flow curve in real time on the processed signal and encodes them into feature vectors.

[0042] In this embodiment of the invention, this multi-level signal processing architecture transforms the raw sensor electrical signals into high-quality, usable data through a step-by-step refinement process. The signal preprocessing layer first utilizes the adaptive properties of wavelet transform to effectively filter out high-frequency noise caused by fluid turbulence or medium inhomogeneity, providing a clean signal foundation for subsequent processing.

[0043] As can be seen, in the feature extraction layer, the system uses dynamic sliding window technology to calculate the key feature values ​​of the flow curve in real time and encode them into compact feature vectors. This process achieves a high degree of data condensation, while retaining the most discriminative information in the original signal and reducing the dimensionality and redundancy of the data.

[0044] As an optional embodiment, the adaptive control engine in step S3 above operates in the following manner: Run a lightweight control model on the local edge node to handle regular requests and achieve low-latency control; Key data is regularly encrypted and uploaded to the cloud platform. The big data analytics capabilities of the cloud platform are used to optimize control model parameters, and the updated model increments are distributed locally.

[0045] In this embodiment of the invention, the operating mechanism effectively balances the system's real-time requirements and global optimization capabilities through a cloud-edge collaborative architecture. It runs a lightweight control model on the local edge node, ensuring that flow control commands can be quickly generated based on on-site data, thereby reducing communication latency caused by data uploading to the cloud for processing.

[0046] As can be seen, the regular encrypted data synchronization and incremental model distribution mechanism constructs a closed-loop optimization process. This process not only ensures the security of data transmission and prevents the leakage of critical production data, but also enables edge nodes to silently update their control models without interrupting services, achieving a smooth upgrade of system performance.

[0047] As an optional embodiment, in the above steps, the adaptive control engine is trained using a deep reinforcement learning algorithm. Its state space is defined as the current flow value, target flow value, environmental parameters, and sensor health index, its action space is the control command, and the reward function integrates control accuracy, response speed, and sensor power consumption indicators.

[0048] In this embodiment of the invention, this step constructs an adaptive control engine through a deep reinforcement learning algorithm. Its state space integrates the current flow rate, target flow rate, environmental parameters, and sensor health index. The action space is directly mapped to control commands, and the reward function collaboratively optimizes control accuracy, response speed, and sensor power consumption indicators. The above multi-dimensional state definition enables the agent to fully perceive the system's operating conditions and equipment status, thereby simultaneously balancing instantaneous adjustment effects and long-term operating efficiency when outputting control commands. Its reward mechanism guides the control strategy to meet accuracy and speed requirements while taking into account energy consumption constraints, achieving multi-objective collaborative optimization by balancing multiple key performance indicators.

[0049] It is evident that the adaptive mechanism based on deep reinforcement learning enables the control system to dynamically adjust its strategy according to real-time state data without relying on a precise mathematical model of the controlled object. This effectively addresses sensor characteristic drift or dynamic characteristic changes in corrosive environments. The explicit constraint on sensor power consumption in the reward function prompts the agent to actively explore low-power control modes, which helps extend the lifespan of sensors in long-term corrosive environments.

[0050] As an optional embodiment, the sensor health status assessment report generation process in step S3 above includes: Based on feature vectors and sensor operating parameters, a real-time health score is calculated using a health assessment algorithm. When the health score falls below a preset threshold, an early warning message is automatically generated, indicating potential performance degradation risks and suggesting maintenance measures.

[0051] In this embodiment of the invention, the core value of the health status assessment report generation process lies in transforming multi-dimensional feature vectors and sensor operating parameters into a quantified health score. This score, as an intuitive indicator, enables continuous tracking of the degree of sensor performance degradation, providing a data foundation for predictive maintenance.

[0052] It is evident that by condensing complex sensor status information into easily understandable health scores and specific warnings through algorithms, maintenance personnel can prioritize high-risk issues and allocate maintenance resources rationally.

[0053] As an optional embodiment, the predictive maintenance strategy in step S4 above includes: Power consumption optimization involves dynamically adjusting the software power supply strategy of the sensor chip, switching to a low-power mode when the flow rate is stable, and instantly resuming full-power operation when a sudden change in flow rate is detected. Virtual performance testing involves building a digital twin model of the sensor system in a software environment and injecting simulated corrosion and aging data to predict performance degradation curves.

[0054] In this embodiment of the invention, the predictive maintenance strategy achieves dynamic matching between sensor chip power consumption and detection requirements through a power consumption optimization mechanism. Under stable fluid flow conditions, the system automatically switches to a low-power mode, effectively reducing the static operating power consumption of the sensor. When a drastic change in flow is detected, the power supply strategy can instantly restore to full power operation, ensuring the real-time performance and accuracy of the measurement response.

[0055] As can be seen, the virtual performance testing strategy simulates the actual corrosion and aging process in a software environment by constructing a digital twin model of the sensor system. By injecting simulated corrosion and aging data, this digital twin model can deduce and predict the performance degradation curve of the physical sensors under real operating conditions.

[0056] As an optional embodiment, the method in the above steps also includes blockchain-based data security technology to generate tamper-proof audit logs for each data acquisition and control command execution, ensuring the traceability of traffic metering data and control processes.

[0057] In this embodiment of the invention, blockchain technology is introduced to generate timestamped audit logs for each data acquisition and control command execution. These logs utilize the distributed ledger characteristics of blockchain, are stored across multiple nodes in the network, and a hash algorithm ensures that the records are immutable once generated.

[0058] As can be seen, based on the immutability and traceability of blockchain, the system can completely reproduce the process of change of traffic metering data and the execution sequence of control commands. When it is necessary to conduct problem diagnosis, dispute verification or compliance review, auditors can accurately trace the source of any data point and the decision chain of related control actions, thereby effectively improving the transparency and credibility of the traffic control process.

[0059] Furthermore, including: 1. Signal preprocessing, adaptive wavelet threshold denoising, the formula is: ; This formula describes the process of extracting effective components from noisy signals, where, The signal after denoising. These are the discrete wavelet transform coefficients. For wavelet basis functions, This is a soft thresholding function, and the threshold value is... , For noise estimation, Corrosiveness level, This is the adjustment coefficient.

[0060] In corrosive fluid environments, turbulence, media inhomogeneity, and the equipment itself generate a large amount of high-frequency noise, drowning out the true flow signal. This formula uses wavelet transform to decompose the signal into different frequency scales and adaptively adjusts the threshold according to the level of corrosivity, accurately removing noise components while preserving the essential characteristics of the signal.

[0061] 2. Drift compensation, based on machine learning to predict the compensation amount, the formula is: ; This formula defines the drift compensation function implemented by a machine learning model, where, Let be the predicted drift compensation amount at time t. For the front A standardized traffic data vector at each moment. The current ambient temperature. The current fluid corrosivity level, For the set of parameters of a pre-trained model (such as a neural network), This is the model mapping function.

[0062] This formula transforms a complex nonlinear compensation prediction problem into a regression task of a machine learning model. The model learns the relationship between historical data, temperature, and corrosion level to dynamically predict the current drift δ and compensate for it in real time, thereby improving the long-term accuracy and stability of the sensor in harsh environments.

[0063] 3. Adaptive control, the value function optimization objective of deep reinforcement learning, the formula is: ; in, For the time-difference objective, For the network of critics, assess the state (Including flow error, corrosion level, health index, etc.) Execute actions The long-term expected return of (control instructions) and As a discount factor, and For the target network.

[0064] This formula incorporates three objectives into the optimization simultaneously: control accuracy (squared deviation), system stability (change in control command), and sensor power consumption.

[0065] 4. Health assessment, real-time health score calculation, formula is: ; in, Let be the health score at time t. Let i be the i-th real-time performance feature (such as signal-to-noise ratio, response time). This serves as the baseline value for this characteristic under healthy conditions. The corresponding weighting coefficients and satisfying .

[0066] This formula compares multiple key features, such as signal-to-noise ratio and response speed, with their health benchmark values, performs weighted fusion, and outputs a comprehensive health score between 0 and 1. This transforms the fuzzy judgment of sensor status into a clear quantitative indicator, providing a precise basis for predictive maintenance decisions.

[0067] 5. Predictive maintenance: prediction of digital twin performance degradation, the formula is as follows: ; in, For the sensor performance parameters (such as sensitivity) predicted at time t. Its initial value, For temperature and corrosive The relevant decay rate function, It is a constant. This is an acceleration factor function related to the corrosion level.

[0068] This formula predicts the decay curve of future performance parameters by constructing a digital model in virtual space that ages synchronously with physical sensors, and substituting real-time monitored environmental stress into an aging rate model based on physicochemical principles.

[0069] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an intelligent control system for a corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention. Figure 2 The intelligent control system for a corrosion-resistant mass flow sensor described herein can be applied to a data processing chip, processing terminal, or processing server. The processing server can be a local server or a cloud server; this invention does not limit the application. Figure 2 As shown, the intelligent control system of this corrosion-resistant mass flow sensor may include the following operations: The data acquisition module 201 is used to acquire raw electrical signals and environmental parameters in real time.

[0070] Specifically, this step lays a precise data foundation for subsequent intelligent processing and control by synchronously acquiring raw electrical signals from sensors and environmental parameters. Real-time acquisition of raw electrical signals ensures the integrity and timeliness of flow rate change information, while the synchronous acquisition of corrosion level and temperature parameters constitutes a multimodal dataset. This comprehensive data acquisition method enables the system to analyze flow signals within specific operating conditions, providing crucial environmental context information for subsequent signal compensation and adaptive control.

[0071] It is evident that the core of associating environmental parameters with electrical signals lies in achieving deep perception of the sensor's operating status. The system can dynamically adjust the parameters of the signal processing algorithm and the decision weights of the control strategy based on real-time corrosion levels and temperature changes. This data-driven approach can effectively identify the coupled influence of environmental factors on the sensor output, thereby providing a quantitative basis for accurately compensating for signal drift caused by temperature fluctuations and media corrosion, and improving the overall system's perception accuracy and control robustness under complex operating conditions.

[0072] The feature extraction module 202 is used to perform multi-level software signal processing on the original electrical signal to generate standardized flow data.

[0073] Specifically, this multi-level software signal processing workflow effectively improves the quality and usability of the original signal. Wavelet transform-based adaptive filtering can accurately remove non-stationary noise from the signal, preserving the true characteristics of flow rate changes. Combined with a baseline drift compensation algorithm for corrosiveness level signals, it dynamically corrects measurement benchmark deviations caused by medium corrosion by modeling the correlation between environmental parameters and signal drift. These processes collectively ensure the high fidelity of the signal source used in subsequent analyses.

[0074] As can be seen, by extracting the flow feature vector, the system transforms continuous time-domain signals into standardized data containing key information. This standardized data format not only eliminates individual differences and environmental interference between different sensors, but also provides a unified and reliable input for the upstream adaptive control engine.

[0075] The adaptive control engine module 203 is used to generate control commands and health status reports based on standardized flow data, environmental parameters, and historical data.

[0076] Specifically, this step integrates real-time flow data, preset corrosion scenario parameters, and historical sensor performance data through an adaptive control engine, enabling precise flow control decisions and simultaneous assessment of sensor health. This multi-source information integration method allows control commands to dynamically adapt to the characteristic changes of different corrosive fluids, while also tracing the sensor's own state decay trend based on historical performance data, thereby maintaining the stability of the control loop under complex operating conditions.

[0077] As can be seen, by synchronously generating control commands and health status assessment reports through software algorithms, the system not only performs real-time flow regulation but also provides quantitative data for predictive maintenance. This mechanism effectively combines control functions with status monitoring, optimizing current control actions and providing data support for early warning of sensor performance degradation and long-term reliable system operation.

[0078] Control module 204 is used to execute control commands and implement predictive maintenance strategies.

[0079] Specifically, the execution process realizes a closed-loop linkage between control commands and maintenance strategies. The control commands precisely drive the actuators through the communication interface to complete the real-time adjustment of fluid flow, ensuring the consistency between the system response and the set target. At the same time, based on the performance degradation trend indicated by the health status assessment report, the system proactively triggers the corresponding maintenance plan, transforming maintenance actions from passive response to proactive intervention.

[0080] It is evident that predictive maintenance strategies based on health status can rationally schedule maintenance timing and resources, and carry out targeted maintenance before sensor performance completely fails, thereby avoiding unplanned downtime. The aforementioned integrated execution and maintenance mechanism not only ensures the continuity of process control but also improves the overall utilization rate and operational reliability of the equipment.

[0081] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an intelligent control system for another corrosion-resistant mass flow sensor disclosed in an embodiment of the present invention. Figure 3 As shown, the device may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute some or all of the steps in the intelligent control method for a corrosion-resistant mass flow sensor disclosed in Embodiment 1 of the present invention.

[0082] Example 4 This invention discloses a computer storage medium storing computer instructions. When these computer instructions are invoked, they are used to execute some or all of the steps in the intelligent control method for a corrosion-resistant mass flow sensor disclosed in Embodiment 1 of this invention.

[0083] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of an intelligent control method for a corrosion-resistant mass flow sensor described in Embodiment 1.

[0084] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0085] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0086] Finally, it should be noted that the intelligent control method and system for a corrosion-resistant mass flow sensor disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of intelligent control of a corrosion resistant mass flow sensor, characterized by, Includes the following steps: S1. The raw electrical signal output by the corrosion-resistant sensor is acquired in real time through the data acquisition interface, and the fluid corrosion level and temperature parameters provided by the environmental monitoring module are acquired simultaneously. S2. Perform multi-level software signal processing on the original electrical signal, including adaptive filtering based on wavelet transform, baseline drift compensation combined with corrosion level signal, and flow feature vector extraction, to generate high-fidelity standardized flow data. S3. Input the standardized flow data, along with the preset corrosion scenario parameters and sensor historical performance data, into the adaptive control engine. The software algorithm dynamically generates flow control commands and simultaneously outputs a sensor health status assessment report. S4. Execute the flow control command, drive the actuator of the quality flow controller through the communication interface, and implement predictive maintenance strategy based on the health status assessment report.

2. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, Step S1 includes: The conveyor belt is controlled to perform intermittent stepping motion, so that the cardboard boxes equipped with sensors enter the processing station in sequence, and then corrosive fluid or media is input into the sensors; Establish a multi-channel data acquisition task to receive data streams from multiple sensors in parallel, and attach a high-precision timestamp and environmental parameter label to each data packet; Run a data integrity verification algorithm, use cyclic redundancy check codes to verify the integrity of data packets, and initiate an automatic retransmission mechanism for data packets that fail verification.

3. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, The signal processing in step S2 specifically includes: The signal preprocessing layer applies an adaptive threshold denoising algorithm based on wavelet transform to filter out high-frequency noise introduced by corrosive fluid turbulence or medium inhomogeneity. The drift compensation layer calls a pre-trained drift compensation model, which takes historical flow data, ambient temperature and corrosion level as input, and outputs a compensation signal to offset the baseline drift of the sensor caused by long-term exposure to a corrosive environment. The feature extraction layer uses dynamic sliding window technology to calculate the feature values ​​of the flow curve in real time on the processed signal and encodes them into feature vectors.

4. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, The adaptive control engine in step S3 operates in the following way: Run a lightweight control model on the local edge node to handle regular requests and achieve low-latency control; Key data is regularly encrypted and uploaded to the cloud platform. The big data analytics capabilities of the cloud platform are used to optimize control model parameters, and the updated model increments are distributed locally.

5. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 4, characterized in that, The adaptive control engine is trained using a deep reinforcement learning algorithm. Its state space is defined as the current flow value, target flow value, environmental parameters, and sensor health index. The action space is the control command. The reward function integrates control accuracy, response speed, and sensor power consumption indicators.

6. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, The sensor health status assessment report generation process in step S3 includes: Based on the feature vector and sensor operating parameters, a real-time health score is calculated using a health assessment algorithm. When the health score falls below a preset threshold, an early warning message is automatically generated, indicating potential performance degradation risks and suggesting maintenance measures.

7. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, The predictive maintenance strategy in step S4 includes: Power consumption optimization involves dynamically adjusting the software power supply strategy of the sensor chip, switching to a low-power mode when the flow rate is stable, and instantly resuming full-power operation when a sudden change in flow rate is detected. Virtual performance testing involves building a digital twin model of the sensor system in a software environment and injecting simulated corrosion and aging data to predict performance degradation curves.

8. The intelligent control method for a corrosion-resistant mass flow sensor according to claim 1, characterized in that, It also includes blockchain-based data security technology, which generates tamper-proof audit logs for each data acquisition and control command execution, ensuring the traceability of traffic metering data and control processes.

9. An intelligent control system for a corrosion-resistant mass flow sensor, used to implement the intelligent control method for a corrosion-resistant mass flow sensor as described in any one of claims 1-8, characterized in that, include: The data acquisition module is used to acquire raw electrical signals and environmental parameters in real time. The feature extraction module is used to perform multi-level software signal processing on the raw electrical signal to generate standardized flow data. The adaptive control engine module is used to generate control commands and health status reports based on standardized flow data, environmental parameters, and historical data. The control module is used to execute control commands and implement predictive maintenance strategies.

10. An intelligent control system for a corrosion-resistant mass flow sensor, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent control method for a corrosion-resistant mass flow sensor as described in any one of claims 1-8.

Images