State monitoring and fault diagnosis method and system for continuous casting equipment

Abstract

The invention discloses a continuous casting equipment state monitoring and fault diagnosis method and system, and relates to the technical field of continuous casting equipment on-line monitoring and fault diagnosis, and the method comprises the steps: collecting vibration data under different working conditions through a server, and obtaining the current, rotating speed and start-stop states from a casting machine primary control system; analyzing the working state of the mechanical equipment according to the start-stop state, and if the mechanical equipment is not in a stable state, ending the monitoring and diagnosis process; performing current and rotating speed coupling compensation on the vibration data under different working conditions; and performing anomaly monitoring on the compensated vibration data, and if an anomaly is detected, calling a corresponding neural network model according to the equipment type, and outputting a fault type and a fault position. According to the invention, in the monitoring and diagnosis process, dependence on hardware computing power can be reduced, and efficient and low-cost equipment state monitoring and fault diagnosis are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of on - line monitoring and fault diagnosis of continuous casting equipment, and particularly relates to a vibration monitoring and deep - learning fault diagnosis system and method for a continuous caster based on motor current and speed compensation. Background Art

[0002] During the continuous casting production process, as a key component, the operating state of the drive equipment directly affects the continuity of continuous casting production and the product quality. During its operation, the drive system will generate complex vibration signals due to changes in load and speed. Traditional on - line monitoring methods based on dimensional vibration characteristic parameters are sensitive to load fluctuations and speed changes, with insufficient stability and accuracy, and it is difficult to accurately and timely detect potential equipment fault hazards.

[0003] At the same time, there are various types of continuous casting equipment, including fan equipment, pump equipment, straightening machine equipment, roller table equipment, etc. The operating characteristics and fault modes of various equipment vary greatly. Using a set of general fault diagnosis models cannot fully consider the uniqueness of different equipment, and it is difficult to ensure the effectiveness and accuracy of fault diagnosis results.

[0004] In addition, existing continuous casting equipment monitoring and diagnosis systems often have too high requirements for the server hardware system, increasing the enterprise's operating costs and maintenance difficulties. In the process of monitoring and diagnosis, if it is possible to reduce the dependence on hardware computing power and achieve efficient and low - cost equipment status monitoring and fault diagnosis, it will have important practical significance. Summary of the Invention

[0005] The embodiments of the present invention provide a method and system for monitoring and diagnosing the state of continuous casting equipment, which can reduce the dependence on hardware computing power during the monitoring and diagnosis process and achieve efficient and low - cost equipment status monitoring and fault diagnosis.

[0006] In the first aspect, the present invention provides a method for monitoring and diagnosing the state of continuous casting equipment, including: Collecting vibration data under different working conditions through a server and obtaining current, speed, and start - stop status from the primary control system of the caster; Analyzing the working state of mechanical equipment according to the start - stop status. If it is not in a stable state, end the current monitoring and diagnosis process; Performing current and speed coupling compensation on the vibration data under different working conditions; Performing abnormal monitoring on the compensated vibration data. If an abnormality is detected, call the corresponding neural network model according to the equipment type and output the fault category and fault location.

[0007] In some instances, from F comp = F raw –αI – βN – γIN Perform current and rotational speed coupling compensation on vibration data under different working conditions, where, F comp is the vibration data after compensation, F raw is the original vibration data, I 、 N are the motor current and rotational speed respectively, introduce the coupling term γIN , α 、 β 、 γ are compensation coefficients.

[0008] In some examples, the method further includes: Display the monitoring and diagnosis results through a human-machine interface, and record the fault data for model optimization.

[0009] In a second aspect, the present invention provides a continuous casting equipment state monitoring and fault diagnosis system, including: A data acquisition module, configured to acquire vibration data under different working conditions through a server and obtain the current, rotational speed, and start-stop status from the casting machine's first-level control system; A working condition screening module, configured to analyze the working state of mechanical equipment according to the start-stop status, and if it is not in a stable state, end the current monitoring and diagnosis process; A signal compensation module, configured to perform current and rotational speed coupling compensation on vibration data under different working conditions; An anomaly detection module, configured to perform anomaly monitoring on the vibration data after compensation; A fault diagnosis module, configured to, when an anomaly is detected, call the corresponding neural network model according to the equipment type and output the fault category and fault location.

[0010] In some examples, from F comp = F raw – αI – βN – γIN Perform current and rotational speed coupling compensation on vibration data under different working conditions, where, F comp is the vibration data after compensation, F raw is the original vibration data, I 、 N are the motor current and rotational speed respectively, introduce the coupling term γIN , α 、 β 、 γ are compensation coefficients.

[0011] In some examples, the system further includes: The status display and data recording module is used to display the monitoring and diagnosis results through the human-machine interface and record the fault data for model optimization.

[0012] Generally speaking, compared with the prior art by the above technical solutions conceived by the present invention, the following beneficial effects can be achieved: The present invention adopts a two-level server centralized processing architecture to uniformly receive vibration signals and operating information such as current and rotational speed in the first-level control system, combines a working condition screening mechanism and a feature correction method based on a compensation model to improve monitoring stability; by constructing a dedicated convolutional neural network model for different equipment types, accurate identification and positioning of faults are realized, ensuring the reliability of the diagnosis effect and the flexibility of deployment. In addition, a hierarchical processing mechanism of "monitoring first and then diagnosing" is adopted to effectively reduce the computing power requirements of the server. Description of the Drawings

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1 It is a schematic flowchart of the continuous casting equipment status monitoring and fault diagnosis method provided by the embodiment of the present invention; Figure 2 It is a schematic structural diagram of the continuous casting equipment status monitoring and fault diagnosis system provided by the embodiment of the present invention. Detailed Embodiments

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0016] In the following description, specific embodiments of the present invention will be described with reference to steps and symbols executed by one or more computers, unless otherwise specified. Therefore, these steps and operations will be referred to as being executed by a computer several times. The computer execution referred to herein includes the operations of a computer processing unit that represents electronic signals in a structured form of data. This operation transforms the data or maintains its position in the computer's memory system, which can reconfigure or otherwise change the operation of the computer in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of the present invention are described in the above text, which does not represent a limitation. Those skilled in the art will understand that the following various steps and operations can also be implemented in hardware.

[0017] As used herein, the term "module" or "unit" can be regarded as a software object executed on the computing system. Different components, modules, engines, and services herein can be regarded as implementation objects on the computing system. The devices and methods herein are preferably implemented in software, but of course can also be implemented in hardware, all within the protection scope of the present invention.

[0018] Those skilled in the art of this technology can understand that, unless specifically stated otherwise, the singular forms "a", "an", and "the" used herein can also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups. It should be understood that when we say an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein can include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit and all combinations of one or more related listed items.

[0019] As Figure 1 shown is a continuous casting equipment status monitoring and fault diagnosis method provided by an embodiment of the present invention, including the following steps: Collect vibration data under different working conditions through a server and obtain current, rotational speed, and start / stop status from the primary control system of the casting machine; Analyze the working status of mechanical equipment according to the start / stop status. If it is not in a stable state, end the current monitoring and diagnosis process; Perform current and rotational speed coupling compensation on the vibration data under different working conditions; Perform anomaly monitoring on the compensated vibration data. If an anomaly is detected, call the corresponding neural network model according to the equipment type and output the fault category and fault location.

[0020] In the embodiment of the present invention, F comp = F raw – αI – βN – γIN Perform current and speed coupling compensation on the vibration data under different working conditions. Among them, F comp is the compensated vibration data, F raw is the original vibration data, I 、 N are the motor current and speed respectively. Introduce the coupling term γIN , α 、 β 、 γ are compensation coefficients.

[0021] In the embodiment of the present invention, the above method further includes: Display the monitoring and diagnosis results through the human-machine interface and record the fault data for model optimization.

[0022] A continuous casting equipment vibration monitoring and fault diagnosis system and method according to an embodiment of the present invention have the following technical features: 1) Working condition screening strategy: Based on the status information of the continuous casting machine's first-level control system (such as shutdown, start-stop status, etc.), screen out the stable working conditions of the driving equipment, and only monitor and analyze the equipment vibration data under this working condition to eliminate the interference of abnormal working conditions and improve the overall monitoring reliability; 2) Vibration feature compensation mechanism: Collect the current and speed information of the drive motor equipment in the continuous casting machine's first-level control system, establish a parametric compensation model based on the influence of both on the vibration signal, and perform real-time dynamic compensation on the traditional dimensional vibration feature parameters, thereby improving the stability and accuracy of on-line monitoring; 3) Multi-model diagnosis system: For different types of drive equipment such as fans, pumps, straightening machines, and roller tables, design and train corresponding convolutional neural network (CNN) fault diagnosis models respectively to ensure the diagnosis accuracy of each equipment type; utilize the highly standardized characteristics of the core equipment of different types of continuous casting machines to achieve model migration and reuse, and reduce the design difficulty of the generalization model; 4) Hierarchical deployment architecture: The monitoring model continuously detects whether the equipment operation status is abnormal. Once an abnormality is detected, a specific diagnosis model is called for fault identification and location, and based on the fault type and location, maintenance suggestions are output; The system only requires one general-purpose secondary server to support the status monitoring and diagnosis of the entire continuous casting machine equipment, reducing the hardware computing power requirements and deployment costs.

[0023] As shown Figure 2 in the following figure is a schematic diagram of a continuous casting equipment status monitoring and fault diagnosis system provided by an embodiment of the present invention, including: Data acquisition module: Collect vibration signals and obtain current, rotational speed, start / stop status from the primary control system of the continuous casting machine; Working condition screening module: Utilize the status signals (shutdown, starting, running) output by the primary system to filter out unstable working conditions such as starting and shutdown, and perform vibration anomaly monitoring only during the stable operation stage; Signal compensation module: Perform current and rotational speed coupling compensation on the characteristic parameters of the original vibration signal (such as RMS, kurtosis, etc.); Abnormality detection module: Based on the compensated vibration characteristic parameters, adopt methods such as threshold determination and trend analysis to achieve real-time abnormality monitoring; Fault diagnosis module: Call the pre-trained device-specific CNN model for fault identification; Model migration module: Perform rapid migration training according to the device type and historical model parameters; Status display and data recording module: Display the monitoring and diagnosis results through a human-machine interface, and record the fault data for model optimization.

[0024] In the embodiment of the present invention, vibration characteristic compensation is performed in the following manner: Construct a parametric compensation model F comp = F raw – αI – βN – γIN Wherein, F comp is the compensated feature, F raw is the original feature, I , N are the motor current and rotational speed respectively, introducing the coupling term γIN , which can further eliminate the interaction effect between the current and rotational speed; α , β , γ are the compensation coefficients obtained by the least squares fitting through the steady-state working condition calibration experiment.

[0025] In the embodiment of the present invention, the equipment status monitoring and fault diagnosis process includes: (1) The server collects vibration data and obtains signals such as current, rotational speed, start-stop status, etc. from the first-level control system of the casting machine; (2) Analyze the working state of the mechanical equipment. If it is not in a stable state, end the current monitoring and diagnosis process; (3) Perform current and rotational speed coupling compensation on the vibration parameter data under different working conditions; (4) Input the compensated vibration parameter data into the monitoring model. If it is determined to be normal, end the current monitoring and diagnosis process; (5) If an anomaly is detected, call the corresponding CNN model according to the equipment type and output the fault category (such as imbalance, bearing wear, abnormal gear meshing, etc.) and location; (6) The system generates a visualization report and saves the vibration data and diagnosis results.

[0026] Through the above technical solutions, the embodiments of the present invention can achieve the following technical effects: 1) By fusing the information of the electrical control system to screen and compensate the vibration data parameters, the robustness and accuracy of anomaly monitoring are effectively improved.

[0027] 2) Adopt a multi-model structure to process different equipment types respectively, which improves the adaptability and reliability of the diagnosis model. At the same time, model migration is realized by means of equipment standardization, enhancing the flexibility of system deployment.

[0028] 3) The design of decoupling monitoring and diagnosis significantly reduces the demand for server computing power, saves costs, and has good engineering implementation capabilities.

[0029] The above has introduced in detail a continuous casting equipment status monitoring and fault diagnosis method and system provided by the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for monitoring the state and diagnosing faults of a continuous casting equipment, characterized in that, including: Collect vibration data under different working conditions through the server and obtain current, rotational speed, start-stop status from the primary control system of the casting machine; Analyze the working status of mechanical equipment according to the start-stop status. If it is not in a stable state, end the current monitoring and diagnosis process; Perform current and rotational speed coupling compensation on the vibration data under different working conditions; Perform abnormal monitoring on the compensated vibration data. If an abnormality is detected, call the corresponding neural network model according to the equipment type and output the fault category and fault location.

2. The method according to claim 1, wherein From F comp = F raw – αI – βN – γIN Perform current and speed coupling compensation on vibration data under different working conditions, where F comp is the vibration data after compensation, F raw is the original vibration data, I 、 N are the motor current and speed respectively, introduce the coupling term γIN , α 、 β 、 γ are compensation coefficients.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Display the monitoring and diagnosis results through a human-machine interface and record the fault data for model optimization.

4. A continuous casting equipment status monitoring and fault diagnosis system, characterized in that, including: A data acquisition module for collecting vibration data under different working conditions through the server and obtaining current, rotational speed, start-stop status from the primary control system of the casting machine; A working condition screening module for analyzing the working status of mechanical equipment according to the start-stop status. If it is not in a stable state, end the current monitoring and diagnosis process; A signal compensation module for performing current and rotational speed coupling compensation on the vibration data under different working conditions; An abnormality detection module for performing abnormal monitoring on the compensated vibration data; A fault diagnosis module for calling the corresponding neural network model according to the equipment type and outputting the fault category and fault location when an abnormality is detected.

5. The system according to claim 4, wherein From F comp = F raw – αI – βN – γIN Perform current and speed coupling compensation on vibration data under different working conditions. Among them, F comp is the vibration data after compensation, F raw is the original vibration data, I 、 N are the motor current and speed respectively. Introduce the coupling term γIN , α 、 β 、 γ are compensation coefficients.

6. The system according to claim 4 or 5, characterized in that, The system further includes: A status display and data recording module for displaying the monitoring and diagnosis results through a human-machine interface and recording the fault data for model optimization.

Images