Method and system for monitoring injection valve in metallurgical dephosphorization system

Abstract

The invention provides a monitoring method and system for an injection valve in a metallurgical dephosphorization system, and relates to the field of injection valve testing. The method comprises the steps that the working state of the metallurgical dephosphorization system is obtained, the metallurgical dephosphorization system comprises at least one injection valve, and the injection valve is provided with a sensor; adjusting a detection threshold value of the sensor for the injection valve based on the working state; acquiring a detection signal acquired by the sensor; and monitoring whether the injection valve leaks or not according to the detection signal and the adjusted detection threshold value.

Description

Technical Field

[0001] The present invention relates to the field of injection valve testing, and particularly to a monitoring method and system for an injection valve in a metallurgical dephosphorization system. Background Art

[0002] During the steel smelting process, the injection valve of the metallurgical dephosphorization system is used to spray dephosphorizing agent onto the surface of the continuous casting billet to remove scale and improve the surface quality of the billet. Since the injection valve works in an environment of high temperature, high pressure and strong corrosion for a long time, it is prone to leakage.

[0003] At present, the leakage monitoring of the injection valve mainly adopts a detection method with a fixed threshold. This method installs sensors on the injection valve. When the detection signal exceeds the preset fixed threshold, the system issues an alarm signal to indicate that leakage may occur.

[0004] However, due to the large variation of working conditions during the actual operation of the metallurgical dephosphorization system, the detection method with a fixed threshold is prone to false alarms, resulting in frequent shutdowns of the system for inspection. This not only increases the equipment maintenance cost but also affects the production efficiency. Summary of the Invention

[0005] The present invention provides a monitoring method and system for an injection valve in a metallurgical dephosphorization system to solve the technical problem that the detection method with a fixed threshold in the prior art is prone to false alarms, resulting in frequent shutdowns of the system for inspection.

[0006] The present invention provides a monitoring method for an injection valve in a metallurgical dephosphorization system, including: Obtaining the working state of the metallurgical dephosphorization system, where the metallurgical dephosphorization system includes at least one injection valve, and the injection valve is provided with a sensor; Adjusting the detection threshold of the sensor for the injection valve based on the working state; Obtaining the detection signal collected by the sensor; Monitoring whether the injection valve leaks according to the detection signal and the adjusted detection threshold.

[0007] According to the monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, the sensor includes at least one of an ultrasonic sensor, a vibration sensor, and an infrared thermal imager. The working state includes the injection mode of the injection valve and the steel temperature. The injection mode includes a pulse injection mode and a continuous injection mode. The fluid pressure and switching frequency of the injection valve are different under different injection modes.

[0008] According to the monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, the adjusting the detection threshold of the sensor for the injection valve based on the working state includes: Adjust the detection threshold corresponding to the ultrasonic signal collected by the ultrasonic sensor according to the injection mode; and / or, Adjust the detection threshold corresponding to the vibration signal collected by the vibration sensor according to the injection mode; and / or, Adjust the detection threshold corresponding to the temperature signal collected by the infrared thermal imager according to the steel temperature.

[0009] According to a monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, monitoring whether the injection valve leaks according to the detection signal and the adjusted detection threshold includes: Calculate the correlation coefficients between the ultrasonic signal collected by the ultrasonic sensor, the vibration signal collected by the vibration sensor, and the temperature signal collected by the infrared thermal imager; When the correlation coefficient is greater than or equal to the correlation coefficient threshold, if it is determined that any one of the ultrasonic signal, the vibration signal, and the temperature signal is greater than or equal to the corresponding adjusted detection threshold, it is determined that the injection valve leaks.

[0010] According to a monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, the method further includes: When the correlation coefficient is less than the correlation coefficient threshold, control the metallurgical dephosphorization system to operate in a low-load state; Obtain the reference signal of the sensor when the metallurgical dephosphorization system is in the low-load operation state; Compensate for the drift error of the sensor of the metallurgical dephosphorization system in the high-load operation state according to the reference signal.

[0011] According to a monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, the method further includes: When it is determined that any one of the injection valves leaks, determine the fault propagation path according to the detection signals of the injection valves.

[0012] According to a monitoring method for an injection valve in a metallurgical dephosphorization system provided by the present invention, after obtaining the detection signal collected by the sensor, it further includes: Filter the ultrasonic signal collected by the ultrasonic sensor through a band-pass filter; and / or, Remove the low-frequency signal in the vibration signal collected by the vibration sensor, where the low-frequency signal represents the slow-changing component in the vibration signal with a frequency lower than the leakage characteristic frequency.

[0013] The present invention also provides a monitoring device for an injection valve in a metallurgical dephosphorization system, including: A working state acquisition module is configured to acquire the working state of a metallurgical dephosphorization system, where the metallurgical dephosphorization system includes at least one injection valve, and the injection valve is provided with a sensor; A detection threshold adjustment module is configured to adjust the detection threshold of the sensor for the injection valve based on the working state; A detection signal acquisition module is configured to acquire the detection signal collected by the sensor; A detection signal monitoring module is configured to monitor whether the injection valve leaks according to the detection signal and the adjusted detection threshold.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the monitoring method of the injection valve in the metallurgical dephosphorization system as described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the monitoring method of the injection valve in the metallurgical dephosphorization system as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the monitoring method of the injection valve in the metallurgical dephosphorization system as described in any one of the above is implemented.

[0017] The monitoring method and system for the injection valve in the metallurgical dephosphorization system provided by the present invention acquire the working state of the metallurgical dephosphorization system and dynamically adjust the detection threshold of the sensor based on this working state, so that the detection threshold can adapt to the working conditions changes during the system operation. This adaptive threshold adjustment mechanism avoids the problem of false alarms easily caused by external factors such as temperature fluctuations and pressure fluctuations in the traditional fixed-threshold detection method. After acquiring the detection signal collected by the sensor, the system performs leakage monitoring and judgment according to the adjusted detection threshold, and can more accurately identify the actual leakage state of the injection valve. This not only reduces the false alarm rate, avoids unnecessary shutdown inspections, but also ensures the monitoring sensitivity of the system and ensures that leakage hazards can be detected in time. The above monitoring method based on the working state to adjust the threshold effectively improves the operation reliability and production efficiency of the metallurgical dephosphorization system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flow chart of a monitoring method for an injection valve in a metallurgical dephosphorization system provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a monitoring device for an injection valve in a metallurgical dephosphorization system provided by an embodiment of the present invention; Figure 3 It is a schematic physical structure diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0020] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of a monitoring method for an injection valve in a metallurgical dephosphorization system provided by an embodiment of the present invention. The method may include the following steps: S101, Obtain the working state of the metallurgical dephosphorization system. The metallurgical dephosphorization system includes at least one injection valve, and the injection valve is provided with a sensor; S102, Adjust the detection threshold of the sensor for the injection valve based on the working state; S103, Obtain the detection signal collected by the sensor; S104, Monitor whether the injection valve leaks according to the detection signal and the adjusted detection threshold.

[0022] In S101, the metallurgical dephosphorization system refers to a special equipment system used for removing scale on the surface of continuous casting billets and improving the surface quality of continuous casting billets during the steel smelting process. The system includes a dephosphorizing agent supply unit, an injection execution unit, a monitoring unit, and a control unit. The system is used to continuously and stably remove oxides on the surface of continuous casting billets during the continuous casting process to ensure that the surface quality of steel meets the process requirements.

[0023] Among them, the injection execution unit is the core component of the system, including at least one injection valve, which is used to direct the injection of high-pressure dephosphorizing agent onto the surface of the continuous casting billet. Each injection valve works in an environment of high temperature, high pressure and strong corrosion, and its performance directly affects the dephosphorization effect.

[0024] Optionally, in order to realize the real-time monitoring of the operating state of the injection valve, a variety of sensors are provided on the injection valve. The sensors include at least one of an ultrasonic sensor, a vibration sensor, and an infrared thermal imager Exemplarily, 6 ultrasonic sensors can be symmetrically arranged in a regular hexagon at the valve seat sealing surface and the valve stem root to capture tiny leakage sound signals; a triaxial vibration sensor can be installed on the valve body surface to monitor the vibration characteristics of the valve; an infrared thermal imager can be set 30 millimeters away from the valve body to monitor the temperature distribution of the sealing area in real time. The above multi-physical-field collaborative sensor configuration scheme can comprehensively reflect the operating state of the injection valve.

[0025] Among them, the operating state of the metallurgical dephosphorization system refers to the combination of process parameters that affect the operating stability and monitoring accuracy of the system. In the embodiment of the present invention, the operating state can be understood to include two main parameters, namely the injection mode of the injection valve and the steel temperature, which are used to provide a basis for the subsequent dynamic adjustment of the detection threshold to ensure the reliability of the monitoring results.

[0026] Optionally, the operating state includes the injection mode of the injection valve and the steel temperature. The injection mode includes a pulse injection mode and a continuous injection mode. Among them, the fluid pressure and switching frequency of the injection valve are different under different injection modes.

[0027] In practical applications, the injection mode of the injection valve can be divided into a pulse injection mode and a continuous injection mode. In the pulse injection mode, the injection valve performs periodic switching actions according to a preset frequency. The switching frequency is usually in the range of 5 - 20 Hz. At this time, the fluid pressure shows periodic fluctuations, and the fluctuation range is 5 - 15 MPa. In this operating mode, due to the frequent switching of the valve, strong mechanical vibrations and fluid pulsations will be generated, which are likely to interfere with the identification of leakage signals. In the continuous injection mode, the injection valve remains continuously open, and the fluid pressure is relatively stable, usually maintained at 8 - 10 MPa. At this time, the background noise of the system is small, which is conducive to the detection of leakage signals. At the same time, the normal operating range of the steel temperature is 250 - 400 °C. When the temperature exceeds this range, it will significantly affect the measurement accuracy of the infrared thermal imager, and corresponding temperature compensation is required.

[0028] In S102, since the working conditions of the metallurgical dephosphorization system vary greatly during actual operation, if a fixed detection threshold is used, false alarms or missed alarms are likely to occur. For example, in the pulse injection mode, the frequent switching of the injection valve will generate strong mechanical vibrations and fluid pulsations. At this time, if the detection threshold in the continuous injection mode is still used, normal working vibrations may be misjudged as leakage signals. Therefore, it is necessary to dynamically adjust the detection threshold according to the operating state of the system to improve the monitoring accuracy.

[0029] Optionally, in the high-pressure continuous injection mode, since the enhanced fluid noise may mask the leakage signal, it is necessary to improve the detection sensitivity and adjust the detection threshold of the ultrasonic sensor to 0.6 - 0.8 times the initial threshold. In the pulse injection mode, since the frequent opening and closing of the valve will generate strong mechanical vibrations, it is necessary to appropriately increase the detection threshold to avoid false alarms. Specifically, the detection threshold of the vibration sensor can be adjusted to 1.2 - 1.5 times the initial threshold. When the steel temperature exceeds the normal operating range of 250 - 400 °C, due to the abnormal temperature significantly affecting the measurement accuracy of the infrared thermal imager, a compensation coefficient is required for temperature compensation.

[0030] The dynamic adjustment scheme of the detection threshold based on the working state can enable the monitoring system to adapt to the signal characteristic changes under different working conditions, effectively reduce the false alarm rate, and improve the accuracy and reliability of leakage detection. At the same time, this scheme can achieve the adaptive adjustment of the detection threshold without manual intervention, reducing the system maintenance cost.

[0031] Based on the above embodiments, as an optional embodiment, S102 may further include the following steps: S201, adjusting the detection threshold corresponding to the ultrasonic signal collected by the ultrasonic sensor according to the injection mode; Specifically, the leakage monitoring accuracy of the injection valve is easily interfered by fluid pressure fluctuations. When the system is in the high-pressure continuous injection mode, the high-speed flow of the dephosphorizing agent will generate strong fluid noise, and its frequency band (0.5 - 1.5 MHz) partially overlaps with the leakage ultrasonic signal (1.0 - 1.2 MHz), making it difficult for the traditional fixed threshold method to distinguish the real leakage signal from the background noise. When operating at low load (such as pressure < 5 MPa), the fluid flow rate decreases, and the leakage signal amplitude may be lower than the fixed threshold, resulting in the risk of missed detection. For this reason, this embodiment proposes a method for dynamically adjusting the ultrasonic detection threshold, which optimizes the sensitivity and reliability of leakage detection by real-time sensing of the fluid pressure and matching the threshold response.

[0032] Exemplarily, the dynamic detection threshold can be defined as: , the injection mode is continuous injection; In the formula, represents the initial detection threshold of the ultrasonic sensor, represents the adjusted detection threshold of the ultrasonic sensor, represents the current fluid pressure, represents the reference fluid pressure for normalization, represents the pressure compensation coefficient for controlling the response of the ultrasonic threshold to pressure changes.

[0033] Specifically, under high-pressure conditions, the energy of fluid noise increases exponentially with increasing pressure, but its share in the characteristic frequency band of leakage signals (1.0-1.2MHz) is relatively low. By lowering the detection threshold, the system can amplify the signal-to-noise ratio of leakage signals in this frequency band, thereby improving sensitivity. At the same time, the introduction of the pressure compensation coefficient allows the threshold adjustment process to take into account the pressure fluctuation characteristics of different production lines, ensuring the robustness of the algorithm under complex conditions.

[0034] Among them, the determination of the compensation coefficient is based on the coupling analysis of the system noise characteristics and the physical laws of the leakage signal. In the high-pressure continuous injection mode, by collecting the background ultrasonic signals at different pressure levels (5-15MPa), the energy distribution characteristics of the 1.0-1.2MHz frequency band are extracted, and it is found that the noise energy increases nonlinearly with the increase of pressure, but its proportion in the characteristic frequency band of the leakage signal is relatively stable. In order to quantify the detectability of the leakage signal, micro-leakage is simulated in the experimental cavity, the corresponding ultrasonic signal amplitude is measured, and the mapping relationship between the leakage signal amplitude and the pressure and leakage amount is established.

[0035] Furthermore, by defining the minimum detectable signal-to-noise ratio, the ratio of the leakage signal amplitude to the background noise energy is used as the theoretical basis for threshold adjustment. The value range of the pressure compensation coefficient derived from the dynamic threshold formula must satisfy the requirement that the leakage signal amplitude is higher than the adjusted threshold.

[0036] S202, adjusting the detection threshold corresponding to the vibration signal collected by the vibration sensor according to the injection mode; Specifically, the high-frequency switching action (5-20Hz) of the injection valve will cause periodic mechanical shock, resulting in a large amount of background noise mixed in the vibration signal. The energy concentration frequency band of this type of noise (1-3kHz) partially overlaps with the fluid impact vibration caused by leakage (typical frequency band 2-4kHz). If a fixed detection threshold is used, normal operating vibration is easily misjudged as leakage. In addition, when the system switches to continuous injection mode, the valve remains normally open, the amplitude of the vibration signal is significantly reduced, and the threshold needs to be dynamically lowered to maintain detection sensitivity. To this end, this embodiment proposes an adaptive vibration detection threshold adjustment method based on switching frequency, which optimizes detection reliability by matching the dynamic characteristics of the injection mode.

[0037] Exemplarily, the dynamic vibration detection threshold may be defined as: = , the injection mode is pulse injection; In the formula, represents the initial detection threshold of the vibration sensor, represents the detection threshold of the vibration sensor after adjustment, Indicates the current switching frequency of the injection valve, represents the reference switching frequency, It represents the frequency gain coefficient, which controls the response of the vibration threshold to the switching frequency.

[0038] Specifically, in the pulse injection mode, the valve switching frequency is positively correlated with the background vibration energy. However, its high-frequency components (>3 kHz) are mainly generated by mechanical impacts, and there are differences in the frequency-domain distribution of fluid vibrations related to leakage. By increasing the detection threshold, the system can weaken the interference of high-frequency noise while retaining the energy of the characteristic frequency band of the leakage signal. The value range of the frequency gain coefficient can be determined through experimental calibration and false alarm rate constraints to ensure the stability of threshold adjustment under extreme working conditions.

[0039] S203. Adjust the detection threshold corresponding to the temperature signal collected by the infrared thermal imager according to the steel temperature.

[0040] Specifically, the change in the steel temperature will significantly affect the capture accuracy of the infrared thermal imager for leakage thermal signals. When the steel temperature exceeds the normal working range (250 - 400 °C), the non-linear change in the thermal radiation intensity may lead to distortion in the temperature field measurement: under high-temperature conditions (>400 °C), the heat diffusion effect in the sealed area is enhanced, and the thermal gradient signal of a small leakage is masked by the ambient thermal radiation; while under low-temperature conditions (<250 °C), the temperature difference caused by the leakage decreases, and the thermal imaging contrast drops, which is prone to missed detection. Therefore, this embodiment introduces a temperature compensation mechanism to match the influence law of the steel temperature change on the thermal signal by dynamically adjusting the infrared detection threshold.

[0041] Exemplarily, the dynamic temperature detection threshold can be defined as: ; In the formula, represents the initial temperature detection threshold of the infrared thermal imager, represents the adjusted temperature detection threshold of the infrared thermal imager, represents the current steel temperature, represents the reference temperature, represents the temperature compensation slope, which is used to control the response of the infrared threshold to the change in the steel temperature.

[0042] Specifically, the steel temperature is positively correlated with the ambient thermal radiation intensity. However, the local temperature rise caused by leakage is affected by the fluid heat capacity and flow rate, and its absolute value increases with the increase in the steel temperature. By introducing the compensation slope, the system can decouple the coupling effect of the ambient temperature and the leakage temperature rise, enabling the threshold adjustment process to adapt to the global temperature fluctuation while retaining the local leakage characteristics. The value of the compensation slope can be determined through heat conduction simulation and fitting of measured data to ensure the detection stability under extreme temperatures.

[0043] S104. Monitor whether the injection valve leaks according to the detection signal and the adjusted detection threshold.

[0044] In the actual operation of the metallurgical dephosphorization system, the identification of the injection valve leakage signal faces multi-physical field coupling interference. For example, in the pulse injection mode, the high-frequency mechanical vibration (1 - 3 kHz) overlaps with the fluid impact frequency band (2 - 4 kHz) caused by leakage, and the thermal radiation noise in the high-temperature environment will mask the temperature rise characteristics of the tiny leakage. If only relying on the threshold comparison of a single sensor, it is easy to cause misjudgment due to the dynamic change of the working conditions. Therefore, this embodiment proposes a multi-modal signal collaborative analysis mechanism to achieve accurate leakage determination through correlation coefficient analysis and hierarchical threshold trigger logic.

[0045] Based on the above embodiment, as an optional embodiment, S104 may specifically further include the following steps: S301, calculate the correlation coefficients among the ultrasonic signal collected by the ultrasonic sensor, the vibration signal collected by the vibration sensor, and the temperature signal collected by the infrared thermal imager.

[0046] In practical applications, due to the complexity of the working environment of the metallurgical dephosphorization system, the accurate identification of the injection valve leakage state requires comprehensive analysis of the collaborative change characteristics of multi-physical field signals. Traditional methods based on single-threshold judgment or bivariate correlation analysis are difficult to cope with multi-source interference in high-temperature and high-pressure environments. For example, when the ultrasonic signal is distorted due to pipeline resonance, or the vibration of adjacent equipment is conducted to the valve body through mechanical coupling, and the environmental thermal radiation mutation affects the infrared temperature measurement accuracy, relying only on the detection results of a single sensor is prone to misjudgment.

[0047] To overcome the above technical difficulties, this embodiment proposes a multi-modal signal correlation analysis method based on the ratio of the determinants of covariance matrices.

[0048] Exemplarily, let the ultrasonic signal , the vibration signal , and the infrared temperature signal be three zero-mean time series signals (number of sampling points N), and their covariance matrix is defined as: ; Among them, each element is calculated as follows: Variance term (diagonal element): ; Covariance term (non-diagonal element): ； ; ; The essence of the covariance matrix is a statistical model that describes the energy coupling relationship between signals: the variance term characterizes the independent fluctuation intensity of each signal. The covariance term reveals the interaction mechanism between signals. After time synchronization and zero-mean preprocessing, the correlation coefficient can be obtained from the diagonal elements of the covariance function. Exemplarily, the above process can be expressed as the following formula: ; In the formula, represents the correlation coefficient, represents , , the covariance matrix between represents the diagonal elements, which are the variances corresponding to their respective signals, represents the signal collected by the ultrasonic sensor at time t, represents the signal collected by the vibration sensor at time t, represents the temperature signal collected by the infrared thermal imager at time t.

[0049] Specifically, when the ultrasonic signal, vibration signal, and temperature signal are completely independent, their distributions in the signal space exhibit orthogonal characteristics. At this time, the actually observed covariance volume is equal to the covariance volume in the ideal independent state, and the determinant ratio is zero. This situation usually occurs when the system is operating normally or is subject to random interference, and the changes in the physical quantities captured by the three types of sensors are independent of each other and there is no significant statistical correlation.

[0050] When the injection valve leaks, since the fluid jet at the leakage point will simultaneously excite acoustic fluctuations, mechanical vibrations, and temperature gradients, a strong coupling effect will occur among the three signals. This coupling effect causes the distribution of the signals in the multi-dimensional space to collapse, and the actually observed covariance volume is less than the covariance volume in the ideal independent state, thus making the determinant ratio greater than zero. It should be noted that this coupling effect may manifest as complex non-linear relationships, such as the frequency modulation effect of the ultrasonic signal, the non-linear impact response of vibration, and the time-delay characteristics of heat diffusion, etc.

[0051] S302. When the correlation coefficient is greater than or equal to the correlation coefficient threshold, if it is determined that any one of the ultrasonic signal, the vibration signal, and the temperature signal is greater than or equal to the corresponding adjusted detection threshold, it is determined that the injection valve leaks.

[0052] Exemplarily, the correlation coefficient threshold can be set to 0.85. When the correlation coefficients of the ultrasonic signal, vibration signal, and temperature signal are greater than or equal to 0.85, it indicates that there is a significant coupling relationship among the three physical quantities. This coupling relationship reflects the multi-physical field synergy effect caused by leakage: the leakage jet not only generates ultrasonic waves but also causes mechanical vibrations, and at the same time forms a temperature gradient near the leakage point. Further, if, on the basis of high correlation, any signal exceeds its corresponding dynamically adjusted detection threshold, it can be confirmed that the injection valve is leaking. This determination logic makes full use of the physical characteristics of the leakage event: leakage will inevitably lead to a synchronous response of multiple physical fields and show significant abnormalities in at least one physical quantity.

[0053] Specifically, when the system detects that the correlation coefficient exceeds 0.85, it will further compare the relationships between the three types of signals and their respective dynamic thresholds. For example, in the pulse injection mode, if the vibration signal exceeds the threshold adjusted according to the switching frequency, and at this time, although the ultrasonic signal and temperature signal do not exceed the limit but show a strong correlation, the system will still determine it as a leakage in this case. This determination mechanism is particularly applicable to the initial stage of leakage. At this time, the changes in some physical quantities may not have reached the alarm threshold, but the coordinated changes of multiple signals have already shown early signs of leakage.

[0054] S303. When the correlation coefficient is less than the correlation coefficient threshold, control the metallurgical dephosphorization system to operate in a low-load state.

[0055] When the correlation coefficient is less than the correlation coefficient threshold, there may be two situations: one is that the sensor itself drifts or fails, resulting in a decrease in signal correlation; the other is that the system operating conditions fluctuate violently, masking the coupling relationship of the multi-physical field signals. Both of these situations will affect the accuracy of leakage detection. If the system continues to operate at a high load, not only may it miss the real leakage signal, but it will also exacerbate equipment wear.

[0056] Exemplarily, when the system detects a decrease in the correlation coefficient, the injection valve can be switched to a low-load operating state through the control system. The injection pressure of the dephosphorizing agent can be reduced to below 5 MPa, and at the same time, the injection frequency can be adjusted to a low-frequency state below 5 Hz. Under this low-load operating condition, the fluid pressure fluctuation and mechanical vibration are significantly weakened, which is beneficial to restoring the intrinsic characteristics of each physical field signal.

[0057] S304. Obtain the reference signal of the sensor when the metallurgical dephosphorization system is operating in a low-load state.

[0058] During the long-term operation of the metallurgical dephosphorization system, the performance of sensors is affected by the working environment and drifts. The reference signal refers to the standard reference signal collected by each sensor under the condition of no leakage and no interference when the metallurgical dephosphorization system is operating at low load. This reference signal can be understood as a characteristic signal reflecting the current actual performance state of the sensor, including parameters such as the frequency response characteristics of ultrasonic sensors, the dynamic response of vibration sensors, and the temperature sensitivity of infrared thermal imagers. These reference signals are used to evaluate the degree of sensor performance attenuation, calculate the drift compensation coefficient, and provide basic data for the dynamic adjustment of detection thresholds to ensure stable detection accuracy during the long-term operation of the system.

[0059] Exemplarily, the system uses a sampling window to obtain the reference signal. At this time, the signal spectral energy of the ultrasonic sensor is concentrated in the range of 0.8 - 1.2 MHz, the vibration sensor shows stable low-frequency response characteristics, and the infrared thermal imager provides a clear thermal distribution image under constant temperature conditions.

[0060] Furthermore, to ensure the reliability of the reference signal, a dynamic evaluation mechanism can be introduced: First, calculate the mean, standard deviation, and kurtosis coefficient of the signal within the sampling window. When the signal fluctuation exceeds the preset range, automatically extend the sampling time until the signal is stable. At the same time, compare the newly obtained reference signal with historical data, and trigger secondary sampling verification when the deviation exceeds 15%.

[0061] S305, compensate for the drift error of the sensors of the metallurgical dephosphorization system in the high-load operating state according to the reference signal.

[0062] Exemplarily, the system uses an adaptive compensation algorithm based on the reference signal to correct the sensor output. For ultrasonic sensors, by comparing the energy distribution of the current frequency band with the reference signal, calculate the frequency response compensation coefficient. This coefficient reflects the change in the frequency response characteristics of the sensor and is used to correct the leakage characteristic signal in the high-frequency band. Similarly, the dynamic response compensation coefficient of the vibration sensor is calculated based on the amplitude ratio of the low-frequency reference signal and is used to correct the vibration signal under high load; the temperature sensitivity compensation coefficient of the infrared thermal imager is determined by comparing the reference temperature field with the current imaging data.

[0063] The compensation process uses a real-time sliding window mechanism. Within each window, the system first extracts the characteristic parameters of the original sensor signal, such as the spectral energy of the ultrasonic signal, the root mean square value of the vibration signal, and the gradient distribution of the temperature signal. Then, it is corrected according to the corresponding compensation coefficient to achieve the calibration of signal characteristics. This compensation method ensures the continuity and smoothness of signal correction and avoids jumps and instability during the compensation process.

[0064] To adapt to the changes in working conditions, the compensation algorithm can also include a dynamic update mechanism. The system periodically evaluates the compensation effect and determines the effectiveness of the compensation coefficient by calculating the fitting degree between the compensated signal and the theoretical model. When the fitting degree is lower than the preset threshold, an automatic optimization process of the compensation coefficient is triggered: first, analyze the trend of the signal deviation, and then update the compensation coefficient by the least squares method to make the signal characteristics after compensation closer to the theoretical expectation.

[0065] Based on the above embodiments, as an alternative embodiment, when the metallurgical dephosphorization system includes multiple injection valves, the above method may further include the following steps: When it is determined that any one of the injection valves has a leak, determine the fault propagation path according to the detection signals of each injection valve.

[0066] In the working condition where the metallurgical dephosphorization system is configured with multiple injection valves, once a leak occurs in a certain injection valve, its leakage effect will spread to the surrounding area through the fluid medium and mechanical structure, which may trigger a chain reaction. Therefore, after detecting the leakage of any injection valve, it is necessary to determine the fault propagation path in time so as to take targeted preventive measures to avoid the expansion of the leakage and cause systemic damage.

[0067] Exemplarily, the system traces the fault propagation path by analyzing the timing relationship of the detection signals of each injection valve sensor. First, identify the injection valve that first shows an abnormality as the fault source, and then analyze the change trend of the signals of the surrounding injection valve sensors. The ultrasonic sensor determines the attenuation law of the acoustic wave energy in the pipeline by monitoring the propagation characteristics of the leakage sound wave; the vibration sensor identifies the fault propagation caused by structural coupling by capturing the transmission mode of mechanical vibration; the infrared thermal imager reveals the diffusion path of the leaked substance by tracking the change of the temperature field.

[0068] A spatio-temporal correlation analysis method can be used to process multi-source sensing signals. By establishing a topological relationship model between the injection valves and combining the characteristics of fluid mechanics and structural dynamics, calculate the propagation speed and direction of the fault influence. When an abnormal signal of a certain injection valve is detected, the system automatically tracks the time series of the signal change and combines the spatial position relationship of the adjacent injection valves to draw a fault propagation path diagram. Based on the obtained fault propagation path, the system can predict the development trend of the leakage and timely identify potential affected areas. Through predictive analysis, maintenance personnel can take preventive measures before the fault spreads, such as adjusting the operating parameters of relevant injection valves, enhancing the monitoring frequency of specific areas or arranging maintenance plans in advance. At the same time, the analysis result of the fault propagation path also provides an important reference for system optimization, which helps to improve the layout design and control strategy of the injection valves and enhance the overall reliability and safety of the system.

[0069] Based on the above embodiments, as an alternative embodiment, after performing S103, the following steps may further be included: S401, filtering the ultrasonic signal collected by the ultrasonic sensor through a band-pass filter.

[0070] Specifically, the original signal collected by the ultrasonic sensor often contains interference components from various sources such as mechanical vibration, electromagnetic interference, and environmental noise. These interference signals overlap with the ultrasonic signal generated by the leak in the frequency domain, which will affect the accuracy of leak detection. Therefore, it is necessary to process the ultrasonic signal through a band-pass filter to extract the frequency components that can best reflect the leak characteristics.

[0071] Exemplarily, the system may use a digital band-pass filter to process the ultrasonic signal. The passband range of this filter is determined according to the characteristic frequency of the leak ultrasonic wave, and the signal-to-noise ratio of the ultrasonic signal is improved by attenuating the interference components outside the passband.

[0072] S402, removing the low-frequency signals in the vibration signal collected by the vibration sensor, where the low-frequency signals represent the slow-changing components in the vibration signal with frequencies lower than the leak characteristic frequency.

[0073] Among them, the low-frequency signal refers to the slow-changing component in the vibration signal with a frequency lower than the leak characteristic frequency. In the embodiments of the present invention, it can be understood as the vibration baseline shift caused by factors such as equipment rotation, mechanical structure resonance, and environmental vibration. These low-frequency components are usually in the 0-100 Hz frequency band and are used to characterize the basic operating state of the metallurgical dephosphorization system and environmental impacts.

[0074] Exemplarily, the system uses a multi-scale trend decomposition method to process the vibration signal. First, the vibration signal is decomposed into different frequency scales by wavelet transform, and the wavelet coefficients representing the low-frequency signals are identified. During the decomposition process, the system adaptively selects the decomposition level and wavelet basis function according to the frequency distribution of the leak vibration characteristics to ensure accurate capture of the low-frequency signals. Then, through the reconstruction technique, the wavelet coefficients that do not contain low-frequency signals are recombined to obtain the detrended vibration signal.

[0075] The monitoring device for the injection valve in the metallurgical dephosphorization system provided by the present invention will be described below. The monitoring device for the injection valve in the metallurgical dephosphorization system described below can be correspondingly referred to the monitoring method for the injection valve in the metallurgical dephosphorization system described above.

[0076] Figure 2 The structural schematic diagram of a monitoring device for an injection valve in a metallurgical dephosphorization system provided by an embodiment of the present invention is as Figure 2 shown. The monitoring device for the injection valve in the metallurgical dephosphorization system includes: A working state acquisition module, configured to acquire the working state of a metallurgical dephosphorization system, where the metallurgical dephosphorization system includes at least one injection valve, and the injection valve is provided with a sensor; A detection threshold adjustment module, configured to adjust the detection threshold of the sensor for the injection valve based on the working state; A detection signal acquisition module, configured to acquire the detection signal collected by the sensor; A detection signal monitoring module, configured to monitor whether the injection valve leaks according to the detection signal and the adjusted detection threshold.

[0077] Based on the above embodiments, as an optional embodiment, the sensor includes at least one of an ultrasonic sensor, a vibration sensor, and an infrared thermal imager, the working state includes the injection mode of the injection valve and the steel temperature, the injection mode includes a pulse injection mode and a continuous injection mode, and the fluid pressure and switching frequency of the injection valve are different under different injection modes.

[0078] Based on the above embodiments, as an optional embodiment, the detection threshold adjustment module is further configured to adjust the detection threshold corresponding to the ultrasonic signal collected by the ultrasonic sensor according to the injection mode; and / or, adjust the detection threshold corresponding to the vibration signal collected by the vibration sensor according to the injection mode; and / or, adjust the detection threshold corresponding to the temperature signal collected by the infrared thermal imager according to the steel temperature.

[0079] Based on the above embodiments, as an optional embodiment, the detection signal monitoring module is further configured to calculate the correlation coefficient between the ultrasonic signal collected by the ultrasonic sensor, the vibration signal collected by the vibration sensor, and the temperature signal collected by the infrared thermal imager; when the correlation coefficient is greater than or equal to a correlation coefficient threshold, if it is determined that any one of the ultrasonic signal, the vibration signal, and the temperature signal is greater than or equal to the corresponding adjusted detection threshold, it is determined that the injection valve leaks.

[0080] Based on the above embodiments, as an optional embodiment, the detection signal monitoring module is further configured to control the metallurgical dephosphorization system to operate in a low-load state when the correlation coefficient is less than the correlation coefficient threshold; acquire the reference signal of the sensor of the metallurgical dephosphorization system in the low-load operating state; compensate for the drift error of the sensor of the metallurgical dephosphorization system in the high-load operating state according to the reference signal.

[0081] Based on the above embodiments, as an optional embodiment, the detection signal monitoring module is further configured to determine the fault propagation path according to the detection signals of the injection valves when it is determined that any one of the injection valves leaks.

[0082] Based on the above embodiments, as an alternative embodiment, the detection signal acquisition module is further configured to filter the ultrasonic signal collected by the ultrasonic sensor through a band-pass filter; and / or remove the low-frequency signal in the vibration signal collected by the vibration sensor, where the low-frequency signal represents the slow-changing component in the vibration signal with a frequency lower than the leakage characteristic frequency.

[0083] Figure 3 The following is a schematic physical structure diagram of an electronic device provided by an embodiment of the present invention. As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute the monitoring method of the injection valve in the metallurgical dephosphorization system.

[0084] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of a software functional unit and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0085] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the monitoring method of the injection valve in the metallurgical dephosphorization system provided by the above-mentioned methods.

[0086] On yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the monitoring method of the injection valve in the metallurgical dephosphorization system provided by the above-mentioned methods.

[0087] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for monitoring an injection valve in a metallurgical dephosphorization system, characterized in that: include: Acquiring a working state of a metallurgical dephosphorization system, wherein the metallurgical dephosphorization system comprises at least one injection valve, wherein the injection valve is provided with a sensor, wherein the sensor comprises at least one of an ultrasonic sensor, a vibration sensor and an infrared thermal imager; adjusting a detection threshold of the sensor for the injection valve based on the working state; Acquiring a detection signal collected by the sensor; monitoring whether the injection valve leaks according to the detection signal and the adjusted detection threshold; Wherein, monitoring whether the injection valve leaks according to the detection signal and the adjusted detection threshold value includes: Calculating the correlation coefficient between the ultrasonic signal collected by the ultrasonic sensor, the vibration signal collected by the vibration sensor, and the temperature signal collected by the infrared thermal imager; When the correlation coefficient is less than a correlation coefficient threshold, the metallurgical phosphorus removal system is controlled to operate in a low-load state; a reference signal of the sensor when the metallurgical phosphorus removal system is in a low-load operation state is obtained; and a drift error of the sensor of the metallurgical phosphorus removal system in a high-load operation state is compensated according to the reference signal.

2. The method for monitoring the injection valve in the metallurgical dephosphorization system according to claim 1, characterized in that: The working state includes an injection mode of the injection valve and a temperature of the steel material. The injection mode includes a pulse injection mode and a continuous injection mode. The fluid pressure and the switching frequency of the injection valve are different in different injection modes.

3. The method for monitoring the injection valve in the metallurgical dephosphorization system according to claim 2, characterized in that: The step of adjusting the detection threshold of the sensor for the injection valve based on the working state includes: Adjusting the detection threshold corresponding to the ultrasonic signal collected by the ultrasonic sensor according to the injection mode; and / or, Adjusting the detection threshold corresponding to the vibration signal collected by the vibration sensor according to the injection mode; and / or, The detection threshold corresponding to the temperature signal collected by the infrared thermal imager is adjusted according to the temperature of the steel.

4. The method for monitoring the injection valve in the metallurgical dephosphorization system according to claim 1, characterized in that: The method further comprises: When the correlation coefficient is greater than or equal to the correlation coefficient threshold, if it is determined that any one of the ultrasonic signal, the vibration signal and the temperature signal is greater than or equal to the corresponding adjusted detection threshold, it is determined that the injection valve is leaking.

5. The method for monitoring the injection valve in the metallurgical dephosphorization system according to claim 4, characterized in that: The metallurgical dephosphorization system includes a plurality of injection valves, and the method further includes: When it is determined that any one of the injection valves is leaking, a fault propagation path is determined based on the detection signal of each of the injection valves.

6. The method for monitoring injection valves in a metallurgical dephosphorization system according to claim 1, characterized in that: After acquiring the detection signal collected by the sensor, the method further includes: Filtering the ultrasonic signal collected by the ultrasonic sensor through a bandpass filter; and / or, A low-frequency signal in the vibration signal collected by the vibration sensor is removed, wherein the low-frequency signal represents a slowly changing component in the vibration signal whose frequency is lower than the leakage characteristic frequency.

7. A monitoring device for an injection valve in a metallurgical dephosphorization system, characterized in that: include: A working status acquisition module, used for acquiring the working status of a metallurgical dephosphorization system, wherein the metallurgical dephosphorization system comprises at least one injection valve, wherein the injection valve is provided with a sensor, wherein the sensor comprises at least one of an ultrasonic sensor, a vibration sensor and an infrared thermal imager; a detection threshold adjustment module, configured to adjust a detection threshold of the sensor for the injection valve based on the working state; A detection signal acquisition module, used to acquire the detection signal collected by the sensor; A detection signal monitoring module, used for monitoring whether the injection valve leaks according to the detection signal and the adjusted detection threshold; The detection signal monitoring module is also used to calculate the correlation coefficient between the ultrasonic signal collected by the ultrasonic sensor, the vibration signal collected by the vibration sensor, and the temperature signal collected by the infrared thermal imager; when the correlation coefficient is less than the correlation coefficient threshold, the metallurgical dephosphorization system is controlled to operate in a low-load state; and a reference signal of the sensor is obtained when the metallurgical dephosphorization system is in a low-load operation state; The drift error of the sensor of the metallurgical dephosphorization system under high load operation is compensated according to the reference signal.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for monitoring the injection valve in the metallurgical dephosphorization system according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring an injection valve in a metallurgical dephosphorization system according to any one of claims 1 to 6 is implemented.

Images