Stirrer fault early warning method and system

Abstract

The invention provides a stirrer fault early warning method and system, and belongs to the field of industrial intelligent early warning. The stirrer fault early-warning method comprises the following steps: establishing a stirrer reverse installation early-warning expert sub-model, and judging whether a stirrer to be detected has a reverse installation fault or not by using the stirrer reverse installation early-warning expert sub-model according to first current data during operation of the stirrer to be detected; establishing a stirrer falling early-warning expert sub-model, and judging whether the stirrer to be detected has a blade falling fault or not according to the second current data during operation of the stirrer to be detected by using the stirrer falling early-warning expert sub-model; and establishing a stirrer corrosion early-warning expert sub-model, and judging whether the blade of the stirrer to be detected is corroded or not by utilizing the stirrer corrosion early-warning expert sub-model according to the second current data when the stirrer to be detected operates. According to the invention, the stirrer is pre-warned according to the actual operation data of the stirrer through various expert pre-warning sub-models, and the problem of lagging of fault discovery time in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of industrial intelligent early warning, and in particular to an agitator fault early warning method and an agitator fault early warning system. Background Art

[0002] The desulfurization system agitator plays a vital role in the desulfurization process. It is mainly used for stirring tanks such as absorption tower slurry, limestone slurry, and accident slurry tanks to prevent slurry sedimentation and stir evenly. Common desulfurization agitators include side-entry agitators and top-entry agitators. Side-entry agitators are mainly used for large-volume tanks such as absorption towers and accident slurry tanks, while top-entry agitators are mainly used for small and medium-sized tanks. An absorption tower or accident slurry tank often requires the installation of multiple side-entry agitators, while a top-entry agitator for small and medium-sized tanks generally only needs to be installed on one tank.

[0003] As long as there is slurry in the tank, the agitator cannot be shut down. Once it is shut down, the slurry will settle. In severe cases, it will cause the system to exit unexpectedly. Therefore, when the agitator fails or has potential faults, it needs to be discovered and dealt with in time to avoid further expansion of the fault.

[0004] At present, it is difficult to realize the early warning of the failure of the agitator. The serious deposition of slurry in the tank is often not discovered until it has endangered the normal operation of the system. In order to ensure the normal operation of the agitator, the slurry in the tank is usually drained when the agitator is shut down for maintenance, and the agitator blades are manually checked and the faults are repaired, which leads to the following problems:

[0005] (1) The condition of the blades can only be checked during maintenance, resulting in a time lag in discovering problems.

[0006] (2) Even after on-site inspection, problems such as reverse installation direction failure and output reduction are not easy to detect.

[0007] (3) Some faults are caused by long-term accumulation. For example, the wear of the agitator is very small in a short period of time, and it is not easy for the operator to detect it. It is difficult to draw a conclusion through direct inspection without comparing it with the original state. Summary of the invention

[0008] In order to solve the above technical defects, the present invention provides a stirrer fault warning method and a stirrer fault warning system. The stirrer fault warning method uses multiple types of expert warning sub-models to warn the stirrer of multiple types of faults, thereby improving the width of the warning of the types of stirrer faults. Each type of expert warning sub-model is used to warn a type of fault, thereby improving the accuracy of the warning of this type of fault. The stirrer is warned according to the actual operation data of the stirrer by various types of expert warning sub-models, thereby solving the problem of delayed fault discovery time in the prior art.

[0009] The first aspect of the present invention provides a stirrer fault early warning method, comprising:

[0010] Establish an agitator reverse installation warning expert sub-model, and use the agitator reverse installation warning expert sub-model to determine whether the agitator to be tested has a reverse installation fault according to the first current data of the agitator to be tested during operation. The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the side-entry agitator and issue a warning;

[0011] Establish an agitator shedding warning expert sub-model, and use the agitator shedding warning expert sub-model to determine whether the agitator to be tested has a blade shedding fault according to the second current data when the agitator to be tested is running;

[0012] An agitator corrosion early warning expert sub-model is established, and the agitator corrosion early warning expert sub-model is used to determine whether the blades of the agitator to be tested are corroded according to the third current data when the agitator to be tested is running.

[0013] In the embodiment of the present invention, the establishment of the agitator reverse installation warning expert sub-model includes:

[0014] Determine a first warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the average current deviation value of the side-entry agitator, wherein the first warning rule includes: the average current deviation value is greater than a preset average current deviation value;

[0015] Determine a second warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to a change value of the actual current of the side-entry agitator in a unit time, wherein the second warning rule includes: a change value of the actual current of the side-entry agitator in a unit time is greater than a preset change value of the actual current;

[0016] Determining a third warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the current vibration similarity value of the side-entry agitator, the third warning rule comprising: the current vibration similarity value of the side-entry agitator is greater than a preset current vibration similarity value;

[0017] A side-entry agitator reverse installation warning sub-model is constructed according to the first warning rule, the second warning rule and the third warning rule.

[0018] In an embodiment of the present invention, the agitator reverse installation warning expert sub-model is used to determine whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running, including:

[0019] Obtaining an average current deviation value of the side-entry agitator to be tested, and determining whether the average current deviation value of the side-entry agitator to be tested meets the first warning rule;

[0020] Obtaining a change value of the actual current of the side-entry agitator to be tested within a unit time, and determining whether the change value of the actual current of the side-entry agitator to be tested within a unit time satisfies the second early warning rule;

[0021] Obtaining a current vibration similarity value of the side-entry agitator to be tested, and determining whether the current vibration similarity value of the side-entry agitator to be tested meets a third warning rule;

[0022] When the average current deviation value of the side-entry agitator to be tested meets the first warning rule, the change value of the actual current meets the second warning rule, and the current vibration similarity value meets the third warning rule, it is determined that the side-entry agitator to be tested has a reverse installation fault.

[0023] In the embodiment of the present invention, the establishment of the agitator reverse installation warning expert sub-model includes:

[0024] Determining a fourth warning rule for judging whether a reverse installation fault occurs in the top-entry agitator according to a similarity value of an effective volume curve of the tank where the top-entry agitator is located, wherein the fourth warning rule comprises: the similarity value of the effective volume curve of the tank where the top-entry agitator is located is greater than a preset similarity value of the effective volume curve;

[0025] A reverse installation warning sub-model for top-entry agitators is constructed according to the fourth warning rule.

[0026] In an embodiment of the present invention, the reverse installation warning sub-model of the top-entry agitator is used to determine whether a reverse installation fault occurs in the top-entry agitator to be tested, including:

[0027] Obtaining a similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located, and determining whether the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located satisfies the fourth warning rule;

[0028] When the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located meets the fourth warning rule, it is determined that a reverse installation fault occurs in the top-entry agitator to be tested.

[0029] In the embodiment of the present invention, the agitator fall-off warning expert sub-model includes:

[0030] Determine a fifth warning rule for judging whether a blade-off fault occurs in the stirrer according to the actual current value of the stirrer and the change value of the actual current, wherein the fifth warning rule includes: the actual current value of the stirrer is less than a preset current value and the change value of the actual current of the stirrer is less than a preset change value of the actual current;

[0031] Determining a sixth warning rule for judging whether a blade-off fault occurs in the stirrer according to the current fluctuation value of the stirrer, the sixth warning rule comprising: the current fluctuation of the stirrer is less than a preset current fluctuation value;

[0032] Determine a seventh warning rule for judging whether a blade-off fault occurs in the stirrer according to the similarity value of the actual density current curve of the stirrer, wherein the seventh warning rule includes: the similarity value of the actual density current curve of the stirrer is greater than the similarity value of the preset actual density current curve;

[0033] A stirring and shedding warning expert sub-model is constructed according to the fifth warning rule, the sixth warning rule and the seventh warning rule.

[0034] In an embodiment of the present invention, the agitator fall-off warning expert sub-model is used to determine whether the agitator under test has a blade fall-off fault according to the second current data when the agitator under test is running, including:

[0035] Obtaining the actual current value and the change value of the actual current of the stirrer to be tested, and determining whether the actual current value and the change value of the actual current of the stirrer to be tested meet the fifth warning rule;

[0036] Obtaining a current fluctuation value of the stirrer to be tested, and determining whether the current fluctuation value of the stirrer to be tested meets the sixth warning rule;

[0037] When the actual current value of the agitator to be tested and the change value of the actual current meet the fifth warning rule, and the current fluctuation value of the agitator to be tested meets the sixth warning rule, the actual density current curve of the agitator to be tested is obtained, and it is determined whether the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule. If the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule, it is determined that a blade detachment failure has occurred in the agitator to be tested.

[0038] In an embodiment of the present invention, the establishment of an agitator corrosion early warning expert sub-model includes:

[0039] Determining an eighth warning rule for judging whether the stirrer is corroded according to a similarity value between an actual current curve of the stirrer and a standard current curve, wherein the eighth warning rule includes: a similarity value of the actual current curve of the stirrer is greater than a similarity value of a preset actual current curve;

[0040] Constructing agitator corrosion early warning expert sub-model according to the eighth early warning rule;

[0041] In an embodiment of the present invention, the method of using the agitator corrosion early warning expert sub-model to determine whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running includes:

[0042] Obtaining a similarity value between an actual current curve of the stirrer to be tested and a standard current curve, and determining whether the similarity value between the actual current curve of the stirrer to be tested and the standard current curve satisfies the eighth early warning rule;

[0043] When the similarity value between the actual current curve of the agitator to be tested and the standard current curve meets the eighth early warning rule, it is determined that the agitator to be tested is corroded.

[0044] A second aspect of the present invention provides a stirrer fault early warning system, comprising: a model building module and a hybrid expert model;

[0045] The model building module is used to establish an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model; wherein the agitator reverse installation warning expert sub-model includes: a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model;

[0046] The hybrid expert model includes: an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model;

[0047] The agitator reverse installation warning expert sub-model determines whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running;

[0048] The agitator fall-off warning expert sub-model is used to determine whether the agitator to be tested has a blade fall-off fault according to the second current data when the agitator to be tested is running;

[0049] The agitator corrosion early warning expert sub-model is used to determine whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running;

[0050] The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the side-entry agitator and issue a warning.

[0051] The agitator fault early warning method uses multiple types of expert early warning sub-models to warn the agitator of multiple types of faults, thereby increasing the breadth of early warnings for agitator fault types, and uses each type of expert early warning sub-model to warn a type of fault, thereby increasing the accuracy of early warnings for that type of fault. Using various types of expert early warning sub-models to warn the agitator based on actual operating data of the agitator solves the problem of time lag in discovering faults in the prior art.

[0052] Other features and advantages of the technical solution of the present invention will be described in detail in the specific implementation section below. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0054] Figure 1 is a flow chart of a stirrer fault early warning method provided by an embodiment of the present invention;

[0055] Figure 2 It is a structural schematic diagram of the agitator fault warning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the technical solutions and advantages of the embodiments of the present invention more clearly understood, the exemplary embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0057] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0058] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0059] In the present invention, unless otherwise clearly specified and limited, the terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] In the process of realizing the present invention, the inventors found that the agitator of the desulfurization system plays a vital role in the desulfurization process. It is mainly used for stirring tanks such as absorption tower slurry, limestone slurry, and accident slurry tanks, and plays a role in preventing slurry sedimentation and uniform stirring. Common desulfurization agitators include side-entry agitators and top-entry agitators. Side-entry agitators are mainly used for super-large-volume tanks such as absorption towers and accident slurry tanks, and top-entry agitators are mainly used for small and medium-sized tanks. An absorption tower or an accident slurry tank often needs to be installed with multiple side-entry agitators, and a top-entry agitator for small and medium-sized tanks generally only needs to be installed in one tank. As long as there is slurry in the tank, the agitator cannot be shut down. Once it is shut down, slurry sedimentation will occur. In severe cases, the system will exit due to an accident. Therefore, when the agitator fails or has potential faults, it needs to be discovered and handled in time to avoid further expansion of the fault. At present, it is difficult to achieve early warning of agitator failures. Often, the serious deposition of slurry in the tank is not discovered until it has endangered the normal operation of the system. In order to ensure the normal operation of the agitator, the slurry in the tank can usually only be emptied when the system is shut down for maintenance, and manual inspection of the agitator blades and repair of faults can be carried out, which leads to the following problems: (1) The blade status can only be checked during maintenance, resulting in a time lag in the discovery of problems. (2) Even after on-site inspection, problems such as reverse installation direction failure and reduced output are not easy to detect. (3) Some faults are caused by long-term accumulation. For example, agitator wear. In a short period of time, the agitator wear changes very little and is not easy for operators to detect. It is also difficult to draw conclusions through direct inspection methods without comparing with the original status.

[0061] Compared with the main boiler turbine system of a power plant, the desulfurization system has its own characteristics. The desulfurization system itself is a chemical process based on acid-base reaction. Specifically, there are two main characteristics. First, the reaction medium of the entire system is almost all slurry, and second, the slurry is either acidic or alkaline. The reaction medium is slurry, so if the stirring is continuous or the stirring output is insufficient, the slurry will be deposited, which will block the pipeline and eventually cause the entire system to fail to operate. The pH value of the slurry in the absorption tower or the accident slurry tank is between 4-5. Long-term operation will cause corrosion to the equipment. In severe cases, it will cause the blades to become smaller and the output to decrease. The characteristics of the failure are different depending on the type and installation location of the agitator, so it is necessary to establish expert models for different types of early warnings for different situations.

[0062] In response to the above problems, an embodiment of the present invention provides a method for warning faults of an agitator, including: establishing an expert sub-model for warning of reverse installation of an agitator, using the expert sub-model for warning of reverse installation of an agitator to determine whether a reverse installation fault occurs in the agitator to be tested according to first current data when the agitator to be tested is running, the expert sub-model for warning of reverse installation of an agitator to be tested includes a reverse installation warning sub-model for a top-entry agitator and a reverse installation warning sub-model for a side-entry agitator, the reverse installation warning sub-model for a top-entry agitator is used to determine the reverse installation fault of a top-entry agitator and issue a warning, and the reverse installation warning sub-model for a side-entry agitator is used to determine the reverse installation fault of a side-entry agitator and issue a warning; establishing an expert sub-model for warning of agitator falling off, using the expert sub-model for warning of agitator falling off to determine whether a blade falling fault occurs in the agitator to be tested according to second current data when the agitator to be tested is running; establishing an expert sub-model for warning of agitator corrosion, using the expert sub-model for warning of agitator corrosion to determine whether the blades of the agitator to be tested are corroded according to third current data when the agitator to be tested is running. The agitator fault early warning method uses multiple types of expert early warning sub-models to warn the agitator of multiple types of faults, thereby increasing the breadth of early warnings for agitator fault types, and uses each type of expert early warning sub-model to warn a type of fault, thereby increasing the accuracy of early warnings for that type of fault. Using various types of expert early warning sub-models to warn the agitator based on actual operating data of the agitator solves the problem of time lag in discovering faults in the prior art.

[0063] Figure 1 FIG. 1 is a flow chart of a method for early warning of agitator failure provided by an embodiment of the present invention. Figure 1 As shown, the stirrer fault early warning method provided in this embodiment includes the following steps:

[0064] Establish an agitator reverse installation warning expert sub-model, and use the agitator reverse installation warning expert sub-model to determine whether the agitator to be tested has a reverse installation fault according to the first current data of the agitator to be tested during operation. The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the side-entry agitator and issue a warning;

[0065] Establish an agitator shedding warning expert sub-model, and use the agitator shedding warning expert sub-model to determine whether the agitator to be tested has a blade shedding fault according to the second current data when the agitator to be tested is running;

[0066] An agitator corrosion early warning expert sub-model is established, and the agitator corrosion early warning expert sub-model is used to determine whether the blades of the agitator to be tested are corroded according to the third current data when the agitator to be tested is running.

[0067] The side-entry agitator is installed on the side wall of the absorption tower or the accident slurry tank, and has a certain inclination angle with the tower wall. The shape of the agitator blades is designed according to the stirring area. It is not easy to intuitively judge whether it is forward or reverse from the appearance. If it is not installed seriously according to the operating instructions provided by the manufacturer, it is possible that the blades are installed upside down. After the blades are installed upside down, there is no obvious problem in operation. It is often shut down for maintenance after one year of operation. Further analysis shows that a large amount of sediment is found in the absorption tower or the accident slurry tank. It is found that the agitator is installed upside down. For side-entry agitators, multiple side-entry agitators of the same power and type will be installed at the same height. Often, several of them are installed upside down at the same time, which also increases the difficulty of finding problems. If the side-entry agitator is installed upside down, its operating current will be higher than normal, and the vibration will be larger. The vibration will cause short-term violent current fluctuations. Since the current of the agitator is closely related to the density of the slurry. Therefore, in this embodiment, the establishment of the agitator reverse installation warning expert sub-model includes:

[0068] Determine a first warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to an average current deviation value of the side-entry agitator;

[0069] Determine a second warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to a change value of the actual current of the side-entry agitator within a unit time;

[0070] Determining a third early warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the current vibration similarity value of the side-entry agitator;

[0071] A side-entry agitator reverse installation warning sub-model is constructed according to the first warning rule, the second warning rule and the third warning rule.

[0072] Specifically, in this embodiment, the first warning rule for determining whether the side-entry agitator has a reverse installation fault is: the average current deviation value of the side-entry agitator is greater than a preset average current deviation value. More specifically, the preset average current deviation value is 2A.

[0073] The second early warning rule for whether the side-entry agitator has a reverse installation fault is: the change value of the actual current of the side-entry agitator in a unit time is greater than the change value of the preset actual current. More specifically, the change value of the preset actual current in a unit time is that the actual current decreases by 20% of the rated current within a unit time of 5s.

[0074] The third early warning rule for determining whether a side-entry agitator has a reverse installation fault is: a current vibration similarity value of the side-entry agitator is greater than a preset current vibration similarity value.

[0075] In this embodiment, the agitator reverse installation warning expert sub-model is used to determine whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running, including:

[0076] Obtaining an average current deviation value of the side-entry agitator to be tested, and determining whether the average current deviation value of the side-entry agitator to be tested meets the first warning rule;

[0077] Obtaining a change value of the actual current of the side-entry agitator to be tested within a unit time, and determining whether the change value of the actual current of the side-entry agitator to be tested within a unit time satisfies the second early warning rule;

[0078] Obtaining a current vibration similarity value of the side-entry agitator to be tested, and determining whether the current vibration similarity value of the side-entry agitator to be tested meets a third warning rule;

[0079] When the average current deviation value of the side-entry agitator to be tested meets the first warning rule, the change value of the actual current meets the second warning rule, and the current vibration similarity value meets the third warning rule, it is determined that the side-entry agitator to be tested has a reverse installation fault.

[0080] Furthermore, the average current deviation value is calculated as follows:

[0081] Obtain the historical operating data of a side-entry agitator of the same type and power as the side-entry agitator to be tested and which has a reverse installation fault, and obtain the standard density-current curve of the side-entry agitator of the same type and power as the side-entry agitator to be tested and which has a reverse installation fault based on the historical operating data; wherein the historical operating data is: the current data corresponding to different density data, and the standard density-current curve is obtained.

[0082] The real-time current data of the side-entry agitator under different densities are obtained from the DCS system (distributed control system) of the side-entry agitator to be tested, and the actual density-current curve is obtained.

[0083] Calculate the difference between the actual density current curve and the standard density current curve, find the integral of the deviation over the entire curve interval, and then divide by the density to obtain the average current deviation.

[0084] The calculation method of the current vibration similarity value is:

[0085] The current amplitude data and frequency data of the historical operation data of the side-entry agitator of the same type and power as the side-entry agitator to be tested which has a reverse installation fault are obtained to obtain a standard vibration fault characteristic curve.

[0086] The current amplitude data and frequency data of the side-entry agitator to be tested are obtained from the DCS system (distributed control system) of the side-entry agitator to be tested, and an actual vibration fault characteristic curve is obtained;

[0087] The standard vibration fault characteristic curve and the actual vibration fault characteristic curve are compared to obtain the current vibration similarity value.

[0088] The top-entry agitator is installed on the top of the tank, and the blades are connected to the bottom of the tank through a rotating shaft. The slurry is stirred by the rotation of the blades. After the top-entry agitator is installed in reverse, there is no obvious feature from the operating current of the agitator, so it is impossible to judge whether the agitator is reversed from the current itself. After the agitator is installed upside down, the stirring effect is reduced. Long-term operation will cause the slurry to gradually accumulate, and the effective volume in the tank will become smaller and smaller. In this way, the effective volume of the tank can be calculated and monitored for a long time. When the effective volume gradually becomes smaller over time, it can be judged that it is installed in reverse. Therefore, in this embodiment, the establishment of the agitator reverse installation warning expert sub-model includes:

[0089] Determining a fourth warning rule for judging whether a reverse installation fault occurs in the top-entry agitator according to a similarity value of an effective volume curve of the tank where the top-entry agitator is located;

[0090] A reverse installation warning sub-model for top-entry agitators is constructed according to the fourth warning rule.

[0091] Specifically, the fourth warning rule for determining whether a top-entry agitator has a reverse installation failure is: a similarity value of an effective volume curve of a tank in which the top-entry agitator is located is greater than a similarity value of a preset effective volume curve.

[0092] In this embodiment, the reverse installation warning sub-model of the top-entry agitator is used to determine whether a reverse installation fault occurs in the top-entry agitator to be tested, including:

[0093] Obtaining a similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located, and determining whether the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located satisfies the fourth warning rule;

[0094] When the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located meets the fourth warning rule, it is determined that a reverse installation fault occurs in the top-entry agitator to be tested.

[0095] Furthermore, the calculation method of the similarity value of the effective volume curve is:

[0096] Obtain the effective volume in the historical operation data of a top-entry agitator of the same type and power as the top-entry agitator to be tested that has a reverse installation fault, obtain a curve of the change of the effective volume over time, and obtain a standard effective volume curve;

[0097] Obtaining a curve of the effective volume of the top-entry agitator to be tested changing with time from the DCS system of the top-entry agitator to be tested, and obtaining an actual effective volume curve of the top-entry agitator to be tested;

[0098] The standard effective volume curve and the actual effective volume curve are compared to obtain a similarity value of the effective volume curves.

[0099] Furthermore, the effective volume is calculated as:

[0100] The effective volume is automatically calculated based on the slurry tank level and water replenishment. When preparing the slurry, water is added first and then powder. Each time, water can be added from a fixed liquid level (as low as possible) and stopped at a fixed position. In this way, the theoretical water replenishment can be calculated based on the diameter of the tank. In addition, the actual cumulative water replenishment is calculated through the flow meter of the water supply pipeline. The ratio of the actual cumulative water replenishment to the theoretical water replenishment is the effective volume.

[0101] If the agitator is running for a long time, and the equipment is of poor quality or the assembly is unqualified, the blades may fall off, the blades may break off from the root, the reducer output coupling may break, etc., which will cause the agitator to lose its stirring function. Whether the agitator falls off or breaks can be judged by the operating parameter characteristics. Therefore, in this embodiment, the establishment of the agitator fall-off warning expert sub-model includes:

[0102] Determining a fifth warning rule for judging whether a blade falling failure occurs in the stirrer according to the actual current value of the stirrer and the change value of the actual current;

[0103] Determining a sixth warning rule for judging whether a blade falling failure occurs in the stirrer according to the current fluctuation value of the stirrer;

[0104] Determining a seventh early warning rule for judging whether a blade falling failure occurs in the stirrer according to a similarity value of an actual density current curve of the stirrer;

[0105] A stirring and shedding warning expert sub-model is constructed according to the fifth warning rule, the sixth warning rule and the seventh warning rule.

[0106] Specifically, in this embodiment, the fifth warning rule for whether the stirrer has a blade-off fault is: the actual current value of the stirrer is less than the preset current value and the change value of the actual current of the stirrer is less than the preset change value of the actual current or there is no change in the actual current. More specifically, the preset current value is 20% of the operating current value; the preset change value of the actual current is 1% of the operating current value.

[0107] The sixth early warning rule for determining whether the stirrer has a blade-off fault is that the current fluctuation of the stirrer is less than a preset current fluctuation value. More specifically, the preset current fluctuation value is 1% of the operating current value.

[0108] The seventh early warning rule for determining whether a blade-off failure occurs in the agitator is that a similarity value of an actual density-current curve of the agitator is greater than a similarity value of a preset actual density-current curve.

[0109] In this embodiment, the agitator fall-off warning expert sub-model is used to determine whether the agitator under test has a blade fall-off fault according to the second current data when the agitator under test is running, including:

[0110] Obtaining the actual current value and the change value of the actual current of the stirrer to be tested, and determining whether the actual current value and the change value of the actual current of the stirrer to be tested meet the fifth warning rule;

[0111] Obtaining a current fluctuation value of the stirrer to be tested, and determining whether the current fluctuation value of the stirrer to be tested meets the sixth warning rule;

[0112] When the actual current value of the agitator to be tested and the change value of the actual current meet the fifth warning rule, and the current fluctuation value of the agitator to be tested meets the sixth warning rule, the actual density current curve of the agitator to be tested is obtained, and it is determined whether the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule. If the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule, it is determined that a blade detachment failure has occurred in the agitator to be tested.

[0113] Furthermore, the calculation method of the similarity value of the actual density current curve is:

[0114] The current data corresponding to different density data of a stirrer of the same type and power as the stirrer to be tested with a blade falling failure are obtained to obtain a standard density current curve.

[0115] Obtaining the real-time current data of the agitator under different densities from the DCS system (distributed control system) of the agitator to be tested, and obtaining the actual density current curve;

[0116] The standard density current curve and the actual density current curve are compared to obtain a similarity value of the actual density current curve.

[0117] The agitator is arranged in the absorption tower. In extreme cases, the pH value can reach 2. This environment close to strong acid will accelerate the corrosion of the agitator, causing the blades to become smaller and thinner, and the output to gradually decrease. The current is reflected in a gradual decrease rather than a sudden decrease. Therefore, in this embodiment, the establishment of the agitator corrosion early warning expert sub-model includes:

[0118] Determining an eighth early warning rule for judging whether the stirrer is corroded according to a similarity value of an actual current curve of the stirrer;

[0119] The agitator corrosion warning expert sub-model is constructed according to the eighth warning rule.

[0120] Furthermore, the eighth warning rule for determining whether the agitator is corroded is: a similarity value of an actual current curve of the agitator is greater than a similarity value of a preset actual current curve.

[0121] In this embodiment, the agitator corrosion early warning expert sub-model is used to determine whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running, including:

[0122] Obtaining a similarity value between an actual current curve of the stirrer to be tested and a standard current curve, and determining whether the similarity value between the actual current curve of the stirrer to be tested and the standard current curve satisfies the eighth early warning rule;

[0123] When it is determined that the similarity value between the actual current curve of the agitator to be tested and the standard current curve satisfies the eighth early warning rule, it is determined that the agitator to be tested is corroded.

[0124] Furthermore, the calculation method of the similarity value of the actual current curve of the stirrer is:

[0125] Obtain a real-time current variation curve over time from historical operation data of a stirrer of the same type and power as the stirrer to be tested that has been corroded, and obtain a standard current curve;

[0126] Obtain the actual current curve of the agitator under test over time from the DCS system of the agitator under test, and obtain the actual current curve of the agitator under test;

[0127] The standard current curve and the actual current curve are compared to obtain a similarity value of the actual current curve.

[0128] The present invention judges faults according to the density current curve of online current, has a long time span, and is more reliable than manual methods. Manual methods have low efficiency in comparing parameters with a long time span, and the quality of personnel is uneven, so fault characteristics may not be discovered.

[0129] The present invention is more intuitive and reliable in judging faults by calculating the effective volume, while it is difficult to detect changes in the effective volume manually and problems are often not found.

[0130] The present invention uses multiple types of expert early warning sub-models to judge the faults of multiple types of agitators, which is more intelligent, faster and easier to promote.

[0131] The present invention can discover problems in advance without stopping the machine for maintenance, making it easy to arrange time for handling.

[0132] Figure 2 FIG. 1 is a schematic diagram of the structure of the agitator fault warning system provided by an embodiment of the present invention. Figure 2 As shown, this embodiment provides a stirrer fault warning system, including: a model building module and a hybrid expert model;

[0133] The model building module is used to establish an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model; wherein the agitator reverse installation warning expert sub-model includes: a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model.

[0134] Specifically, the model building module is used to establish an agitator reverse installation warning expert sub-model, including:

[0135] Determine a first warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to an average current deviation value of the side-entry agitator;

[0136] Determine a second warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to a change value of the actual current of the side-entry agitator within a unit time;

[0137] Determining a third early warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the current vibration similarity value of the side-entry agitator;

[0138] A side-entry agitator reverse installation warning sub-model is constructed according to the first warning rule, the second warning rule and the third warning rule.

[0139] Specifically, in this embodiment, the first warning rule for determining whether the side-entry agitator has a reverse installation fault is: the average current deviation value of the side-entry agitator is greater than a preset average current deviation value. More specifically, the preset average current deviation value is 2A.

[0140] The second early warning rule for whether the side-entry agitator has a reverse installation fault is: the change value of the actual current of the side-entry agitator in a unit time is greater than the change value of the preset actual current. More specifically, the change value of the preset actual current in a unit time is that the actual current decreases by 20% of the rated current within a unit time of 5s.

[0141] The third early warning rule for determining whether a side-entry agitator has a reverse installation fault is: a current vibration similarity value of the side-entry agitator is greater than a preset current vibration similarity value.

[0142] In this embodiment, the model building module is used to establish an agitator reverse installation warning expert sub-model, including:

[0143] Determining a fourth warning rule for judging whether a reverse installation fault occurs in the top-entry agitator according to a similarity value of an effective volume curve of the tank where the top-entry agitator is located;

[0144] A reverse installation warning sub-model for top-entry agitators is constructed according to the fourth warning rule.

[0145] Specifically, the fourth warning rule for determining whether a top-entry agitator has a reverse installation failure is: a similarity value of an effective volume curve of a tank in which the top-entry agitator is located is greater than a similarity value of a preset effective volume curve.

[0146] In this embodiment, the model building module is used to establish an agitator fall-off warning expert sub-model, including:

[0147] Determining a fifth warning rule for judging whether a blade falling failure occurs in the stirrer according to the actual current value of the stirrer and the change value of the actual current;

[0148] Determining a sixth warning rule for judging whether a blade falling failure occurs in the stirrer according to the current fluctuation value of the stirrer;

[0149] Determining a seventh early warning rule for judging whether a blade falling failure occurs in the stirrer according to a similarity value of an actual density current curve of the stirrer;

[0150] A stirring and shedding warning expert sub-model is constructed according to the fifth warning rule, the sixth warning rule and the seventh warning rule.

[0151] Specifically, in this embodiment, the fifth warning rule for whether the stirrer has a blade-off fault is: the actual current value of the stirrer is less than the preset current value and the change value of the actual current of the stirrer is less than the preset change value of the actual current or there is no change in the actual current. More specifically, the preset current value is 20% of the operating current value; the preset change value of the actual current is 1% of the operating current value.

[0152] The sixth early warning rule for determining whether the stirrer has a blade-off fault is that the current fluctuation of the stirrer is less than a preset current fluctuation value. More specifically, the preset current fluctuation value is 1% of the operating current value.

[0153] The seventh early warning rule for determining whether a blade-off failure occurs in the agitator is that a similarity value of an actual density-current curve of the agitator is greater than a similarity value of a preset actual density-current curve.

[0154] In this embodiment, the model building module is used to establish an agitator corrosion early warning expert sub-model, including:

[0155] Determining an eighth early warning rule for judging whether the stirrer is corroded according to a similarity value between an actual current curve of the stirrer and a standard current curve;

[0156] The agitator corrosion warning expert sub-model is constructed according to the eighth warning rule.

[0157] Furthermore, the eighth warning rule for determining whether the agitator is corroded is: a similarity value of an actual current curve of the agitator is greater than a similarity value of a preset actual current curve.

[0158] The hybrid expert model includes: an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model;

[0159] The agitator reverse installation warning expert sub-model determines whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running;

[0160] The agitator fall-off warning expert sub-model is used to determine whether the agitator to be tested has a blade fall-off fault according to the second current data when the agitator to be tested is running;

[0161] The agitator corrosion early warning expert sub-model is used to determine whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running;

[0162] The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the side-entry agitator and issue a warning.

[0163] The hybrid expert model includes: a top-entry agitator reverse installation warning sub-model, a side-entry agitator reverse installation warning sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model;

[0164] The top-entry agitator reverse installation warning expert sub-model is used to determine whether the top-entry agitator to be tested has a reverse installation fault according to the actual operation data of the top-entry agitator to be tested;

[0165] The side-entry agitator reverse installation warning expert sub-model is used to determine whether the side-entry agitator to be tested has a reverse installation fault according to the actual operation data of the side-entry agitator to be tested;

[0166] The agitator fall-off warning expert sub-model is used to determine whether the agitator under test has a blade fall-off fault according to the actual operation data of the agitator under test;

[0167] The agitator corrosion early warning expert sub-model is used to determine whether the agitator to be tested is corroded according to the actual operation data of the agitator to be tested.

[0168] In this embodiment, the side-entry agitator reverse installation warning expert sub-model determines whether the side-entry agitator to be tested has a reverse installation fault according to the first current data when the side-entry agitator to be tested is running, including:

[0169] Obtaining an average current deviation value of the side-entry agitator to be tested, and determining whether the average current deviation value of the side-entry agitator to be tested meets the first warning rule;

[0170] Obtaining a change value of the actual current of the side-entry agitator to be tested within a unit time, and determining whether the change value of the actual current of the side-entry agitator to be tested within a unit time satisfies the second early warning rule;

[0171] Obtaining a current vibration similarity value of the side-entry agitator to be tested, and determining whether the current vibration similarity value of the side-entry agitator to be tested meets a third warning rule;

[0172] When the average current deviation value of the side-entry agitator to be tested meets the first warning rule, the change value of the actual current meets the second warning rule, and the current vibration similarity value meets the third warning rule, it is determined that the side-entry agitator to be tested has a reverse installation fault.

[0173] Furthermore, the average current deviation value is calculated as follows:

[0174] Obtain the historical operating data of a side-entry agitator of the same type and power as the side-entry agitator to be tested and which has a reverse installation fault, and obtain the standard density-current curve of the side-entry agitator of the same type and power as the side-entry agitator to be tested and which has a reverse installation fault based on the historical operating data; wherein the historical operating data is: the current data corresponding to different density data, and the standard density-current curve is obtained.

[0175] The real-time current data of the side-entry agitator under different densities are obtained from the DCS system (distributed control system) of the side-entry agitator to be tested, and the actual density-current curve is obtained.

[0176] Calculate the difference between the actual density current curve and the standard density current curve, find the integral of the deviation over the entire curve interval, and then divide by the density to obtain the average current deviation.

[0177] The calculation method of the current vibration similarity value is:

[0178] The current amplitude data and frequency data of the historical operation data of the side-entry agitator of the same type and power as the side-entry agitator to be tested which has a reverse installation fault are obtained to obtain a standard vibration fault characteristic curve.

[0179] The current amplitude data and frequency data of the side-entry agitator to be tested are obtained from the DCS system (distributed control system) of the side-entry agitator to be tested, and an actual vibration fault characteristic curve is obtained;

[0180] The standard vibration fault characteristic curve and the actual vibration fault characteristic curve are compared to obtain the current vibration similarity value.

[0181] In this embodiment, the top-entry agitator reverse installation warning expert sub-model determines whether the top-entry agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running, including:

[0182] Obtaining a similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located, and determining whether the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located satisfies the fourth warning rule;

[0183] When the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located meets the fourth warning rule, it is determined that a reverse installation fault occurs in the top-entry agitator to be tested.

[0184] Furthermore, the calculation method of the similarity value of the effective volume curve is:

[0185] Obtain the effective volume in the historical operation data of a top-entry agitator of the same type and power as the top-entry agitator to be tested that has a reverse installation fault, obtain a curve of the change of the effective volume over time, and obtain a standard effective volume curve;

[0186] Obtaining a curve of the effective volume of the top-entry agitator to be tested changing with time from the DCS system of the top-entry agitator to be tested, and obtaining an actual effective volume curve of the top-entry agitator to be tested;

[0187] The standard effective volume curve and the actual effective volume curve are compared to obtain a similarity value of the effective volume curves.

[0188] Furthermore, the effective volume is calculated as:

[0189] The effective volume is automatically calculated based on the slurry tank level and water replenishment. When preparing the slurry, water is added first and then powder. Each time, water can be added from a fixed liquid level (as low as possible) and stopped at a fixed position. In this way, the theoretical water replenishment can be calculated based on the diameter of the tank. In addition, the actual cumulative water replenishment is calculated through the flow meter of the water supply pipeline. The ratio of the actual cumulative water replenishment to the theoretical water replenishment is the effective volume.

[0190] In this embodiment, the agitator fall-off warning expert sub-model determines whether the agitator to be tested has a blade fall-off fault according to the second current data when the agitator to be tested is running, including:

[0191] Obtaining the actual current value and the change value of the actual current of the stirrer to be tested, and determining whether the actual current value and the change value of the actual current of the stirrer to be tested meet the fifth warning rule;

[0192] Obtaining a current fluctuation value of the stirrer to be tested, and determining whether the current fluctuation value of the stirrer to be tested meets the sixth warning rule;

[0193] When the actual current value of the agitator to be tested and the change value of the actual current meet the fifth warning rule, and the current fluctuation value of the agitator to be tested meets the sixth warning rule, the actual density current curve of the agitator to be tested is obtained, and it is determined whether the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule. If the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule, it is determined that a blade detachment failure has occurred in the agitator to be tested.

[0194] Furthermore, the calculation method of the similarity value of the actual density current curve is:

[0195] The current data corresponding to different density data of a stirrer of the same type and power as the stirrer to be tested with a blade falling failure are obtained to obtain a standard density current curve.

[0196] Obtaining the real-time current data of the agitator under different densities from the DCS system (distributed control system) of the agitator to be tested, and obtaining the actual density current curve;

[0197] The standard density current curve and the actual density current curve are compared to obtain a similarity value of the actual density current curve.

[0198] In this embodiment, the agitator corrosion early warning expert sub-model determines whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running, including:

[0199] Obtaining a similarity value between an actual current curve of the stirrer to be tested and a standard current curve, and determining whether the similarity value between the actual current curve of the stirrer to be tested and the standard current curve satisfies the eighth early warning rule;

[0200] When it is determined that the similarity value between the actual current curve of the agitator to be tested and the standard current curve satisfies the eighth early warning rule, it is determined that the agitator to be tested is corroded.

[0201] Furthermore, the calculation method of the similarity value of the actual current curve of the stirrer is:

[0202] Obtain a real-time current variation curve over time from historical operation data of a stirrer of the same type and power as the stirrer to be tested that has been corroded, and obtain a standard current curve;

[0203] Obtain the actual current curve of the agitator under test over time from the DCS system of the agitator under test, and obtain the actual current curve of the agitator under test;

[0204] The standard current curve and the actual current curve are compared to obtain a similarity value of the actual current curve.

[0205] An embodiment of the present invention further provides a computer device, comprising: a memory, a processor, and a computer program, wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the above-mentioned agitator fault early warning method.

[0206] The embodiment of the present invention further provides a machine-readable storage medium having computer program instructions stored thereon, and the computer program instructions, when executed by a processor, implement the above-mentioned stirrer fault early warning method.

[0207] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0208] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0209] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0211] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0212] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A stirrer fault early warning method, characterized in that: include: Establish an agitator reverse installation warning expert sub-model, and use the agitator reverse installation warning expert sub-model to determine whether the agitator to be tested has a reverse installation fault according to the first current data of the agitator to be tested during operation. The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation fault of the side-entry agitator and issue a warning; Establish an agitator shedding warning expert sub-model, and use the agitator shedding warning expert sub-model to determine whether the agitator to be tested has a blade shedding fault according to the second current data when the agitator to be tested is running; An agitator corrosion early warning expert sub-model is established, and the agitator corrosion early warning expert sub-model is used to determine whether the blades of the agitator to be tested are corroded according to the third current data when the agitator to be tested is running.

2. The stirrer failure early warning method according to claim 1, characterized in that: The establishment of the agitator reverse installation early warning expert sub-model comprises: Determine a first warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the average current deviation value of the side-entry agitator, wherein the first warning rule includes: the average current deviation value is greater than a preset average current deviation value; Determine a second warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to a change value of the actual current of the side-entry agitator in a unit time, wherein the second warning rule includes: a change value of the actual current of the side-entry agitator in a unit time is greater than a preset change value of the actual current; Determining a third warning rule for judging whether a reverse installation fault occurs in the side-entry agitator according to the current vibration similarity value of the side-entry agitator, the third warning rule comprising: the current vibration similarity value of the side-entry agitator is greater than a preset current vibration similarity value; A side-entry agitator reverse installation warning sub-model is constructed according to the first warning rule, the second warning rule and the third warning rule.

3. The stirrer failure early warning method according to claim 2, characterized in that: The agitator reverse installation warning expert sub-model is used to determine whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running, including: Obtaining an average current deviation value of the side-entry agitator to be tested, and determining whether the average current deviation value of the side-entry agitator to be tested meets the first warning rule; Obtaining a change value of the actual current of the side-entry agitator to be tested within a unit time, and determining whether the change value of the actual current of the side-entry agitator to be tested within a unit time satisfies the second early warning rule; Obtaining a current vibration similarity value of the side-entry agitator to be tested, and determining whether the current vibration similarity value of the side-entry agitator to be tested meets a third warning rule; When the average current deviation value of the side-entry agitator to be tested meets the first warning rule, the change value of the actual current meets the second warning rule, and the current vibration similarity value meets the third warning rule, it is determined that the side-entry agitator to be tested has a reverse installation fault.

4. The stirrer failure early warning method according to claim 1, characterized in that: The establishment of the agitator reverse installation early warning expert sub-model comprises: Determining a fourth warning rule for judging whether a reverse installation fault occurs in the top-entry agitator according to a similarity value of an effective volume curve of the tank where the top-entry agitator is located, wherein the fourth warning rule comprises: the similarity value of the effective volume curve of the tank where the top-entry agitator is located is greater than a preset similarity value of the effective volume curve; A reverse installation warning sub-model for top-entry agitators is constructed according to the fourth warning rule.

5. The stirrer failure early warning method according to claim 4, characterized in that: Using the top-entry agitator reverse installation warning sub-model to determine whether the top-entry agitator to be tested has a reverse installation fault includes: Obtaining a similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located, and determining whether the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located satisfies the fourth warning rule; When the similarity value of the effective volume curve of the tank where the top-entry agitator to be tested is located meets the fourth warning rule, it is determined that a reverse installation fault occurs in the top-entry agitator to be tested.

6. The stirrer failure early warning method according to claim 1, characterized in that: The agitator fall-off warning expert sub-model includes: Determine a fifth warning rule for judging whether a blade-off fault occurs in the stirrer according to the actual current value of the stirrer and the change value of the actual current, wherein the fifth warning rule includes: the actual current value of the stirrer is less than a preset current value and the change value of the actual current of the stirrer is less than a preset change value of the actual current; Determining a sixth warning rule for judging whether a blade-off fault occurs in the stirrer according to the current fluctuation value of the stirrer, the sixth warning rule comprising: the current fluctuation of the stirrer is less than a preset current fluctuation value; Determine a seventh warning rule for judging whether a blade-off fault occurs in the stirrer according to the similarity value of the actual density current curve of the stirrer, wherein the seventh warning rule includes: the similarity value of the actual density current curve of the stirrer is greater than the similarity value of the preset actual density current curve; A stirring and shedding warning expert sub-model is constructed according to the fifth warning rule, the sixth warning rule and the seventh warning rule.

7. The stirrer failure early warning method according to claim 6, characterized in that: The method of using the agitator fall-off warning expert sub-model to judge whether the agitator to be tested has a blade fall-off fault according to the second current data when the agitator to be tested is running includes: Obtaining the actual current value and the change value of the actual current of the stirrer to be tested, and determining whether the actual current value and the change value of the actual current of the stirrer to be tested meet the fifth warning rule; Obtaining a current fluctuation value of the stirrer to be tested, and determining whether the current fluctuation value of the stirrer to be tested meets the sixth warning rule; When the actual current value of the agitator to be tested and the change value of the actual current meet the fifth warning rule, and the current fluctuation value of the agitator to be tested meets the sixth warning rule, the actual density current curve of the agitator to be tested is obtained, and it is determined whether the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule. If the similarity value of the actual density current curve of the agitator to be tested meets the seventh warning rule, it is determined that a blade detachment failure has occurred in the agitator to be tested.

8. The stirrer failure early warning method according to claim 1, characterized in that: The establishment of the agitator corrosion early warning expert sub-model includes: Determining an eighth warning rule for judging whether the stirrer is corroded according to a similarity value between an actual current curve of the stirrer and a standard current curve, wherein the eighth warning rule includes: a similarity value of the actual current curve of the stirrer is greater than a similarity value of a preset actual current curve; The agitator corrosion warning expert sub-model is constructed according to the eighth warning rule.

9. The stirrer failure early warning method according to claim 8, characterized in that: The method of using the agitator corrosion early warning expert sub-model to judge whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running includes: Obtaining a similarity value between an actual current curve of the stirrer to be tested and a standard current curve, and determining whether the similarity value between the actual current curve of the stirrer to be tested and the standard current curve satisfies the eighth early warning rule; When the similarity value between the actual current curve of the agitator to be tested and the standard current curve meets the eighth early warning rule, it is determined that the agitator to be tested is corroded.

10. A stirrer fault warning system, characterized in that: include: Model building modules and hybrid expert models; The model building module is used to establish an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model; wherein the agitator reverse installation warning expert sub-model includes: a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model; The hybrid expert model includes: an agitator reverse installation warning expert sub-model, an agitator fall-off warning expert sub-model and an agitator corrosion warning expert sub-model; The agitator reverse installation warning expert sub-model determines whether the agitator to be tested has a reverse installation fault according to the first current data when the agitator to be tested is running; The agitator fall-off warning expert sub-model is used to determine whether the agitator to be tested has a blade fall-off fault according to the second current data when the agitator to be tested is running; The agitator corrosion early warning expert sub-model is used to determine whether the agitator to be tested is corroded according to the third current data when the agitator to be tested is running; The agitator reverse installation warning expert sub-model includes a top-entry agitator reverse installation warning sub-model and a side-entry agitator reverse installation warning sub-model. The top-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the top-entry agitator and issue a warning, and the side-entry agitator reverse installation warning sub-model is used to determine the reverse installation failure of the side-entry agitator and issue a warning.

Images