Method for cooling product with cooling section in kiln

Abstract

The invention discloses a product cooling method with a cooling section in a kiln, and relates to the technical field of high-temperature industrial sintering, and the method comprises the following steps: an air cooling system cools a product in the kiln at an initial air speed, and a stable initial cooling environment is established; through real-time monitoring, data preprocessing, intelligent evaluation and dynamic adjustment, a closed-loop control system is formed, and it is ensured that airflow disturbance in the kiln cooling process does not resonate with the inherent frequency of product stacking. The machine learning model intelligently analyzes the product stacking frequency change, automatically adjusts the rotating speed of the fan when detecting the resonance risk, and avoids resonance in real time. And the stability and safety of the cooling process are guaranteed through continuous frequency monitoring and feedback adjustment. According to the intelligent dynamic adjusting method, the production stability and the cooling efficiency of the kiln are improved, equipment damage and potential safety hazards are reduced, and the safety and the reliability of the whole production system are improved.

Description

Technical Field

[0001] This invention relates to the field of high-temperature industrial sintering technology, specifically to a product cooling method with a cooling section inside the kiln. Background Technology

[0002] Kiln cooling and temperature reduction sections refer to a dedicated area within the kiln structure for cooling and lowering the temperature of products after high-temperature treatment. This section effectively reduces the product temperature through specific cooling media (such as air, water, or cooling airflow) and methods like flow control and heat exchange devices, allowing the product to transition stably from a high-temperature state to a suitable outlet or post-processing temperature. This method typically includes the following steps: after sintering, the product is introduced into the cooling and temperature reduction section according to the process flow; this section uses forced convection, spray cooling, or heat recovery devices to rapidly and uniformly cool the product; simultaneously, temperature changes are monitored to ensure that the cooling process does not cause thermal stress cracking or changes in physical properties. This type of cooling method not only ensures the quality of the product after sintering but also improves the system's thermal energy utilization efficiency and safety.

[0003] Existing technologies have the following shortcomings: During the cooling process of kiln products using an air-cooling system, airflow disturbance or pulsating airflow is a common phenomenon. If the pulsating frequency of the airflow overlaps with the natural frequency of the product stack, a resonance effect may occur. In this case, the product stack, as a structure with a certain degree of flexibility and elasticity, will generate a violent vibration response under the influence of periodic airflow disturbance, causing the product stack system to enter a resonance state. The resonance phenomenon amplifies the vibration amplitude, causing instability of particles or blocks in the product stack, manifested as product slippage, displacement, or even tilting or collapse of the entire product stack. This process not only disrupts the stability of the material in the cooling section but may also cause a series of serious consequences, including interruption of material flow, uneven cooling, and mechanical damage to the cooling equipment, ultimately affecting the kiln's production efficiency and product quality. More seriously, product stack instability may also cause safety hazards such as equipment jamming and damage, further jeopardizing the normal operation of the production system.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide a product cooling method with a cooling section within the kiln. Through real-time monitoring, data preprocessing, intelligent evaluation, and dynamic adjustment, a closed-loop control system is formed to ensure that airflow disturbances during the kiln cooling process do not resonate with the natural frequency of the product stack. A machine learning model intelligently analyzes changes in the product stack frequency and automatically adjusts the fan speed when resonance risk is detected, avoiding resonance in real time. Continuous frequency monitoring and feedback adjustments ensure the stability and safety of the cooling process. This intelligent dynamic adjustment method improves kiln production stability and cooling efficiency, reduces equipment damage and safety hazards, and enhances the overall safety and reliability of the production system, thus solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for cooling and reducing the temperature of products in a kiln equipped with a cooling and temperature reduction section, comprising the following steps: The air-cooling system cools the products in the kiln with an initial air velocity, establishing a stable initial cooling environment; High-precision sensors are used to acquire real-time data on the frequency changes of product stacking in the kiln. The acquired raw data is preprocessed and the complex raw data is transformed into a structured dataset. The core indicators reflecting the risk of overlap between airflow pulsation frequency and product stacking natural frequency are extracted from the dataset. The extracted core indicators are then comprehensively analyzed to quantify the degree of overlap between airflow pulsation frequency and product stacking natural frequency, thereby assessing the resonance risk. The core indicators after comprehensive analysis are input into a pre-trained machine learning model. The model is used to intelligently evaluate the changes in product stacking frequency and determine whether there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking. When a risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack is detected, the fan speed is dynamically adjusted to change the airflow pulsation frequency, so that it avoids the overlap range with the natural frequency of the product stack. At the same time, the airflow disturbance and the product stack response status are continuously monitored, and closed-loop adjustment is automatically executed according to the frequency change to achieve real-time avoidance and dynamic control of resonance risk.

[0007] Preferably, the specific steps for establishing a stable initial cooling environment by cooling the products in the kiln using an initial air velocity are as follows: First, start the air-cooling system and set the initial air speed. The air speed is calculated based on the product's heat load and the design requirements of the cooling section to ensure that the airflow intensity is moderate and does not disturb the product stacking too violently. Next, the fan starts working at the set initial wind speed, continuously providing a uniform airflow to the product surface, so that the heat on the product surface is gradually dissipated into the airflow, thus starting the cooling process; At this point, the wind speed is maintained within a fixed range to ensure a uniform and continuous cooling process. At the same time, the temperature changes of the product and the airflow are monitored to ensure the stability of the cooling environment, laying the foundation for subsequent dynamic adjustments and further operations.

[0008] Preferably, core indicators reflecting the risk of overlap between airflow pulsation frequency and the natural frequency of product stacking are extracted from the dataset. The extracted indicators include the response intensity of airflow periodic disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking. The response intensity of airflow periodic disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking are comprehensively analyzed to generate periodic excitation response reference values ​​and dynamic stress enhancement reference values, respectively. Through the periodic excitation response reference values ​​and dynamic stress enhancement reference values, the degree of overlap between airflow pulsation frequency and the natural frequency of product stacking is quantified, thereby assessing the resonance risk.

[0009] Preferably, the specific steps for generating a reference value for the periodic excitation response by comprehensively analyzing the response intensity of periodic airflow disturbances to product stacking vibration within the detection window are as follows: Vibration response data of product stacks under periodic airflow disturbances are acquired using high-precision vibration sensors. The dominant disturbance frequency of the current airflow and the dominant response frequency of the product stack under the disturbance are identified. Simultaneously, the vibration amplitude of the product stack at the dominant response frequency is extracted to generate a nonlinear vibration response factor. The generation formula is as follows: In the formula, It is a nonlinear vibration response factor. It is the product stacking response frequency. It is the frequency of the main airflow disturbance. Is the product stacking at the response frequency The vibration amplitude below, It is the vibration amplitude enhancement index. It is the frequency difference attenuation index; After acquiring data pairs of multiple disturbance frequencies and corresponding product stacking response frequencies, the nonlinear vibration response factors under all disturbance frequencies are combined to generate a periodic excitation response reference value, representing the sensitivity of the product stacking to all periodic disturbance frequencies within the entire detection window. The calculation expression is as follows: In the formula, It is a reference value for periodic excitation response. It is the first Nonlinear vibration response factor at a disturbance frequency It represents the total number of disturbance frequencies. It is the first The proximity coefficient between the disturbance frequency and the product stacking response frequency.

[0010] Preferably, the specific steps for generating dynamic stress enhancement reference values ​​by comprehensively analyzing the stress distribution inside the product stack based on the airflow pulsation frequency within the detection window are as follows: Multiple product stacking observation points were selected to collect stress response values ​​under disturbance and base stress values ​​collected under undisturbed conditions. A disturbance response ratio model was introduced to calculate the disturbance stress enhancement ratio. The calculation expression is as follows: In the formula, It is the instantaneous stress value under disturbance conditions. It is the reference stress value under undisturbed conditions. It is the maximum stress increase caused by the disturbance. It is the minimum reference stress. It is a tiny positive number set to prevent the denominator from approaching zero. It is the ratio of disturbance stress enhancement; Based on the ratio of disturbance stress enhancement The deviation between the main airflow disturbance frequency and the product stacking response frequency is considered, and coupled quantization is performed using a nonlinear gain function to generate a dynamic stress enhancement reference value. The generation formula is as follows: In the formula, It is a reference value for dynamic stress enhancement. It is the product stacking response frequency. It is the frequency of the main airflow disturbance. It is a frequency coupling sensitivity parameter. It is the natural base.

[0011] Preferably, the periodic excitation response reference value and dynamic stress enhancement reference value after comprehensive analysis are input into a pre-trained machine learning model. The machine learning model generates a frequency overlap risk coefficient, and the frequency overlap risk coefficient is used to intelligently evaluate the product stacking frequency change to determine whether there is a risk of overlap between the airflow pulsation frequency and the product stacking inherent frequency.

[0012] Preferably, the frequency overlap risk coefficient generated when intelligently assessing product stacking frequency changes using a pre-trained machine learning model is compared and analyzed with a pre-set frequency overlap risk coefficient reference threshold to determine whether there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking. The judgment logic is as follows: If the frequency overlap risk coefficient is greater than the preset frequency overlap risk coefficient reference threshold, it is determined that there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking; if the frequency overlap risk coefficient is less than or equal to the preset frequency overlap risk coefficient reference threshold, it is determined that there is no risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking.

[0013] Preferably, when a risk of overlap between the airflow pulsation frequency and the inherent frequency of the product stack is detected, the airflow pulsation frequency is changed by dynamically adjusting the fan speed; simultaneously, the airflow disturbance and product stack response status are continuously monitored, and closed-loop adjustments are automatically executed based on frequency changes. The specific steps are as follows: The machine learning model outputs the current frequency overlap risk coefficient. And compare it with the preset frequency overlap risk coefficient reference threshold to form a judgment standard: in, It is a reference threshold for the frequency overlap risk coefficient; When an overlap risk is identified, the fan speed is adjusted based on the difference between the current airflow pulsation frequency and the natural frequency of the product stack. The updated fan speed calculation expression is as follows: In the formula, This is the adjusted fan speed. It is the initial fan speed. It is the inherent frequency of product stacking. It is the pulsation frequency of the airflow in the current air-cooling system. It is the sensitivity coefficient for adjusting the fan speed. It is a tiny positive number set to prevent the denominator from approaching zero; After the rotation speed is adjusted, a closed-loop monitoring system is entered, continuously tracking the adjusted airflow frequency and product stacking frequency, and recalculating the latest frequency overlap risk factor. If the following conditions are still met: ;like The risk of frequency overlap has been eliminated, the current wind turbine speed is locked, and the system has returned to monitoring status.

[0014] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This invention combines real-time monitoring, data preprocessing, intelligent evaluation, and dynamic adjustment to form a closed-loop control system that ensures airflow disturbances during kiln cooling do not resonate with the natural frequency of the product stack. Through intelligent analysis using a machine learning model, the system can accurately determine changes in the product stack frequency and automatically adjust the fan speed when a potential resonance risk is detected, thus preventing resonance in real time. Simultaneously, continuous frequency monitoring and feedback adjustments ensure stability and safety during the cooling process. This intelligent, dynamic adjustment method not only improves the stability and cooling efficiency of kiln production but also effectively reduces equipment damage and safety hazards, enhancing the overall safety and reliability of the production system. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0016] Figure 1 This is a flowchart of a product cooling method with a cooling section inside a kiln, according to the present invention. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0018] This invention provides, for example Figure 1 The product cooling method shown includes the following steps: A cooling section is provided inside the kiln. The air-cooling system cools the products in the kiln with an initial air velocity, establishing a stable initial cooling environment; The primary objective is to establish a basic cooling environment in the initial stage, upon which subsequent adjustments can be optimized. With an initial airflow rate, the airflow begins to act on the product stack, helping to lower the product temperature and providing basic data for the system to monitor frequency changes in the product stack. Setting the initial airflow rate provides a working baseline for the system, ensuring that subsequent frequency change monitoring and airflow adjustment are performed based on this standard. This is also necessary to ensure stable system operation, accumulating preliminary data for subsequent steps and providing a reference for further adjustments to airflow rate and airflow.

[0019] The specific steps for establishing a stable initial cooling environment by cooling the products in the kiln using initial air velocity are as follows: First, the air-cooling system is activated and an initial airflow speed is set. This speed is calculated based on the product's heat load and the design requirements of the cooling section, ensuring moderate airflow intensity that does not excessively disturb the product stacking. Next, the fan begins operating at the set initial airflow speed, continuously providing a uniform airflow to the product surface, allowing heat from the product surface to gradually dissipate into the airflow, thus initiating the cooling process. In this way, the air-cooling system gradually establishes a stable initial cooling environment, allowing the product temperature to steadily decrease within the cooling section. At this point, the airflow speed is maintained within a fixed range to ensure a uniform and continuous cooling process, while monitoring temperature changes in both the product and the airflow to guarantee the stability of the cooling environment, laying the foundation for subsequent dynamic adjustments and further operations.

[0020] High-precision sensors (such as accelerometers and laser vibrometers) are used to acquire real-time frequency variation data of product stacking in the kiln. The acquired raw data is preprocessed and the complex raw data is transformed into a structured dataset. To obtain real-time data on the frequency changes of product stacking in the kiln, the following high-precision sensors can be used: 1. Accelerometer: Used to measure the vibration acceleration of product stacks, it can capture the dynamic response of product stacks in different directions.

[0021] High-precision accelerometers can provide a wide frequency range for detecting vibration characteristics and frequency changes in product stacks, and are especially suitable for dynamic monitoring with a wide frequency range.

[0022] 2. Laser Doppler Vibrometer (LDV): Laser vibration meters measure the vibration velocity of a product stack surface by reflecting a laser beam. They can obtain the vibration frequency and amplitude of the product stack very accurately, making them suitable for non-contact monitoring.

[0023] LDV provides high-precision vibration data without causing any interference to the product or kiln, making it ideal for real-time frequency monitoring in high-temperature or harsh environments.

[0024] 3. Displacement Sensor: Displacement sensors deduce the frequency and vibration characteristics of product stacks by measuring changes in their displacement. Commonly used displacement sensors include laser displacement sensors and eddy current displacement sensors, which can detect product stack displacement very accurately.

[0025] Suitable for high-precision displacement detection, it can help analyze the impact of airflow disturbance on product stacks during the cooling process.

[0026] 4. Piezoelectric sensor: Piezoelectric sensors can detect vibrations in product stacks and convert mechanical vibrations into electrical signals, providing high-precision vibration data.

[0027] It is particularly suitable for detecting minute vibration changes and can accurately capture the inherent frequency changes of product stacking and frequency fluctuations caused by airflow disturbances.

[0028] 5. Strain Gauge: Strain gauges can be used to measure the minute deformations of product stacks under airflow disturbances, and the frequency characteristics of the product stacks can be calculated by combining the strain changes.

[0029] High-precision strain gauges can provide real-time structural feedback, helping to assess the stability and resonance risk of product stacking.

[0030] 6. Fiber Optic Sensor: Fiber optic sensors use changes in the reflection of light signals within optical fibers to measure the vibration or displacement of objects, making them suitable for monitoring in high-temperature environments.

[0031] By deploying fiber optic sensors in the kiln, it is possible to achieve remote and high-precision monitoring of changes in the frequency of product stacking.

[0032] These high-precision sensors can help capture changes in the vibration frequency of product stacks in real time and provide accurate data support for subsequent analysis and adjustment, ensuring the stability of product stacks during kiln production.

[0033] These sensors can accurately capture the vibration changes of product stacks under the influence of airflow. The data acquisition frequency must be high enough to ensure accurate recording of the product stack's vibration patterns, especially changes in its natural frequency. Real-time data acquisition allows the system to dynamically track the vibration state of the product stack and provides real-time input for subsequent data analysis and wind speed adjustment. If the vibration frequency of the product stack changes, or when the airflow disturbance frequency approaches the product stack's natural frequency, these changes can be immediately reflected, providing a basis for further processing.

[0034] After acquiring data on product stacking frequency variations, this raw data needs to be preprocessed to remove noise, fill in missing values, and standardize the data. The purpose of data preprocessing is to transform the complex raw data into a structured dataset, which will serve as the basis for subsequent analysis. Data preprocessing includes the following steps: noise removal, data smoothing, frequency range standardization, and removal of invalid or outlier data. After preprocessing, the dataset will be more reliable and accurate, and can be used to extract and analyze core indicators reflecting the overlap between airflow pulsation frequency and the inherent frequency of product stacking. Through preprocessing, data quality is improved, ensuring the accuracy and effectiveness of subsequent machine learning models.

[0035] The core indicators reflecting the risk of overlap between airflow pulsation frequency and product stacking natural frequency are extracted from the dataset. The extracted core indicators are then comprehensively analyzed to quantify the degree of overlap between airflow pulsation frequency and product stacking natural frequency, thereby assessing the resonance risk. Frequency analysis (such as Fourier transform and time-frequency analysis) can identify the pulsating frequency of airflow disturbances and the natural frequency of product stacking. Then, the overlap of these frequencies is quantified to determine the presence of resonance risk. Overlap quantification typically involves calculating the frequency difference between the airflow pulsating frequency and the natural frequency of the product stacking, and whether they coincide within a certain error range. The quantified data provides the system with quantitative data for resonance risk assessment and offers necessary feature information for input to machine learning models.

[0036] Core indicators reflecting the risk of overlap between airflow pulsation frequency and the natural frequency of product stacking were extracted from the dataset. The extracted indicators include the response intensity of periodic airflow disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking. The response intensity of periodic airflow disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking were comprehensively analyzed to generate periodic excitation response reference values ​​and dynamic stress enhancement reference values. The degree of overlap between airflow pulsation frequency and the natural frequency of product stacking was quantified by the periodic excitation response reference values ​​and dynamic stress enhancement reference values, thereby assessing the resonance risk.

[0037] The increased response intensity of the product stack vibration to periodic airflow disturbances indeed indicates a risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack. This is because when the periodic airflow disturbance approaches or coincides with the natural frequency of the product stack, the vibration response of the product stack is significantly affected by the resonance effect. When resonance occurs, the frequency of the external airflow disturbance matches the natural frequency of the product stack, leading to an amplification of the vibration amplitude – this is the so-called increased vibration response. This increased vibration response indicates that the product stack system has entered a resonance range, meaning the airflow pulsation frequency overlaps with the natural frequency of the product stack. Under these circumstances, the vibration amplitude of the product stack will continue to increase, potentially leading to instability, displacement, or even collapse of the product stack, severely affecting the stability of the kiln cooling process. By monitoring changes in this response intensity, the risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack can be effectively assessed, and measures can be taken to avoid entering a resonance state, thereby ensuring a smooth cooling process and safe equipment operation.

[0038] The specific steps for generating reference values ​​for periodic excitation response by comprehensively analyzing the response intensity of periodic airflow disturbances to product stacking vibration within a detection window are as follows: Vibration response data of product stacks under periodic airflow disturbances are acquired using high-precision vibration sensors. The dominant disturbance frequency of the current airflow and the dominant response frequency of the product stack under the disturbance are identified. Simultaneously, the vibration amplitude of the product stack at the dominant response frequency is extracted to generate a nonlinear vibration response factor. The generation formula is as follows: In the formula, It is a nonlinear vibration response factor, representing the frequency at which the vibration response occurs. The following is a comprehensive index of the intensity and risk level of the vibration response caused by product stacking. It is the product stacking response frequency, which represents the main response frequency at which the product stack generates the maximum amplitude after being disturbed, reflecting the "response characteristic frequency point" of the product stack. It is the dominant airflow disturbance frequency, representing the dominant disturbance frequency caused by the periodic changes of the fan, blade interference, or structure in the air-cooled system. Is the product stacking at the response frequency The vibration amplitude below indicates the product stacking structure at a specific frequency. The actual vibration amplitude generated below It is the vibration amplitude enhancement index, an exponential amplification factor applied to the vibration amplitude of product stacking, used to improve the recognition sensitivity during large-amplitude responses. It is the frequency difference attenuation index, used to adjust the influence of the deviation between the disturbance frequency and the response frequency in the formula; Identify and quantify the dynamic coupling relationship between airflow disturbance frequency and product stacking natural frequency, and construct a nonlinear vibration response factor. This process accurately detects whether product stacking exhibits a resonance trend under specific airflow excitation. This step provides a highly sensitive basis for determining frequency overlap in subsequent risk assessments and fan adjustments, ensuring that resonance risks can be accurately identified at an early stage.

[0039] After acquiring data pairs of multiple disturbance frequencies and corresponding product stacking response frequencies, the nonlinear vibration response factors under all disturbance frequencies are combined to generate a periodic excitation response reference value, representing the sensitivity of the product stacking to all periodic disturbance frequencies within the entire detection window. The calculation expression is as follows: In the formula, It is a reference value for periodic excitation response. It is the first Nonlinear vibration response factor at a disturbance frequency It represents the total number of disturbance frequencies. It is the first The proximity coefficient between the disturbance frequency and the product stacking response frequency.

[0040] By weighted and fused with the frequency proximity of the product stack's response intensity at multiple disturbance frequencies, a comprehensive index reflecting the product stack's sensitivity to periodic airflow disturbances is constructed. The generated periodic excitation response reference value can be used to dynamically determine whether the current system is in the resonance critical region, thus providing a quantitative basis for real-time adjustment of fan parameters.

[0041] The larger the periodic excitation response reference value generated by comprehensively analyzing the response intensity of product stack vibration to periodic airflow disturbances within a detection window, the greater the risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack; conversely, a smaller value indicates the absence of overlap. Specifically, the periodic excitation response reference value reflects the vibration amplification effect of the product stack on airflow disturbances. When the airflow pulsation frequency is close to or overlaps with the natural frequency of the product stack, the vibration amplitude of the product stack increases significantly, resulting in a larger response reference value. This is because, under resonance, the natural frequency of the product stack and the airflow pulsation frequency match, leading to vibration amplification and a stronger response. Conversely, if the frequencies differ significantly, no resonance effect occurs, the vibration response of the product stack is weaker, and the periodic excitation response reference value will be lower. Therefore, the performance value of the periodic excitation response reference value is an effective indicator for assessing whether the airflow pulsation frequency overlaps with the natural frequency of the product stack; a larger value indicates a higher risk of overlap, and vice versa.

[0042] A reference-value-level increase in the stress distribution within the product stack due to airflow pulsation frequency indicates a risk of overlap between the airflow pulsation frequency and the product stack's natural frequency. When this overlap occurs, resonance occurs within the product stack, leading to a sharp increase in vibration amplitude and exacerbating internal stress. Since the product stack is a flexible structure composed of particles or blocks, when the airflow pulsation frequency is close to or coincides with the stack's natural frequency, the resonance effect amplifies the energy of external disturbances, resulting in a reference-value-level stress increase. This stress increase indicates that the product stack structure is facing a greater vibration load, exceeding its stability limit, potentially leading to instability or structural failure. Particularly when the airflow pulsation frequency is near the stack's natural frequency, micro-cracks or stress concentration areas within the stack are amplified, increasing the risk of rupture or collapse. Therefore, monitoring the reference-value-level increase in stress distribution can effectively identify the risk of overlap between the airflow pulsation frequency and the stack's natural frequency, allowing for adjustment measures to avoid entering the resonance range and ensuring the stability and safety of the cooling process.

[0043] The specific steps for generating dynamic stress enhancement reference values ​​by comprehensively analyzing the stress distribution inside the product stack based on the airflow pulsation frequency within the detection window are as follows: Multiple product stacking observation points (e.g., contact surfaces, structural transition zones, etc.) were selected to collect stress response values ​​under disturbance and basic stress values ​​collected under undisturbed conditions. A disturbance response ratio model was introduced to calculate the disturbance stress enhancement ratio. The calculation expression is as follows: In the formula, It refers to the instantaneous stress value under disturbance conditions, specifically the dynamic stress response value generated at each measuring point of the product stack under the current airflow pulsation frequency. It reflects the internal stress state of the product stack under the influence of external periodic disturbances. It is the reference stress value under undisturbed conditions, representing the initial stress state of the product stacking structure under conditions of no airflow disturbance or extremely small disturbance intensity, equivalent to the "static baseline value". This represents the maximum stress increase caused by the disturbance. It indicates the point with the largest stress increase among all measuring points, representing the most extreme response under the current disturbance conditions. It is the minimum reference stress. Among all the reference stresses collected, the one with the smallest value is selected, representing the area in the product stack that is most "loose" or has the lowest stress due to disturbance. It is a small positive number set to prevent the denominator from approaching zero (such as...). ), to enhance numerical stability, It is the disturbance stress amplification ratio, which represents the local stress amplification factor in the product stacking structure under airflow disturbance conditions. It is a physical indicator for measuring the resonance-induced effect of airflow on product stacking. By modeling the difference in product stacking stress under disturbed and steady-state conditions, the amplification effect of airflow pulsation on local stress in the product stack is quantified, thereby identifying potential stress surge points within the structure caused by external disturbances. This step can sensitively capture local stress anomalies caused by airflow disturbances, providing crucial physical evidence and response characteristics for determining the existence of resonance-induced risks.

[0044] Based on the ratio of disturbance stress enhancement The deviation between the main airflow disturbance frequency and the product stacking response frequency is considered, and coupled quantization is performed using a nonlinear gain function to generate a dynamic stress enhancement reference value. The generation formula is as follows: In the formula, It is a reference value for dynamic stress enhancement. It is the product stacking response frequency. It is the frequency of the main airflow disturbance. It is a frequency coupling sensitivity parameter used to control the main airflow disturbance frequency. Product stacking response frequency The "steepness" of the response of the difference in the exponential function, i.e., the sensitivity adjustment coefficient for identifying the resonant critical state, It is the natural base.

[0045] By quantifying the proximity of the current airflow pulsation frequency to the natural frequency of the product stack, and coupling this with the stress amplification effect caused by disturbances, a more sensitive dynamic identification index for resonance risk is formed. This step enables precise amplification of the response within the resonance critical range, allowing the system to identify and warn of product stack instability risks in advance when frequencies are close, thus improving the safety and intelligent control capabilities of the entire cooling process.

[0046] A larger dynamic stress enhancement reference value, generated by comprehensively analyzing the stress distribution within the product stack under a detection window based on airflow pulsation frequency, indicates a higher risk of overlap between the airflow pulsation frequency and the product stack's natural frequency. This is because when the airflow pulsation frequency is close to or overlaps with the product stack's natural frequency, the product stack enters a resonance state, causing the stress induced by external airflow disturbances to amplify rapidly within the product stack, resulting in a significant increase in the reference stress value. This enhancement reflects the degree of matching between the airflow disturbance energy and the product stack's natural frequency, indicating a large vibration load and a risk of instability. Conversely, a smaller dynamic stress enhancement reference value indicates a larger gap between the airflow pulsation frequency and the product stack's natural frequency, meaning it has not entered the resonance range and therefore there is no risk of overlap.

[0047] The core indicators after comprehensive analysis are input into a pre-trained machine learning model. The model is used to intelligently evaluate the changes in product stacking frequency and determine whether there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking. The periodic excitation response reference value and dynamic stress enhancement reference value after comprehensive analysis are input into the pre-trained machine learning model. The machine learning model generates a frequency overlap risk coefficient, and the frequency overlap risk coefficient is used to intelligently evaluate the product stacking frequency change to determine whether there is a risk of overlap between the airflow pulsation frequency and the product stacking inherent frequency.

[0048] A pre-trained machine learning model refers to a model that has been trained and learned from a large amount of data, enabling it to make intelligent decisions and predictions on a specific task. In this case, the goal of the machine learning model is to intelligently assess the risk of overlap between airflow pulsation frequency and the natural frequency of product stacking using input features (such as periodic excitation response reference values ​​and dynamic stress enhancement reference values). During training, the model learns from a large amount of historical data to establish the relationship between airflow disturbances and product stacking vibrations, and understands how they interact, especially when resonance occurs. The training process involves using a dataset containing known results and continuously optimizing the model's parameters so that the model can accurately predict whether there is an overlap risk given the input features. This training data typically includes actual airflow disturbances, product stacking vibration responses, and frequency overlap cases under various operating conditions. Through this data, the machine learning algorithm learns how to assess the dynamic relationship between airflow and product stacking, and whether their relative frequency relationship will lead to resonance.

[0049] Once the machine learning model is trained and its effectiveness validated, it can be used in real-time applications. During kiln production, the system acquires key features such as periodic excitation response reference values ​​and dynamic stress enhancement reference values ​​from sensors in real time. This data is input into a pre-trained model, which uses its learned knowledge to generate a frequency overlap risk coefficient. This coefficient represents the degree of overlap between the airflow pulsation frequency and the inherent frequency of the product stack; a higher value indicates a greater risk of overlap, and vice versa. Through this intelligent assessment, the system can determine whether resonance risk exists and take corresponding adjustment measures based on the level of risk, such as dynamically adjusting the fan speed and adjusting the airflow frequency, thereby avoiding resonance and ensuring the stability and safety of the production process. Therefore, the pre-trained machine learning model not only helps analyze the relationship between airflow and product stack frequency in real time but also provides intelligent support for frequency management in kiln production.

[0050] The machine learning model is not limited here, as long as it can achieve the reference value of periodic stimulus response. and dynamic stress enhancement reference value A comprehensive analysis is conducted to generate a frequency overlap risk coefficient. Any machine learning model can be used. To implement the technical solution of this invention, this invention provides a specific implementation method: Frequency overlap risk coefficient The formula for generating the formula is as follows: In the formula, and These are the reference values ​​for periodic excitation response. and dynamic stress enhancement reference value The preset proportional coefficient, and and All are greater than 0.

[0051] Preset ratio coefficient and It is a constant used to adjust the reference value of the periodic excitation response. and dynamic stress enhancement reference value Frequency overlap risk coefficient The proportion of contribution.

[0052] Preset ratio coefficient and These are constants obtained through experience or model calibration, representing the degree of influence of each factor on the total frequency overlap risk. Specifically, The reference value for periodic excitation response is determined. Weights in frequency overlap risk This determines the reference value for dynamic stress enhancement. The influence. Based on the system's characteristics and experimental data, and The value can be adjusted to ensure that the influence of each factor is appropriately amplified or reduced.

[0053] The values ​​of these proportionality coefficients are typically determined through actual testing or numerical simulation, reflecting reference values ​​for the periodic excitation response. and dynamic stress enhancement reference value The specific contributions of these two parameters to the risk of frequency overlap. In this model, and All values ​​are greater than zero, meaning the periodic excitation response reference value and dynamic stress enhancement reference value Both will have a positive impact on the risk of frequency overlap.

[0054] In summary, the preset scaling factor is used to adjust the parameters in the model to ensure that the impact of periodic excitation response and dynamic stress enhancement on the risk of frequency overlap is reasonably quantified and controlled.

[0055] As can be seen from the frequency overlap risk coefficient, the larger the reference value of the periodic excitation response generated after comprehensively analyzing the response intensity of the periodic airflow disturbance to the product stack vibration under the detection window, and the larger the reference value of the dynamic stress enhancement generated after comprehensively analyzing the stress distribution inside the product stack under the detection window, the larger the frequency overlap risk coefficient generated when intelligently evaluating the frequency change of the product stack through the pre-trained machine learning model, the greater the probability that the airflow pulsation frequency and the natural frequency of the product stack overlap. Conversely, the smaller the frequency overlap risk coefficient, the smaller the probability that the airflow pulsation frequency and the natural frequency of the product stack overlap.

[0056] The frequency overlap risk coefficient generated by the pre-trained machine learning model when intelligently assessing product stacking frequency changes is compared with a pre-set frequency overlap risk coefficient reference threshold to determine whether there is an overlap risk between the airflow pulsation frequency and the inherent frequency of product stacking. The judgment logic is as follows: If the frequency overlap risk coefficient is greater than the preset frequency overlap risk coefficient reference threshold, it is determined that there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking; if the frequency overlap risk coefficient is less than or equal to the preset frequency overlap risk coefficient reference threshold, it is determined that there is no risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking.

[0057] When a risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack is detected, the fan speed is dynamically adjusted to change the airflow pulsation frequency, so that it avoids the overlap range with the natural frequency of the product stack. At the same time, the airflow disturbance and the product stack response status are continuously monitored, and closed-loop adjustment is automatically executed according to the frequency change to achieve real-time avoidance and dynamic control of resonance risk. By dynamically adjusting the fan speed and implementing closed-loop control, the system mitigates the resonance risk caused by the overlap between the airflow pulsation frequency and the natural frequency of the product stack, ensuring the stability and safety of the kiln cooling process. Specifically, when the airflow pulsation frequency is detected to be close to or overlap with the natural frequency of the product stack, the fan speed is first adjusted to change the airflow pulsation frequency, thus moving the airflow frequency away from the natural frequency of the product stack and preventing it from entering the resonance range. Through variable frequency control technology, the fan speed can be adjusted in real time to precisely control the airflow pulsation frequency and prevent resonance. Simultaneously, the system continuously monitors airflow disturbances and the vibration response of the product stack, using a real-time feedback mechanism to continuously detect changes in the airflow frequency and product stack frequency to determine if resonance risk still exists. Based on the monitoring data, automatic closed-loop adjustments are performed to ensure that the matching between the airflow frequency and the natural frequency of the product stack remains within a safe range. This automatic adjustment and real-time monitoring closed-loop control strategy not only effectively avoids resonance risks but also ensures stable system operation, preventing problems such as product stack instability, uneven cooling, or equipment damage, thereby improving the efficiency and safety of the production process.

[0058] When a risk of overlap between the airflow pulsation frequency and the inherent frequency of the product stack is detected, the airflow pulsation frequency is changed by dynamically adjusting the fan speed. Simultaneously, the airflow disturbance and product stack response status are continuously monitored, and closed-loop adjustments are automatically executed based on frequency changes. The specific steps are as follows: The machine learning model outputs the current frequency overlap risk coefficient. And compare it with the preset frequency overlap risk coefficient reference threshold to form a judgment standard: in, It is a reference threshold for the frequency overlap risk coefficient; When an overlap risk is identified, the fan speed is adjusted based on the difference between the current airflow pulsation frequency and the natural frequency of the product stack. The updated fan speed calculation expression is as follows: In the formula, This is the adjusted fan speed. It is the initial fan speed. It is the natural frequency of the product stack, that is, the natural vibration frequency of the product stack when it is not subject to external interference. It is the pulsation frequency of the airflow in the current air-cooling system. It is the sensitivity coefficient for fan speed regulation, which controls the degree to which changes in fan speed affect airflow frequency adjustment. It is a small positive number set to prevent the denominator from approaching zero (such as...). ), to enhance numerical stability; By using a normalized adjustment function based on the frequency difference, precise peak avoidance operation of the fan pulsation frequency can be achieved, effectively escaping the resonance range with the inherent frequency of the product stack, and preventing stack tip instability, slippage or collapse caused by resonance.

[0059] After the rotation speed is adjusted, a closed-loop monitoring system is entered, continuously tracking the adjusted airflow frequency and product stacking frequency, and recalculating the latest frequency overlap risk factor. If the following conditions are still met: ;like The risk of frequency overlap has been eliminated, the current wind turbine speed is locked, and the system has returned to monitoring status.

[0060] This step ensures the system has adaptive adjustment capabilities, enabling continuous optimization of the wind turbine's operating status under dynamically changing frequency disturbances. It achieves real-time avoidance of resonance risks, closed-loop control, and maintenance of dynamic stability.

[0061] This invention combines real-time monitoring, data preprocessing, intelligent evaluation, and dynamic adjustment to form a closed-loop control system that ensures airflow disturbances during kiln cooling do not resonate with the natural frequency of the product stack. Through intelligent analysis using a machine learning model, the system can accurately determine changes in the product stack frequency and automatically adjust the fan speed when a potential resonance risk is detected, thus preventing resonance in real time. Simultaneously, continuous frequency monitoring and feedback adjustments ensure stability and safety during the cooling process. This intelligent, dynamic adjustment method not only improves the stability and cooling efficiency of kiln production but also effectively reduces equipment damage and safety hazards, enhancing the overall safety and reliability of the production system.

[0062] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0063] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0064] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0065] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0066] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0069] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0070] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0071] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for cooling and reducing the temperature of products in a kiln equipped with a cooling and temperature-reducing section, characterized in that, Includes the following steps: The air-cooling system cools the products in the kiln with an initial air velocity, establishing a stable initial cooling environment; High-precision sensors are used to acquire real-time data on the frequency changes of product stacking in the kiln. The acquired raw data is preprocessed and the complex raw data is transformed into a structured dataset. The core indicators reflecting the risk of overlap between airflow pulsation frequency and product stacking natural frequency are extracted from the dataset. The extracted core indicators are then comprehensively analyzed to quantify the degree of overlap between airflow pulsation frequency and product stacking natural frequency, thereby assessing the resonance risk. The core indicators after comprehensive analysis are input into a pre-trained machine learning model. The model is used to intelligently evaluate the changes in product stacking frequency and determine whether there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking. When a risk of overlap between the airflow pulsation frequency and the natural frequency of the product stack is detected, the fan speed is dynamically adjusted to change the airflow pulsation frequency, so that it avoids the overlap range with the natural frequency of the product stack. At the same time, the airflow disturbance and the product stack response status are continuously monitored, and closed-loop adjustment is automatically executed according to the frequency change to achieve real-time avoidance and dynamic control of resonance risk.

2. The product cooling method according to claim 1, wherein a cooling section is provided inside the kiln, characterized in that, The specific steps for establishing a stable initial cooling environment by cooling the products in the kiln using initial air velocity are as follows: First, start the air-cooling system and set the initial air speed. The air speed is calculated based on the product's heat load and the design requirements of the cooling section to ensure that the airflow intensity is moderate and does not disturb the product stacking too violently. Next, the fan starts working at the set initial wind speed, continuously providing a uniform airflow to the product surface, so that the heat on the product surface is gradually dissipated into the airflow, thus starting the cooling process; At this point, the wind speed is maintained within a fixed range to ensure a uniform and continuous cooling process. At the same time, the temperature changes of the product and the airflow are monitored to ensure the stability of the cooling environment, laying the foundation for subsequent dynamic adjustments and further operations.

3. A product cooling method with a cooling section inside a kiln according to claim 1, characterized in that, Core indicators reflecting the risk of overlap between airflow pulsation frequency and the natural frequency of product stacking were extracted from the dataset. The extracted indicators include the response intensity of periodic airflow disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking. The response intensity of periodic airflow disturbance to product stack vibration and the effect of airflow pulsation frequency on the internal stress distribution of product stacking were comprehensively analyzed to generate periodic excitation response reference values ​​and dynamic stress enhancement reference values. The degree of overlap between airflow pulsation frequency and the natural frequency of product stacking was quantified by the periodic excitation response reference values ​​and dynamic stress enhancement reference values, thereby assessing the resonance risk.

4. A product cooling method with a cooling section inside a kiln according to claim 3, characterized in that, The specific steps for generating reference values ​​for periodic excitation response by comprehensively analyzing the response intensity of periodic airflow disturbances to product stacking vibration within a detection window are as follows: Vibration response data of product stacks under periodic airflow disturbances are acquired using high-precision vibration sensors. The dominant disturbance frequency of the current airflow and the dominant response frequency of the product stack under the disturbance are identified. Simultaneously, the vibration amplitude of the product stack at the dominant response frequency is extracted to generate a nonlinear vibration response factor. The generation formula is as follows: In the formula, It is a nonlinear vibration response factor. It is the product stacking response frequency. It is the frequency of the main airflow disturbance. Is the product stacking at the response frequency The vibration amplitude below, It is the vibration amplitude enhancement index. It is the frequency difference attenuation index; After acquiring data pairs of multiple disturbance frequencies and corresponding product stacking response frequencies, the nonlinear vibration response factors under all disturbance frequencies are combined to generate a periodic excitation response reference value, representing the sensitivity of the product stacking to all periodic disturbance frequencies within the entire detection window. The calculation expression is as follows: In the formula, It is a reference value for periodic excitation response. It is the first Nonlinear vibration response factor at a disturbance frequency It represents the total number of disturbance frequencies. It is the first The proximity coefficient between the disturbance frequency and the product stacking response frequency.

5. A product cooling method with a cooling section inside a kiln according to claim 3, characterized in that, The specific steps for generating dynamic stress enhancement reference values ​​by comprehensively analyzing the stress distribution inside the product stack based on the airflow pulsation frequency within the detection window are as follows: Multiple product stacking observation points were selected to collect stress response values ​​under disturbance and base stress values ​​collected under undisturbed conditions. A disturbance response ratio model was introduced to calculate the disturbance stress enhancement ratio. The calculation expression is as follows: In the formula, It is the instantaneous stress value under disturbance conditions. It is the reference stress value under undisturbed conditions. It is the maximum stress increase caused by the disturbance. It is the minimum reference stress. It is a tiny positive number set to prevent the denominator from approaching zero. It is the ratio of disturbance stress enhancement; Based on the ratio of disturbance stress enhancement The deviation between the main airflow disturbance frequency and the product stacking response frequency is considered, and coupled quantization is performed using a nonlinear gain function to generate a dynamic stress enhancement reference value. The generation formula is as follows: In the formula, It is a reference value for dynamic stress enhancement. It is the product stacking response frequency. It is the frequency of the main airflow disturbance. It is a frequency coupling sensitivity parameter. It is the natural base.

6. A product cooling method with a cooling section inside a kiln according to claim 3, characterized in that, The periodic excitation response reference value and dynamic stress enhancement reference value after comprehensive analysis are input into the pre-trained machine learning model. The machine learning model generates a frequency overlap risk coefficient, and the frequency overlap risk coefficient is used to intelligently evaluate the product stacking frequency change to determine whether there is a risk of overlap between the airflow pulsation frequency and the product stacking inherent frequency.

7. A product cooling method with a cooling section inside a kiln according to claim 6, characterized in that, The frequency overlap risk coefficient generated by the pre-trained machine learning model when intelligently assessing product stacking frequency changes is compared with a pre-set frequency overlap risk coefficient reference threshold to determine whether there is an overlap risk between the airflow pulsation frequency and the inherent frequency of product stacking. The judgment logic is as follows: If the frequency overlap risk coefficient is greater than the preset frequency overlap risk coefficient reference threshold, it is determined that there is a risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking; if the frequency overlap risk coefficient is less than or equal to the preset frequency overlap risk coefficient reference threshold, it is determined that there is no risk of overlap between the airflow pulsation frequency and the inherent frequency of product stacking.

8. A product cooling method with a cooling section inside a kiln according to claim 7, characterized in that, When a risk of overlap between the airflow pulsation frequency and the inherent frequency of the product stack is detected, the airflow pulsation frequency is changed by dynamically adjusting the fan speed. Simultaneously, the airflow disturbance and product stack response status are continuously monitored, and closed-loop adjustments are automatically executed based on frequency changes. The specific steps are as follows: The current frequency overlap risk coefficient is output through a machine learning model. And compare it with the preset frequency overlap risk coefficient reference threshold to form a judgment standard: in, It is a reference threshold for the frequency overlap risk coefficient; When an overlap risk is identified, the fan speed is adjusted based on the difference between the current airflow pulsation frequency and the natural frequency of the product stack. The updated fan speed calculation expression is as follows: In the formula, This is the adjusted fan speed. It is the initial fan speed. It is the inherent frequency of product stacking. It is the pulsation frequency of the airflow in the current air-cooling system. It is the sensitivity coefficient for adjusting the fan speed. It is a tiny positive number set to prevent the denominator from approaching zero; After the rotation speed is adjusted, a closed-loop monitoring system is entered, continuously tracking the adjusted airflow frequency and product stacking frequency, and recalculating the latest frequency overlap risk factor. If the following conditions are still met: ;like The risk of frequency overlap has been eliminated, the current wind turbine speed is locked, and the system has returned to monitoring status.

Images