A blast furnace top gas seal box monitoring device

Abstract

This invention discloses a monitoring device for the airtight box at the top of a blast furnace, relating to the field of blast furnace ironmaking equipment condition monitoring technology. It includes a sensor module, a data acquisition and processing module, a feature extraction and enhancement module, and an early warning module, all electrically connected in sequence. The data acquisition and processing module performs signal processing and standardization on the raw data from the sensor module. The feature extraction and enhancement module includes a transmission ratio mapping unit and a feature amplification unit. The transmission ratio mapping unit performs frequency mapping based on the transmission ratio relationship of the transmission system, and the feature amplification unit performs time-domain feature extraction and frequency-domain feature analysis on the mapped signal. The early warning module includes a multi-parameter collaborative judgment model and a hierarchical early warning unit. The multi-parameter collaborative judgment model performs multi-parameter fusion judgment based on weight allocation, and the hierarchical early warning unit outputs hierarchical early warning signals based on the judgment results. This invention achieves rapid fault location and hierarchical early warning, improving the efficiency and safety of airtight box operation and maintenance.

Description

Technical Field

[0001] This invention relates to the technical field of blast furnace ironmaking equipment condition monitoring, specifically a monitoring device for the gas-tight box at the top of a blast furnace. Background Technology

[0002] The blast furnace top airtight box is a core component that ensures the sealing of the furnace top and drives the charging chute. It contains key structures such as a large slewing bearing and a gear transmission system. These components operate under harsh conditions of high temperature, high dust, low speed and heavy load for a long time. The initial characteristics of their failure development are extremely weak and often manifest as coupled changes in multiple parameters (such as vibration, temperature and lubrication status).

[0003] Traditional monitoring devices for the gas-tight box at the top of blast furnaces often analyze and alarm parameters such as vibration and temperature independently, lacking coordination and fusion analysis between parameters. This makes it impossible to comprehensively judge the overall health status of the equipment, which can easily lead to false alarms or missed alarms. Furthermore, the sensors are usually installed directly on low-speed components, and due to the weak signal and susceptibility to environmental noise interference, it is difficult to extract clear characteristic frequencies. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a monitoring device for the gas-tight box at the top of a blast furnace.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] This invention provides a monitoring device for the gas-tight box at the top of a blast furnace, comprising:

[0007] The sensor module, data acquisition and processing module, feature extraction and enhancement module, and early warning module are connected in sequence.

[0008] The sensor module includes a vibration sensor, a temperature sensor, a lubrication status sensor, and a sealing pressure sensor;

[0009] The data acquisition and processing module is used to perform signal processing and standardization on the raw data from the sensor module;

[0010] The feature extraction and enhancement module includes a transmission ratio mapping unit and a feature amplification unit. The transmission ratio mapping unit performs frequency mapping based on the transmission ratio relationship of the transmission system, and the feature amplification unit is used to perform time-domain feature extraction and frequency-domain feature analysis on the mapped signal.

[0011] The early warning module includes a multi-parameter collaborative judgment model and a hierarchical early warning unit. The multi-parameter collaborative judgment model performs multi-parameter fusion judgment based on weight allocation, and the hierarchical early warning unit outputs hierarchical early warning signals based on the judgment results.

[0012] As a preferred embodiment of the present invention, the vibration sensor is deployed in the airtight box transmission system; the temperature sensor is deployed in the bearing mounting area, the gear meshing area, and the sealing ring mounting area; the lubrication status sensor is installed in the airtight box lubrication oil circuit; and the sealing pressure sensor is deployed in the sealed cavity of the airtight box.

[0013] As a preferred technical solution of the present invention, multiple vibration sensors are provided, and the vibration sensors are deployed at the high-speed end measuring points according to the power transmission path of the airtight box transmission system. The high-speed end measuring points are positions that have a fixed transmission association with the low-speed components.

[0014] The location includes the mounting position corresponding to the output shaft of the gearbox, the connecting flange of the drive motor, and the outer ring support structure of the slewing bearing.

[0015] As a preferred embodiment of the present invention, multiple temperature sensors are provided, and the temperature sensors are deployed in different areas inside the airtight box. The deployment range includes the housing surface of the bearing mounting part, the housing surface of the gear meshing area, and the inside of the sealing ring mounting groove.

[0016] As a preferred embodiment of the present invention, the lubrication status sensor is installed in the lubrication oil circuit through an interface, and the sensor probe is immersed in the oil.

[0017] As a preferred embodiment of the present invention, a plurality of sealing pressure sensors are provided, and the plurality of sealing pressure sensors are arranged in a symmetrical layout within the sealed cavity of the airtight box.

[0018] As a preferred embodiment of the present invention, the data acquisition and processing module adopts a multi-channel data acquisition device, which is electrically connected to the sensor module through a shielded cable;

[0019] The data acquisition and processing module performs low-frequency filtering on the vibration signal, smoothing filtering on the temperature signal, lubrication status signal, and pressure signal, and normalization processing on all monitoring signals.

[0020] As a preferred technical solution of the present invention, the transmission ratio mapping unit converts the vibration signal characteristics collected by the vibration sensor from the high-speed end frequency domain to the actual operating frequency domain of the low-speed component according to the rotational speed ratio between the high-speed end measuring point and the low-speed component to be monitored.

[0021] The feature amplification unit performs amplitude feature extraction in the time domain and harmonic component analysis in the frequency domain on the frequency-mapped vibration signal.

[0022] As a preferred technical solution of the present invention, the multi-parameter collaborative judgment model is based on each monitoring parameter and assigns corresponding weight coefficients according to the preset importance level, and performs fusion analysis through weighted calculation.

[0023] The graded early warning unit is configured to receive the output results of the multi-parameter collaborative judgment model, and generate and output early warning signals with different degrees of urgency by combining the values ​​of each monitoring parameter with the preset threshold conditions.

[0024] As a preferred embodiment of the present invention, the sensor module further includes a power sensor, which is deployed in the control cabinet of the airtight box drive motor and is used to collect the current and voltage parameters of the motor.

[0025] The airtight box monitoring device also includes a wireless communication module, which is integrated into the data acquisition and processing module, the feature extraction and enhancement module, and the early warning module, and is used to realize wireless data transmission between the modules.

[0026] The beneficial effects of this invention are:

[0027] 1. In this invention, the sensor module includes a vibration sensor, a temperature sensor, a lubrication status sensor, and a sealing pressure sensor, which are respectively deployed at the high-speed end measuring point, bearing mounting location, gear meshing area, sealing ring mounting area, lubrication oil circuit, and sealing cavity of the airtight box transmission system. This enables multi-parameter coordinated monitoring of vibration, temperature, lubrication status, and sealing pressure, overcoming the problem of incomplete monitoring caused by relying on only a single parameter in the prior art. It can comprehensively cover the operating status of key components of the airtight box and avoid fault omissions caused by parameter omissions.

[0028] 2. In this invention, the transmission ratio mapping unit of the feature extraction enhancement module performs frequency mapping based on the transmission ratio relationship of the transmission system, converting the high-speed end vibration signal features collected by the vibration sensor to the actual operating frequency domain of the low-speed component. Combined with the time-domain feature extraction and frequency-domain feature analysis of the feature amplification unit, the ability to extract weak fault features of the low-speed component is enhanced. This effectively solves the problem that fault feature signals are weak and easily masked by environmental noise under low-speed heavy-load conditions, and improves the accuracy and reliability of early fault identification.

[0029] 3. In this invention, the multi-parameter collaborative judgment model of the early warning module performs fusion analysis of multiple parameters based on weight allocation, and outputs graded early warning signals according to the judgment results and preset threshold conditions by the graded early warning unit. At the same time, it is connected to the blast furnace control system through the communication interface to transmit early warning level information, fault nature and type information, and fault location information, thereby realizing rapid fault location and graded early warning, and improving the efficiency and safety of airtight box operation and maintenance. Attached Figure Description

[0030] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0031] Figure 1 This is a schematic diagram of the overall structure of the airtight box monitoring device of the present invention. Detailed Implementation

[0032] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0033] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0034] like Figure 1 As shown, a monitoring device for the airtight box at the top of a blast furnace includes:

[0035] The sensor module, data acquisition and processing module, feature extraction and enhancement module, and early warning module are connected in sequence.

[0036] The sensor module includes a vibration sensor, a temperature sensor, a lubrication status sensor, and a sealing pressure sensor;

[0037] The vibration sensor is deployed in the airtight box transmission system, specifically at the high-speed end of the transmission system, including the mounting position corresponding to the gearbox output shaft, the transmission motor connecting flange, and the outer ring support structure of the slewing bearing. This deployment method utilizes the transmission ratio relationship of the transmission system, which can effectively collect fault signals of low-speed components amplified by the transmission. The temperature sensor is deployed at the bearing mounting position, gear meshing area, and sealing ring mounting area to achieve comprehensive monitoring of temperature distribution in key parts. The lubrication status sensor is installed in the airtight box lubrication oil circuit, with the sensor probe immersed in the oil, which can monitor the lubrication oil status in real time. The sealing pressure sensor is deployed in the sealed cavity of the airtight box, using a symmetrical layout, which can accurately reflect the pressure status in the sealed cavity.

[0038] The data acquisition and processing module is used to perform signal processing and standardization on the raw data from the sensor module;

[0039] The data acquisition and processing module employs a multi-channel data acquisition device, which is electrically connected to the sensor module via a shielded cable. This module performs low-frequency filtering on the vibration signal to effectively remove high-frequency noise interference; it performs smoothing filtering on the temperature signal, lubrication status signal, and pressure signal to eliminate instantaneous interference; and it performs normalization processing on all monitoring signals, uniformly converting parameters of different dimensions to a standard range, providing a standardized data foundation for subsequent analysis.

[0040] The feature extraction and enhancement module includes a transmission ratio mapping unit and a feature amplification unit. The transmission ratio mapping unit performs frequency mapping based on the transmission ratio relationship of the transmission system, and the feature amplification unit is used to perform time-domain feature extraction and frequency-domain feature analysis on the mapped signal.

[0041] The transmission ratio mapping unit converts the vibration signal characteristics collected by the vibration sensor from the high-speed end frequency domain to the actual operating frequency domain of the low-speed component based on the speed ratio relationship between the high-speed end measuring point and the low-speed component to be monitored. This frequency mapping process can restore the true fault characteristic frequency of the low-speed component. The feature amplification unit performs amplitude feature extraction in the time domain and harmonic component analysis in the frequency domain on the frequency-mapped vibration signal. Through this dual analysis mechanism, the characteristic information representing the equipment status is effectively enhanced, and the accuracy of fault identification is improved.

[0042] The early warning module includes a multi-parameter collaborative judgment model and a hierarchical early warning unit. The multi-parameter collaborative judgment model performs multi-parameter fusion judgment based on weight allocation, and the hierarchical early warning unit outputs hierarchical early warning signals based on the judgment results.

[0043] The multi-parameter collaborative judgment model assigns corresponding weight coefficients to each monitoring parameter according to the preset importance level, and performs fusion analysis through weighted calculation to achieve a comprehensive evaluation of the equipment status. The hierarchical early warning unit receives the output results of the multi-parameter collaborative judgment model and, in combination with the comparison of the values ​​of each monitoring parameter with preset threshold conditions, generates and outputs early warning signals with different urgency levels. The early warning module is also equipped with a communication interface for data exchange with the blast furnace control system, which can transmit early warning signals containing early warning level information, fault nature and type information, and fault location information to the blast furnace control system.

[0044] During operation, the sensors in the sensor module collect real-time operating parameters of the airtight box, including vibration, temperature, lubrication status, and sealing pressure data. The collected raw data is transmitted to the data acquisition and processing module via shielded cable. After filtering and normalization, standardized monitoring data is formed. This standardized data is then transmitted to the feature extraction and enhancement module. First, the transmission ratio mapping unit performs frequency domain conversion, and then the feature amplification unit performs feature enhancement processing. The processed feature parameters are sent to the early warning module for fusion analysis through a multi-parameter collaborative judgment model. Finally, the hierarchical early warning unit outputs corresponding early warning signals based on the analysis results. The entire process forms a complete monitoring closed loop from data acquisition, processing, feature extraction to status judgment and early warning.

[0045] Furthermore, the vibration sensor is deployed in the airtight box transmission system. This deployment method is designed based on the structural characteristics of the airtight box transmission system. The airtight box transmission system contains multiple meshing gears and bearings. The vibration signals generated by these components during operation can directly reflect the operating status of the equipment. Deploying the vibration sensor in the transmission system can effectively capture the vibration characteristics of these key components.

[0046] The temperature sensors are deployed in the bearing mounting area, the gear meshing area, and the sealing ring mounting area. This regional deployment design takes into account the heat distribution characteristics inside the airtight box. The bearing mounting area will generate heat due to friction during operation, the gear meshing area will generate temperature rise due to tooth surface contact, and the sealing ring mounting area will experience temperature changes due to sealing friction and the influence of medium temperature. By deploying temperature sensors in these three key areas, comprehensive monitoring of the temperature field of the airtight box can be achieved.

[0047] The lubrication status sensor is installed in the lubrication oil circuit of the airtight box. The choice of this deployment location is based on the circulation characteristics of the lubrication oil circuit. After the lubrication oil flows through each lubrication point, it will carry information reflecting the wear status of the components and the quality of the lubrication oil. By installing the lubrication status sensor in the lubrication oil circuit, the overall status of the lubrication system can be monitored in real time, and lubrication abnormalities and component wear problems can be detected in time.

[0048] The sealing pressure sensor is deployed inside the sealed cavity of the airtight box. The sealed cavity is a key part for maintaining the sealing performance of the airtight box. The pressure change inside it directly reflects the working status of the sealing system. By deploying the sealing pressure sensor in this part, the pressure status of the sealing medium can be monitored in real time, providing a direct basis for judging the sealing performance.

[0049] Furthermore, multiple vibration sensors are provided, and these sensors are deployed at the high-speed end measuring points according to the power transmission path of the airtight box transmission system. In the airtight box transmission system, power is transmitted from the drive motor through the reduction gearbox to the slewing bearing, ultimately driving the fabric chute. Deploying vibration sensors at the high-speed end measuring points allows for the amplification and acquisition of weak fault characteristics of low-speed components through frequency conversion, utilizing the transmission ratio relationship of the transmission system.

[0050] The high-speed end measuring point is a position that has a fixed transmission connection with the low-speed component, including the mounting position corresponding to the output shaft of the gearbox, the connecting flange of the transmission motor and the outer ring support structure of the slewing bearing.

[0051] The mounting position corresponding to the gearbox output shaft can reflect the operating status of the gear transmission system, the transmission motor connection flange can monitor the connection status between the motor and the transmission system, and the outer ring support structure of the slewing bearing can capture the operating characteristics of the slewing bearing. By deploying vibration sensors at these key locations, the vibration characteristic acquisition requirements of the airtight box transmission system can be fully covered.

[0052] In practical applications, this deployment method can effectively solve the problem that the fault characteristics of low-speed components are weak and difficult to collect directly. For example, when the slewing bearing has an early fault, its weak fault characteristics will be transmitted to the high-speed end through the transmission system. The signal collected by the vibration sensor at the high-speed end can be processed to restore the actual fault characteristics of the low-speed component.

[0053] Furthermore, multiple temperature sensors are provided, and the temperature sensors are deployed in different areas inside the airtight box. The deployment range includes the housing surface of the bearing mounting part, the housing surface of the gear meshing area, and the inside of the sealing ring mounting groove.

[0054] At the bearing mounting location, temperature sensors are placed on the outer surface of the bearing housing to monitor the operating temperature of the bearing through heat conduction. In the gear meshing area, temperature sensors are placed at corresponding positions on the gearbox housing to monitor the temperature rise generated by gear transmission. Inside the sealing ring mounting groove, temperature sensors are directly installed near the sealing ring to monitor the operating temperature of the sealing system in real time.

[0055] This zoned deployment scheme can fully cover the key heat-generating parts of the airtight box, promptly detect local overheating, and in actual operation, the temperature data of each zone corroborate each other, providing a reliable basis for judging the operating status of the equipment.

[0056] Furthermore, the lubrication status sensor is installed in the lubrication oil circuit via an interface, and the sensor probe is immersed in the oil.

[0057] This installation method ensures that the lubrication status sensor can directly contact the flowing lubricating oil and monitor the status of the lubrication system in real time. The lubrication oil circuit is the circulation channel of the lubrication system. After flowing through each lubrication point, the lubricating oil carries information reflecting the system status. The design of the sensor probe being immersed in the oil ensures the accuracy and real-time nature of the monitoring data. The lubrication status sensor detects the physicochemical parameters of the lubricating oil, including viscosity, iron filings content, and moisture content, to comprehensively judge the working status of the lubrication system and the wear of components.

[0058] Furthermore, multiple sealing pressure sensors are provided, and these multiple sealing pressure sensors are deployed in a symmetrical layout within the sealed cavity of the airtight box;

[0059] The symmetrical layout can comprehensively reflect the pressure distribution within the sealed cavity and promptly detect abnormal pressure phenomena. The sealed cavity is a key component for maintaining the sealing performance of the airtight box, and its internal pressure directly affects the sealing effect. By comparing pressure data at different locations, the flow status of the sealing medium and the working status of the sealing ring can be determined. When an abnormal pressure occurs in a certain area, the system can accurately locate the abnormal location, providing guidance for subsequent maintenance and repair.

[0060] Optionally, two sealing pressure sensors are configured. During deployment, the two sealing pressure sensors are symmetrically installed inside the sealing cavity of the airtight box, specifically close to both sides of the sealing ring. That is, one sensor is installed on the driving side of the sealing ring, and the other sensor is installed on the driven side of the sealing ring.

[0061] Furthermore, the data acquisition and processing module adopts a multi-channel data acquisition device, which is electrically connected to the sensor module through a shielded cable;

[0062] The data acquisition and processing module performs low-frequency filtering on the vibration signal, smoothing filtering on the temperature signal, lubrication status signal, and pressure signal, and normalization processing on all monitoring signals.

[0063] Low-frequency filtering is a signal processing method designed specifically for the low-speed, heavy-load operating conditions of airtight boxes. Because the core transmission components of the airtight box rotate at extremely low speeds (0.5-5 r / min), their fault characteristic frequencies are mainly concentrated in the low-frequency range (0.008-0.08 Hz), while environmental noise at the blast furnace site (such as furnace vibration and equipment operation) is mainly distributed in the high-frequency range. By setting appropriate low-frequency filtering parameters, useful low-frequency fault characteristics can be effectively preserved while high-frequency noise interference is filtered out.

[0064] Smoothing filtering is used to eliminate transient interference and random fluctuations in slowly changing signals, thereby improving signal stability and reliability. While temperature, lubrication status, and pressure signals change relatively slowly, they are susceptible to transient interference in the harsh environment of a blast furnace. Smoothing filtering can effectively improve signal quality in these conditions.

[0065] Normalization is performed to eliminate dimensional differences between different physical parameters and to convert all parameters into the same numerical range, thus facilitating subsequent multi-parameter collaborative analysis.

[0066] For example, in practical application scenarios, the workflow of the data acquisition and processing module is as follows:

[0067] First, the raw data from each sensor is collected synchronously using a multi-channel data acquisition device, with the sampling frequency set to 1000Hz to ensure that complete signal characteristics can be captured.

[0068] Secondly, the vibration signal is subjected to a 50Hz low-pass filter to remove high-frequency noise interference; the temperature signal, lubrication status signal, and pressure signal are subjected to a moving average filter with a window length of 5 seconds to eliminate instantaneous interference.

[0069] Finally, based on the safety threshold range of each parameter, a normalization formula is used to convert all monitoring signals into the standard interval [0,1], forming standardized monitoring data.

[0070] Furthermore, the transmission ratio mapping unit converts the vibration signal characteristics collected by the vibration sensor from the high-speed end frequency domain to the actual operating frequency domain of the low-speed component based on the rotational speed ratio between the high-speed end measuring point and the low-speed component to be monitored.

[0071] The transmission ratio mapping unit works as follows: First, the unit receives standardized vibration data from the data acquisition and processing module. This data comes from vibration sensors deployed at the high-speed end measurement point. Then, based on the preset transmission ratio between the high-speed end and the low-speed component, the frequency of the vibration signal acquired at the high-speed end is converted to the actual operating frequency domain of the low-speed component according to the proportional relationship. For example, when the transmission ratio is 20:1, the 20Hz vibration signal measured at the high-speed end corresponds to the 1Hz actual operating frequency of the low-speed component.

[0072] The feature amplification unit performs amplitude feature extraction in the time domain and harmonic component analysis in the frequency domain on the frequency-mapped vibration signal to enhance the feature information characterizing the equipment status.

[0073] The amplitude feature extraction process in the time domain includes: selecting a time window of 5-10 seconds, identifying abnormal vibration peaks that exceed 1.2 times the normal peak value within the time window, and calculating the arithmetic mean of these abnormal peaks as the time domain feature parameter. This time domain feature extraction method can effectively amplify the amplitude features of the fault signal while avoiding the influence of random fluctuations of a single peak.

[0074] The harmonic component analysis process in the frequency domain includes: performing a fast Fourier transform on the vibration signal after frequency mapping to obtain the frequency domain spectrum of the signal; then selectively amplifying the 3rd and 5th harmonic components of the fault characteristic frequency, with the amplification factor adjusted in the range of 1.5-2.0 according to the on-site noise intensity. This frequency domain analysis method can effectively enhance the harmonic components of the fault characteristic frequency and improve the signal-to-noise ratio of feature identification.

[0075] This feature extraction enhancement mechanism has the following technical characteristics: it solves the problem of direct measurement of fault feature frequencies of low-speed components by mapping the transmission ratio; it enhances the saliency of fault features through dual analysis in the time and frequency domains; and the entire processing is specifically optimized for the characteristics of low-speed heavy-load operation of airtight boxes, making it highly practical and reliable.

[0076] Furthermore, the multi-parameter collaborative judgment model assigns corresponding weight coefficients to each monitoring parameter according to a preset importance level, and performs fusion analysis through weighted calculation.

[0077] The weighting coefficients can be set as follows:

[0078] The vibration enhancement feature weight coefficient is 0.4: The vibration enhancement feature is the core fault parameter obtained through transmission ratio mapping and feature amplification. It directly corresponds to the essential faults such as mechanical wear and meshing abnormalities of low-speed components. It has the highest correlation with the fault and the strongest parameter sensitivity (significant changes can occur in the early stage of the fault). Therefore, it is assigned the highest weight.

[0079] The weighting coefficient for lubrication status is 0.3: Lubrication status directly reflects the degree of deterioration of lubricating oil and the content of impurities generated by component wear. Lubrication failure is a direct cause of gear and bearing failure. Furthermore, indicators such as iron filings content and viscosity changes can reflect early wear earlier than temperature and vibration. The parameter sensitivity is second only to vibration intensification characteristics, and it is assigned the second highest weight.

[0080] Temperature weighting coefficient is 0.2: Temperature changes are an indirect reflection of abnormal component operation. For example, increased bearing wear will lead to an increase in temperature, and seal leakage will cause local temperature fluctuations. However, temperature changes have a lag (the fault will only appear after it has developed to a certain stage). The parameter sensitivity is moderate, so a moderate weight is assigned.

[0081] The sealing pressure weighting coefficient is 0.1: The sealing pressure is only applicable to specific faults such as sealing ring leakage, with a narrow scope of application. Moreover, pressure changes often show obvious abnormalities only in the later stages of seal failure, so the parameter sensitivity is the lowest and the lowest weight is assigned.

[0082] The weighted fusion analysis uses a weighted summation algorithm to calculate the comprehensive value S of the airtight box state, as shown in the following formula:

[0083] ;

[0084] Where S is the comprehensive state value of the airtight box, ranging from [0,1]. The closer the value is to 1, the higher the risk of failure and the more unstable the state of the airtight box; w1 is the vibration intensification characteristic weighting coefficient (e.g., w1=0.4); S vib The normalized value of the vibration enhancement feature is [0,1], which is obtained by weighted summation of the mean of the time-domain peak value, the amplitude of multiple (e.g., 3rd) harmonics, and the amplitude of multiple (e.g., 5th) harmonics output by the feature extraction enhancement module.

[0085] w2 is the lubrication state weighting coefficient (e.g., w2=0.3); S lub The normalized value for lubrication status is [0,1], and is obtained by weighted summation of viscosity, iron filings content, and moisture content collected by the lubrication status sensor.

[0086] w3 is the temperature weighting coefficient (e.g., w3=0.2); S temp This is the normalized temperature value, ranging from [0,1], and is the maximum value of all temperature sensor measurements.

[0087] w4 is the sealing pressure weighting coefficient (e.g., w4=0.1); S pres The normalized value of the sealing pressure is [0,1], and the absolute value of the difference between the measurements of the two sealing pressure sensors is 0.

[0088] The graded early warning unit is configured to receive the output results of the multi-parameter collaborative judgment model, and generate and output early warning signals with different degrees of urgency by combining the values ​​of each monitoring parameter with the preset threshold conditions.

[0089] The warning levels are divided into three levels: warning (low risk), alarm (medium risk), and danger (high risk). The classification is based on the different stages of the airtight box failure (early, middle, and late stages) and the corresponding handling requirements, combined with on-site operation and maintenance experience and the degree of failure impact, to determine the judgment criteria for each level.

[0090] Warning (Low Risk): This corresponds to the early stage of a fault or the equipment status approaching an abnormality. At this time, the fault has not yet affected the normal operation of the airtight box, but monitoring needs to be strengthened to prevent the fault from escalating. The judgment criteria are: Status comprehensive value S∈[0.8,0.9): This indicates that the equipment status after multi-parameter fusion is close to the abnormal threshold, but has not reached the fault level, or any single parameter normalized value∈[0.8,1.0): This indicates that a certain parameter is close to the safety threshold, but has not exceeded it, indicating that the status of the component corresponding to the parameter needs to be closely monitored.

[0091] Alarm (Medium Risk): Corresponds to a mid-stage or minor fault. At this point, the fault has become apparent, and continued operation may worsen the fault. A shutdown inspection should be arranged. The judgment criteria are: a comprehensive state value S∈[0.9,1.0) indicates that the equipment has shown obvious abnormalities after multi-parameter fusion, and a minor fault exists; or any two parameters with normalized values ​​≥1.0 indicates that two parameters have exceeded the safety threshold simultaneously, the coupling relationship between the parameters has become apparent, and the probability of fault is extremely high.

[0092] Dangerous (High Risk): This corresponds to a late-stage or severe fault. At this point, the fault has affected the normal operation of the airtight box, and continued use may lead to a safety accident. Immediate shutdown and maintenance are required. The judgment criteria are: a comprehensive state value S=1.0: indicating that the equipment state has reached the most dangerous level after multi-parameter fusion, and a serious fault exists; or a normalized value of any single parameter ≥1.2: indicating that a certain parameter has exceeded 120% of the safety threshold, and the component corresponding to that parameter has experienced serious failure, with an extremely high risk.

[0093] By optimizing the multi-parameter collaborative judgment mechanism, accurate assessment and timely early warning of the airtight box's operating status were achieved, thereby improving the reliability and safety of equipment operation.

[0094] Furthermore, the early warning module is equipped with a communication interface for data exchange with the blast furnace control system, used to transmit the early warning signal to the blast furnace control system;

[0095] The communication interface is an industrial Ethernet interface, designed to fully adapt to the communication requirements of blast furnace industrial control scenarios, ensuring the real-time performance, stability, and anti-interference of early warning signal transmission. The communication interface is deployed on the outside of the early warning module's housing, surrounded by sealing gaskets and dust covers. When not in use, the covers can be closed to prevent dust from entering. The connection between the interface and the blast furnace control system uses a shielded network cable with a braided copper mesh shielding structure, similar to the high-temperature shielded cable of the sensor module. This effectively resists electromagnetic interference generated by electrical control equipment and motors during blast furnace production, ensuring no distortion or loss of signals during transmission. The network cable length is determined based on the actual distance between the blast furnace control room and the airtight box, typically controlled within 50m. If the distance exceeds 50m, signal relay can be used via an industrial Ethernet switch to ensure a transmission delay of ≤100ms, consistent with the transmission delay of the data acquisition and processing module, ensuring the real-time performance of the early warning signal.

[0096] The warning signal includes warning level information determined by the multi-parameter collaborative judgment model, fault nature type information determined by analyzing abnormal combination patterns of each parameter, and fault location information determined by analyzing the abnormal sources of each sensor signal.

[0097] The three types of information contained in the warning signal do not exist in isolation, but are generated collaboratively based on the results of sensor layout, feature extraction, and collaborative judgment mentioned above. The generation of each type of information has a clear logical basis to ensure accuracy and uniqueness.

[0098] The warning level information is the direct result of the combined action of the multi-parameter collaborative judgment model and the hierarchical warning unit. Its generation logic is completely consistent with the judgment criteria of the hierarchical warning unit, that is, the warning level (warning, alarm, danger) is determined based on the state comprehensive value (S) and the abnormal situation of a single parameter.

[0099] The nature and type of the fault are determined by analyzing the abnormal combination patterns of various parameters. The core basis is the "fixed parameter coupling relationship corresponding to different fault types". This coupling relationship is derived from the fault mechanism of the airtight box and the field test data.

[0100] The location of the fault is determined by analyzing the source of abnormal signals from each sensor. The core basis for this is the "targeted layout of sensors"—each sensor has a clear deployment location and corresponds one-to-one with the core components of the airtight box. The sensor number is pre-bound to the component location to ensure that abnormal signals can be directly traced to the specific component.

[0101] Finally, the complete early warning signal, including the warning level, fault type, and fault location, is packaged and transmitted to the blast furnace control system via the industrial Ethernet communication interface, and output to the display terminal (such as the central control computer or the operator's mobile phone).

[0102] Optionally, the sensor module further includes a power sensor, which is deployed in the control cabinet of the airtight box drive motor to collect the current and voltage parameters of the motor. The current and voltage parameters collected by the power sensor are transmitted to the data acquisition and processing module. After smoothing, filtering and normalization, they are input together with vibration, temperature, lubrication status and sealing pressure data into the feature extraction and enhancement module to provide load dimension monitoring data for the multi-parameter collaborative judgment model.

[0103] The introduction of power sensors is based on the fact that during the operation of a motor drive system, its electrical parameters (such as current and voltage) can directly reflect the load status, power quality, and the health status of the motor itself. By monitoring the fluctuations, harmonic components, phase, and other characteristics of current and voltage, it is possible to effectively identify whether the motor has electrical faults such as overload, phase loss, voltage imbalance, and harmonic pollution, and at the same time provide auxiliary basis for mechanical load fault diagnosis.

[0104] If a power sensor is introduced, the formula for calculating the overall state value S of the airtight box in this embodiment is as follows:

[0105]

[0106] ;

[0107] Where w5 is the current state weighting coefficient; S I The current characteristic value is an anomaly degree calculated by comparing the characteristics of the current signal collected by the current sensor (such as the degree to which the effective value of the current deviates from the rated value and the total harmonic distortion rate of the current) with a preset threshold.

[0108] w6 is the voltage weighting coefficient; S U The voltage characteristic value is an anomaly degree calculated by comparing the characteristics of the voltage signal collected by the voltage sensor (such as voltage fluctuation rate and total voltage harmonic distortion rate) with a preset threshold.

[0109] In this embodiment, current and voltage parameters are monitored as electrical load dimensions, which can indirectly reflect mechanical load abnormalities and power supply problems. Their weights are relatively low but cannot be ignored. Optionally, the weight values ​​are allocated as follows: w1=0.3, w2=0.2, w3=0.15, w4=0.15, w5=0.1, w6=0.1.

[0110] The airtight box monitoring device also includes a wireless communication module, which is integrated into the data acquisition and processing module, the feature extraction and enhancement module, and the early warning module, and is used to realize wireless data transmission between the modules.

[0111] The adoption of wireless communication modules aims to solve the installation and maintenance difficulties caused by complex on-site wiring and harsh environments in the blast furnace top airtight box. Wireless transmission not only reduces cable laying costs but also improves system flexibility and scalability, making it particularly suitable for scenarios in the metallurgical industry where equipment is widely distributed and there are many moving parts.

[0112] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A monitoring device for the airtight box at the top of a blast furnace, characterized in that, include: The sensor module, data acquisition and processing module, feature extraction and enhancement module, and early warning module are connected in sequence. The sensor module includes a vibration sensor, a temperature sensor, a lubrication status sensor, and a sealing pressure sensor; The data acquisition and processing module is used to perform signal processing and standardization on the raw data from the sensor module; The feature extraction and enhancement module includes a transmission ratio mapping unit and a feature amplification unit. The transmission ratio mapping unit performs frequency mapping based on the transmission ratio relationship of the transmission system, and the feature amplification unit is used to perform time-domain feature extraction and frequency-domain feature analysis on the mapped signal. The early warning module includes a multi-parameter collaborative judgment model and a hierarchical early warning unit. The multi-parameter collaborative judgment model performs multi-parameter fusion judgment based on weight allocation, and the hierarchical early warning unit outputs hierarchical early warning signals based on the judgment results. The vibration sensor is deployed in the airtight box transmission system; the temperature sensor is deployed in the bearing mounting area, gear meshing area, and sealing ring mounting area; the lubrication status sensor is installed in the airtight box lubrication oil circuit; and the sealing pressure sensor is deployed in the sealed cavity of the airtight box. Multiple vibration sensors are provided, and the vibration sensors are deployed at the high-speed end measuring points according to the power transmission path of the airtight box transmission system. The high-speed end measuring points are positions that have a fixed transmission association with the low-speed components. The location includes the mounting position corresponding to the output shaft of the gearbox, the connecting flange of the drive motor, and the outer ring support structure of the slewing bearing. The transmission ratio mapping unit converts the vibration signal characteristics collected by the vibration sensor from the high-speed end frequency domain to the actual operating frequency domain of the low-speed component based on the rotational speed ratio between the high-speed end measuring point and the low-speed component to be monitored. The feature amplification unit performs amplitude feature extraction in the time domain and harmonic component analysis in the frequency domain on the frequency-mapped vibration signal.

2. The monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, Multiple temperature sensors are provided and deployed in different areas inside the airtight box. The deployment areas include the housing surface of the bearing mounting area, the housing surface of the gear meshing area, and the inside of the sealing ring mounting groove.

3. The monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, The lubrication status sensor is installed in the lubrication oil circuit via an interface, with the sensor probe immersed in the oil.

4. The monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, Multiple sealing pressure sensors are provided, and these sensors are arranged symmetrically within the sealed cavity of the airtight box.

5. A monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, The data acquisition and processing module uses a multi-channel data acquisition device, which is electrically connected to the sensor module via a shielded cable. The data acquisition and processing module performs low-frequency filtering on the vibration signal, smoothing filtering on the temperature signal, lubrication status signal, and pressure signal, and normalization processing on all monitoring signals.

6. The monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, The multi-parameter collaborative judgment model is based on each monitoring parameter and assigns corresponding weight coefficients according to the preset importance level, and performs fusion analysis through weighted calculation. The graded early warning unit is configured to receive the output results of the multi-parameter collaborative judgment model, and generate and output early warning signals with different degrees of urgency by combining the values ​​of each monitoring parameter with the preset threshold conditions.

7. A monitoring device for the airtight box at the top of a blast furnace according to claim 1, characterized in that, The sensor module also includes a power sensor, which is deployed in the control cabinet of the airtight box drive motor and is used to collect the current and voltage parameters of the motor. The airtight box monitoring device also includes a wireless communication module, which is integrated into the data acquisition and processing module, the feature extraction and enhancement module, and the early warning module, and is used to realize wireless data transmission between the modules.

Images