Aluminum electrolysis crown block insulator fault diagnosis method and monitoring system
By constructing a polynomial regression model, combining the insulator state and temperature calibration leakage current, the inconvenience of aluminum electrolytic insulator fault detection is solved, more accurate and real-time fault diagnosis is achieved, and equipment and personal safety is ensured.
Patent Information
- Application Number
- CN202510625533.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-15
- Publication Date
- 2025-08-15
AI Technical Summary
The aluminum electrolytic multi-functional trolley lacks a real-time insulation monitoring system, which leads to large and inconvenient workload of insulation point detection, and failure to detect faults in time, which can easily lead to equipment damage and personal injury.
By constructing a polynomial regression model, combining the insulator state and plant temperature, the total deviation compensation value of leakage current is calculated, the actual measured leakage current is calibrated, the true leakage current value is obtained, and the fault diagnosis results are output with the preset threshold.
It realizes more accurate insulator fault diagnosis, ensures the safe and stable operation of the aluminum electrolytic hoist, reduces fault diagnosis delays, and improves real-time and accuracy.
Smart Images
Figure CN120490709A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of aluminum electrolysis, and in particular to a fault diagnosis method and monitoring system for an aluminum electrolysis overhead crane insulator. Background Art
[0002] Due to its working environment and process requirements, the various parts of the aluminum electrolysis multifunctional overhead crane must undergo multi-level insulation treatment. Otherwise, a short circuit will occur between the high-current DC in the electrolytic cell and the AC power used for operation and control on the overhead crane, causing the control system to burn out and damage the multifunctional overhead crane and the electrolytic cell. At the same time, the short-circuit current will also cause personal injury to the overhead crane operator. Therefore, real-time insulation monitoring between the various parts of the aluminum electrolysis multifunctional overhead crane is very important.
[0003] At present, aluminum electrolysis multifunctional overhead cranes are not equipped with real-time insulation monitoring systems. Instead, in actual operation, maintenance workers have to climb onto the multifunctional overhead cranes to conduct post-inspection of insulation points at all levels of the overhead cranes. This results in heavy workload and inconvenience. On the other hand, since the multifunctional overhead cranes have many insulation points and are widely distributed, and the inspection is performed while the cranes are parked and offline, when an insulation point is damaged and short-circuited, the insulation condition of the point cannot be detected in time. This can easily cause insulation short-circuiting of the aluminum electrolysis multifunctional overhead crane, burning equipment, and endangering the personal safety of the operators. Summary of the Invention
[0004] The purpose of the present invention is to provide an aluminum electrolysis overhead crane insulator fault diagnosis method and monitoring system, which takes into account the influence of the insulator state and plant temperature on the leakage current, constructs a polynomial regression model and calculates the total deviation compensation value of the leakage current, calibrates the measured leakage current, obtains a more realistic leakage current value, and can output the insulator fault diagnosis result more accurately, thereby ensuring the safe and stable operation of the aluminum electrolysis overhead crane, so as to solve the technical problems pointed out in the background technology.
[0005] The present invention is implemented through the following technical solution: a method for diagnosing faults of aluminum electrolytic overhead crane insulators, comprising the following steps:
[0006] Collecting the measured leakage current of the insulator, the insulator image and the plant temperature, and performing image preprocessing on the insulator image;
[0007] Performing feature extraction on the insulator image after image preprocessing to obtain the insulator state;
[0008] Setting a leakage current offset influence weight, constructing a polynomial regression model of the insulator leakage current, the insulator state, and the plant temperature, and calculating a total leakage current deviation compensation value based on the insulator state and the plant temperature;
[0009] Calibrate the measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value;
[0010] The actual leakage current value is compared with a preset leakage current threshold value, and a fault diagnosis result is output.
[0011] According to a preferred embodiment, the insulator state at least includes the degree of contamination and aging of the insulator surface.
[0012] According to a preferred embodiment, the expression of the polynomial regression model is as follows:
[0013]
[0014] In the above formula, ΔI total It represents the total deviation compensation value of leakage current caused by temperature and insulator state, n represents the highest order of temperature polynomial, a m It represents the m-order coefficient of temperature T, reflecting the weight of the nonlinear effect of temperature on leakage current. m It represents the m-order term of temperature T, which is used to describe the nonlinear relationship between temperature and leakage current. p represents the highest order of the insulator state polynomial. b i,k represents the state parameter X of the i-th insulator i The k-order coefficient reflects the weight of the nonlinear effect of the insulator state on the leakage current. Indicates the state parameter X of i insulators i The k-th term, c j,l It represents the cross coefficient between temperature T and the state parameter of the first insulator, reflecting the influence of the interaction between the two on the leakage current. j represents the jth order term of temperature T, Indicates the state parameter X of the lth insulator l The k-th term of .
[0015] According to a preferred embodiment, the measured leakage current of the insulator is calibrated according to the total leakage current deviation compensation value, and the expression of the true leakage current value is obtained as follows:
[0016] I calibrated =I measured +ΔI total
[0017] In the above formula, I calibrated Indicates the actual leakage current value, I measured Indicates the measured leakage current.
[0018] The present invention further provides an aluminum electrolytic overhead crane insulator fault monitoring system, which is applied to the aluminum electrolytic overhead crane insulator fault diagnosis method according to any one of claims 1 to 4, and the system comprises:
[0019] A data acquisition unit configured to collect insulator leakage current, insulator image, and plant temperature;
[0020] an edge computing unit configured to perform image preprocessing on the insulator image, perform feature extraction on the preprocessed insulator image, obtain the insulator state, set a leakage current offset influence weight, construct a polynomial regression model of the insulator leakage current, the insulator state, and the plant temperature, and calculate a total leakage current deviation compensation value based on the insulator state and the plant temperature;
[0021] a data processing unit configured to calibrate the actually measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value, and obtain a fault diagnosis result by comparing the true leakage current value with a preset leakage current threshold;
[0022] The output unit is configured to output the fault diagnosis result.
[0023] According to a preferred embodiment, the data acquisition unit includes a leakage current sensor, an image sensor and a temperature sensor, wherein the leakage current sensor is used to collect the leakage current of the insulator, the image sensor is used to collect the image of the insulator, and the temperature sensor is used to collect the factory temperature corresponding to the insulator.
[0024] According to a preferred embodiment, the system also includes a data transmission unit, which is composed of a sampling network, an amplification network, an isolation network and an A / D conversion module, wherein the data transmission unit is connected to the data acquisition unit, is used to receive data uploaded by the data acquisition unit and transmit the data to the edge computing unit via the amplification network, the signal output end of the edge computing unit is connected to the isolation unit, is used to transmit the signal to the remote A / D conversion module via the isolation unit, and the signal output end of the A / D conversion module is connected to the data processing unit.
[0025] According to a preferred embodiment, the data processing unit is composed of a control chip and a SCADA fault analysis module, wherein the control chip is connected to the SCADA fault analysis module, the signal output end of the SCADA fault analysis module is connected to the output unit, and the SCADA fault analysis module is used to calibrate the measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value, and obtain a fault diagnosis result by comparing the true leakage current value with a preset leakage current threshold.
[0026] According to a preferred embodiment, the system further comprises a real-time monitoring module and a fault alarm module, and the signal input ends of the real-time monitoring module and the fault alarm module are both connected to the output unit.
[0027] According to a preferred embodiment, the system also includes an overhead crane database, and the signal output end of the output unit is connected to the overhead crane database for sending the fault diagnosis results to the overhead crane database for storage. The signal input ends of the real-time monitoring module and the fault alarm module are both connected to the overhead crane database.
[0028] The technical solution of the aluminum electrolytic overhead crane insulator fault diagnosis method and monitoring system provided by the present invention has at least the following advantages and beneficial effects: (1) The present invention takes into account the influence of the insulator state and the plant temperature on the leakage current, and calibrates the measured leakage current by constructing a polynomial regression model and calculating the total deviation compensation value of the leakage current, thereby obtaining a more realistic leakage current value, and can output the insulator fault diagnosis result more accurately, thereby ensuring the safe and stable operation of the aluminum electrolytic overhead crane; (2) For weak leakage current at the milliampere level, the amplification network is used to amplify the leakage current, which can effectively improve the authenticity of the measured leakage current; (3) By calculating the total deviation compensation value of the leakage current on site, the delay can be effectively reduced and the real-time performance of the fault diagnosis can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 A schematic flow chart of a method for diagnosing faults of aluminum electrolytic overhead crane insulators provided in Example 1 of the present invention;
[0030] Figure 2 This is a structural block diagram of the aluminum electrolysis overhead crane insulator fault monitoring system provided in Example 1 of the present invention. DETAILED DESCRIPTION
[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.
[0032] Example 1
[0033] The embodiment of the present invention provides a method for diagnosing faults of aluminum electrolytic overhead crane insulators. Figure 1 As shown, the aluminum electrolytic overhead crane insulator fault diagnosis method can be divided into five steps, from step 1 to step 5, each step is as follows:
[0034] Step 1: Data collection;
[0035] The detection device is used to obtain insulator target information in real time. The target information includes the insulator's measured leakage current, insulator image and plant temperature.
[0036] Step 2: Image processing;
[0037] The insulator image is subjected to image preprocessing, including but not limited to contrast enhancement, noise removal, etc., which are not specifically limited here; further, feature extraction is performed on the insulator image after image preprocessing to obtain the insulator state to quantify the insulator image.
[0038] In some implementations of this embodiment, the insulator state at least includes the degree of contamination and aging of the insulator surface.
[0039] The specific feature extraction process can be selected as follows: for the degree of surface contamination, image segmentation processing can be performed on the insulator image after image preprocessing to segment the contaminated area on the insulator surface; the image segmentation used can consider threshold segmentation, edge detection, etc.; further, the machine learning model performs classification or regression, the extracted contaminated area is input into the model, and the contamination degree value is output; similarly, the degree of aging is manifested as surface cracks, discoloration, wear, etc. For crack detection, edge detection algorithm can be used, for discoloration detection, the color features of the image can be analyzed, and for wear detection, texture analysis methods such as grayscale co-occurrence matrix can be used to extract texture features, and further cracks, discoloration, wear, etc. are integrated to judge the degree of aging through the classification model to obtain the aging degree value. No further details will be given here.
[0040] Step 3: Calculate compensation value;
[0041] The weight of the leakage current offset influence is set, and a polynomial regression model of the insulator leakage current, the insulator state, and the plant temperature is constructed. In some implementations of this embodiment, the polynomial regression model is expressed as follows:
[0042]
[0043] In the above formula, ΔI total It represents the total deviation compensation value of leakage current caused by temperature and insulator state, n represents the highest order of temperature polynomial, a m It represents the m-order coefficient of temperature T, reflecting the weight of the nonlinear effect of temperature on leakage current. m It represents the m-order term of temperature T, which is used to describe the nonlinear relationship between temperature and leakage current. p represents the highest order of the insulator state polynomial. b i,k represents the state parameter X of the i-th insulator i The k-order coefficient reflects the weight of the nonlinear effect of the insulator state on the leakage current. Indicates the state parameter X of i insulators i The k-th term, c j,l It represents the cross coefficient between temperature T and the state parameter of the first insulator, reflecting the influence of the interaction between the two on the leakage current. jrepresents the jth order term of temperature T, Indicates the state parameter X of the lth insulator l The k-th term of .
[0044] Furthermore, based on the insulator state and the plant temperature, the insulator state and the plant temperature are input into a polynomial regression model to calculate a total deviation compensation value of the leakage current.
[0045] Step 4: Leakage current calibration;
[0046] The actual leakage current of the insulator is calibrated according to the total leakage current deviation compensation value to obtain a true leakage current value.
[0047] In some implementations of this embodiment, the measured leakage current of the insulator is calibrated according to the total leakage current deviation compensation value, and the expression for the true leakage current value is obtained as follows:
[0048] I calibrated =I measured +ΔI total
[0049] In the above formula, I calibrated Indicates the actual leakage current value, I measured Indicates the measured leakage current.
[0050] Step 5: Diagnostic output;
[0051] The actual leakage current value is compared with a preset leakage current threshold value, and a fault diagnosis result is output.
[0052] In some implementations of this embodiment, the fault diagnosis results can be divided into three situations, which respectively indicate: 1) the insulation of the overhead crane is normal and the leakage current is within a safe and negligible range; 2) a warning appears in the insulation of the overhead crane, the leakage current is not negligible, and timely inspection and cleaning are required; 3) the insulation of the overhead crane disappears and a serious insulation failure occurs, and the overhead crane needs to be shut down for inspection and replacement of insulation parts.
[0053] Specifically, the present invention takes into account the influence of the insulator state and plant temperature on the leakage current. By constructing a polynomial regression model and calculating the total deviation compensation value of the leakage current, the measured leakage current is calibrated to obtain a more realistic leakage current value. It can output the insulator fault diagnosis result more accurately and ensure the safe and stable operation of the aluminum electrolysis overhead crane.
[0054] Example 2
[0055] This embodiment provides an aluminum electrolysis overhead crane insulator fault monitoring system based on the technical solution provided in Example 1. The system is applied to the aluminum electrolysis overhead crane insulator fault diagnosis method as described in Example 1. Figure 2As shown, the system includes a data acquisition unit, an edge computing unit, a data processing unit and an output unit.
[0056] Among them, the data acquisition unit is configured to collect the actual leakage current of the insulator, the insulator image and the factory temperature; the edge computing unit is configured to perform image preprocessing on the insulator image, perform feature extraction on the insulator image after image preprocessing, obtain the insulator state, and set the leakage current offset influence weight, construct a polynomial regression model of the insulator leakage current, the insulator state and the factory temperature, and calculate the total leakage current deviation compensation value based on the insulator state and the factory temperature; the data processing unit is configured to calibrate the actual leakage current of the insulator according to the total leakage current deviation compensation value to obtain the true leakage current value, and obtain the fault diagnosis result by comparing the true leakage current value with the preset leakage current threshold; the output unit is configured to output the fault diagnosis result.
[0057] In some embodiments, the data acquisition unit includes a leakage current sensor, an image sensor, and a temperature sensor, wherein the leakage current sensor is used to collect the leakage current of the insulator, the image sensor is used to collect the image of the insulator, and the temperature sensor is used to collect the factory temperature corresponding to the insulator.
[0058] The system also includes a data transmission unit, which is composed of a sampling network, an amplification network, an isolation network, and an A / D conversion module. The data transmission unit is connected to the data acquisition unit and is used to receive data uploaded by the data acquisition unit and transmit the data to the edge computing unit via the amplification network. Specifically, for weak leakage currents at the milliampere level, amplification processing is performed by the amplification network, which can effectively improve the authenticity of the measured leakage current. In addition, by using edge computing, the total deviation compensation value of the leakage current is calculated on-site, which can effectively reduce delays and improve the real-time nature of fault diagnosis. Furthermore, the signal output end of the edge computing unit is connected to the isolation unit, which is used to transmit the signal to the remote A / D conversion module via the isolation unit for analog-to-digital conversion. The signal output end of the A / D conversion module is connected to the data processing unit, which sends the data to the data processing unit for analysis and processing.
[0059] Furthermore, the data processing unit is composed of a control chip and a SCADA fault analysis module, wherein the control chip is connected to the SCADA fault analysis module, the signal output end of the SCADA fault analysis module is connected to the output unit, and the SCADA fault analysis module is used to calibrate the measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value, and obtain a fault diagnosis result by comparing the true leakage current value with a preset leakage current threshold.
[0060] Furthermore, the system also includes a real-time monitoring module, a fault alarm module and an overhead crane database. The signal output end of the output unit is connected to the overhead crane database, and is used to send the fault diagnosis results to the overhead crane database for storage for subsequent historical data analysis; the signal input ends of the real-time monitoring module and the fault alarm module are both connected to the overhead crane database.
[0061] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.
Claims
1. A method for diagnosing faults of aluminum electrolytic overhead crane insulators, characterized in that: The steps include: Collecting the measured leakage current of the insulator, the insulator image and the plant temperature, and performing image preprocessing on the insulator image; Performing feature extraction on the insulator image after image preprocessing to obtain the insulator state; Setting a leakage current offset influence weight, constructing a polynomial regression model of the insulator leakage current, the insulator state, and the plant temperature, and calculating a total leakage current deviation compensation value based on the insulator state and the plant temperature; Calibrate the measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value; The actual leakage current value is compared with a preset leakage current threshold value, and a fault diagnosis result is output.
2. The aluminum electrolytic overhead crane insulator fault diagnosis method according to claim 1, characterized in that: The insulator state at least includes the degree of contamination and aging of the insulator surface.
3. The aluminum electrolytic overhead crane insulator fault diagnosis method according to claim 2, characterized in that: The expression of the polynomial regression model is as follows: In the above formula, ΔI total It represents the total deviation compensation value of leakage current caused by temperature and insulator state, n represents the highest order of temperature polynomial, a m It represents the m-order coefficient of temperature T, reflecting the weight of the nonlinear effect of temperature on leakage current. m It represents the m-order term of temperature T, which is used to describe the nonlinear relationship between temperature and leakage current. p represents the highest order of the insulator state polynomial. b i,k represents the state parameter X of the i-th insulator i The k-order coefficient reflects the weight of the nonlinear effect of the insulator state on the leakage current. Indicates the state parameter X of i insulators i The k-th term, c j,l It represents the cross coefficient between temperature T and the state parameter of the first insulator, reflecting the influence of the interaction between the two on the leakage current. j represents the jth order term of temperature T, Indicates the state parameter X of the lth insulator l The k-th term of .
4. The aluminum electrolytic overhead crane insulator fault diagnosis method according to claim 3, characterized in that: The measured leakage current of the insulator is calibrated according to the total leakage current deviation compensation value, and the expression of the true leakage current value is obtained as follows: I calibrated =I measured +ΔI total In the above formula, I calibrated Indicates the actual leakage current value, I measured Indicates the measured leakage current.
5. An aluminum electrolysis overhead crane insulator fault monitoring system, characterized in that: Applied to the aluminum electrolysis overhead crane insulator fault diagnosis method according to any one of claims 1 to 4, the system comprises: A data acquisition unit configured to collect insulator leakage current, insulator image, and plant temperature; an edge computing unit configured to perform image preprocessing on the insulator image, perform feature extraction on the preprocessed insulator image, obtain the insulator state, set a leakage current offset influence weight, construct a polynomial regression model of the insulator leakage current, the insulator state, and the plant temperature, and calculate a total leakage current deviation compensation value based on the insulator state and the plant temperature; a data processing unit configured to calibrate the actually measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value, and obtain a fault diagnosis result by comparing the true leakage current value with a preset leakage current threshold; The output unit is configured to output the fault diagnosis result.
6. The aluminum electrolysis overhead crane insulator fault monitoring system according to claim 5, characterized in that: The data acquisition unit includes a leakage current sensor, an image sensor, and a temperature sensor, wherein the leakage current sensor is used to collect the leakage current of the insulator, the image sensor is used to collect the image of the insulator, and the temperature sensor is used to collect the factory temperature corresponding to the insulator.
7. The aluminum electrolysis overhead crane insulator fault monitoring system according to claim 5, characterized in that: The system also includes a data transmission unit, which is composed of a sampling network, an amplification network, an isolation network and an A / D conversion module. The data transmission unit is connected to the data acquisition unit, is used to receive data uploaded by the data acquisition unit and transmit the data to the edge computing unit via the amplification network. The signal output end of the edge computing unit is connected to the isolation unit, which is used to transmit the signal to the remote A / D conversion module via the isolation unit. The signal output end of the A / D conversion module is connected to the data processing unit.
8. The aluminum electrolysis overhead crane insulator fault monitoring system according to claim 7, characterized in that: The data processing unit is composed of a control chip and a SCADA fault analysis module, wherein the control chip is connected to the SCADA fault analysis module, the signal output end of the SCADA fault analysis module is connected to the output unit, and the SCADA fault analysis module is used to calibrate the measured leakage current of the insulator according to the total leakage current deviation compensation value to obtain a true leakage current value, and obtain a fault diagnosis result by comparing the true leakage current value with a preset leakage current threshold.
9. The aluminum electrolysis overhead crane insulator fault monitoring system according to claim 8, characterized in that: The system also includes a real-time monitoring module and a fault alarm module. The signal input ends of the real-time monitoring module and the fault alarm module are both connected to the output unit.
10. The aluminum electrolysis overhead crane insulator fault monitoring system according to claim 9, characterized in that: The system also includes an overhead crane database. The signal output end of the output unit is connected to the overhead crane database for sending the fault diagnosis result to the overhead crane database for storage. The signal input ends of the real-time monitoring module and the fault alarm module are both connected to the overhead crane database.