Parameter control method and system for flue gas denitration catalyst preparation process

Abstract

The invention discloses a parameter control method and system for a flue gas denitration catalyst preparation process, and relates to the technical field of catalyst production control, and the method comprises the steps: obtaining equipment operation parameters and physicochemical characteristic information of raw materials; according to the equipment operation parameters and the physicochemical characteristic information, the part loss influence degree is evaluated; according to the part loss influence degree, the physicochemical characteristic information, the equipment operation parameter and the parameter reference range, calculating a target stress value generated on the equipment part when the operation parameter deviates from the reference; performing cumulative calculation on the plurality of target stress values to obtain a cumulative fatigue index; according to the accumulated fatigue index, evaluating the loss trend of the equipment part; and generating a parameter control strategy according to the equipment part loss trend. According to the invention, the accumulated fatigue index and the equipment part loss trend can be combined to generate the parameter control strategy so as to realize parameter control, and the accuracy and the product quality are improved.

Description

Technical Field

[0001] This invention relates to the field of catalyst production control technology, and in particular to a parameter control method and system for the preparation process of flue gas denitrification catalyst. Background Technology

[0002] The production process of flue gas denitrification catalysts includes steps such as raw material mixing, kneading, extrusion molding, drying, and high-temperature calcination. Traditionally, manual parameter adjustments are relied upon, leading to significant batch-to-batch performance variations, high energy consumption, and unstable activity, thus affecting nitrogen oxide removal efficiency. Existing control systems collect information such as temperature, pressure, and humidity, adjusting actuators according to preset rules. However, raw material powders from different suppliers, or even different batches from the same supplier, vary in particle size distribution, surface area, and trace impurity content. These differences directly impact subsequent production; for example, smaller particles require more moisture during kneading, altering the drying burden; certain impurities react with active components during high-temperature calcination, reducing catalyst activity. Existing systems struggle to identify differences between batches of raw materials, resulting in fluctuating catalyst performance, low parameter control precision, and compromised product quality.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this invention is to propose a parameter control method and system for the preparation process of flue gas denitrification catalysts. This method can combine cumulative fatigue indexes and equipment component wear trends to generate parameter control strategies, thereby achieving parameter control and improving accuracy and product quality.

[0005] On one hand, embodiments of the present invention provide a parameter control method for the preparation process of a flue gas denitrification catalyst, comprising the following steps: Obtain information on equipment operating parameters and the physicochemical properties of raw materials; Based on the equipment operating parameters and the physicochemical properties information, assess the degree of impact of component wear; Based on the degree of impact of component wear, the physicochemical property information, the equipment operating parameters and parameter reference range, calculate the target stress value generated on the equipment components when the operating parameters deviate from the reference. The cumulative fatigue index is obtained by accumulating multiple target stress values. The wear trend of equipment components is assessed based on the cumulative fatigue index. A parameter control strategy is generated based on the wear trend of the equipment components.

[0006] In some embodiments, assessing the impact of component wear based on the device operating parameters and the physicochemical property information includes: Obtain historical running parameters; Based on the historical operating parameters, calculate the average value and range of the parameters; Based on the aforementioned physicochemical properties, determine the raw material property weighting coefficient and the duration weighting coefficient; The load factor is calculated based on the equipment operating parameters, the average value of the parameters, the parameter range, the weighting coefficient of the raw material characteristics, and the weighting coefficient of the duration. Calculate the rate of change of the load factors based on the multiple load factors mentioned above; The degree of impact of component wear is assessed based on the rate of change of the load factor.

[0007] In some embodiments, calculating the target stress value generated on the equipment component when the operating parameters deviate from the reference, based on the degree of component wear, the physicochemical property information, the equipment operating parameters, and the parameter reference range, includes: Acquire microscopic physical response signals during device operation; Based on the microscopic physical response signal, an impact event caused by the microscopic non-uniformity of the raw material is identified; The intensity of the impact event is calculated based on the type of microscopic non-uniformity of the raw materials and the impact characteristics corresponding to the impact event. Calculate the initial stress value based on the aforementioned physicochemical properties; Calculate the degree of parameter deviation based on the equipment operating parameters and the parameter reference range; The target stress value is calculated based on the intensity of the impact event, the initial stress value, the degree of impact of component wear, and the degree of parameter deviation.

[0008] In some embodiments, identifying impact events caused by microscopic non-uniformity of raw materials based on the microscopic physical response signal includes: The microscopic physical response signal is subjected to time-domain feature extraction to obtain time-domain features, which include instantaneous energy, peak amplitude and rise time. Frequency domain features are extracted from the microscopic physical response signal to obtain frequency domain features, which include the dominant frequency component and bandwidth. The time-frequency domain features are compared with the background vibration signal template to identify the difference signal segments. The time-frequency domain features include the time domain features and the frequency domain features. The impact event is identified based on the difference in the signal segments.

[0009] In some embodiments, identifying the impact event based on the differential signal segment includes: Time-frequency analysis was performed on the differential signal segments to obtain energy distribution and transient response characteristics; The energy distribution, the transient response characteristics, and the impact feature map are matched to obtain the matching results. The impact feature map contains various types of microscopic non-uniformity of raw materials. The impact event is identified based on the matching results.

[0010] In some embodiments, calculating the initial stress value based on the physicochemical property information includes: Acquire the reflectance spectrum image of the raw material; Based on the reflectance spectrum image, identify the feature deviation region; Extract spectral features from the region of feature deviation; Based on the spectral characteristics, information on abnormal impurities and hard particles is identified; Calculate the abnormal particle strength index based on the abnormal impurity information and the hard particle information; The initial stress value is calculated based on the physicochemical properties and the abnormal particle strength index.

[0011] In some embodiments, calculating the target stress value based on the impact event intensity, the initial stress value, the degree of component wear impact, and the degree of parameter deviation includes: The influence weight is determined based on the degree of impact of the component loss and the degree of deviation of the parameters; Calculate the weighted impact intensity value based on the impact event intensity and the impact weight; The target stress value is obtained by superimposing the weighted impact strength value with the initial stress value.

[0012] In some embodiments, assessing the wear trend of equipment components based on the cumulative fatigue index includes: Calculate the rate of change of the index based on the cumulative fatigue index; The fatigue loss conversion function is adjusted based on the rate of change of the aforementioned indicators, the equipment operating parameters, and the physicochemical properties. Based on the fatigue loss conversion function, the cumulative fatigue index is converted into the actual wear and tear of the equipment components. The wear trend of the equipment components is assessed based on their actual and historical wear.

[0013] In some embodiments, generating a parameter control strategy based on the wear trend of the device components includes: Obtain information on the current production line's production throughput demand, raw material inventory, product delivery deadlines, and equipment energy consumption levels; Based on the wear trend of the equipment components, the production throughput demand information, and the equipment energy consumption level information, a production adjustment strategy is determined. The production adjustment strategy includes adjusting the production speed, switching production batches, or temporarily stopping the machine for maintenance. Based on the wear and tear trend of the equipment components, the raw material inventory information, and the product delivery deadline information, a maintenance scheduling strategy is determined, which includes preventive maintenance, delayed maintenance, or component replacement. A comprehensive production impact assessment is performed on the production adjustment strategy and the maintenance scheduling strategy to obtain the comprehensive production impact. The parameter control strategy is generated based on the overall production impact, the production adjustment strategy, and the maintenance scheduling strategy.

[0014] On the other hand, embodiments of the present invention provide a parameter control system for the preparation process of a flue gas denitrification catalyst, comprising: The data acquisition module is used to acquire equipment operating parameters and physicochemical properties of raw materials; The impact assessment module is used to assess the impact of component wear based on the equipment operating parameters and the physicochemical properties information. The stress value calculation module is used to calculate the target stress value generated on the equipment component when the operating parameters deviate from the reference, based on the degree of component wear, the physicochemical property information, the equipment operating parameters and the parameter reference range; The stress accumulation module is used to accumulate and calculate multiple target stress values ​​to obtain cumulative fatigue indexes; The wear trend assessment module is used to assess the wear trend of equipment components based on the cumulative fatigue index. The control strategy generation module is used to generate parameter control strategies based on the wear trend of the equipment components.

[0015] The embodiments of this application include at least the following beneficial effects: First, the embodiments of this application obtain equipment operating parameters and physicochemical property information of raw materials. Based on the equipment operating parameters and physicochemical property information, the degree of influence of component wear is evaluated. Then, based on the degree of influence of component wear, physicochemical property information, equipment operating parameters and parameter reference range, the target stress value generated on the equipment component when the operating parameters deviate from the reference is calculated. Multiple target stress values ​​are accumulated to obtain a cumulative fatigue index. Then, based on the cumulative fatigue index, the wear trend of the equipment component is evaluated. Finally, based on the wear trend of the equipment component, a parameter control strategy is generated. Thus, the parameter control strategy can be generated by combining the cumulative fatigue index and the wear trend of the equipment component to achieve parameter control, thereby improving accuracy and product quality.

[0016] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0018] Figure 1 This is a flowchart of a parameter control method for the preparation process of a flue gas denitrification catalyst according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a parameter control system for the preparation process of a flue gas denitrification catalyst according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments.

[0020] In related technologies, the production process of flue gas denitrification catalysts includes steps such as raw material mixing, kneading, extrusion molding, drying, and high-temperature calcination. Traditionally, this relies on manual parameter adjustments, leading to significant batch-to-batch performance variations, high energy consumption, and unstable activity, thus affecting nitrogen oxide removal efficiency. Specifically, in the production workshop of flue gas denitrification catalysts, the preparation process typically includes the following key steps. First, powdered materials such as titanium dioxide, tungsten oxide, and vanadium pentoxide are mixed according to a specific formula, then binders and water are added, and the mixture is kneaded to form a slurry with a certain degree of plasticity. Next, the slurry is sent to an extrusion molding machine, where it is extruded under high pressure through a die to form a honeycomb catalyst carrier with a specific porous structure. The formed carrier is then dried in a drying kiln to remove moisture, and finally sintered in a high-temperature calcination furnace to ensure the catalyst has sufficient strength and nitrogen oxide removal capacity. In the past production model, the parameters of each step, such as kneading time, extrusion pressure, drying temperature changes, and the heating rate and maximum temperature during calcination, were mainly controlled by fixed operating procedures and worker experience. Operators manually adjust the parameters by looking at the numbers on the instruments. This method is difficult to be very precise, resulting in significant differences in pore structure, surface area, and distribution of active ingredients between different batches of catalysts. Ultimately, this affects the stability and consistency of its nitrogen oxide removal performance.

[0021] To ensure more consistent product quality, existing control systems employ numerous sensors installed on key equipment such as kneading, extrusion, drying, and calcination to collect information on temperature, pressure, and humidity. These sensors then adjust actuators according to preset rules, such as adjusting heater power or motor speed. However, raw material powders, such as titanium dioxide powder, from different suppliers or even different batches from the same supplier, exhibit variations in particle size distribution, surface area, and trace impurity content. These differences directly impact subsequent production. For instance, smaller particles require more moisture during kneading, altering the drying burden; certain impurities react with active ingredients during high-temperature calcination, reducing catalyst activity. Existing systems struggle to identify these differences between batches of raw materials, leading to fluctuations in catalyst performance, low parameter control precision, and ultimately, compromised product quality.

[0022] In the production process of flue gas denitrification catalyst, it is necessary to consider the characteristics of incoming raw materials, real-time process parameters, and the wear and tear status of key equipment. Adjustments should be made in advance based on raw material information. It is also necessary to evaluate the current performance status of the equipment in real time and predict the impact of different combinations of process parameters on the future wear and tear rate of the equipment. In this way, while ensuring the quality of each batch of products, effective management of equipment wear and tear can be achieved, avoiding long-term production instability caused by the gradual decline of equipment performance.

[0023] The embodiments of this application will be explained in detail below with reference to the accompanying drawings: Figure 1 This is an optional flowchart of a parameter control method for the preparation process of a flue gas denitrification catalyst provided in this application embodiment. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0024] Step S101: Obtain equipment operating parameters and physicochemical properties information of raw materials; Step S102: Based on the equipment operating parameters and physicochemical properties, assess the degree of impact of component wear; Step S103: Based on the degree of component wear, physicochemical properties, equipment operating parameters, and parameter reference range, calculate the target stress value generated on the equipment components when the operating parameters deviate from the reference. Step S104: Accumulate and calculate the cumulative fatigue index by accumulating multiple target stress values; Step S105: Evaluate the wear trend of equipment components based on the cumulative fatigue index; Step S106: Generate parameter control strategies based on the wear and tear trends of equipment components.

[0025] Steps S101 to S106 as shown in the embodiments of this application can combine cumulative fatigue index and equipment component wear trend to generate parameter control strategy, thereby achieving parameter control and improving accuracy and product quality.

[0026] In some embodiments, steps S101-S106 may involve acquiring equipment operating parameters and the physicochemical properties of the raw materials. Equipment operating parameters can be collected in real time by installing various sensors on the production equipment, such as temperature sensors, pressure sensors, flow sensors, and speed sensors. These sensors transmit the collected data to the data processing unit. For example, in the extrusion molding process, parameters such as extruder speed, extrusion pressure, and die temperature can be acquired. The physicochemical properties of the raw materials can be acquired using specialized testing equipment. For example, a laser particle size analyzer can be used to obtain particle size distribution, a specific surface area and pore size analyzer can be used to obtain specific surface area and porosity, X-ray fluorescence spectrometry (XRF) or inductively coupled plasma optical emission spectrometry (ICP-OES) can be used to analyze trace impurity content, and a moisture analyzer can be used to obtain initial moisture content. This information is collected before the raw materials are stored or put into use.

[0027] Then, based on the equipment operating parameters and physicochemical properties, the degree of component wear is assessed. The wear condition of the extruder's screw pusher can be preliminarily determined by parameters such as operating current and vibration frequency when the extruder processes raw materials of different particle sizes and hardnesses, combined with the physicochemical properties of the raw materials. Alternatively, the aging rate of the heating elements can be assessed in the calcining furnace based on the calcination temperature, calcination time, and the content of volatile impurities in the raw materials.

[0028] Then, based on the degree of component wear, physicochemical properties, equipment operating parameters, and parameter reference ranges, the target stress value generated on the equipment components when the operating parameters deviate from the reference range is calculated. The parameter reference range is a preset ideal parameter range that ensures normal equipment operation and product quality. When the actual operating parameters deviate from this reference range, additional stress will be generated on the equipment components. For example, when an extruder is processing high-hardness raw materials, if the extrusion pressure is increased to maintain production efficiency, the pressure value deviating from the reference range will be combined with the assessed degree of component wear and raw material characteristics to calculate the target stress value generated on the screw pusher. As another example, when the actual temperature of the calcining furnace deviates from the set value due to heating element aging, this deviation will be combined with the degree of heating element wear and the thermal sensitivity of the raw material to calculate the target stress value generated on the heating element.

[0029] Cumulative fatigue indices are obtained by accumulating multiple target stress values. During production, equipment components continuously endure various stresses. By accumulating target stress values ​​calculated at different time points or under different operating conditions, the total fatigue damage experienced by the component can be quantified. For example, linear cumulative damage theories (such as Miner's rule) or other nonlinear cumulative models can be used to weighted summations of stress values ​​of different magnitudes and durations, thereby obtaining a comprehensive cumulative fatigue index. This index reflects the degree of fatigue experienced by the component since it was put into use.

[0030] The wear trend of equipment components is assessed based on cumulative fatigue indices. Changes in the cumulative fatigue index reflect the dynamic process of component wear. For example, if the growth rate of the cumulative fatigue index accelerates, it indicates that the component's wear rate is accelerating. By analyzing historical cumulative fatigue index data, predictive models can be built to predict the wear of components over a future period, such as predicting when a screw push rod will reach its wear limit or when a heating element will fail.

[0031] Finally, based on the wear trends of equipment components, parameter control strategies are generated. After assessing the wear trends of equipment components, corresponding control strategies can be formulated to extend equipment life, ensure product quality, and optimize production efficiency. For example, if it is predicted that the wear of the extruder screw pusher will reach a critical value in the short term, the system may suggest reducing the extrusion pressure or adjusting the raw material formula to slow down the wear rate and arrange preventative maintenance. If it is predicted that the aging of the calcining furnace heating elements will lead to a decrease in temperature control accuracy, the system may suggest adjusting the calcining temperature setpoint or arranging for the replacement of the heating elements. The generation of these strategies aims to achieve intelligent management of the production process and avoid production interruptions or product quality problems caused by equipment wear.

[0032] Through the above technical solution, this embodiment achieves refined management of the production process by introducing a real-time assessment and prediction mechanism for equipment component wear. First, it acquires information on equipment operating parameters and the physicochemical properties of raw materials; this information is fundamental to understanding the production process and equipment status. Then, based on this information, it assesses the degree of impact of component wear, enabling the system to perceive the health status of the equipment under different operating conditions. Further, by calculating the target stress values ​​generated on equipment components when operating parameters deviate from the baseline, the potential damage caused by parameter adjustments to the equipment is quantified. These target stress values ​​are accumulated to obtain a cumulative fatigue index, thereby dynamically tracking the fatigue damage process of components. Based on the cumulative fatigue index, the wear trend of equipment components is assessed, allowing the system to predict the future state of the components. Finally, a parameter control strategy is generated based on the wear trend of equipment components, realizing intelligent adjustment of production parameters. This effectively extends equipment life and reduces maintenance costs while ensuring product quality and production efficiency.

[0033] In some embodiments, step S102, assessing the impact of component wear based on equipment operating parameters and physicochemical properties, may include, but is not limited to, the following steps: Obtain historical running parameters; Calculate the average value and range of parameters based on historical operating parameters; Based on physicochemical properties, determine the weighting coefficients for raw material properties and the weighting coefficients for duration; Calculate the load factor based on equipment operating parameters, average parameter values, parameter ranges, raw material characteristic weighting coefficients, and duration weighting coefficients. Calculate the rate of change of load factors based on multiple load factors; The impact of component wear is assessed based on the rate of change of the load factor.

[0034] In some embodiments, historical operating parameters can be acquired first. Various operating data of the equipment over a past period, such as temperature, pressure, speed, and vibration, can be continuously monitored and recorded. This data is stored for subsequent analysis. Based on the historical operating parameters, the average value and range of the parameters are calculated. Statistical analysis can be performed on the acquired historical operating parameters to derive the long-term average level and fluctuation range of each parameter. For example, moving averages, standard deviations, maximum values, and minimum values ​​can be calculated. The purpose is to establish the normal operating baseline and fluctuation boundaries of the parameters.

[0035] Then, based on the physicochemical properties, the weighting coefficients for raw material characteristics and duration are determined. Appropriate weighting factors can be set based on the physicochemical properties of the raw materials, such as hardness, abrasiveness, and corrosiveness, as well as the duration of contact between the equipment and the raw materials under specific operating conditions. For example, for raw materials with high abrasiveness, the characteristic weighting coefficient will be set to a higher value; for long-term operating conditions, the duration weighting coefficient will also increase accordingly. The purpose is to quantify the relative importance of different factors to component wear.

[0036] Then, based on equipment operating parameters, average parameter values, parameter ranges, raw material characteristic weighting coefficients, and duration weighting coefficients, the load factor is calculated. It can comprehensively consider factors such as the deviation of current equipment operating parameters from historical baselines, raw material characteristics, and operating time, and calculate a comprehensive load index through a preset mathematical model or algorithm. This load factor reflects the comprehensive pressure or wear potential borne by equipment components under current operating conditions, aiming to provide a quantitative indicator to measure the immediate risk of component wear.

[0037] The rate of change of load factors is calculated based on multiple load factors. Time series analysis can be performed on multiple load factors calculated at different time points or under different operating conditions to obtain the rate of change of load factors over time. For example, the trend of change can be calculated through methods such as differencing and regression analysis, with the aim of capturing dynamic changes in load and identifying potential accelerated wear risks.

[0038] Finally, the degree of component wear is assessed based on the load factor change rate. The calculated load factor change rate can be compared with a preset wear threshold to determine the extent to which the current equipment components are affected by wear. For example, if the load factor change rate continues to rise and exceeds a certain threshold, it indicates that the degree of component wear is intensifying. This is intended to provide accurate input for subsequent target stress value calculations. The preset wear threshold can be calculated by statistically analyzing a large amount of historical data and using the average load factor change rate as the preset wear threshold.

[0039] This embodiment acquires and analyzes historical operating parameters to establish a normal operating baseline and fluctuation range, thereby accurately identifying deviations in current equipment operating parameters. Simultaneously, by introducing raw material characteristic weighting coefficients and duration weighting coefficients, the inherent characteristics of raw materials and their contact time with the equipment are quantified to influence component wear. These factors are combined to calculate a load factor, which comprehensively reflects the overall load borne by equipment components under current operating conditions. Furthermore, by analyzing the rate of change of the load factor, the acceleration or deceleration trend of component wear can be dynamically captured, thereby achieving a precise and dynamic assessment of the degree of impact on component wear, providing a solid data foundation for subsequent stress calculations and fatigue analysis.

[0040] Through the above technical solution, this embodiment enables a refined and dynamic assessment of the impact of component wear on the preparation of flue gas denitrification catalysts. This embodiment not only considers the current operating status of the equipment but also incorporates historical operating data, the physicochemical properties of raw materials, and operating time, making the assessment of component wear impact more comprehensive and accurate. This helps to identify potential component wear risks earlier, providing a more reliable basis for subsequent target stress value calculations and parameter control strategies, thereby effectively extending equipment lifespan, reducing maintenance costs, and ensuring the stability and efficiency of the production process.

[0041] In some embodiments, step S103, based on the degree of component wear, physicochemical property information, equipment operating parameters, and parameter reference range, calculates the target stress value generated on the equipment component when the operating parameters deviate from the reference. This may include, but is not limited to, the following steps: Step S201: Collect the microscopic physical response signals during device operation; Step S202: Identify impact events caused by microscopic non-uniformity of raw materials based on microscopic physical response signals; Step S203: Calculate the intensity of the impact event based on the type of microscopic non-uniformity of the raw materials and the impact characteristics corresponding to the impact event; Step S204: Calculate the initial stress value based on the physicochemical properties information; Step S205: Calculate the degree of parameter deviation based on the equipment operating parameters and parameter reference range; Step S206: Calculate the target stress value based on the impact event intensity, initial stress value, component wear impact, and parameter deviation.

[0042] In some embodiments, microscopic physical response signals during equipment operation can be acquired first. Highly sensitive sensors, such as acoustic emission sensors, vibration sensors, or strain sensors, can be used to monitor subtle physical changes in equipment components during the preparation of the flue gas denitrification catalyst in real time. These signals can reflect the stress conditions and material responses at the microscopic level within the equipment. Based on the microscopic physical response signals, impact events caused by microscopic non-uniformity of the raw materials can be identified. Transient signal characteristics significantly different from background noise or normal operation signals can be extracted by analyzing the acquired microscopic physical response signals, such as time-domain analysis, frequency-domain analysis, or time-frequency analysis. These transient signal characteristics are typically associated with instantaneous impact, friction, or wear events generated on equipment components by microscopic non-uniformity such as hard particles, agglomerates, or foreign matter present in the raw materials.

[0043] Then, based on the type of micro-uniformity of the raw materials and the impact characteristics corresponding to the impact event, the intensity of the impact event is calculated. Based on the signal characteristics of the identified impact event (such as amplitude, duration, frequency components, etc.) and the pre-established impact characteristic spectrum, the type of micro-uniformity of the raw materials that caused the impact (e.g., whether it is hard particle impact or agglomerate friction) can be determined, and the instantaneous stress or energy release caused by the impact event on the equipment components can be quantified.

[0044] Then, based on the physicochemical properties, the initial stress value is calculated. The baseline stress that equipment components experience during normal operation due to contact with the raw materials can be assessed based on the raw materials' physicochemical properties, such as hardness, toughness, density, particle size distribution, and chemical composition. For example, high-hardness raw materials typically result in higher initial contact stress.

[0045] Based on the equipment's operating parameters and reference ranges, the degree of parameter deviation is calculated. Current equipment operating parameters (such as temperature, pressure, rotational speed, and feed rate) can be compared with preset reference ranges that ensure stable equipment operation and low component wear, quantifying the extent to which the current operating state deviates from the ideal state. A greater deviation typically indicates greater additional stress on the equipment components.

[0046] Finally, the target stress value is calculated based on the impact event intensity, initial stress value, the degree of component wear, and the degree of parameter deviation. The initial stress value can be used as a benchmark, and the impact event intensity, the degree of component wear, and the degree of parameter deviation can be weighted and superimposed or multiplied to apply to the initial stress value, thus obtaining a more comprehensive and accurate target stress value that reflects the actual stress condition of the equipment components.

[0047] This embodiment, by introducing the acquisition and analysis of microscopic physical response signals during equipment operation, can accurately identify and quantify impact events caused by the microscopic non-uniformity of raw materials. By calculating the intensity of the impact event and comprehensively considering it in conjunction with the initial stress value obtained based on physicochemical properties, the degree of parameter deviation caused by macroscopic operating parameters deviating from the baseline, and the degree of component wear, this embodiment can more comprehensively and realistically reflect the actual stress state of equipment components under complex operating conditions. This multi-dimensional and refined stress calculation method allows the target stress value to more accurately characterize the fatigue load borne by the equipment components, thus providing a more reliable data foundation for subsequent calculation of cumulative fatigue indicators and assessment of equipment component wear trends.

[0048] Through the above technical solution, this embodiment can significantly improve the calculation accuracy of the target stress value generated on equipment components when operating parameters deviate from the baseline. Specifically, by capturing and quantifying impact events caused by the microscopic non-uniformity of raw materials, the calculated target stress value can more accurately reflect the true stress state of equipment components, especially in the presence of local transient impact loads. This provides a more accurate input for subsequent calculation of cumulative fatigue indicators, thereby improving the accuracy and reliability of equipment component wear trend assessment. It also helps to identify potential equipment failure risks earlier and more accurately, laying a solid foundation for developing refined parameter control strategies.

[0049] In some embodiments, in step S202, identifying the impact event caused by the microscopic non-uniformity of the raw material based on the microscopic physical response signal may include, but is not limited to, the following steps: Step S301: Extract time-domain features from the microscopic physical response signal to obtain time-domain features, which include instantaneous energy, peak amplitude, and rise time. Step S302: Extract frequency domain features from the microscopic physical response signal to obtain frequency domain features, which include the main frequency component and bandwidth; Step S303: Compare the time-frequency domain features with the background vibration signal template to identify the difference signal segments. The time-frequency domain features include time domain features and frequency domain features. Step S304: Identify the impact event based on the difference signal segments.

[0050] In some embodiments, time-domain features can be extracted from the microscopic physical response signal to obtain time-domain features. These time-domain features refer to the signal's representation on the time axis and include instantaneous energy, peak amplitude, and rise time. Instantaneous energy refers to the signal's energy intensity at a given moment, reflecting the overall energy magnitude of the impact event; peak amplitude refers to the signal's maximum amplitude over a given time period, characterizing the instantaneous maximum intensity of the impact event; and rise time refers to the time required for the signal to rise from a reference value to its peak, reflecting the steepness or velocity of the impact event. Extracting these time-domain features helps capture the transient characteristics of impact events.

[0051] Then, frequency domain features are extracted from the microscopic physical response signal to obtain frequency domain features. Frequency domain features refer to the signal's representation on the frequency axis, including the dominant frequency component and bandwidth. The dominant frequency component refers to the frequency element with the most concentrated energy in the signal, which may indicate the type or source of the impact event; bandwidth refers to the range of the signal's frequency distribution, reflecting the complexity of the impact event's frequency composition. These frequency domain features can be obtained by performing frequency domain analysis methods such as Fourier transform on the signal, thereby revealing the frequency characteristics of the impact event.

[0052] The time-frequency domain features are then compared with the background vibration signal template to identify discrepancies in signal segments. The time-frequency domain features include both time-domain and frequency-domain characteristics. The background vibration signal template is a set of microscopic physical response signal features of the equipment under normal operating conditions, assuming no impact events caused by microscopic non-uniformity of raw materials. By comparing the currently acquired time-frequency domain features with this template, signal segments that significantly differ from the normal operating conditions can be identified. These discrepancies typically exhibit energy distributions, frequency components, or transient characteristics that do not match the background vibration signal template, thus indicating the occurrence of abnormal events.

[0053] Finally, impact events are identified based on the differential signal segments. These differential signal segments are unique signal patterns generated when microscopic non-uniformities in the raw materials (such as hard particles or abnormal impurities) collide or rub against components during equipment operation. By analyzing these differential signal segments, impact events can be identified.

[0054] This embodiment, through comprehensive time-domain and frequency-domain analysis of the microscopic physical response signal, effectively separates impact events caused by the microscopic non-uniformity of raw materials from complex equipment operating noise. Time-domain features (such as instantaneous energy, peak amplitude, and rise time) capture the transient characteristics and energy distribution of the impact event, while frequency-domain features (such as dominant frequency components and bandwidth) reveal the frequency composition and spectral width of the impact event. By comparing these time- and frequency-domain features with a pre-established background vibration signal template, signal segments that significantly differ from the normal operating state can be accurately identified. These differing signal segments directly reflect the impact events caused by the microscopic non-uniformity of raw materials. Therefore, this embodiment avoids misjudging normal equipment vibration as impact events, improving the accuracy and sensitivity of impact event identification.

[0055] Through the above technical solution, this embodiment can more accurately and reliably identify impact events caused by the microscopic non-uniformity of raw materials. By combining the comprehensive analysis of time-domain and frequency-domain characteristics and introducing a comparison mechanism with the background vibration signal template, this embodiment can effectively filter out interference and highlight the unique signal patterns of impact events, thereby significantly improving the accuracy and robustness of impact event identification and providing more reliable input data for subsequent target stress value calculation.

[0056] In some embodiments, identifying the impact event based on the difference signal segments in step S304 may include, but is not limited to, the following steps: Time-frequency analysis of the differential signal segments yields energy distribution and transient response characteristics; The energy distribution, transient response characteristics and impact feature maps are matched to obtain the matching results. The impact feature maps contain various types of microscopic non-uniformity of raw materials. Based on the matching results, identify the impact event.

[0057] In some embodiments, time-frequency analysis can be performed on the differential signal segments to obtain energy distribution and transient response characteristics. Signal processing techniques such as Short-Time Fourier Transform (STFT), Wavelet Transform, or Hilbert-Huang Transform can be used to analyze the signal's variation patterns in the time and frequency dimensions. Through time-frequency analysis, the signal's energy distribution, i.e., the energy intensity at different time points and frequency ranges, and transient response characteristics, such as the onset time, duration, peak amplitude, and decay rate of the impact event, can be obtained. These characteristics can comprehensively characterize the dynamic properties of the impact event.

[0058] Then, the energy distribution, transient response characteristics, and impact feature maps are matched to obtain matching results. The impact feature maps contain various types of microscopic non-uniformity in raw materials. The impact feature maps are pre-established time-frequency feature template libraries containing typical impact events caused by various types of microscopic non-uniformity in raw materials (e.g., hard particles, agglomerates, bubbles, fibrous impurities, etc.). Each type of microscopic non-uniformity generates impact events with unique energy distribution and transient response characteristics during equipment operation. Similarity calculations can determine which type of microscopic non-uniformity in the map best matches the current impact event, thus obtaining the matching result. Based on the matching result, the impact event is identified.

[0059] This embodiment, through refined time-frequency analysis of differential signal segments, can extract richer energy distribution and transient response characteristics of impact events. Subsequently, these detailed characteristics are matched with a pre-defined impact feature map containing various types of microscopic inhomogeneities in raw materials. This allows impact event identification to go beyond simply detecting abnormal signals, further clarifying which specific microscopic inhomogeneity of raw materials caused the abnormal signals. This feature-matching-based identification method significantly improves the accuracy and specificity of impact event identification.

[0060] Through the above technical solution, this embodiment can more accurately identify impact events caused by the microscopic non-uniformity of different raw materials, thus providing a more reliable basis for subsequent calculation of the impact event intensity. This refined identification capability helps to more accurately assess the target stress value generated on equipment components when operating parameters deviate from the baseline, thereby improving the accuracy and effectiveness of the entire parameter control method and ensuring the stability of the flue gas denitrification catalyst preparation process and the reliability of equipment components.

[0061] In some embodiments, step S204, calculating the initial stress value based on physicochemical property information, may include, but is not limited to, the following steps: Acquire reflectance spectrum images of raw materials; Identify regions with discrepancies in features based on reflectance spectral images; Extract spectral features from regions of feature deviation; Based on spectral characteristics, identify information on abnormal impurities and hard particles; Calculate the abnormal particle strength index based on the abnormal impurity information and hard particle information; The initial stress value is calculated based on the physicochemical properties and the strength index of the abnormal particles.

[0062] In some embodiments, a reflectance spectral image of the raw material can be acquired first. The reflectance spectral image can reflect information such as the chemical composition, crystal structure, and microscopic defects on or inside the surface of the raw material. For example, hyperspectral imaging or near-infrared spectroscopy can be used to scan the raw material to obtain its reflectance intensity data at different wavelengths, thereby forming a detailed spectral image.

[0063] Then, based on the reflectance spectrum image, the feature deviation regions are identified. Feature deviation regions typically exhibit spectral responses different from normal raw material regions, potentially indicating the presence of abnormal substances, structural inhomogeneities, or physical defects. Identification can be achieved using image processing algorithms, such as setting thresholds, performing cluster analysis, or employing machine learning models to distinguish between normal and abnormal spectral patterns. Spectral features are then extracted from the feature deviation regions. These spectral features can be absorbance at a specific wavelength, reflectance peaks, peak shape, full width at half maximum (FWHM), or combinations of multiple wavelength points. These features quantify the properties of the deviation regions, providing a basis for subsequent substance identification.

[0064] Next, based on spectral characteristics, information on anomalous impurities and hard particles is identified. The extracted spectral features can be compared with a spectral database of known impurities or hard particles to determine the specific composition of the off-target regions. Anomalous impurities may include elements or compounds detrimental to catalyst performance, while hard particles may cause mechanical wear or impact on equipment components during the preparation process. Based on the information on anomalous impurities and hard particles, an anomalous particle strength index is calculated to quantify the combined impact of the content, size, hardness, or distribution density of anomalous particles in the raw materials. For example, this index can be calculated based on the concentration of anomalous particles, their average particle size, and a weighting factor for their potential damage to equipment components.

[0065] Finally, the initial stress value is calculated based on the physicochemical properties and the abnormal particle strength index. The initial stress value can be obtained by superimposing or multiplying the base stress (determined by the macroscopic properties of the raw material) with the abnormal particle strength index (reflecting the influence of microscopic defects). Physicochemical properties can include macroscopic properties such as the density, hardness, toughness, and elastic modulus of the raw material. The initial stress value reflects the influence of inherent defects in the raw material on the initial stress state of the equipment components.

[0066] This embodiment utilizes refined reflectance spectral analysis of raw materials to reveal their non-uniformity and potential defects at the microscopic level. By acquiring reflectance spectral images and further identifying regions of feature deviation and extracting spectral features, this embodiment identifies abnormal impurities and hard particles, enabling the detection of microscopic non-uniformity in raw materials. Therefore, by calculating the abnormal particle intensity index, the impact of these microscopic defects is quantified. Combined with the macroscopic physicochemical properties of the raw materials, the initial stress value experienced by equipment components upon contact with the raw materials can be calculated more comprehensively and accurately. This stress calculation method based on microscopic characteristic analysis significantly improves the accuracy and reliability of initial stress assessment.

[0067] Through the above technical solution, this embodiment introduces steps such as reflectance spectral image acquisition, feature deviation region identification, spectral feature extraction, and identification of abnormal impurities and hard particles. This provides a quantitative assessment basis for potential microscopic defects in raw materials that could lead to early wear of equipment components. Consequently, the calculated abnormal particle strength index more accurately reflects the potential damage risk of raw materials to equipment components. Finally, the accuracy of the initial stress value calculated by combining physicochemical properties and the abnormal particle strength index is significantly improved, providing a more reliable starting point for subsequent target stress value calculation and equipment component wear assessment. This helps to more accurately predict the fatigue life of equipment components and formulate more effective parameter control strategies.

[0068] In some embodiments, in step S206, calculating the target stress value based on the impact event intensity, initial stress value, component wear impact, and parameter deviation may include, but is not limited to, the following steps: The impact weights are determined based on the degree of influence of component wear and the degree of parameter deviation. Calculate the weighted impact intensity value based on the impact event intensity and its impact weight; The target stress value is obtained by superimposing the weighted impact strength value with the initial stress value.

[0069] In some embodiments, the degree of influence of component wear and parameter deviation on the stress generated by equipment components is not constant; their relative importance may dynamically adjust due to changes in equipment condition, raw material characteristics, or operating conditions. If these factors are simply combined without considering their differential effects, the calculated target stress value may not accurately reflect the true stress state of the equipment components, thereby affecting the accuracy and effectiveness of the parameter control strategy.

[0070] Therefore, the influence weights can be determined first based on the degree of component wear and parameter deviation. These two key indicators—the degree of component wear and parameter deviation—can be used to quantify their proportion of influence on the stress of equipment components under current operating conditions. For example, when the degree of component wear is high, it means the component is already in a relatively fragile state. In this case, even a small degree of parameter deviation may lead to significant stress, thus requiring a higher influence weight. Conversely, if the degree of component wear is low, the impact of parameter deviation may be more significant. This influence weight can be a dynamically adjusted coefficient, the purpose of which is to ensure that subsequent stress calculations more accurately reflect the actual situation.

[0071] Then, based on the impact event intensity and its influence weights, a weighted impact intensity value is calculated. The impact event intensity can be combined with the determined influence weights to obtain a value that better reflects the actual destructive force of the impact event under the current equipment condition. For example, the impact event intensity can be multiplied by the influence weights, or calculated using a pre-defined weighted model. The aim is to combine the original intensity of the impact event with the vulnerability of equipment components and the degree of deviation of operating parameters, thereby obtaining a more representative impact intensity index.

[0072] The weighted impact intensity value is then superimposed with the initial stress value to obtain the target stress value. By superimposing the weighted impact intensity value with the initial stress value, the inherent characteristics of the raw materials, external impact events, and the current state and deviations of the operating parameters of the equipment components can be comprehensively considered, thus obtaining a comprehensive and dynamic target stress value. This superposition can be a simple numerical addition or a more complex mathematical combination, with the aim of providing a comprehensive stress assessment result.

[0073] This embodiment determines the impact weight based on the degree of component wear and parameter deviation, allowing the impact event intensity to be dynamically adjusted when calculating the target stress value according to the actual vulnerability of the equipment components and the degree of deviation of operating parameters. When the equipment components are severely worn or the operating parameters deviate significantly from the baseline, the impact weight is increased accordingly, thereby amplifying the impact of the impact event intensity on the target stress value, making the calculation results more reflective of the actual risk. Conversely, when the equipment components are in good condition and the operating parameters are stable, the impact weight is reduced to avoid over-evaluating the stress. This weighted superposition mechanism ensures that the target stress value not only considers the inherent stress of the raw materials (initial stress value) and the intensity of the impact event, but also incorporates the real-time health status of the equipment components and the degree of deviation of operating parameters, thus providing a more comprehensive, dynamic, and accurate stress assessment.

[0074] To illustrate this technical solution more clearly, a specific example is used below. Suppose that during the preparation of a flue gas denitrification catalyst, the impact of component wear on a certain reactor part is assessed as moderately high, while the equipment operating parameters deviate significantly from the baseline range. In this case, the system will determine a higher impact weight, such as 0.8, based on this information. If an impact event caused by the microscopic non-uniformity of the raw materials is detected, with an impact intensity of 100 units, and the initial stress value calculated based on the physicochemical properties of the raw materials is 200 units, this embodiment first calculates the weighted impact intensity value, i.e., 100 units multiplied by 0.8, resulting in 80 units. Then, this weighted impact intensity value of 80 units is superimposed with the initial stress value of 200 units, ultimately obtaining a target stress value of 280 units. This higher target stress value will prompt the system to generate a more conservative parameter control strategy, such as reducing the production speed or triggering a preventative maintenance alarm, to avoid further component damage.

[0075] In another scenario, if the impact of component wear is low and the parameter deviation is small, the impact weight might be set to 0.2. With the same impact event intensity of 100 units and an initial stress value of 200 units, the weighted impact intensity value would be 100 units multiplied by 0.2, or 20 units. After superposition, the target stress value is 220 units. This relatively low target stress value allows the system to maintain normal production operation and avoids unnecessary intervention. Through this dynamic weighting mechanism, the proposed solution can flexibly adjust the stress assessment according to the actual situation, thereby achieving more intelligent and precise parameter control.

[0076] Through the above technical solution, this embodiment achieves refined and dynamic calculation of target stress values ​​for equipment components. This solution overcomes the evaluation bias that may result from simply combining various factors. By introducing influence weights, the target stress value can more accurately reflect the actual stress state of equipment components under different operating conditions. Therefore, it can provide more reliable input for subsequent calculation of cumulative fatigue indices and generation of parameter control strategies, significantly improving the accuracy and responsiveness of parameter control in the flue gas denitrification catalyst preparation process, effectively preventing premature failure of equipment components, extending equipment service life, and optimizing production efficiency.

[0077] In some embodiments, step S105, assessing the wear trend of equipment components based on cumulative fatigue indices, may include, but is not limited to, the following steps: Calculate the rate of change of the cumulative fatigue index; Adjust the fatigue loss conversion function based on the rate of change of indicators, equipment operating parameters, and physicochemical properties. Based on the fatigue loss conversion function, the cumulative fatigue index is converted into the actual wear and tear of equipment components. Assess the wear trend of equipment components based on their actual and historical wear.

[0078] In some embodiments, if the evaluation is based solely on a single cumulative fatigue index, it may not adequately reflect the actual wear and tear of equipment components under different operating conditions and raw material characteristics, resulting in insufficient accuracy and real-time performance of the evaluation results, which in turn affects the effectiveness of the parameter control strategy.

[0079] Therefore, we can first calculate the rate of change of the cumulative fatigue index. The change of the cumulative fatigue index over time can be quantified, for example, by performing difference or regression analysis on the cumulative fatigue index over a continuous time period. The purpose is to capture the dynamic trend of fatigue accumulation and provide a basis for subsequent function adjustments.

[0080] Then, based on the rate of change of the indicators, equipment operating parameters, and physicochemical properties, the fatigue loss conversion function is adjusted. The fatigue loss conversion function is a mathematical model or empirical formula that maps abstract cumulative fatigue indicators to the actual wear and tear of specific equipment components. This function needs to be dynamically adjusted according to the rate of change of the indicators, equipment operating parameters, and physicochemical properties. For example, when equipment operating parameters (such as temperature, pressure, and speed) change significantly, or when the physicochemical properties of raw materials (such as hardness and abrasiveness) fluctuate, the fatigue loss conversion function will be modified accordingly to more accurately reflect the relationship between fatigue accumulation and actual wear and tear under the current operating conditions. The purpose is to ensure that the fatigue assessment model can adapt to the constantly changing production environment and improve the accuracy of the assessment.

[0081] Then, based on the fatigue loss conversion function, the cumulative fatigue index is converted into the actual wear and tear of the equipment components. An adjusted fatigue loss conversion function can be used to transform the calculated cumulative fatigue index into directly measurable physical losses, such as wear thickness, crack propagation length, or performance degradation of components. The purpose is to visualize abstract fatigue data, facilitating intuitive understanding and decision-making.

[0082] Finally, based on the actual and historical wear and tear of equipment components, the wear and tear trend of the components is assessed. By comprehensively considering the currently calculated actual and historical wear and tear data, and through trend analysis and predictive models, the future wear and tear trajectory and potential failure risks of the components can be predicted. The purpose is to provide a reliable basis for developing forward-looking maintenance scheduling and parameter control strategies.

[0083] This embodiment addresses the limitations of relying solely on a single cumulative fatigue index for assessment by introducing the rate of index change, dynamically adjusting the fatigue loss conversion function, and combining actual and historical loss amounts. Specifically, calculating the rate of index change allows the system to perceive the dynamic nature of fatigue accumulation. Based on this, the fatigue loss conversion function is adjusted using equipment operating parameters and physicochemical properties, enabling it to adapt in real-time to different operating conditions and raw material characteristics, thus more accurately converting the cumulative fatigue index into actual physical loss amounts. This dynamic conversion mechanism ensures the accuracy of the assessment results and avoids assessment deviations caused by changes in operating conditions. Finally, combining actual and historical loss amounts for trend assessment provides more comprehensive and predictive loss trend information, supporting more precise parameter control and maintenance decisions.

[0084] To illustrate this technical solution more clearly, a specific example is used below. Suppose that during the preparation of a flue gas denitrification catalyst, a key mixing component reaches a certain threshold in its cumulative fatigue index after operating normally for a period of time. If only this cumulative fatigue index is used for evaluation, it might lead to the conclusion that the component is about to fail. This embodiment first calculates the rate of change of this cumulative fatigue index and finds that its rate of change has recently slowed down. Simultaneously, the system obtains current equipment operating parameters showing that the mixing speed and temperature are at low levels, and the physicochemical properties of the raw materials indicate that the hardness of the raw materials used recently has decreased. Based on this information, the fatigue loss conversion function is dynamically adjusted so that the same cumulative fatigue index is converted into a relatively low actual wear amount of the equipment component under the current operating conditions. Furthermore, comparing this actual wear amount with historical wear amounts reveals that the actual wear trend of the component has not deteriorated as rapidly as expected. Therefore, the system can assess that the actual wear trend of the component is slowly increasing, rather than indicating imminent failure, thus avoiding unnecessary downtime for maintenance. The system can also adjust parameter control strategies based on the new evaluation results, such as appropriately extending the maintenance cycle or fine-tuning operating parameters to further mitigate wear.

[0085] Through the above technical solution, this embodiment can significantly improve the accuracy and real-time performance of equipment component wear trend assessment. The dynamically adjusted fatigue wear transformation function enables the system to better adapt to complex and ever-changing production environments, avoiding errors that may arise from static assessments. Therefore, it is possible to more accurately predict the remaining lifespan and potential failure risks of equipment components, thereby achieving more refined parameter control and optimized maintenance scheduling, effectively reducing unplanned downtime, extending equipment lifespan, and improving production efficiency and safety.

[0086] In some embodiments, step S106, generating a parameter control strategy based on the wear trend of equipment components, may include, but is not limited to, the following steps: Obtain information on the current production line's production throughput demand, raw material inventory, product delivery deadlines, and equipment energy consumption levels; Based on the wear and tear trends of equipment components, production throughput demand information, and equipment energy consumption level information, production adjustment strategies are determined. These strategies include adjusting production speed, switching production batches, or temporary shutdown for maintenance. Based on the wear and tear trends of equipment components, raw material inventory information, and product delivery deadline information, a maintenance scheduling strategy is determined. The maintenance scheduling strategy includes preventive maintenance, delayed maintenance, or component replacement. A comprehensive production impact assessment is conducted on the production adjustment strategy and maintenance scheduling strategy to obtain the comprehensive production impact. Based on the overall impact on production, production adjustment strategies, and maintenance scheduling strategies, a parameter control strategy is generated.

[0087] In some embodiments, if parameter control strategies are generated solely based on equipment component wear trends, it may fail to adequately consider comprehensive factors such as the actual operational needs of the production line, raw material supply, product delivery deadlines, and energy consumption levels. This could result in a strategy that optimizes equipment lifespan while sacrificing production efficiency, increasing operating costs, or impacting market responsiveness.

[0088] To this end, we can first obtain information on the current production line's production throughput demand, raw material inventory, product delivery deadlines, and equipment energy consumption levels. Key data related to production operations can be collected in real-time or periodically. Specifically, production throughput demand information reflects market demand for products and production plan objectives; raw material inventory information provides the types and quantities of currently available raw materials, affecting production continuity; product delivery deadlines are the final delivery times required by contracts or the market, directly constraining production progress; and equipment energy consumption levels are used to assess the energy efficiency under different production strategies. This information collectively forms the decision-making basis for generating a comprehensive parameter control strategy.

[0089] Then, based on the wear and tear trends of equipment components, production throughput requirements, and equipment energy consumption levels, production adjustment strategies are determined to balance equipment lifespan with production efficiency and energy consumption. These strategies include adjusting production speed, switching production batches, or arranging temporary shutdowns for maintenance. For example, when the wear and tear trend of equipment components indicates that a component is approaching its critical point, but the production throughput requirement is high and energy consumption is controllable, adjusting the production speed to extend component lifespan, switching production batches to products with lower loads on that component, or even arranging temporary shutdowns for maintenance if necessary to avoid unexpected failures.

[0090] Based on equipment component wear trends, raw material inventory information, and product delivery deadlines, a maintenance scheduling strategy is determined. This strategy aims to optimize the timing and methods of equipment maintenance while ensuring production continuity and delivery capacity. Maintenance scheduling strategies include preventative maintenance, delayed maintenance, or component replacement. For example, when equipment component wear trends indicate an impending failure, but raw material inventory is sufficient and product delivery deadlines are still far off, preventative maintenance can be implemented. If delivery deadlines are approaching and raw material inventory is tight, delayed maintenance may need to be considered, or components may need to be replaced directly when wear reaches a certain level to ensure uninterrupted production.

[0091] A comprehensive production impact assessment is conducted on production adjustment strategies and maintenance scheduling strategies to obtain the overall production impact. This assessment process quantifies the impact of different strategy combinations on multiple dimensions such as production efficiency, cost, delivery time, and equipment lifespan. For example, simulation or predictive models are used to analyze the potential benefits and risks of various strategy combinations.

[0092] Finally, based on the overall impact on production, production adjustment strategies, and maintenance scheduling strategies, a parameter control strategy is generated. The parameter control strategy is a comprehensive decision-making scheme that not only guides the adjustment of equipment operating parameters but also includes the optimization of production plans and the arrangement of maintenance activities, in order to achieve long-term equipment stability, maximize production efficiency, and minimize operating costs.

[0093] This embodiment overcomes the limitations of relying solely on wear trends to generate strategies by deeply integrating equipment component wear trends with multi-dimensional production and operation information, including production throughput demand information, raw material inventory information, product delivery deadline information, and equipment energy consumption level information. Specifically, firstly, acquiring comprehensive production and operation information provides a broader perspective and richer data support for strategy formulation. Secondly, the combination of equipment component wear trends with production throughput demand information and equipment energy consumption level information enables dynamic determination of production adjustment strategies. This ensures that decisions regarding production speed, batch switching, or downtime maintenance are no longer isolated but rather comprehensively consider the balance between equipment health and production efficiency. For example, when a wear trend indicates risk, if production demand is not urgent, slowing down or downtime maintenance can be implemented to avoid excessive wear; if production demand is urgent, it may be necessary to weigh the risks and prepare for a faster maintenance response. Simultaneously, by combining equipment component wear trends with raw material inventory information and product delivery deadline information, maintenance scheduling strategies can be determined more intelligently. This allows maintenance activities to be closely coordinated with material supply and product delivery cycles, avoiding production interruptions or delivery delays caused by maintenance. Finally, by conducting a comprehensive production impact assessment of production adjustment strategies and maintenance scheduling strategies, the potential impact of different strategy combinations can be quantified. This allows for the selection of the optimal parameter control strategy in the face of multiple conflicting objectives, ensuring the comprehensiveness and effectiveness of the strategy.

[0094] To illustrate this technical solution more clearly, a specific example is used below. Suppose that the wear trend of a mixer component in a flue gas denitrification catalyst production line indicates that its fatigue index is approaching the warning threshold, and a failure is expected within the next two weeks. At this time, the system will obtain information on the current production line's production throughput requirements (e.g., 100 tons of catalyst need to be completed this month, 80 tons have been completed, and the remaining 20 tons need to be delivered within 5 days), raw material inventory information (e.g., sufficient raw material inventory for type A catalyst, and tight raw material inventory for type B catalyst), product delivery deadlines (e.g., delivery date for type A catalyst is 3 days later, and delivery date for type B catalyst is 10 days later), and equipment energy consumption levels (e.g., the mixer is currently operating at high speed with high energy consumption).

[0095] Based on this information, the system will determine production adjustment and maintenance scheduling strategies. For example, given the approaching delivery date of Type A catalyst and sufficient raw materials, the system may recommend prioritizing the production of Type A catalyst and appropriately reducing the mixer's operating speed during this period to mitigate wear and tear. Meanwhile, considering the distant delivery date of Type B catalyst and tight raw material inventory, the system may recommend immediate preventative maintenance or replacement of critical components in the mixer after completing the production of Type A catalyst to avoid malfunctions during the production of Type B catalyst, which could affect delivery.

[0096] Subsequently, the system will conduct a comprehensive production impact assessment of the combined strategy of "reducing the mixer speed to complete the production of Type A catalyst product + immediate mixer maintenance." The assessment results may show that this strategy can ensure the timely delivery of Type A catalyst product, effectively avoid sudden mixer failures, and schedule maintenance before the production of Type B catalyst product, minimizing the impact on the overall production plan while keeping energy consumption within acceptable limits. Finally, based on the assessment results, the system generates parameter control strategies to guide operators in adjusting mixer operating parameters, scheduling production batch switching, and coordinating with the maintenance department for component maintenance or replacement, thereby ensuring healthy equipment operation while balancing production efficiency, cost, and delivery time.

[0097] Through the above technical solution, this embodiment can generate a more comprehensive and optimized parameter control strategy. This strategy not only focuses on the health status of equipment components but also incorporates key factors such as the actual operational needs of the production line, resource availability, market delivery pressure, and energy efficiency. Therefore, it can effectively avoid problems such as low production efficiency, increased costs, or delivery delays caused by solely focusing on equipment wear and tear. This embodiment, by comprehensively evaluating the combined production impact of production adjustment strategies and maintenance scheduling strategies, enables the final parameter control strategy to achieve an optimal balance between equipment lifespan, production efficiency, operating costs, and market responsiveness, thereby significantly improving the overall operating efficiency and economic benefits of the flue gas denitrification catalyst preparation process.

[0098] The beneficial effects of implementing the embodiments of the present invention include: First, the embodiments of this application obtain equipment operating parameters and physicochemical property information of raw materials. Based on the equipment operating parameters and physicochemical property information, the degree of influence of component wear is evaluated. Then, based on the degree of influence of component wear, physicochemical property information, equipment operating parameters and parameter reference range, the target stress value generated on the equipment component when the operating parameters deviate from the reference is calculated. Multiple target stress values ​​are accumulated to obtain a cumulative fatigue index. Based on the cumulative fatigue index, the wear trend of the equipment component is evaluated. Finally, based on the wear trend of the equipment component, a parameter control strategy is generated. Thus, the parameter control strategy can be generated by combining the cumulative fatigue index and the wear trend of the equipment component to achieve parameter control, thereby improving accuracy and product quality.

[0099] like Figure 2 As shown, this embodiment of the invention also provides a parameter control system for the preparation process of a flue gas denitrification catalyst, comprising: The data acquisition module 401 is used to acquire equipment operating parameters and physicochemical properties of raw materials; Impact assessment module 402 is used to assess the impact of component wear based on equipment operating parameters and physicochemical properties. The stress value calculation module 403 is used to calculate the target stress value generated on the equipment components when the operating parameters deviate from the reference, based on the degree of component wear, physicochemical property information, equipment operating parameters and parameter reference range; The stress accumulation module 404 is used to accumulate and calculate multiple target stress values ​​to obtain the cumulative fatigue index; The wear trend assessment module 405 is used to assess the wear trend of equipment components based on the cumulative fatigue index. The control strategy generation module 406 is used to generate parameter control strategies based on the wear and tear trends of equipment components.

[0100] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0101] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

Claims

1. A parameter control method for the preparation process of a flue gas denitrification catalyst, characterized in that, Includes the following steps: Obtain information on equipment operating parameters and the physicochemical properties of raw materials; Based on the equipment operating parameters and the physicochemical properties information, assess the degree of impact of component wear; Based on the degree of impact of component wear, the physicochemical property information, the equipment operating parameters and parameter reference range, calculate the target stress value generated on the equipment components when the operating parameters deviate from the reference. The cumulative fatigue index is obtained by accumulating multiple target stress values. The wear trend of equipment components is assessed based on the cumulative fatigue index. A parameter control strategy is generated based on the wear trend of the equipment components.

2. The method according to claim 1, characterized in that, The assessment of the impact of component wear based on the equipment operating parameters and the physicochemical properties includes: Obtain historical running parameters; Based on the historical operating parameters, calculate the average value and range of the parameters; Based on the aforementioned physicochemical properties, determine the raw material property weighting coefficient and the duration weighting coefficient; The load factor is calculated based on the equipment operating parameters, the average value of the parameters, the parameter range, the weighting coefficient of the raw material characteristics, and the weighting coefficient of the duration. Calculate the rate of change of the load factors based on the multiple load factors mentioned above; The degree of impact of component wear is assessed based on the rate of change of the load factor.

3. The method according to claim 1, characterized in that, The step of calculating the target stress value generated on the equipment components when the operating parameters deviate from the reference range, based on the degree of impact of component wear, the physicochemical property information, the equipment operating parameters, and the parameter reference range, includes: Acquire microscopic physical response signals during device operation; Based on the microscopic physical response signal, an impact event caused by the microscopic non-uniformity of the raw material is identified; The intensity of the impact event is calculated based on the type of microscopic non-uniformity of the raw materials and the impact characteristics corresponding to the impact event. Calculate the initial stress value based on the aforementioned physicochemical properties; Calculate the degree of parameter deviation based on the equipment operating parameters and the parameter reference range; The target stress value is calculated based on the intensity of the impact event, the initial stress value, the degree of impact of component wear, and the degree of parameter deviation.

4. The method according to claim 3, characterized in that, The step of identifying impact events caused by microscopic non-uniformity of raw materials based on the microscopic physical response signal includes: The microscopic physical response signal is subjected to time-domain feature extraction to obtain time-domain features, which include instantaneous energy, peak amplitude and rise time. Frequency domain features are extracted from the microscopic physical response signal to obtain frequency domain features, which include the dominant frequency component and bandwidth. The time-frequency domain features are compared with the background vibration signal template to identify the difference signal segments. The time-frequency domain features include the time domain features and the frequency domain features. The impact event is identified based on the difference in the signal segments.

5. The method according to claim 4, characterized in that, The step of identifying the impact event based on the difference signal segment includes: Time-frequency analysis was performed on the differential signal segments to obtain energy distribution and transient response characteristics; The energy distribution, the transient response characteristics, and the impact feature map are matched to obtain the matching results. The impact feature map contains various types of microscopic non-uniformity of raw materials. The impact event is identified based on the matching results.

6. The method according to claim 3, characterized in that, The step of calculating the initial stress value based on the physicochemical property information includes: Acquire the reflectance spectrum image of the raw material; Based on the reflectance spectrum image, identify the feature deviation region; Extract spectral features from the region of feature deviation; Based on the spectral characteristics, information on abnormal impurities and hard particles is identified; Calculate the abnormal particle strength index based on the abnormal impurity information and the hard particle information; The initial stress value is calculated based on the physicochemical properties and the abnormal particle strength index.

7. The method according to claim 3, characterized in that, The step of calculating the target stress value based on the impact event intensity, the initial stress value, the degree of component wear impact, and the parameter deviation includes: The influence weight is determined based on the degree of impact of the component loss and the degree of deviation of the parameters; Calculate the weighted impact intensity value based on the impact event intensity and the impact weight; The target stress value is obtained by superimposing the weighted impact strength value with the initial stress value.

8. The method according to claim 1, characterized in that, The step of assessing the wear trend of equipment components based on the cumulative fatigue index includes: Calculate the rate of change of the index based on the cumulative fatigue index; The fatigue loss conversion function is adjusted based on the rate of change of the aforementioned indicators, the equipment operating parameters, and the physicochemical properties. Based on the fatigue loss conversion function, the cumulative fatigue index is converted into the actual wear and tear of the equipment components. The wear trend of the equipment components is assessed based on their actual and historical wear.

9. The method according to claim 1, characterized in that, The step of generating a parameter control strategy based on the wear trend of the equipment components includes: Obtain information on the current production line's production throughput demand, raw material inventory, product delivery deadlines, and equipment energy consumption levels; Based on the wear trend of the equipment components, the production throughput demand information, and the equipment energy consumption level information, a production adjustment strategy is determined. The production adjustment strategy includes adjusting the production speed, switching production batches, or temporarily stopping the machine for maintenance. Based on the wear and tear trend of the equipment components, the raw material inventory information, and the product delivery deadline information, a maintenance scheduling strategy is determined, which includes preventive maintenance, delayed maintenance, or component replacement. A comprehensive production impact assessment is performed on the production adjustment strategy and the maintenance scheduling strategy to obtain the comprehensive production impact. The parameter control strategy is generated based on the overall production impact, the production adjustment strategy, and the maintenance scheduling strategy.

10. A parameter control system for the preparation process of a flue gas denitrification catalyst, characterized in that, include: The data acquisition module is used to acquire equipment operating parameters and physicochemical properties of raw materials; The impact assessment module is used to assess the impact of component wear based on the equipment operating parameters and the physicochemical properties information. The stress value calculation module is used to calculate the target stress value generated on the equipment component when the operating parameters deviate from the reference, based on the degree of component wear, the physicochemical property information, the equipment operating parameters and the parameter reference range; The stress accumulation module is used to accumulate and calculate multiple target stress values ​​to obtain cumulative fatigue indexes; The wear trend assessment module is used to assess the wear trend of equipment components based on the cumulative fatigue index. The control strategy generation module is used to generate parameter control strategies based on the wear trend of the equipment components.

Images