A consistency guarantee method and system for water treatment and gas turbine DCS integrated data

Abstract

The application relates to a consistency guarantee method and system for water treatment and gas turbine DCS integrated data, and belongs to the field of data consistency guarantee. The method comprises the following steps: collecting water treatment DCS data and gas turbine DCS data to obtain serialized data; constructing a transmission quality evaluation model based on the serialized data and dynamically selecting an optimal transmission path; transmitting data based on the optimal transmission path, constructing a consistency risk early warning model based on a consistency risk early warning index, and performing bidirectional verification and risk assessment; when the consistency risk early warning index exceeds a preset threshold, realizing self-adaptive error correction and intelligent scheduling of error correction priority through the construction of an intelligent fault tolerance mechanism; and performing self-adaptive optimization through the construction of a deep reinforcement learning model, and continuously performing state assessment. Through serialized data management, transmission quality dynamic evaluation, consistency risk early warning, intelligent fault tolerance and deep reinforcement learning self-adaptive optimization, the consistency guarantee of water treatment and gas turbine DCS integrated data is realized.

Description

Technical Field

[0001] This invention belongs to the field of data consistency assurance technology, specifically relating to a method and system for ensuring the consistency of integrated data of water treatment and gas turbine DCS. Background Technology

[0002] In the field of industrial automation, ensuring the consistency of integrated data between water treatment and gas turbine DCS (Distributed Control System) is crucial for ensuring the safe and stable operation of the system. Existing technologies mainly rely on periodic data verification, fixed threshold alarms, and manual retransmission mechanisms, such as traditional network protocols based on CRC checksums and TCP retransmission. While these methods can basically maintain data transmission, they have significant shortcomings: First, traditional methods lack dynamic evaluation of transmission path quality and cannot adapt to network fluctuations (such as latency jitter or bandwidth contention), leading to data loss or duplicate transmissions. Second, consistency verification often uses one-way or fixed-frequency comparisons, making it difficult to capture timing deviations and data semantic errors in real time. Especially in multi-source heterogeneous data integration scenarios such as water treatment and gas turbine, changes in system load and transmission delays can easily trigger false alarms or missed alarms. In addition, existing fault tolerance mechanisms often use static thresholds, resulting in rigid error correction strategies that cannot adaptively schedule based on data criticality and system status, leading to resource waste or risk accumulation. Finally, they lack predictive optimization capabilities, and the system's performance may degrade due to parameter fixation during long-term operation. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for ensuring the consistency of integrated data between water treatment and gas turbine DCS.

[0004] The objective of this invention can be achieved through the following technical solutions: A consistency assurance method for integrated water treatment and gas turbine DCS data, the implementation of which includes the following steps: Step S1: Collect water treatment DCS data and gas turbine DCS data, and add a sequence number and timestamp to each data point to obtain serialized data, which includes water treatment serialized data and gas turbine serialized data; Step S2: Construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path; Step S3: Transmit data based on the optimal transmission path, and construct a consistency risk warning model based on the consistency risk warning index, and perform bidirectional verification and risk assessment; Step S4: When the consistency risk warning index exceeds the preset threshold, an intelligent fault-tolerant mechanism is constructed to achieve adaptive error correction and intelligent scheduling of error correction priorities; Step S5: Adaptive optimization is performed by constructing a deep reinforcement learning model, while continuously evaluating the state.

[0005] Preferably, the construction of the transmission quality evaluation model in step S2 specifically involves: obtaining the timestamp synchronization error and the maximum allowable synchronization error based on the serialized data, and obtaining the number of successful transmissions and the total number of transmissions; dynamically selecting the optimal transmission path based on the transmission quality index, wherein the mathematical description of the transmission quality index is... ,in, For transmission quality index, This is the scaling factor. For timestamp synchronization error, To the maximum permissible synchronization error, Number of successful transmissions This represents the total number of transmissions.

[0006] Preferably, the timestamp synchronization error is obtained by: obtaining the transmission delay and average transmission delay of the i-th data point, and counting the number of samples to obtain the timestamp synchronization error, which is mathematically described as follows: ,in, The timestamp synchronization error is N, where N is the number of samples. Let i be the transmission delay of the i-th data point. For average transmission delay, These are the weighting coefficients.

[0007] Preferably, the construction of the consistency risk warning model in step S3 specifically involves: obtaining the consistency risk warning index through the data consistency probability, wherein the mathematical description of the consistency risk warning index is... ,in, This is a consistency risk warning index. For data consistency probability, This is the current verification frequency. To normalize the parity check frequency, For timestamp synchronization error, This represents the maximum permissible synchronization error.

[0008] Preferably, the data consistency probability is obtained by: obtaining the exponentially weighted sum of successful verification counts and the exponentially weighted sum of failed verification counts, and obtaining the current system load; the data consistency probability is then obtained, mathematically described as follows: ,in, For success sensitivity coefficient, The failure sensitivity coefficient. The exponentially weighted sum of the number of successful verifications. The exponentially weighted sum of the number of failed checks. The current system load, This represents the maximum allowable load.

[0009] Preferably, the construction of the intelligent fault-tolerant mechanism in step S4 specifically involves: obtaining the error correction threshold, mathematically described as follows: ,in, The error correction threshold, Based on the basic fault tolerance threshold, This represents the number of recent errors. Total number of errors This represents the current average transmission delay. As a reference delay; compare the data deviation with the error correction threshold in real time and perform the adaptive error correction; when multiple data points need error correction, obtain the error correction priority evaluation index, mathematically described as... ,in, As an index for evaluating the priority of error correction, This represents the absolute value of the data deviation. As a key index for data, This is the time interval between the last error correction. The normalized time constant is used to process error correction tasks in descending order based on the error correction priority evaluation index.

[0010] Preferably, the construction of the deep reinforcement learning model in step S5 specifically includes: The parity frequency is dynamically adjusted using an adaptive parity frequency formula, mathematically described as follows: ,in, To optimize the verification frequency, Minimum verification frequency, The maximum verification frequency, The attenuation coefficient is... The current system load, For the maximum allowable load, For data consistency probability, The target consistency probability is preset.

[0011] Preferably, the state assessment specifically includes: The operational status is comprehensively monitored through a health assessment index, mathematically described as follows: ,in, As a comprehensive health assessment index, , and These are the weighting coefficients. For timestamp synchronization error, To the maximum permissible synchronization error, This is the current verification frequency; Overall performance is evaluated through a system optimization index, mathematically described as follows: ,in, To optimize the index of the system, The standard deviation of the system load is used; when the system optimization index is lower than the preset threshold, multimodal diagnostics is automatically initiated.

[0012] A consistency assurance system for integrated water treatment and gas turbine DCS data is provided to execute the aforementioned consistency assurance method for integrated water treatment and gas turbine DCS data, including a data acquisition module, a transmission quality assessment module, a risk warning module, an adaptive error correction module, and an adaptive optimization module. The data acquisition module is used to collect water treatment DCS data and gas turbine DCS data, and add a sequence number and timestamp to each data point to obtain serialized data, which includes water treatment serialized data and gas turbine serialized data. The transmission quality assessment module is used to construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path. The risk warning module is used to transmit data based on the optimal transmission path and to construct a consistency risk warning model based on the consistency risk warning index, and to perform bidirectional verification and risk assessment. The adaptive error correction module is used to achieve adaptive error correction and intelligently schedule error correction priority by constructing an intelligent fault tolerance mechanism when the consistency risk warning index exceeds a preset threshold. The adaptive optimization module is used to perform adaptive optimization by constructing a deep reinforcement learning model, while continuously evaluating the state.

[0013] The beneficial effects of this invention are as follows: (1) By using serialized data structures and dynamic transmission path selection, the risk of data loss and duplication is reduced, and transmission efficiency is improved.

[0014] (2) By combining a consistent risk warning model with two-way verification, early risk identification and preventive intervention were achieved.

[0015] (3) The intelligent fault tolerance mechanism avoids unnecessary error correction operations and optimizes resource utilization through dynamic threshold and priority scheduling.

[0016] (4) The adaptive optimization capability of deep reinforcement learning models enables the system to adjust parameters according to real-time load and consistency status, and maintain high-performance operation. Attached Figure Description

[0017] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart of the steps of a method for ensuring consistency of integrated DCS data for water treatment and gas turbines according to the present invention. Detailed Implementation

[0019] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values ​​that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0020] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0021] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] Example 1: Please see Figure 1 A method for ensuring consistency of integrated data between water treatment and gas turbine DCS includes: Step S1: Collect water treatment DCS data and gas turbine DCS data, and add a sequence number and timestamp to each data point (such as water level and temperature). The sequence number is used to track the data order, and the timestamp is used for time sequence alignment to obtain serialized data. ,in, For serial number, For data values, The serialized data, including water treatment serialized data and gas turbine serialized data, serves as a timestamp. This data version sequence prevents data duplication or loss. Example: When the water treatment system collects data showing a "raw water pump station water level" of 50.2 tons, it generates serial number 1001 and a timestamp, thus obtaining the water treatment serialized data. ; Step S2: Construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path; Step S3: Transmit data based on the optimal transmission path, and construct a consistency risk warning model based on the consistency risk warning index. Perform bidirectional verification and risk assessment. In the forward verification, the gas turbine DCS returns an acknowledgment signal containing a hash value. In the reverse verification, the gas turbine periodically requests data snapshots for comparison. Step S4: When the consistency risk warning index exceeds the preset threshold, an intelligent fault-tolerant mechanism is constructed to achieve adaptive error correction and intelligent scheduling of error correction priorities; Step S5: Adaptive optimization is performed by constructing a deep reinforcement learning model, while continuously evaluating the state.

[0024] In this embodiment, step S2 can be implemented through the following steps: The transmission quality assessment model is constructed as follows: Based on the serialized data, the timestamp synchronization error and the maximum allowable synchronization error are obtained; and based on historical data, the number of successful transmissions and the total number of transmissions are obtained; the optimal transmission path is dynamically selected based on the transmission quality index, the mathematical description of which is... ,in, For transmission quality index, Scaling factor (default value 0.1ms) -1 ), used for adjustment right The intensity of the impact, The timestamp synchronization error is in milliseconds. To the maximum permissible synchronization error, Number of successful transmissions The total number of transmissions is calculated. When the transmission quality index is higher than a preset high threshold, the main transmission path is used. When the transmission quality index is lower than a preset low threshold, the system switches to the redundant network and issues an alarm. Otherwise, the backup transmission path is activated. The timestamp synchronization error is obtained as follows: Water treatment serialized data is transmitted to the gas turbine DCS via a dual-path independent optical fiber network to obtain the gas turbine serialized data (the receiver and sender can be interchanged); the transmission delay and average transmission delay of the i-th data point are obtained, and the number of samples is counted (the last 100 data points are taken by default), to obtain the timestamp synchronization error, mathematically described as follows: ,in, The timestamp synchronization error is N, where N is the number of samples. Let i be the transmission delay of the i-th data point. For average transmission delay, These are the weighting coefficients.

[0025] In this embodiment, step S3 can be implemented through the following steps: The construction of the consistency risk early warning model specifically involves: obtaining the consistency risk early warning index through the data consistency probability; identifying potential risks in advance based on the consistency risk early warning index; and achieving two-way verification and risk assessment. The mathematical description of the consistency risk early warning index is... ,in, This is a consistency risk warning index. For data consistency probability, This represents the current verification frequency (times / second). To normalize the parity check frequency, The timestamp synchronization error is in milliseconds. The maximum permissible synchronization error; The data consistency probability is obtained by: obtaining the exponentially weighted sum of successful verifications and the exponentially weighted sum of failed verifications, and obtaining the current system load; the data consistency probability is then obtained, mathematically described as follows: ,in, For success sensitivity coefficient, Failure sensitivity coefficient ( Need to be greater than ), The exponentially weighted sum of the number of successful verifications. The exponentially weighted sum of the number of failed checks. The current system load (%) This represents the maximum allowable load.

[0026] In this embodiment, step S4 can be implemented through the following steps: The construction of the intelligent fault-tolerant mechanism specifically involves: obtaining the error correction threshold, mathematically described as follows: ,in, To ensure error correction thresholds, the unit must be consistent with the data value (e.g., tons, percentages, etc.). The basic fault tolerance threshold should be used, with units consistent with the data values. This represents the number of recent errors. Total number of errors This represents the current average transmission delay. For reference delay; real-time comparison of data deviation with the error correction threshold and adaptive error correction; when the data deviation is less than the error correction threshold, only logging is performed without error correction to avoid unnecessary operations within an acceptable range; when the data deviation is greater than the error correction threshold but less than twice the error correction threshold, mild error correction is initiated to attempt data repair; when the data deviation is greater than or equal to twice the error correction threshold, forced error correction is immediately executed to ensure data consistency; when multiple data points require error correction, an error correction priority evaluation index is obtained, mathematically described as... ,in, As an index for evaluating the priority of error correction, This represents the absolute value of the data deviation. As a key index for data, This is the time interval between the last error correction. As a normalized time constant, error correction tasks are processed in descending order according to the error correction priority evaluation index to ensure that key data is processed first and to achieve intelligent scheduling of the error correction priority.

[0027] In this embodiment, step S5 can be implemented through the following steps: The construction of the deep reinforcement learning model specifically includes: The parity frequency is dynamically adjusted using an adaptive parity frequency formula, mathematically described as follows: ,in, To optimize the verification frequency, Minimum verification frequency, The maximum verification frequency, The attenuation coefficient is... The current system load, For the maximum allowable load, For data consistency probability, The target consistency probability is preset; The status assessment specifically includes: The operational status is comprehensively monitored through a health assessment index, mathematically described as follows: ,in, As a comprehensive health assessment index, , and These are the weighting coefficients. For timestamp synchronization error, To the maximum permissible synchronization error, This is the current verification frequency; Overall performance is evaluated through a system optimization index, mathematically described as follows: ,in, To optimize the index of the system, The standard deviation of the system load is used; when the system optimization index is lower than the preset threshold, multimodal diagnostics are automatically initiated (checking the continuity of the data time series, analyzing the consistency of related data items, etc.).

[0028] Example 2: A consistency assurance system for integrated DCS data of water treatment and gas turbine includes a data acquisition module, a transmission quality assessment module, a risk warning module, an adaptive error correction module, and an adaptive optimization module; The data acquisition module is used to collect water treatment DCS data and gas turbine DCS data, and adds a sequence number and timestamp to each data point (such as water level and temperature). The sequence number is used to track the data order, and the timestamp is used for time sequence alignment to obtain serialized data. ,in, For serial number, For data values, The serialized data, including water treatment serialized data and gas turbine serialized data, serves as a timestamp. This data version sequence prevents data duplication or loss. Example: When the water treatment system collects data showing a "raw water pump station water level" of 50.2 tons, it generates serial number 1001 and a timestamp, thus obtaining the water treatment serialized data. ; The transmission quality assessment module is used to construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path. The risk warning module is used to transmit data based on the optimal transmission path and to build a consistency risk warning model based on the consistency risk warning index. It performs bidirectional verification and risk assessment. In the forward verification, the gas turbine DCS returns an acknowledgment signal containing a hash value. In the reverse verification, the gas turbine periodically requests data snapshots for comparison. The adaptive error correction module is used to achieve adaptive error correction and intelligently schedule error correction priority by constructing an intelligent fault tolerance mechanism when the consistency risk warning index exceeds a preset threshold. The adaptive optimization module is used to perform adaptive optimization by constructing a deep reinforcement learning model, while continuously evaluating the state.

[0029] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for ensuring consistency of integrated data between water treatment and gas turbine DCS, characterized in that, Includes the following steps: Step S1: Collect water treatment DCS data and gas turbine DCS data, and add a sequence number and timestamp to each data point to obtain serialized data, which includes water treatment serialized data and gas turbine serialized data; Step S2: Construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path; Step S3: Transmit data based on the optimal transmission path, and construct a consistency risk warning model based on the consistency risk warning index. Perform bidirectional verification and risk assessment. The construction of the consistency risk warning model specifically involves obtaining the consistency risk warning index through the data consistency probability. The mathematical description of the consistency risk warning index is... ,in, This is a consistency risk warning index. For data consistency probability, This is the current verification frequency. To normalize the parity check frequency, For timestamp synchronization error, To determine the maximum allowable synchronization error, the data consistency probability is obtained by: obtaining the exponentially weighted sum of successful verifications and the exponentially weighted sum of failed verifications, and obtaining the current system load; the data consistency probability is then obtained, mathematically described as follows: ,in, For success sensitivity coefficient, The failure sensitivity coefficient. The exponentially weighted sum of the number of successful verifications. The exponentially weighted sum of the number of failed checks. The current system load, Maximum allowable load; Step S4: When the consistency risk warning index exceeds a preset threshold, an intelligent fault-tolerance mechanism is constructed to achieve adaptive error correction and intelligent scheduling of error correction priorities. The construction of the intelligent fault-tolerance mechanism specifically involves: obtaining the error correction threshold, mathematically described as... ,in, The error correction threshold, Based on the basic fault tolerance threshold, This represents the number of recent errors. Total number of errors This represents the current average transmission delay. As a reference delay; compare the data deviation with the error correction threshold in real time and perform the adaptive error correction; when multiple data points need error correction, obtain the error correction priority evaluation index, mathematically described as... ,in, As an index for evaluating the priority of error correction, This represents the absolute value of the data deviation. As a key index for data, This is the time interval between the last error correction. The time constant is normalized, and the error correction tasks are processed in descending order according to the error correction priority evaluation index. Step S5: Adaptive optimization is performed by constructing a deep reinforcement learning model, while continuously evaluating the state. The construction of the deep reinforcement learning model specifically includes: dynamically adjusting the verification frequency using an adaptive verification frequency formula, mathematically described as follows: ,in, To optimize the verification frequency, Minimum verification frequency, The maximum verification frequency, The attenuation coefficient is... The target consistency probability is preset; the state assessment specifically includes: comprehensively monitoring the operational status through a comprehensive health assessment index, mathematically described as... ,in, As a comprehensive health assessment index, , and These are weighting coefficients; the overall performance is evaluated through a system optimization index, mathematically described as follows: ,in, To optimize the index of the system, The standard deviation of the system load is used; when the system optimization index is lower than the preset threshold, multimodal diagnostics is automatically initiated.

2. The method for ensuring consistency of integrated DCS data for water treatment and gas turbines according to claim 1, characterized in that, The construction of the transmission quality assessment model in step S2 specifically involves: obtaining the timestamp synchronization error and the maximum allowable synchronization error based on the serialized data, and obtaining the number of successful transmissions and the total number of transmissions; The optimal transmission path is dynamically selected based on the transmission quality index, which is mathematically described as follows: ,in, For transmission quality index, This is the scaling factor. For timestamp synchronization error, To the maximum permissible synchronization error, Number of successful transmissions This represents the total number of transmissions.

3. The method for ensuring consistency of integrated DCS data for water treatment and gas turbines according to claim 2, characterized in that, The timestamp synchronization error is obtained by: acquiring the transmission delay and average transmission delay of the i-th data point, and counting the number of samples to obtain the timestamp synchronization error, which is mathematically described as follows: ,in, The timestamp synchronization error is N, where N is the number of samples. Let i be the transmission delay of the i-th data point. For average transmission delay, These are the weighting coefficients.

4. A consistency assurance system for integrated DCS data of water treatment and gas turbine, characterized in that, The system is applied to the consistency assurance method for integrated DCS data of water treatment and gas turbine as described in any one of claims 1-3, including a data acquisition module, a transmission quality assessment module, a risk warning module, an adaptive error correction module, and an adaptive optimization module; The data acquisition module is used to collect water treatment DCS data and gas turbine DCS data, and add a sequence number and timestamp to each data point to obtain serialized data, which includes water treatment serialized data and gas turbine serialized data. The transmission quality assessment module is used to construct a transmission quality assessment model based on the serialized data and dynamically select the optimal transmission path. The risk warning module is used to transmit data based on the optimal transmission path and to construct a consistency risk warning model based on the consistency risk warning index, and to perform bidirectional verification and risk assessment. The construction of the consistency risk warning model specifically involves: obtaining the exponentially weighted sum of the number of successful verifications and the exponentially weighted sum of the number of failed verifications, and obtaining the current system load, thereby obtaining the data consistency probability; and obtaining the consistency risk warning index through the data consistency probability. The adaptive error correction module is used to implement adaptive error correction and intelligently schedule error correction priorities by constructing an intelligent fault tolerance mechanism when the consistency risk warning index exceeds a preset threshold. The construction of the intelligent fault tolerance mechanism specifically includes: obtaining an error correction threshold; comparing the data deviation with the error correction threshold in real time and performing the adaptive error correction; when multiple data points need to be corrected, obtaining an error correction priority evaluation index, and processing the error correction tasks in descending order according to the error correction priority evaluation index. The adaptive optimization module is used to perform adaptive optimization by constructing a deep reinforcement learning model, while continuously evaluating the state. The construction of the deep reinforcement learning model specifically involves dynamically adjusting the verification frequency using an adaptive verification frequency formula. The state evaluation specifically includes: comprehensively monitoring the operating status through a health comprehensive evaluation index; evaluating the overall performance through a system optimization index; and automatically initiating multimodal diagnostics when the system optimization index is lower than a preset threshold.

Images