A method and system for monitoring abnormal behavior of a flow meter

Abstract

The application discloses a kind of flow meter abnormal behavior monitoring method and system, method includes flow meter abnormal state description, preliminary control input, unknown dynamic approximation, adaptive parameter update law, final control input and flow meter abnormal behavior monitoring.The application belongs to the field of data processing, specifically refers to a kind of flow meter abnormal behavior monitoring method and system, the scheme is compensated unknown disturbance by using adaptive switching control gain through preliminary control input design, unknown nonlinear dynamics caused by temperature change and medium fluctuation factor to flow meter are approximated using logic system, to further improve the precision of abnormal monitoring;Adopting online adaptive updating fuzzy approximator parameter, set fusion updating mechanism in combination with fusion coefficient, realize the continuous learning of dynamic characteristics under normal and abnormal state of flow meter;Adaptive dynamic abnormal threshold mechanism is introduced, dynamically adjusts abnormal threshold, avoids false alarm and miss problem caused by fixed threshold.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a flow table abnormal behavior monitoring method and system. BACKGROUND

[0002] The flow table abnormal behavior monitoring method aims to identify and analyze abnormal patterns in flow data to discover potential security threats, system failures or other abnormal situations. However, the general flow table abnormal behavior monitoring method has the problem of slow response speed when an abnormality occurs due to environmental interference or hardware aging, which leads to insufficient or excessive control response and easily causes misjudgment. The general flow table abnormal behavior monitoring method lacks dynamic adaptability and cannot dynamically adjust the monitoring strategy as the flow table changes in different working environments and states, resulting in a slow response when external interference and abnormalities occur. SUMMARY

[0003] In view of the above problems, in order to overcome the defects of the prior art, the present application provides a flow table abnormal behavior monitoring method and system. In view of the problem that the general flow table abnormal behavior monitoring method has slow response speed when an abnormality occurs due to environmental interference or hardware aging, which leads to insufficient or excessive control response and easily causes misjudgment, the present application uses preliminary control input design, uses adaptive switching control gain to compensate for unknown disturbances, ensures smooth convergence of errors, and uses a logic system to approximate unknown nonlinear dynamics of the flow table caused by temperature changes and medium fluctuations, thereby improving the accuracy of abnormal monitoring. In view of the problem that the general flow table abnormal behavior monitoring method lacks dynamic adaptability and cannot dynamically adjust the monitoring strategy as the flow table changes in different working environments and states, resulting in a slow response when external interference and abnormalities occur, the present application uses online adaptive update of fuzzy approximator parameters, sets a fusion update mechanism in combination with a fusion coefficient, and realizes continuous learning of dynamic characteristics of the flow table in normal and abnormal states. An adaptive dynamic abnormal threshold mechanism is introduced to dynamically adjust the abnormal threshold according to the real-time state of the flow table, avoiding false positives and false negatives caused by fixed thresholds.

[0004] The technical solutions adopted by the present application are as follows: The present application provides a flow table abnormal behavior monitoring method, which comprises the following steps:

[0005] Step S1: flow table abnormal state description;

[0006] Step S2: preliminary control input;

[0007] Step S3: unknown dynamic approximation;

[0008] Step S4: adaptive parameter update law;

[0009] Step S5: Final control input;

[0010] Step S6: Flow table abnormal behavior monitoring.

[0011] Further, in step S1, the flow table abnormal state description is defined as tracking error e(t) = x(t) - y(t); where x(t) is the flow signal actually collected by the flow table; t is the sampling time; y(t) is the ideal reference signal; the error between the collected flow data and the reference signal is introduced to two state error components and , respectively taking the error and the error derivative; a sliding mode surface is constructed to describe the comprehensive deviation, expressed as: ; wherein, and are design coefficients.

[0012] Further, in step S2, the preliminary control input is designed as: ; wherein, is a fractional derivative for capturing the memory effect of the flow table; and respectively represent unknown nonlinear parts in the actual dynamic and the reference dynamic of the flow table, x is the flow data; sgn(·) is a sign function, which functions as reaching control; is a switching control gain; set ; is the switching control gain at t-1 sampling; and are gain promotion coefficients and attenuation coefficients, respectively.

[0013] Further, in step S3, the unknown dynamic approximation is to approximate the unknown function using a logic system; the uncertain dynamic of the flow table is represented by a unified parameter vector and , defined as: ; ; wherein, , , and are basis functions constructed by Gaussian membership functions, and are approximations to the actual dynamic of the flow table, and are approximations to the reference signal dynamic, , , and are parameter vectors corresponding to the basis functions; T is the transpose operation.

[0014] Further, in step S4, the adaptive parameter updating law is to update the fuzzy approximator parameters by online adaptive method, and introduce fusion coefficients The fusion updating mechanism is set, and the adaptive updating law is represented as: ; wherein n(x) and n(y) are fuzzy membership functions constructed according to the flow data; and is a positive regulation gain parameter; y is the ideal output of the flow meter under normal working conditions.

[0015] Further, in step S5, the final control input is to generate a smooth switching control signal by using fuzzy rules , and the reaching control part is defined as: ; the equivalent control and the reaching control are combined, and the final control input is represented as: ; wherein is a normalized parameter.

[0016] Further, in step S6, the flow meter abnormal behavior monitoring is to set a basic abnormal threshold in advance , and an adaptive dynamic abnormal threshold is introduced, and is represented as: ; when , it is determined that the flow meter has abnormal behavior, and relevant personnel are warned; wherein is an abnormal threshold at time t; is an adjustment coefficient; TR is the length of a sliding window; is the mean value in the window; is an integral variable.

[0017] The flow meter abnormal behavior monitoring system provided by the application comprises a flow meter abnormal state description module, a preliminary control input module, an unknown dynamic approximation module, an adaptive parameter updating law module, a final control input module and a flow meter abnormal behavior monitoring module.

[0018] The flow meter abnormal state description module describes the abnormal state of the flow meter by comparing the actually collected flow with the ideal reference signal and constructing a sliding mode surface;

[0019] The preliminary control input module designs a preliminary control input by compensating for interference;

[0020] The unknown dynamic approximation module approximates unknown nonlinear dynamics in the flow meter and the reference signal;

[0021] The adaptive parameter updating law module updates the fuzzy approximator parameters by using an adaptive parameter updating law and a fusion coefficient; ​​​

[0022] The final control input module forms a final control input based on a smooth switching control signal;

[0023] The flow table abnormal behavior monitoring module performs flow table abnormal behavior monitoring based on an adaptive dynamic abnormal threshold.

[0024] The above scheme has the following beneficial effects:

[0025] (1) For the general flow table abnormal behavior monitoring method, the response speed is slow when the abnormality occurs due to environmental interference or hardware aging, which leads to insufficient or excessive control response, and easily causes misjudgment. Through the preliminary control input design, the adaptive switching control gain is used to compensate for unknown disturbances, ensuring smooth convergence of errors, and the logic system is used to approximate the unknown nonlinear dynamics of the flow table caused by temperature changes and medium fluctuations, thereby improving the accuracy of abnormal monitoring.

[0026] (2) For the general flow table abnormal behavior monitoring method, it lacks dynamic adaptability and cannot dynamically adjust the monitoring strategy as the flow table changes in different working environments and states, resulting in a slow response when external interference and abnormalities occur. This scheme uses online adaptive updating of fuzzy approximator parameters, sets a fusion update mechanism combined with a fusion coefficient, and realizes continuous learning of the dynamic characteristics of the flow table in normal and abnormal states. An adaptive dynamic abnormal threshold mechanism is introduced to dynamically adjust the abnormal threshold according to the real-time state of the flow table, avoiding false positives and false negatives caused by fixed thresholds. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 A flow chart of a flow table abnormal behavior monitoring method provided by the present application is shown in the figure;

[0028] Figure 2 A schematic diagram of a flow table abnormal behavior monitoring system provided by the present application is shown in the figure.

[0029] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0031] In the description of the present application, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the systems or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0032] Embodiment one, refer to Figure 1 The present application provides a flow table abnormal behavior monitoring method, which comprises the following steps:

[0033] Step S1: flow table abnormal state description; by comparing the actual collected flow with the ideal reference signal, a sliding mode surface is constructed to describe the abnormal state of the flow table;

[0034] Step S2: preliminary control input; the preliminary control input is designed by compensating for the disturbance;

[0035] Step S3: unknown dynamic approximation; the unknown nonlinear dynamics in the flow table and the reference signal are approximated;

[0036] Step S4: adaptive parameter updating law; the fuzzy approximator parameters are updated by the adaptive parameter updating law and the fusion coefficient;

[0037] Step S5: final control input; the final control input is formed based on the smooth switching control signal;

[0038] Step S6: flow table abnormal behavior monitoring; the flow table abnormal behavior monitoring is performed based on the adaptive dynamic abnormal threshold.

[0039] Embodiment two, refer to Figure 1 This embodiment is based on the above-mentioned embodiment, in step S1, the flow table abnormal state description is that the liquid flow data actually collected in the liquid flow table monitoring task is affected by various factors such as sensor error, environmental disturbance and hardware aging, there are unknown nonlinear dynamics and disturbances; define the tracking error e(t) as e(t)= x(t)- y(t); wherein x(t) is the flow signal actually collected by the flow table; t is the sampling time; y(t) is the ideal reference signal, reflecting the expected output of the flow table in the normal state; in order to realize abnormal tracking, the error between the collected flow data and the reference signal is introduced, two state error components and are taken respectively, the error and the derivative of the error; a sliding mode surface is constructed to describe the comprehensive deviation, which is expressed as: ; wherein, and is the design coefficient, which is used to weight the error component so that the sliding mode surface can reflect the abnormal change comprehensively.

[0040] Embodiment three, refer to Figure 1 This embodiment is based on the above embodiment, in step S2, the preliminary control input is used to compensate for the disturbance and ensure the smooth convergence of the error, and the preliminary control input is designed as: ; wherein, is the fractional derivative, which is used to capture the memory effect of the flow table; and respectively represent unknown nonlinear parts in the actual dynamic and reference dynamic of the flow table, and x is the flow data; sgn(·) is the sign function, which is used to reach the control; is the switching control gain; in order to ensure sufficient disturbance compensation, set ; in the flow table abnormality monitoring is used to drive the actuator to adjust the physical output of the liquid flow table; is the switching control gain at t-1 sampling; and are the gain promotion coefficient and the attenuation coefficient respectively.

[0041] Embodiment four, refer to Figure 1 This embodiment is based on the above embodiment, in step S3, the unknown dynamic approximation is used to handle the unknown nonlinear dynamic caused by temperature change and medium fluctuation in the liquid flow table, the unknown function is approximated using a logic system, and the characterization ability of the uncertainty information is enhanced; the unified parameter vector and are used to represent the uncertain dynamic of the liquid flow table, which is defined as: ; ; wherein, , , and are the basis functions constructed by the Gaussian membership function, and are the approximations to the actual dynamic of the liquid flow table, and are the approximations to the reference signal dynamic, , , and are the parameter vectors corresponding to the basis functions; T is the transpose operation.

[0042] By performing the above operation, the general flow table abnormal behavior monitoring method exists due to environmental interference or hardware aging, the response speed is slow when the abnormality occurs, and then the control response is insufficient or excessive, which easily causes misjudgment. Through the preliminary control input design, the adaptive switching control gain is used to compensate for unknown disturbances, ensure smooth convergence of errors, and use a logic system to approximate unknown nonlinear dynamics of the flow table caused by temperature changes and medium fluctuations, thereby improving the accuracy of abnormal monitoring.

[0043] Embodiment five, refer to Figure 1 This embodiment is based on the above embodiment. In step S4, the adaptive parameter updating law is updated by online adaptive updating of the fuzzy approximator parameters, so that the system can continuously learn the dynamic characteristics of the flow table in normal and abnormal states, thereby quickly responding to external disturbances; a fusion coefficient The fusion update mechanism is set to directly update the response quickly, and indirectly capture the uncertainty with the help of the indirect adaptive, to ensure that the monitoring task has higher sensitivity; the adaptive updating law is represented as: ; ; wherein n(x) and n(y) are fuzzy membership functions constructed according to flow data; 、 、 and are positive regulation gain parameters; y is the ideal output of the flow table under normal working conditions.

[0044] Embodiment six, refer to Figure 1 This embodiment is based on the above embodiment. In step S5, the final control input is to quickly correct the liquid flow table output in the abnormal state, while avoiding the chattering problem caused by the sign function, and a smooth switching control signal is generated using fuzzy rules The arrival control part is defined as: ; the equivalent control and the arrival control are combined, and the final control input is represented as: ; wherein is a normalized parameter.

[0045] Embodiment seven, refer to Figure 1 This embodiment is based on the above embodiment. In step S6, the flow table abnormal behavior monitoring is pre-set based on the abnormal threshold An adaptive dynamic abnormal threshold is introduced, represented as: ; when , it is determined that the liquid flow table has abnormal behavior, and relevant personnel are warned; wherein is the abnormal threshold at time t; is an adjustment coefficient; TR is the sliding window length; is the mean value in the window; is an integral variable.

[0046] By performing the above operation, the general flow table abnormal behavior monitoring method lacks dynamic adaptation capability and cannot dynamically adjust the monitoring strategy as the flow table changes in different working environments and states, resulting in the problem of delayed response when external interference and abnormalities occur. The present scheme uses online adaptive updating of fuzzy approximator parameters, sets a fusion updating mechanism in combination with a fusion coefficient, and realizes continuous learning of the dynamic characteristics of the flow table in normal and abnormal states. An adaptive dynamic abnormal threshold mechanism is introduced to dynamically adjust the abnormal threshold according to the real-time state of the flow table, avoiding false positives and false negatives caused by fixed thresholds.

[0047] Embodiment eight, refer to Figure 2 This embodiment is based on the above-mentioned embodiments, and the present application provides a flow table abnormal behavior monitoring system, which comprises a flow table abnormal state description module, a preliminary control input module, an unknown dynamic approximation module, an adaptive parameter updating law module, a final control input module and a flow table abnormal behavior monitoring module.

[0048] The flow table abnormal state description module describes the abnormal state of the flow table by comparing the actual collected flow with the ideal reference signal to construct a sliding mode surface.

[0049] The preliminary control input module designs a preliminary control input by compensating for interference.

[0050] The unknown dynamic approximation module approximates the unknown nonlinear dynamics in the flow table and the reference signal.

[0051] The adaptive parameter updating law module updates the fuzzy approximator parameters through an adaptive parameter updating law and a fusion coefficient.

[0052] The final control input module forms a final control input based on a smooth switching control signal.

[0053] The flow table abnormal behavior monitoring module monitors the flow table abnormal behavior based on an adaptive dynamic abnormal threshold.

[0054] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0055] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary and that changes can be made in the embodiments without departing from the spirit and scope of the application.

[0056] The above description of the application and its embodiments is not restrictive, and the embodiments shown in the drawings are only one of the embodiments of the application, and the actual structure is not limited thereto. In general, if a person skilled in the art is inspired by it, without departing from the purpose of the application, without creative design, similar structure and embodiments of the technical solution should belong to the protection scope of the application.

Claims

1. A flow meter abnormal behavior monitoring method characterized by: The method comprises the following steps: Step S1: flow table abnormal state description; Step S2: preliminary control input; Step S3: unknown dynamic approximation; Step S4: adaptive parameter updating law; Step S5: final control input; Step S6: flow table abnormal behavior monitoring; In step S1, the flowmeter abnormal state description is defined as tracking error e(t) = x(t) - y(t); where x(t) is the flow signal actually collected by the flowmeter; t is the sampling time; y(t) is the ideal reference signal; using the error between the collected flow data and the reference signal, two state error components are introduced and , respectively taking the error and the error derivative; a sliding mode surface is constructed for describing the comprehensive deviation situation, expressed as: ; where, and are design coefficients; In step S2, the preliminary control input is designed as: ; where, is a fractional derivative, used to capture the flow table memory effect; and represent unknown nonlinear parts in the actual dynamics and reference dynamics of the flow table, respectively, and x is the flow data; sgn(·) is a sign function, which functions as an arrival control; is a switching control gain; set ; is the switching control gain at t-1 sampling; and are the gain promotion coefficient and the attenuation coefficient, respectively; In step S3, the unknown dynamic approximation is using a logic system to approximate the unknown function; with a uniform parameter vector and representing the uncertain dynamic of the flow table, defined as: ; ; where, , , and are the basis functions constructed by Gaussian membership functions, and are the approximations to the actual dynamic of the flow table, and are the approximations to the reference signal dynamic, , , and are the parameter vectors corresponding to the basis functions; T is the transpose operation; In step S4, the adaptive parameter updating law is introduced by online adaptive updating the parameters of the fuzzy approximator with fusion coefficients The fusion updating mechanism is set; the adaptive updating law is expressed as: ; ; wherein n(x) and n(y) are fuzzy membership functions constructed according to the flow data; 、 、 and is a positive regulation gain parameter; y is the ideal output of the flow table under normal working conditions; In step S5, the final control input is generated using fuzzy rules to generate a smooth switching control signal , the reaching control part is defined as: ; the final control input is expressed as: ; where, is a normalized parameter; In step S6, the flow table abnormal behavior monitoring is pre-set based on an abnormal threshold , an adaptive dynamic abnormal threshold is introduced, expressed as: ; when , it is determined that the flow table has abnormal behavior, and relevant personnel are warned; wherein, is the abnormal threshold at time t; is an adjustment coefficient; TR is the sliding window length; is the mean value in the window; is the integral variable.

2. A flow meter abnormal behavior monitoring system for implementing a flow meter abnormal behavior monitoring method as claimed in claim 1, characterized by: The method comprises a flow table abnormal state description module, a preliminary control input module, an unknown dynamic approximation module, an adaptive parameter updating law module, a final control input module and a flow table abnormal behavior monitoring module; The flow table abnormal state description module describes the abnormal state of the flow table by constructing a sliding mode surface through comparison of the actual collected flow and the ideal reference signal; The preliminary control input module designs the preliminary control input by compensating for the interference; The unknown dynamic approximation module approximates the unknown nonlinear dynamics in the flow table and the reference signal; The adaptive parameter updating law module updates the fuzzy approximator parameters through the adaptive parameter updating law and the fusion coefficient; The final control input module forms the final control input based on the smooth switching control signal; The flow table abnormal behavior monitoring module performs flow table abnormal behavior monitoring based on the adaptive dynamic abnormal threshold.

Images