Method and system for controlling production and processing quality of disinfection equipment based on intelligent analysis

Abstract

The invention provides a disinfection equipment production and processing quality control method and system based on intelligent analysis. Precise control of the drying process is achieved through three-stage collaborative optimization, firstly, hot air distribution parameters and historical energy consumption data of the drying process are integrated, a hot air uniformity and energy efficiency collaborative optimization model is constructed, and a dynamic target parameter system is established. Secondly, temperature field distribution data are collected in real time in the equipment operation process, multi-dimensional dynamic correlation analysis is conducted on the temperature field distribution data and energy consumption data of the heat supply device, heat field abnormal fluctuation and energy consumption correlation characteristics are recognized through a machine learning algorithm, and finally a heating power dynamic adjusting instruction is generated based on an analysis result; and by adopting the synergistic effect of a differential control algorithm and a frequency conversion regulation technology, process requirements are accurately converted into power supply frequency regulation and control signals, and millisecond-level dynamic response and self-adaptive regulation of the heating power are realized. According to the technical scheme provided by the invention, the production and processing quality control efficiency and accuracy of the disinfection equipment can be improved.

Description

Technical Field

[0001] This application relates to the technical field of quality control in the production and processing of disinfection equipment, and particularly to a quality control method and system for the production and processing of disinfection equipment based on intelligent analysis. Background Art

[0002] During the production and processing of disinfection equipment, the thermal field uniformity and energy consumption efficiency of the heating system are the core factors affecting product quality and production costs. The high-temperature drying process needs to ensure the uniformity of the temperature distribution inside the box to avoid material deformation caused by local overheating or under-drying. At the same time, it is necessary to optimize the energy consumption efficiency of the heating device to reduce carbon emissions and operating costs. However, the dynamic disturbance of the thermal field (such as the fluctuation of the fan air flow and the difference in material heat absorption) and the energy consumption characteristics of multi-variable coupling make it difficult for traditional control methods to achieve the coordinated optimization of uniformity and energy efficiency, and there is an urgent need for an intelligent dynamic control method.

[0003] The current mainstream solution adopts a thermal field regulation system based on differential control. By deploying multi-point temperature sensors to collect hot air temperature data in real time, combined with preset temperature thresholds and energy consumption benchmark curves, the heating module is adjusted in segments for power. The system corrects the temperature deviation through a feedback mechanism and uses a static energy consumption model (such as a linear regression model) to predict the energy consumption trend, initially realizing partial optimization of temperature stability and energy consumption.

[0004] This solution has three deficiencies. First, differential control depends on fixed parameters and is difficult to adapt to variable working condition disturbances (such as sudden changes in material load), resulting in a lag in dynamic compensation of the temperature field and an easy over-limit of the uniformity deviation. Second, the static energy consumption model cannot real-time associate the temperature field distribution with the transient power demand of the heating device, resulting in the disconnection between energy consumption optimization and thermal field regulation, and the actual operating energy consumption is still higher than the theoretical value. Third, relying only on temperature feedback data and lacking the integrated analysis of multi-physical field parameters such as hot air flow velocity and humidity, it is difficult to analyze the deep coupling relationship between thermal field non-uniformity and energy consumption abnormality, and the accuracy of the control instruction is limited. Summary of the Invention

[0005] This application provides a quality control method and system for the production and processing of disinfection equipment based on intelligent analysis, aiming to solve the problems of low efficiency and poor accuracy in the quality control of the production and processing of disinfection equipment in the prior art.

[0006] In the first aspect, this application provides a quality control method for the production and processing of disinfection equipment based on intelligent analysis, including:

[0007] Obtain the hot air distribution parameters corresponding to the drying technology during the production process of the disinfection equipment, and synchronously collect the historical energy consumption data of the heating device. Based on the hot air distribution parameters and historical energy consumption data, construct a coordinated optimization target parameter for hot air uniform distribution and energy consumption efficiency;

[0008] Obtain the dynamic distribution data of the temperature field during the heating operation of the disinfection device according to the collaborative optimization target parameters, and perform dynamic correlation analysis on the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection device to obtain the result of the dynamic correlation analysis;

[0009] Generate a heating power adjustment instruction based on the result of the dynamic correlation analysis, and convert it into a regulation signal of the power supply frequency by using the synergistic effect of differential control and frequency conversion regulation according to the heating power adjustment instruction.

[0010] Optionally, the converting the heating power adjustment instruction into a regulation signal of the power supply frequency by using the synergistic effect of differential control and frequency conversion regulation includes:

[0011] Perform differential control processing on the heating power adjustment instruction, and extract the attenuation coefficient of the high-frequency fluctuation component and the compensation amount of the cumulative deviation in the heating power to generate an intermediate adjustment signal;

[0012] Calculate the reference offset of the power supply frequency based on the intermediate adjustment signal and the frequency-power response curve of the heating device;

[0013] Input the reference offset into the dynamic weight distribution mechanism of frequency conversion regulation, and generate a frequency adjustment step size and a phase compensation threshold in combination with the spatial propagation delay characteristics of the hot air distribution parameters;

[0014] Adjust the proportional relationship between the frequency adjustment step size and the phase compensation threshold so that the instantaneous change rate of the power supply frequency matches the spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, and output the regulation signal of the power supply frequency.

[0015] Optionally, the adjusting the proportional relationship between the frequency adjustment step size and the phase compensation threshold includes:

[0016] Based on the propagation direction and spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, establish a dynamic mapping relationship between the instantaneous change rate of the power supply frequency and the spatio-temporal attenuation rate of the temperature gradient to extract the initial proportional coefficient of the frequency adjustment step size and the phase compensation threshold;

[0017] Determine the dynamic adjustment factor of the initial proportional coefficient according to the real-time deviation amount between the instantaneous change rate and the spatio-temporal attenuation rate in the dynamic mapping relationship;

[0018] Input the dynamic adjustment factor and the initial proportional coefficient into the dynamic weight distribution mechanism, and perform multi-dimensional weighted fusion on the proportional relationship between the frequency adjustment step size and the phase compensation threshold in combination with the propagation path length of the maximum temperature gradient in the hot air distribution parameters to generate an updated proportional coefficient;

[0019] Based on the updated proportionality coefficient, iteratively approximate the instantaneous change rate. When the cumulative error between the instantaneous change rate and the spatio-temporal attenuation rate is lower than a preset threshold, obtain the adjusted proportional relationship.

[0020] Optionally, the step of obtaining the adjusted proportional relationship when the cumulative error between the instantaneous change rate and the spatio-temporal attenuation rate is lower than a preset threshold includes:

[0021] Based on the real-time monitoring data of the spatio-temporal attenuation rate in the updated proportionality coefficient and the hot air distribution parameters, calculate the cumulative error amount of the instantaneous change rate;

[0022] According to the cumulative error amount and the propagation path length of the maximum temperature gradient in the hot air distribution parameters, dynamically adjust the adaptation range of the preset threshold;

[0023] When the cumulative error amount is lower than the adjusted preset threshold, based on the spatial propagation delay characteristic of the hot air distribution parameters and the attenuation trend of the cumulative error amount, perform multi-cycle fluctuation suppression verification on the instantaneous change rate;

[0024] After the multi-cycle fluctuation suppression verification passes, combine the long-term convergence trend slope of the cumulative error amount and the critical propagation rate of the spatio-temporal attenuation rate, trigger a global locking instruction, and output the adjusted proportional relationship.

[0025] Optionally, the step of dynamically correlating and analyzing the dynamic temperature field distribution data and the real-time energy consumption data of the heating device includes:

[0026] Based on the temperature deviation amount at each position point in the dynamic temperature field distribution data and the real-time energy consumption data of the heating device, extract the temperature deviation propagation direction and the energy consumption fluctuation coefficient;

[0027] Perform coupling analysis on the temperature deviation propagation direction and the energy consumption fluctuation coefficient to generate a joint optimization index for the attenuation rate of the uniform distribution of hot air and the energy consumption efficiency;

[0028] Combine the mean offset of the historical energy consumption data and the propagation delay characteristic of the temperature gradient to dynamically correct the weight ratio of the joint optimization index;

[0029] Based on the spatio-temporal consistency of the temperature gradient propagation direction and the thermal inertia parameters, perform multi-cycle iterative verification on the corrected weight ratio, and output the dynamic correlation analysis result when the verification error is lower than the tolerance boundary of the joint optimization index.

[0030] Optionally, the step of combining the mean offset of the historical energy consumption data and the propagation delay characteristic of the temperature gradient to dynamically correct the weight ratio of the joint optimization index includes:

[0031] Determine the dynamic correction factor for the attenuation rates of the uniform hot air distribution and energy consumption efficiency based on the fluctuation amplitude of the mean offset of the historical energy consumption data and the attenuation rate of the propagation delay characteristic of the temperature gradient;

[0032] Input the dynamic correction factor into the weight allocation mechanism of the joint optimization index, and in combination with the real-time change rate of the propagation direction of the temperature gradient and the thermal inertia parameters of the heating device, perform multi-dimensional coupling correction on the weight ratio of the attenuation rates of the uniform hot air distribution and energy consumption efficiency;

[0033] Based on the corrected weight ratio, calculate the collaborative deviation amount between the maximum temperature gradient in the dynamic temperature field distribution data and the real-time energy consumption data of the heating device. When the attenuation trend of the collaborative deviation amount matches the stability boundary of the thermal inertia parameters, determine the optimal weight ratio;

[0034] Feed back the optimal weight ratio to the dynamic mapping relationship mechanism of the joint optimization index, update the correlation logic of the thermal field energy consumption mapping in the heating device, and output the dynamic correction result.

[0035] Optionally, the construction of the collaborative optimization target parameters for the uniform hot air distribution and energy consumption efficiency based on the hot air distribution parameters and historical energy consumption data includes:

[0036] Decompose the hot air distribution parameters into multiple orthogonal modal components in the spatial dimension, and calculate the energy proportion coefficient and spatial variation index of the orthogonal modal components;

[0037] Construct a multi-dimensional decomposition model of the historical energy consumption data, extract the eigenvectors dynamically associated with the temperature field during different operation cycles of the heating device, and calculate the stability index of the eigenvectors;

[0038] Establish an asymmetric mapping relationship between the energy proportion coefficient and the stability index, and determine the sensitivity coefficient of the uniform hot air distribution to the energy consumption efficiency;

[0039] Construct a collaborative optimization function based on the spatial variation index and the sensitivity coefficient, and use the dynamic change range of the eigenvectors as the constraint condition to generate a two-objective optimization boundary;

[0040] By iteratively correcting the weight allocation of the orthogonal modal components, make the collaborative optimization function satisfy the Pareto optimal condition within the two-objective optimization boundary, and generate the collaborative optimization target parameters for the uniform hot air distribution and energy consumption efficiency.

[0041] In a second aspect, the present application provides a quality control system for the production and processing of disinfection equipment based on intelligent analysis, including:

[0042] An acquisition module acquires the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection device, and synchronously collects the historical energy consumption data of the heating device, and constructs a collaborative optimization target parameter for the uniform distribution of hot air and energy consumption efficiency based on the hot air distribution parameters and the historical energy consumption data;

[0043] An analysis module obtains the dynamic distribution data of the temperature field during the heating operation of the disinfection device according to the collaborative optimization target parameter, and performs dynamic correlation analysis on the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection device to obtain the result of the dynamic correlation analysis;

[0044] A generation module generates a heating power adjustment instruction based on the result of the dynamic correlation analysis, and converts the heating power adjustment instruction into a control signal for the power supply frequency by using the synergistic effect of differential control and frequency conversion adjustment.

[0045] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a quality control method for the production and processing of a disinfection device based on intelligent analysis as described in the first aspect above.

[0046] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which when executed by a computer, implements a quality control method for the production and processing of a disinfection device based on intelligent analysis as described in the first aspect.

[0047] In the embodiment of the present application, the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection device are acquired, and the historical energy consumption data of the heating device is synchronously collected, and a collaborative optimization target parameter for the uniform distribution of hot air and energy consumption efficiency is constructed based on the hot air distribution parameters and the historical energy consumption data; according to the collaborative optimization target parameter, the dynamic distribution data of the temperature field during the heating operation of the disinfection device is acquired, and the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection device are dynamically correlated and analyzed to obtain the result of the dynamic correlation analysis; a heating power adjustment instruction is generated based on the result of the dynamic correlation analysis, and the heating power adjustment instruction is converted into a control signal for the power supply frequency by using the synergistic effect of differential control and frequency conversion adjustment.

[0048] The technical solution of the present application has the following beneficial effects:

[0049] This application constructs a multi-objective optimization model for thermal field uniformity and energy consumption efficiency by synchronously collecting hot air distribution parameters and historical energy consumption data, providing quantitative benchmark parameters for dynamic regulation, and solving the problem of the separation of thermal performance and energy efficiency in traditional single-objective optimization. It fuses the dynamic distribution data of the temperature field and the heating energy consumption data in real time, accurately locates the associated nodes of thermal field fluctuations and energy consumption anomalies based on the coupled analysis of multi-source data, and improves the collaborative diagnosis ability of process disturbances and energy consumption offsets. Through the collaborative mechanism of differential control and frequency conversion regulation, the power regulation demand is converted into a high-precision power supply frequency regulation signal, realizing millisecond-level closed-loop control of dynamic thermal field compensation and energy consumption optimization.

[0050] Furthermore, based on the differential algorithm, dynamic noise reduction and deviation compensation processing are performed on the power regulation command. A reference frequency offset model is established by combining the frequency-power response characteristics of the heating device, and the spatial delay law of hot air propagation is further integrated. Through the dynamic weight allocation strategy, the coupling relationship between the frequency adjustment step size and the phase compensation parameter is constructed, and finally, the dynamic adaptation of the transient response rate of the power supply frequency and the temperature field gradient decay process is achieved. The differential algorithm is used to suppress high-frequency noise interference and correct historical deviations, and the frequency conversion regulation timing is optimized by combining the spatial propagation characteristics of the thermal field to ensure that the change rate of the power supply frequency exactly matches the dynamic decay process of the temperature field, thereby synchronously improving the response speed of the thermal field uniformity control and the dynamic adaptability of the frequency conversion energy efficiency conversion.

[0051] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. Brief Description of the Drawings

[0052] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 Shows a flowchart of a method for quality control of the production and processing of a disinfection device based on intelligent analysis provided by this application;

[0054] Figure 2 Shows a schematic structural diagram of a quality control system for the production and processing of a disinfection device based on intelligent analysis provided by this application;

[0055] Figure 3 Shows a schematic structural diagram of a computing device provided by this application. Detailed Embodiments

[0056] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0057] In some processes described in the specification, claims and above-mentioned accompanying drawings of this application, a number of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish each different operation, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are different types.

[0058] Researchers found that it is difficult to dynamically coordinate and optimize the hot air distribution and energy consumption efficiency during the production process of existing disinfection equipment, resulting in uneven drying and high energy consumption. Based on this, a quality control method for the production and processing of disinfection equipment based on intelligent analysis is provided. This method can construct collaborative optimization parameters for uniform hot air distribution and energy consumption efficiency, combine the correlation analysis of temperature field dynamic data and real-time energy consumption, and use differential control and frequency conversion regulation to jointly control the power supply frequency to achieve precise control of the thermal field distribution during the drying process and synchronous improvement of energy utilization efficiency. This solution is applicable to the scenario of uniformity and energy consumption optimization of the heating system of disinfection equipment. By fusing multi-source data (hot air distribution parameters and historical energy consumption data) to construct a dynamic optimization model, and based on the dynamic correlation analysis of real-time temperature field distribution data and heating energy consumption, the coupling relationship between thermal field fluctuations and energy consumption anomalies is identified. Then, a differential control algorithm is used to analyze the high-frequency disturbance characteristics of power regulation, and combined with frequency conversion regulation technology, a dynamic compensation for the spatial and temporal attenuation rate matching of the power supply frequency is carried out, and finally a closed-loop control for precise thermal field regulation and energy efficiency optimization is achieved.

[0059] Throughout the research process, through intelligent analysis means, collaborative optimization modeling of hot air distribution parameters and heating energy consumption data is carried out, the temperature field distribution and real-time energy consumption information are dynamically correlated, and a collaborative control mechanism combining differential control and frequency conversion regulation is used to solve problems such as uneven hot air distribution and low energy consumption efficiency in the production of traditional disinfection equipment. It significantly improves the uniformity and stability of the drying process, and at the same time realizes precise optimization control of energy consumption, reduces energy waste while ensuring product quality, and provides an efficient and intelligent quality control solution for the production and processing of disinfection equipment.

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0061] Figure 1 The figure is a flowchart of a method for quality control of the production and processing of disinfection equipment based on intelligent analysis provided by an embodiment of the present application. As Figure 1 shown, the method includes:

[0062] 101. Obtain the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection equipment, and synchronously collect the historical energy consumption data of the heating device. Based on the hot air distribution parameters and the historical energy consumption data, construct a collaborative optimization target parameter for the uniform distribution of hot air and energy consumption efficiency;

[0063] In this step, the drying technology refers to a process method for removing moisture on the surface and inside of materials by means of hot air circulation, radiation heat transfer, or conduction heating during the production process of the disinfection equipment.

[0064] The hot air distribution parameters refer to the spatial distribution characteristic data such as the hot air temperature, flow rate, and uniformity in the box collected by devices such as multi-point temperature sensors and anemometers during the drying process.

[0065] The historical energy consumption data refers to the recorded data such as power consumption, thermal efficiency, and carbon emissions of the heating device (such as electric heating tubes, gas boilers) during the historical operation cycle.

[0066] The uniform distribution of hot air means that in the drying process of the disinfection equipment, by regulating the heating device and the air flow circulation system, the hot air temperature, flow rate, and heat transfer rate in each area of the box reach spatial consistency, avoiding material denaturation or uneven drying caused by local overheating or under-drying.

[0067] The energy consumption efficiency refers to the ratio reflecting the conversion of the input energy (electric energy, gas, etc.) of the heating device into effective heat energy.

[0068] The collaborative optimization target parameter refers to a quantitative index generated by a multi-objective optimization algorithm for balancing the conflicting requirements of the uniformity of the thermal field and the energy consumption efficiency.

[0069] In the embodiments of the present application, a high-precision temperature sensor array (such as an infrared thermal imager) and a wind speed probe are deployed inside the drying oven to collect hot air distribution parameters in real time. At the same time, the historical energy consumption data of the heating device is recorded through an energy consumption metering module. A multi-objective optimization algorithm (such as the non-dominated sorting genetic algorithm) is used, with the minimization of the standard deviation of the hot air temperature and the maximization of the energy consumption efficiency as the objective functions, and the model weights are trained in combination with historical data to generate cooperative optimization target parameters (such as the temperature uniformity threshold, the energy efficiency weight coefficient). Finally, the optimized target parameters (such as temperature uniformity of ±1.5°C, energy efficiency weight of 0.7) are input into the control system as the benchmark for subsequent regulation.

[0070] In a certain disinfection equipment production line, a 16-channel temperature sensor and an ultrasonic anemometer are installed inside the drying oven to synchronously collect hot air temperature distribution data (such as the temperature range at each point is 120-125°C). At the same time, the historical energy consumption data of the heating device in the past 30 days (such as the average daily power consumption of 500 kW·h) is extracted from the energy management system. Through calculation by a multi-objective optimization model, cooperative optimization target parameters are generated, and the temperature uniformity is controlled within ±1.5°C, and the energy consumption efficiency is greatly improved.

[0071] 102. According to the cooperative optimization target parameters, obtain the dynamic distribution data of the temperature field during the heating operation of the disinfection equipment, and perform dynamic correlation analysis on the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection equipment to obtain the result of the dynamic correlation analysis;

[0072] In this step, the dynamic distribution data of the temperature field refers to the real-time monitoring data of the temperature change of each region in the box over time during the heating process.

[0073] The real-time energy consumption data refers to the energy consumption information instantaneously collected during the operation of the heating device, including parameters such as power (such as the current power of 80 kW), fuel flow rate (such as the natural gas flow rate of 10 m 3 / h), and thermal efficiency (such as the real-time thermal efficiency of 82%).

[0074] The dynamic correlation analysis refers to using statistical or machine learning methods to analyze the real-time coupling relationship between the temperature field fluctuations and the energy consumption changes, and identify abnormal correlation nodes.

[0075] In the embodiments of the present application, the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device are transmitted to the edge computing node in real time through the Internet of Things protocol, and the timestamps are aligned to the millisecond level of accuracy. The dynamic time warping algorithm or Granger causality analysis is used to calculate the correlation coefficients between the standard deviation of the temperature field, the gradient change rate, and the real-time energy consumption fluctuations, and identify key correlation features (such as a sudden increase in energy consumption caused by a sudden change in the temperature gradient). Based on clustering analysis, normal operating conditions and abnormal operating conditions are divided, and a dynamic correlation analysis report is generated (such as a 2°C sudden drop in temperature in a certain area resulting in an increase in energy consumption).

[0076] Continuing with the above case, during the operation of the production line, the system detected that the temperature in the left front area of the drying oven dropped by 2°C within 5 minutes (from 123°C to 121°C), and at the same time, the power of the heating device increased from 80 kW to 92 kW. Through dynamic correlation analysis, it was determined that the temperature drop was caused by abnormal fan speed, resulting in blocked hot air circulation, and there was a strong correlation between the abnormal increase in energy consumption and the non-uniformity of the temperature field (correlation coefficient 0.89).

[0077] 103. Generate a heating power adjustment instruction based on the result of the dynamic correlation analysis, and convert it into a control signal for the power supply frequency by using the synergistic effect of differential control and frequency conversion adjustment according to the heating power adjustment instruction.

[0078] In this step, the heating power refers to the total amount of heat energy output by the heating device per unit time, with the unit of kilowatt, which directly affects the drying rate and the stability of the temperature field.

[0079] Differential control refers to a control algorithm that predicts future system deviations by calculating the change rate of the error signal and is used to suppress high-frequency disturbances.

[0080] Frequency conversion adjustment refers to changing the output power of the motor or heating element by adjusting the power supply frequency to achieve energy efficiency optimization.

[0081] The power supply frequency refers to the periodic change frequency of alternating current. By adjusting the power supply frequency of the motor or heating element through a frequency converter (such as from 50 Hz to 45 Hz), the rotational speed or power output of the equipment can be controlled.

[0082] The control signal is an instruction signal generated by the control system and is used to drive the actuator (such as a frequency converter, relay) to adjust the operating state of the equipment.

[0083] In the embodiment of the present application, based on the result of the dynamic correlation analysis, a fuzzy differential control algorithm is used to generate a heating power adjustment instruction. For example, the target power is adjusted from 90 kW to 85 kW. Perform a differential operation on the heating power adjustment instruction, extract the high-frequency fluctuation component and calculate the attenuation coefficient to generate a smoothed intermediate adjustment signal. According to the frequency-power response curve of the frequency converter (such as 50 Hz corresponding to 100 kW), combined with the hot air propagation delay time (such as 0.5 s), dynamically allocate the frequency adjustment step size (such as 0.2 Hz / step) and the phase compensation amount, and output the control signal to the frequency converter.

[0084] When the system detects an abnormal temperature gradient in the right rear area (too fast heating rate), a heating power reduction adjustment instruction is generated (from 95 kW to 88 kW). The differential control algorithm suppresses the high-frequency noise in the instruction (such as the fluctuations caused by the fan vibration). The frequency converter adjusts the power supply frequency from 49 Hz to 47.5 Hz according to the control signal, smoothly reducing the heating pipe power to the target value. At the same time, it compensates for the hot air circulation delay and restores the temperature uniformity to ±1.2 °C within 5 seconds.

[0085] In summary, steps 101 to 103 achieve the synchronous optimization of the thermal field uniformity and energy consumption efficiency in the drying process of the disinfection equipment through the multi-objective dynamic optimization that integrates the thermal field distribution and energy consumption data, combines the correlation analysis of the temperature field energy consumption and the differential frequency conversion collaborative control technology, and simultaneously suppresses the process disturbances through the millisecond-level dynamic response, ensuring the product quality stability and reducing the production cost.

[0086] To solve the problem of the collaborative optimization of high-frequency disturbance suppression and thermal field response delay in the dynamic regulation of heating power, this solution filters the high-frequency noise in the power instruction and compensates for the historical deviation through the differential control algorithm, quantifies the frequency offset requirement by combining the frequency-power response curve, further integrates the characteristics of the hot air propagation delay to design a dynamic weight allocation mechanism, and finally matches the change rate of the power supply frequency with the temperature gradient attenuation process to achieve the spatio-temporal synchronous optimization of the thermal field regulation and the frequency conversion energy efficiency. In some embodiments, the conversion of the heating power adjustment instruction into the control signal of the power supply frequency by using the collaborative effect of differential control and frequency conversion regulation in step 103 further includes:

[0087] 201. Perform differential control processing on the heating power adjustment instruction, extract the attenuation coefficient of the high-frequency fluctuation component and the compensation amount of the cumulative deviation in the heating power, and generate an intermediate adjustment signal;

[0088] In step 201, the differential control processing is a control algorithm based on the error change rate. By calculating the instantaneous change rate of the target parameter (such as heating power) in real time, it predicts the future deviation trend of the system and generates the corresponding compensation signal. The attenuation coefficient of the high-frequency fluctuation component refers to the suppression intensity parameter of the fast fluctuation component in the heating power signal caused by equipment vibration or power supply interference, which characterizes the noise filtering ability of the control system. The compensation amount of the cumulative deviation refers to the cumulative difference in power demand caused by historical regulation errors (such as the long-term uncorrected temperature deviation), which needs to be dynamically compensated through integral operation. The intermediate adjustment signal is the power adjustment instruction after differential control processing, including the noise-reduced target power value and the deviation compensation value.

[0089] In the embodiments of the present application, differential control processing is used to decompose the heating power adjustment command in the time domain. The high-frequency fluctuation component (such as ±2 kW / s) is extracted through a high-pass filter, and its attenuation coefficient (such as 0.8) is calculated. At the same time, an integrator is used to accumulate the historical power deviation (such as the cumulative under-regulation of 3 kW in the past 5 minutes) to generate a compensation amount. The attenuation coefficient and the compensation amount are superimposed on the target power reference value (such as from 90 kW to 87 kW), and a smoothed intermediate adjustment signal is output.

[0090] 202. Calculate the reference offset of the power supply frequency based on the intermediate adjustment signal and the frequency-power response curve of the heating device;

[0091] In step 202, the intermediate adjustment signal is the power adjustment command after differential control processing, including the noise-reduced target power value and the deviation compensation value. The frequency-power response curve is a curve representing the corresponding relationship between the power supply frequency (such as 50 Hz) and the output power (such as 100 kW) of the heating device, which is obtained through experimental calibration or data fitting. The reference offset refers to the change amount of the power supply frequency (such as from 50 Hz to 48 Hz) required to achieve the target power adjustment.

[0092] In the embodiments of the present application, according to the target power value (such as 87 kW) of the intermediate adjustment signal, the pre-stored frequency-power response curve is queried (such as the frequency-power relationship is linear, about 1 Hz is equal to 2 kW), and the reference frequency offset is calculated (such as to reduce 3 kW, the frequency is lowered by 1.5 Hz). The frequency-power nonlinear error is calibrated in combination with the real-time working conditions (such as the curve offset caused by the decrease in thermal efficiency at high temperatures), and the reference offset is corrected to 1.8 Hz.

[0093] 203. Input the reference offset into the dynamic weight distribution mechanism of the variable frequency adjustment, and generate the frequency adjustment step size and the phase compensation threshold in combination with the spatial propagation delay characteristics of the hot air distribution parameters;

[0094] In step 203, the dynamic weight distribution mechanism is an adaptive algorithm that dynamically adjusts the parameter weight ratio according to the real-time working conditions, and is used to solve the priority conflict problem in the multi-variable coupling regulation. By fusing the spatial propagation delay characteristics of the heat field (such as the diffusion time difference of hot air from the heating end to the end of the box), it performs differential weight distribution on the regulation parameters (such as the frequency adjustment step size, the phase compensation threshold) to ensure that the regulation command matches the dynamic response characteristics of the heat field. The spatial propagation delay characteristic refers to the time difference of hot air diffusing from the outlet of the heating device to each area of the box (such as a 0.3-second delay in the left area and a 0.5-second delay in the right area). The frequency adjustment step size is the change amplitude of the power supply frequency in a single regulation (such as adjusting 0.2 Hz each time). The phase compensation threshold is the trigger condition for predicting the effective moment of the frequency adjustment according to the delay time (such as sending a command 0.5 seconds in advance).

[0095] In the embodiments of the present application, based on the spatial propagation delay characteristics of the hot air distribution parameters (such as a 0.3-second delay in the left area and a 0.5-second delay in the right area), the reference offset (1.8 Hz) is input into the dynamic weight allocation mechanism. The fuzzy logic algorithm is used to allocate the frequency adjustment step weight according to the regional delay time (such as a 0.1-Hz / step in the left area and a 0.25-Hz / step in the right area), and generate a phase compensation threshold (such as the right area instruction is executed 0.5 seconds in advance). Finally, the regionally differentiated regulation parameters are output.

[0096] 204. Adjust the proportional relationship between the frequency adjustment step and the phase compensation threshold so that the instantaneous change rate of the power supply frequency matches the spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, and output the regulation signal of the power supply frequency.

[0097] In step 204, the instantaneous change rate of the power supply frequency refers to the adjustment rate of the power supply frequency per unit time (such as a change of 0.5 Hz per second), which characterizes the response speed of the frequency converter to the regulation instruction. This parameter needs to be dynamically matched with the spatio-temporal attenuation rate of the temperature gradient in the thermal field (such as the diffusion rate from the high-temperature area to the low-temperature area) to ensure that the frequency adjustment is synchronized with the thermal field change and avoid temperature fluctuations or energy consumption waste caused by inconsistent response speeds. The spatio-temporal attenuation rate of the temperature gradient refers to the heat diffusion rate in the uneven temperature area in the box (such as from the high-temperature area to the low-temperature area), which is calculated by the heat conduction equation.

[0098] In the embodiments of the present application, according to the temperature gradient attenuation rate (such as a 0.5°C / s cooling rate in the right rear area), adjust the proportional relationship between the frequency adjustment step (0.25 Hz / step) and the phase compensation threshold (0.5 seconds) so that the instantaneous change rate of the power supply frequency (such as 0.5 Hz / s) matches the spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters. The proportional coefficient is calibrated in real time through a differential controller, and finally a power supply frequency regulation signal synchronized with the thermal field dynamically is generated (such as the frequency in the right area changes from 49 Hz to 47.2 Hz, and the frequency in the left area changes from 49 Hz to 48.5 Hz).

[0099] The following is a specific example:

[0100] In a production line of a disinfection device, the temperature gradient in the right rear area of the drying oven is abnormal due to material accumulation (from 130°C to 122°C, with a cooling rate of 0.6°C / s). The system performs the following regulation: detecting power command fluctuations (target power from 95 kW to 88 kW), differential control filtering out high-frequency noise caused by fan vibration (±1.2 kW), and compensating for the historical cumulative deviation (undertuning of 2.5 kW in the past 10 minutes), generating an intermediate adjustment signal of 89.5 kW. Querying the frequency-power curve (1 Hz is approximately equal to 2.2 kW), calculating the reference frequency offset of -3.4 Hz (from 50 Hz to 46.6 Hz), and correcting it to -3.6 Hz after calibration. According to the 0.6-second delay characteristic of the right area, allocating a frequency adjustment step of 0.3 Hz per time and a phase compensation threshold of 0.6 seconds, and a step of 0.15 Hz per time for the left area. Matching the temperature decay rate of 0.6°C / s in the right area, adjusting the frequency change rate to 0.5 Hz / s, and finally outputting a regulation signal with a frequency of 46.6 Hz in the right area and 48.4 Hz in the left area, restoring the temperature uniformity to ±1.3°C within 10 seconds.

[0101] In summary, steps 201 to 204 suppress high-frequency disturbances through differential control and compensate for historical deviations. Combining the frequency-power response characteristics and the thermal field space delay law, dynamically allocate the frequency adjustment step and the phase compensation threshold to achieve precise matching between the power supply frequency change rate and the temperature gradient decay process. This method improves the control accuracy of the thermal field uniformity, synchronously reduces the ineffective energy consumption caused by regulation lag, and shortens the temperature anomaly recovery time to the 10-second level, significantly improving the quality stability and energy utilization efficiency of the drying process of the disinfection device.

[0102] To solve the problem of temperature uniformity fluctuation caused by the mismatch between the power supply frequency regulation and the dynamic attenuation rate of the thermal field, the solution establishes a dynamic mapping model of the temperature gradient propagation direction and the frequency change rate by targeting the proportional adaptation problem of the frequency adjustment step and the phase compensation threshold. Generating a proportional coefficient adjustment factor through the real-time deviation amount, and performing multi-dimensional weighted fusion and iterative approximation in combination with the propagation path length to ensure that the proportional relationship adaptively matches the dynamic attenuation characteristics of the thermal field. In some embodiments, adjusting the proportional relationship between the frequency adjustment step and the phase compensation threshold in step 204 further includes:

[0103] 301. Based on the propagation direction and the spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, establish a dynamic mapping relationship between the instantaneous change rate of the power supply frequency and the spatio-temporal attenuation rate of the temperature gradient to extract the initial proportional coefficient of the frequency adjustment step and the phase compensation threshold;

[0104] In step 301, the propagation direction of the temperature gradient is the direction of the heat diffusion path from the high-temperature area to the low-temperature area in the box (such as propagating from left to right).

[0105] The spatio-temporal decay rate refers to the heat diffusion rate of the temperature gradient in a specific direction (for example, the high-temperature area decays towards the low-temperature area at a rate of 0.5 °C per second).

[0106] The initial proportionality coefficient refers to the parameter of the initial proportional relationship between the frequency adjustment step (the amount of single-frequency change) and the phase compensation threshold (the advance time of the control instruction).

[0107] In the embodiments of the present application, a spatio-temporal decay rate model of the temperature gradient is established based on the heat conduction equation, and the propagation direction of the temperature gradient is fitted by combining the data of multiple-point temperature sensors (for example, the right rear area is the main heat diffusion direction). Through regression analysis, a dynamic mapping relationship between the instantaneous change rate of the power supply frequency (such as 0.6 Hz / s) and the spatio-temporal decay rate of the temperature gradient (0.5 °C / s) is constructed, and the initial proportionality coefficient is extracted (for example, a step size of 0.2 Hz per time corresponds to a compensation threshold of 0.4 seconds).

[0108] 302. Determine the dynamic adjustment factor of the initial proportionality coefficient according to the real-time deviation amount between the instantaneous change rate and the spatio-temporal decay rate in the dynamic mapping relationship;

[0109] In step 302, the dynamic mapping relationship refers to the real-time correspondence relationship established between the instantaneous change rate of the power supply frequency (such as adjusting 0.5 Hz per second) and the spatio-temporal decay rate of the temperature gradient (such as decreasing 0.6 °C per second) through a mathematical model or algorithm. Its essence is to describe the matching rule between the control response speed and the dynamic decay characteristics of the thermal field, and is used to guide the proportional allocation of the frequency adjustment step and the phase compensation threshold. The real-time deviation amount is the real-time difference value between the instantaneous change rate and the temperature decay rate (for example, a frequency change rate of 0.7 Hz / s corresponds to a temperature decay of 0.5 °C / s, with a deviation of 0.2 Hz·s / °C). The dynamic adjustment factor refers to the dynamic parameter used to correct the initial proportionality coefficient, reflecting the influence weight of the deviation on the control timing.

[0110] In the embodiments of the present application, by real-time monitoring the spatio-temporal decay rate (such as 0.48 °C / s) and the instantaneous change rate of the frequency (such as 0.65 Hz / s), the real-time deviation amount (0.17 Hz·s / °C) is calculated. The proportional integral algorithm is used to generate the dynamic adjustment factor (such as a correction coefficient of 1.2 times), and the initial proportionality coefficient is corrected (the step size changes from 0.2 Hz to 0.24 Hz, and the compensation threshold changes from 0.4 seconds to 0.33 seconds).

[0111] 303. Input the dynamic adjustment factor and the initial proportionality coefficient into the dynamic weight allocation mechanism, and combine the propagation path length of the maximum temperature gradient in the hot air distribution parameters to perform multi-dimensional weighted fusion on the proportional relationship between the frequency adjustment step and the phase compensation threshold to generate an updated proportionality coefficient;

[0112] In step 303, the propagation path length is the maximum diffusion distance of the temperature gradient from the heat source to the target area (eg, the path length of the right rear area is 2 meters).

[0113] The frequency adjustment step refers to the change in the power supply frequency within a single control cycle (such as 0.2Hz each adjustment), which is used to approach the target frequency value in stages. Its size needs to be dynamically set in combination with the hot air propagation delay characteristics (such as 0.5 seconds for hot air to diffuse in a certain area) to ensure that the timing of the control command taking effect matches the thermal field changes.

[0114] Multi-dimensional weighted fusion refers to dynamically allocating weights based on multiple factors such as path length and thermal inertia parameters to optimize the proportional coefficient.

[0115] In the embodiment of the present application, according to the propagation path length (2 meters) of the maximum temperature gradient in the right rear area and the thermal inertia parameters (such as heat capacity coefficient), the fuzzy logic algorithm is used to assign weights (such as path length weight 0.6, thermal inertia weight 0.4). The dynamic adjustment factor (1.2 times) and the initial proportional coefficient are input into the dynamic weight allocation mechanism to generate an updated proportional coefficient (step size 0.24Hz to 0.26Hz, compensation threshold 0.33 seconds to 0.28 seconds).

[0116] 304. Based on the updated proportional coefficient, the instantaneous change rate is iteratively approximated, and when the cumulative error between the instantaneous change rate and the spatiotemporal attenuation rate is lower than a preset threshold, an adjusted proportional relationship is obtained.

[0117] In step 304, iterative approximation is an optimization method that gradually approaches the target value through multiple parameter corrections. During regulation, by calculating the cumulative error between the instantaneous rate of change and the temperature decay rate (such as 0.1Hz·s / ℃), the proportional coefficient (such as the ratio of the step size to the compensation threshold) is dynamically adjusted until the error is lower than the preset threshold (such as 0.05Hz·s / ℃). The cumulative error is the cumulative value of the deviation between the instantaneous rate of change and the temperature decay rate over multiple regulation cycles. The preset threshold refers to the maximum allowable cumulative error range, which is used to determine whether the proportional relationship converges.

[0118] In the embodiment of the present application, the gradient descent method is used to iteratively update the proportional coefficient and calculate the cumulative error between the instantaneous rate of change and the spatiotemporal attenuation rate (e.g., the error drops to 0.05 Hz·s / °C after 5 adjustments). When the error is lower than the preset threshold (e.g., 0.1 Hz·s / °C), a multi-cycle verification is triggered (e.g., the error is stable for 3 consecutive cycles), and the proportional relationship is finally determined (step size 0.26 Hz / time, compensation threshold 0.28 seconds).

[0119] Here is a specific example:

[0120] In a production line of a disinfection device, the temperature gradient in the right front area of the drying oven is abnormal due to poor hot air circulation (the high-temperature area of 130°C diffuses to the left at a rate of 0.4°C / s). The system performs the following regulation: establish a dynamic mapping relationship between the temperature gradient attenuation rate (0.4°C / s) in the right front area and the frequency change rate (0.5Hz / s), and extract the initial proportionality coefficient (step size 0.18Hz / time, compensation threshold 0.45 seconds). Detect the real-time deviation (frequency change 0.55Hz / s, temperature attenuation 0.38°C / s, deviation 0.17Hz·s / °C), generate a 1.15-fold adjustment factor, correct the step size to 0.207Hz, and the compensation threshold to 0.39 seconds. Combine with the path length (1.8 meters) in the right front area for weighted fusion, and update the proportionality coefficient to a step size of 0.22Hz / time and a compensation threshold of 0.35 seconds. After 5 iterations, the cumulative error drops to 0.08Hz·s / °C, triggering the locking mechanism, outputting the final proportional relationship (step size 0.22Hz / time, compensation threshold 0.35 seconds), and the temperature uniformity is restored to ±1.4°C within 15 seconds.

[0121] In summary, steps 301 to 304 establish a dynamic mapping relationship between temperature gradient attenuation and frequency change, generate a dynamic adjustment factor based on real-time deviation, and perform multi-dimensional weighted fusion based on the propagation path length to achieve adaptive iterative optimization of the proportionality coefficient. This method shortens the lag time of temperature gradient regulation, reduces the cumulative error to about half of the preset threshold, and at the same time avoids overshoot oscillation through the locking mechanism, stabilizes the temperature uniformity within the range of ±1.5°C, and reduces the ineffective energy consumption caused by frequency mismatch, significantly improving the dynamic response accuracy and energy efficiency balance of the drying process of the disinfection device.

[0122] To solve the collaborative optimization problem of dynamic correction of cumulative error and verification of regulation stability, the solution dynamically adjusts the threshold range based on the cumulative error amount and the propagation path length, verifies through multi-period fluctuation suppression and analyzes the long-term convergence trend, triggers the global locking mechanism, solves the stability verification problem of the instantaneous change rate and the temperature gradient attenuation rate, and avoids regulation overshoot or oscillation. In some embodiments, when the cumulative error between the instantaneous change rate and the spatio-temporal attenuation rate in step 304 is lower than the preset threshold, obtaining the adjusted proportional relationship further includes:

[0123] 401. Calculate the cumulative error amount of the instantaneous change rate based on the real-time monitoring data of the updated proportionality coefficient and the spatio-temporal attenuation rate in the hot air distribution parameters;

[0124] In step 401, the hot air distribution parameters refer to the spatial distribution characteristic data such as the hot air temperature, flow rate, and uniformity inside the chamber collected by devices such as multi-point temperature sensors and anemometers during the drying process. The cumulative error amount refers to the cumulative value of the deviation between the instantaneous change rate (such as the frequency adjustment rate) and the temperature gradient attenuation rate within multiple regulation cycles, reflecting the total error caused by insufficient historical regulation accuracy.

[0125] In the embodiment of the present application, based on the real-time monitoring data of the updated proportional coefficient (such as step size 0.25 Hz / time, compensation threshold 0.3 s) and the spatio-temporal attenuation rate (such as 0.45 °C / s), the instantaneous deviation within each regulation cycle is calculated (such as when the frequency change rate is 0.5 Hz / s, the corresponding temperature attenuation is 0.45 °C / s, and the single deviation is 0.05 Hz·s / °C). The total error amount of the past 10 regulations is accumulated through a moving average algorithm (such as the cumulative error is 0.4 Hz·s / °C).

[0126] 402. Dynamically adjust the adaptation range of the preset threshold according to the cumulative error amount and the propagation path length of the maximum temperature gradient in the hot air distribution parameters;

[0127] In step 402, the cumulative error amount refers to the cumulative value of the deviation between the instantaneous change rate (such as the frequency adjustment rate) and the temperature gradient attenuation rate within multiple regulation cycles, reflecting the total error caused by insufficient historical regulation accuracy. The maximum temperature gradient refers to the maximum temperature difference value between different regions inside the drying chamber of the disinfection device at a certain moment (such as 130 °C in the left area, 122 °C in the right area, and the gradient is 8 °C), or the extreme value of the temperature change rate (such as a certain area heating up at a rate of 1 °C / s). It characterizes the severity of the non-uniformity of the thermal field and is the core parameter for determining the regulation priority. The preset threshold adaptation range refers to the allowable cumulative error boundary dynamically adjusted according to the propagation path length of the maximum temperature gradient (such as 2 meters) (such as the original threshold 0.5 Hz·s / °C is adjusted to 0.6 Hz·s / °C).

[0128] In the embodiment of the present application, according to the propagation path length of the maximum temperature gradient (such as 2 meters) and the thermal diffusion resistance coefficient (such as 0.8), a fuzzy logic control algorithm is used to dynamically adjust the preset threshold range (such as the original threshold 0.5 Hz·s / °C is relaxed to 0.65 Hz·s / °C) to meet the delay tolerance requirements of long-path thermal field regulation.

[0129] 403. When the cumulative error amount is lower than the adjusted preset threshold, perform multi-cycle fluctuation suppression verification on the instantaneous change rate based on the spatial propagation delay characteristic of the hot air distribution parameters and the attenuation trend of the cumulative error amount;

[0130] In step 403, the preset threshold refers to the maximum allowable cumulative error range, which is used to determine whether the proportional relationship converges. The spatial propagation delay characteristic refers to the time difference of the hot air diffusing from the outlet of the heating device to each area of the box body (for example, the left area is delayed by 0.3 seconds and the right area is delayed by 0.5 seconds). The multi-cycle fluctuation suppression verification refers to verifying whether the fluctuation of the instantaneous change rate converges within a continuous plurality of regulation cycles after the cumulative error is lower than the threshold, so as to avoid misjudgment caused by accidental errors.

[0131] In the embodiment of the present application, when the cumulative error amount drops to 0.55 Hz·s / ℃ (lower than the adjusted threshold of 0.65 Hz·s / ℃), based on the spatial propagation delay characteristic of the hot air distribution parameter (such as the right area is delayed by 0.6 seconds), the multi-cycle fluctuation suppression verification (such as standard deviation calculation) is performed on the instantaneous change rate of the subsequent 5 regulation cycles, and combined with the error attenuation trend prediction model (such as exponential smoothing method), it is verified whether the fluctuation converges stably (such as the standard deviation ≤ 0.02 Hz / s).

[0132] 404. After the multi-cycle fluctuation suppression verification passes, combine the long-term convergence trend slope of the cumulative error amount with the critical propagation rate of the spatio-temporal attenuation rate, trigger a global locking instruction, and output the adjusted proportional relationship.

[0133] In step 404, the long-term convergence trend slope refers to the attenuation rate of the cumulative error changing with time (such as decreasing by 0.1 Hz·s / ℃ per day). The critical propagation rate is the safety upper limit of the heat field diffusion rate (such as the temperature gradient attenuation rate shall not exceed 1℃ / s).

[0134] In the embodiment of the present application, if the multi-cycle fluctuation suppression verification passes (such as the fluctuation standard deviation ≤ 0.02 Hz / s within 5 cycles), further analyze whether the long-term convergence trend slope of the cumulative error amount (such as -0.08 Hz·s / ℃ / cycle) meets the critical propagation rate constraint (such as the attenuation rate ≤ 1℃ / s). When the long-term convergence trend slope is compatible with the critical propagation rate, trigger a global locking instruction to fix the proportional relationship (such as the step size is 0.25 Hz / time and the compensation threshold is 0.3 seconds).

[0135] The following is a specific example:

[0136] In a production line of a disinfection device, due to uneven hot air circulation in the left rear area of the drying oven, there are a maximum temperature gradient (12°C) and a long propagation path (2.5 meters). The system performs the following regulations: Based on the proportional coefficient (step size 0.28 Hz / time, compensation threshold 0.35 seconds) and the real-time decay rate (0.4°C / s), the cumulative error amount of 0.58 Hz·s / °C is calculated. According to the path length of 2.5 meters, the threshold is extended to 0.7 Hz·s / °C, and it is determined that 0.58 Hz·s / °C meets the conditions. The instantaneous change rate fluctuation (standard deviation 0.018 Hz / s) is verified for 5 consecutive cycles, and the error trend is predicted to converge. The analysis shows that the trend slope (-0.07 Hz·s / °C / cycle) is lower than the critical propagation rate (1°C / s), triggering global locking, and the proportional relationship (step size 0.28 Hz / time, compensation threshold 0.35 seconds) is output, and the temperature uniformity is restored to ±1.3°C within 20 seconds.

[0137] In summary, steps 401 to 404 achieve the global stability locking of the proportional relationship through the dynamic calculation of the cumulative error amount and the adjustment of the threshold adaptation range, combined with multi-cycle fluctuation suppression verification and long-term convergence trend analysis. This method improves the cumulative error control accuracy by more than 30%, expands the fault tolerance threshold of the long-path thermal field regulation, significantly increases the passing rate of multi-cycle verification, and at the same time avoids parameter drift through the global locking mechanism, making the temperature uniformity stably within ±1.5°C for a long time, and reducing the number of ineffective frequency adjustments caused by error accumulation, significantly enhancing the robustness and energy efficiency sustainability of the drying process of the disinfection device.

[0138] To solve the problem of insufficient accuracy in the dynamic correlation decision of the thermal field uniformity and the energy consumption efficiency, the solution constructs a joint optimization index through the coupled analysis of the temperature deviation propagation direction and the energy consumption fluctuation coefficient, dynamically corrects the weight ratio in combination with the historical energy consumption offset and the propagation delay characteristics, and performs multi-cycle iterative verification based on spatio-temporal consistency to achieve the precise correlation decision of the thermal field uniformity and the energy efficiency decay rate. In some embodiments, the dynamically correlating and analyzing the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in step 102 further includes:

[0139] 501. Extract the temperature deviation propagation direction and the energy consumption fluctuation coefficient based on the temperature deviation amount at each position point in the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device;

[0140] In step 501, the dynamic temperature field distribution data refers to the spatio-temporal distribution information of the temperature in each area inside the disinfection device during the drying process, which is collected in real time through a sensor array (such as an infrared thermal imager, a thermocouple), including parameters such as temperature values, temperature gradients (temperature difference per unit distance), and temperature change rates. The temperature deviation amount refers to the difference between the actual temperature and the target temperature (or the temperature of the adjacent area), and is used to characterize the degree of local overheating or under-drying. The temperature deviation propagation direction is the direction of the heat diffusion path from the abnormal temperature area (such as the high-temperature area) inside the box to the adjacent area (such as from the center to the edge). The energy consumption fluctuation coefficient refers to the degree of deviation of the real-time energy consumption of the heating device relative to the historical average value.

[0141] In the embodiment of the present application, the temperature data at each position point in the dynamic temperature field distribution data is collected through a temperature sensor array (such as 125°C in the left area and 118°C in the right area), the temperature deviation amount is calculated ( + 5°C in the left area and - 2°C in the right area), and the temperature deviation propagation direction (diffusing from the left area to the top) is determined by combining thermal imaging analysis. The real-time energy consumption data is collected synchronously (such as the current power of 92 kW), and the energy consumption fluctuation coefficient (15%) is calculated by comparing with the historical average value (80 kW).

[0142] 502. Perform a coupling analysis on the temperature deviation propagation direction and the energy consumption fluctuation coefficient to generate a joint optimization index for the decay rates of the uniform distribution of hot air and the energy consumption efficiency;

[0143] In step 502, the coupling analysis is a multi-source data joint modeling method, which uses statistical or machine learning algorithms (such as Granger causality test, neural network) to mine the correlation between the temperature field parameters (such as temperature gradient, flow rate) and the energy consumption data (such as power, thermal efficiency), and reveals the synergistic action mechanism of the thermal field uniformity and the energy consumption efficiency. The joint optimization index is a synergistic optimization objective function that quantifies the decay rate of the uniform distribution of hot air (such as the temperature gradient decreases by 0.3°C per second) and the decay rate of the energy consumption efficiency (such as the energy consumption efficiency decreases by 0.5% per second).

[0144] In the embodiment of the present application, the dynamic time warping algorithm is used to align the temperature deviation propagation direction and the energy consumption fluctuation coefficient, a coupling model of the decay rate of the uniform distribution of hot air (0.3°C / s) and the decay rate of the energy consumption efficiency (0.5% / s) is established, and a joint optimization index is generated (such as the weight ratio: the thermal field uniformity accounts for 60%, and the energy consumption efficiency accounts for 40%).

[0145] 503. Dynamically correct the weight ratio of the joint optimization index in combination with the mean offset of the historical energy consumption data and the propagation delay characteristics of the temperature gradient;

[0146] In step 503, the mean offset refers to the systematic deviation of historical energy consumption data relative to the long-term mean (e.g., the energy consumption has been continuously 8% higher in the past week). The propagation delay characteristic refers to the time difference of the diffusion of the temperature gradient from the heat source to the target area (e.g., a 0.7-second delay in the top area). Dynamic correction means adjusting control parameters (such as weight ratio, regulation threshold) based on real-time monitoring data and historical trends through adaptive algorithms (such as fuzzy logic control, rolling horizon optimization) to cope with changes in working conditions (such as material load fluctuations, environmental temperature and humidity disturbances).

[0147] In the embodiment of the present application, the combined optimization index weights are corrected according to the mean offset (+8%) of the historical energy consumption data and the propagation delay characteristic of the temperature gradient (the heat field weight is reduced to 55% and the energy consumption weight is increased to 45%). Combining the propagation delay characteristic (0.7 seconds) of the temperature gradient in the top area, the fuzzy logic algorithm is used to dynamically adjust the weight distribution ratio (such as 52% for the heat field weight and 48% for the energy consumption weight).

[0148] 504. Based on the spatio-temporal consistency of the temperature gradient propagation direction and the thermal inertia parameter, perform multi-period iterative verification on the corrected weight ratio, and output the dynamic correlation analysis result when the verification error is lower than the tolerance boundary of the combined optimization index.

[0149] In step 504, the thermal inertia parameter is the lag characteristic of the temperature change after the material absorbs heat (e.g., the material temperature rise needs to lag the heat supply by 3 seconds). Spatio-temporal consistency refers to the distribution uniformity and dynamic stability of the temperature field in the time dimension (such as the entire drying process) and the space dimension (such as each area of the box). It is comprehensively evaluated by indicators such as the standard deviation of the time series (e.g., the temperature fluctuation per hour ≤ 1.5°C) and the coefficient of variation of space (e.g., the temperature difference at each point ≤ 5%). The tolerance boundary is the maximum verification error range allowed by the combined optimization index (e.g., the temperature uniformity error ±1.5°C).

[0150] In the embodiment of the present application, based on the temperature gradient propagation direction and the thermal inertia parameter (3-second lag), perform iterative verification on the corrected weight ratio (52%:48%) for 5 regulation cycles. Predict the error trend through the Kalman filter. When the verification error (such as ±1.2°C) is lower than the tolerance boundary (±1.5°C) of the combined optimization index, output the dynamic correlation analysis result (the power in the left area needs to be reduced by 10%, and the wind speed at the top is increased by 20%).

[0151] The following is a specific example:

[0152] In a sterilization equipment production line, the temperature deviation (135°C in the center and 120°C in the edge) and abnormal energy consumption (power 110kW, historical average 95kW) in the center of the drying box were caused by material accumulation. The propagation direction of the temperature deviation (center to edge) was extracted, and the energy consumption fluctuation coefficient was calculated to be +15.8%. Then a joint optimization index was generated (thermal field weight 65%, energy consumption weight 35%). Combined with the historical energy consumption offset (+10%) and the edge area delay of 0.8 seconds, the weights were corrected to 58% for the thermal field and 42% for energy consumption. After three cycles of verification, the error dropped to ±1.3°C, and the control instructions were output (power reduction of 12% in the center area and frequency increase of 2Hz in the edge area). Within 15 seconds, the temperature uniformity was restored to ±1.4°C, and the energy consumption dropped to 98kW.

[0153] In summary, steps 501 to 504 achieve precise collaborative optimization of thermal field uniformity and energy efficiency by analyzing the coupling of temperature deviation propagation direction and energy consumption fluctuation coefficient, combining historical offset and propagation delay characteristics to dynamically correct weight ratios, and performing multi-cycle iterative verification based on thermal inertia parameters. This method reduces the temperature uniformity control error and energy consumption fluctuation coefficient, while improving energy efficiency utilization through dynamic weight allocation, significantly enhancing the multi-objective collaborative control capability and long-term operation stability of the drying process of disinfection equipment.

[0154] In order to solve the problem of uneven hot air distribution and energy efficiency attenuation being difficult to coordinately optimize, the solution generates a dynamic correction factor based on the historical energy consumption mean offset and the temperature gradient attenuation rate, combines the real-time change rate and thermal inertia parameters to perform multi-dimensional coupling correction on the weight ratio, and determines the final weight by matching the coordinated deviation attenuation trend with the stability boundary, thereby improving the adaptability and robustness of the joint optimization index. In some embodiments, the dynamic correction of the weight ratio of the joint optimization index by combining the mean offset of the historical energy consumption data and the propagation delay characteristics of the temperature gradient in step 503 also includes:

[0155] 601. Determine a dynamic correction factor of the decay rate of hot air uniform distribution and energy efficiency based on the fluctuation amplitude of the mean offset of the historical energy consumption data and the decay rate of the propagation delay characteristic of the temperature gradient;

[0156] In step 601, the mean shift refers to the absolute deviation of the historical energy consumption data sequence from its moving average. The fluctuation amplitude refers to the deviation of the mean energy consumption per unit time (such as per hour) relative to the long-term average value in the historical energy consumption data, which is calculated by the sliding window standard deviation to reflect the short-term fluctuation intensity of energy consumption. The temperature gradient propagation delay characteristic represents the hysteresis effect of the heat transfer speed in the temperature field attenuating with distance. The decay rate describes the degree to which the hysteresis effect weakens over time. The dynamic correction factor is an adjustment coefficient that comprehensively considers the relationship between thermal field uniformity and energy efficiency attenuation.

[0157] In the embodiment of the present application, first, a moving average algorithm is used to calculate the mean curve of the historical energy consumption data in the past 24 hours, and the fluctuation amplitude of the mean offset at each time point is obtained by point-by-point difference. At the same time, the time series analysis method is used to perform Fourier transform on the temperature gradient propagation data collected by the temperature sensor network, and the amplitude attenuation rate of the main frequency component is extracted. The two types of parameters are input into a multivariate regression model, and a coupling equation between the fluctuation amplitude and the attenuation rate is established through partial least squares regression, and finally a dynamic correction factor with time-varying characteristics is determined.

[0158] 602. Input the dynamic correction factor into the weight allocation mechanism of the joint optimization index, and combine the real-time change rate of the propagation direction of the temperature gradient and the thermal inertia parameters of the heating device to perform multi-dimensional coupling correction on the weight ratio of the attenuation rate of the uniform distribution of hot air and the energy consumption efficiency;

[0159] In step 602, the joint optimization index is a composite evaluation function of the thermal field uniformity and the energy consumption efficiency, and the weight allocation mechanism is constructed by using the fuzzy analytic hierarchy process. The real-time change rate of the propagation direction is obtained through temperature field vector analysis, and the thermal inertia parameters include physical properties such as the specific heat capacity and thermal conductivity of the heating device. Multi-dimensional coupling correction refers to the coordinated adjustment of the weight ratio from multiple dimensions such as spatial distribution, time change, and parameter correlation.

[0160] In the embodiment of the present application, the dynamic correction factor is input into a pre-trained weight allocation mechanism, which includes 3 hidden layers and an adaptive activation function. Combining the calculation result of the spatial derivative of the propagation direction of the temperature field gradient and the thermal inertia parameters obtained through material property tests, joint constraint conditions of the heat conduction equation and the energy flow equation are constructed in the weight allocation mechanism. The particle swarm optimization algorithm is used for multi-dimensional coupling correction, and finally the weight ratio divided by the spatial dimension is output.

[0161] 603. Based on the corrected weight ratio, calculate the collaborative deviation amount between the maximum temperature gradient in the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device. When the attenuation trend of the collaborative deviation amount matches the stability boundary of the thermal inertia parameters, determine the optimal weight ratio;

[0162] In step 603, the collaborative deviation amount is the comprehensive deviation degree between the maximum temperature gradient and the real-time energy consumption under the standardized dimension, and the stability boundary is the system safe operation threshold determined by the Lyapunov function. The thermal inertia parameter is a characteristic that characterizes the response of the heating device or the heated object to temperature changes, including physical properties such as specific heat capacity (the amount of heat required for a unit mass of substance to increase by 1 °C), thermal conductivity (heat transfer rate), and thermal diffusivity (temperature field change rate).

[0163] In the embodiments of the present application, based on the corrected weight ratio, the gradient modulus value of each grid point is calculated in the dynamic distribution data of the temperature field, and the maximum temperature gradient region is extracted through Gaussian filtering. After the real-time energy consumption data is processed by wavelet denoising, the covariance is calculated with the maximum gradient value. An exponential decay model of the collaborative deviation amount is constructed, and spectral matching is performed on the stability criterion matrix composed of its characteristic roots and the thermal inertia parameters. When the decay rate enters the convergence domain, the optimal weight ratio is locked.

[0164] 604. Feed back the optimal weight ratio to the dynamic mapping relationship mechanism of the joint optimization index, update the association logic of the thermal field energy consumption mapping in the heating device, and output a dynamic correction result.

[0165] In step 604, the dynamic mapping relationship mechanism is a knowledge graph that describes the non-linear association between thermal field parameters and energy consumption indicators. The update of the association logic is realized by an incremental learning method. The thermal field energy consumption mapping refers to the association relationship model between the distribution characteristics of the temperature field (thermal field) and the energy consumption of the heating device, and specifically shows the variation law of the energy consumption values corresponding to different temperature gradient distribution patterns.

[0166] In the embodiments of the present application, the determined optimal weight ratio is input into the dynamic mapping relationship mechanism constructed based on the graph database, and the association path of the thermal field energy consumption mapping is reconstructed through the node attribute update algorithm. The long short-term memory network is used to extract the features of the historical mapping relationship, and combined with the real-time collected thermal field energy consumption data stream, the edge weights of the knowledge graph are dynamically adjusted through the online learning mechanism, and finally a dynamic correction result including spatio-temporal characteristics is output.

[0167] The following is a specific example:

[0168] In a production line of a disinfection device, in response to the optimization requirement of the hot air distribution in the high-temperature sterilization chamber, the time-series energy consumption data and temperature field distribution records of 216 devices in the past 30 days were first collected. Through Hilbert-Huang transform, the natural oscillation period of the hot air circulation system was analyzed to be 8 minutes. Based on this, a moving average window was set, and the mean deviation fluctuation of each partition of the sterilization chamber was calculated to be within the range of ±12%. At the same time, it was found that the propagation delay attenuation coefficient of the temperature gradient from the air inlet to the discharge outlet was 0.35 / min. The dynamic correction factor matrix generated by combining the two showed that the adjustment intensity of the core area needed to be increased. Based on the thermal inertia parameters of the 316L stainless steel of the chamber body (thermal conductivity 16.3 W / m·K, specific heat capacity 500 J / kg·K), the weight distribution model adjusted the thermal uniformity weight from the initial 0.6 to 0.72. When it was monitored that the change in the loading density of a certain batch of products caused the change of the hot air flow direction, the model completed the spatial reallocation of the weight coefficients within 5 seconds. It was detected that the local temperature gradient at the discharge end exceeded the standard, and at this time, the real-time energy consumption increased by 15% compared with the reference value. Through collaborative deviation calculation, it was found that the deviation degree between the two reached the threshold, and the system automatically triggered the adjustment of the weight ratio, increasing the weight ratio of the temperature gradient by 18% to ensure the deviation convergence within the allowable range of the thermal inertia parameters (stability boundary). By updating the mapping relationship, it was identified that the correlation intensity between the fan speed and the power of the bottom heater needed to be increased by 22%. After implementation, the temperature uniformity of the sterilization chamber increased by 37%, and the fluctuation range of the energy consumption in the same period decreased by 29%, and it could automatically adapt to the production switch of different product specifications.

[0169] In summary, steps 601 to 604 achieved the collaborative optimization of the thermal field distribution and energy consumption efficiency by constructing a dynamic correction factor and a multi-dimensional weight adjustment mechanism. The spatio-temporal coupling analysis technology was used to form a closed-loop control between the temperature gradient propagation characteristics and the thermal inertia parameters of the equipment. Through actual application verification, on the premise of ensuring the uniformity of the thermal field, the attenuation rate of the system energy consumption efficiency was reduced, and it could dynamically adapt to the changes in production conditions, and the comprehensive energy efficiency of the equipment was greatly improved. By continuously optimizing the correlation model through the online learning mechanism, the system always maintained the best operating state, solving the problem of energy efficiency loss caused by static parameter settings in traditional methods.

[0170] To solve the problem that it is difficult to achieve a dynamic balance between the uniform distribution of hot air and energy consumption efficiency, the solution decomposes the hot air distribution parameters into orthogonal modal components and quantifies the energy proportion, constructs an asymmetric mapping relationship by combining the historical energy consumption eigenvectors, defines the double-objective optimization boundary through the sensitivity coefficient and the spatial variation index, and iteratively corrects the modal weights to achieve Pareto optimality, solving the problem of generating multi-objective collaborative parameters for thermal field uniformity and energy efficiency. In some embodiments, the step of constructing the collaborative optimization target parameters for the uniform distribution of hot air and energy consumption efficiency based on the hot air distribution parameters and historical energy consumption data in step 101 further includes:

[0171] 701. Decompose the hot air distribution parameters into multiple orthogonal modal components in the spatial dimension, and calculate the energy proportion coefficient and the spatial variation index of the orthogonal modal components;

[0172] In step 701, the orthogonal modal components are obtained by performing proper orthogonal decomposition on the hot air distribution parameters to decompose them into independent spatial patterns. Each mode represents the characteristics of the thermal field distribution in a specific direction or region. The energy proportion coefficient refers to the contribution ratio of each modal component to the total energy, reflecting its dominance in the overall thermal field distribution. The spatial variation index is used to describe the fluctuation intensity of the modal component in the spatial dimension, and is calculated as the ratio of the standard deviation to the mean.

[0173] In the embodiments of the present application, the proper orthogonal decomposition algorithm is used to process the hot air distribution parameters collected by the temperature sensor network, and the first N orthogonal modal components are extracted (N is determined according to the cumulative energy proportion exceeding the set threshold). The square of the amplitude of each orthogonal modal component is normalized to obtain the energy proportion coefficient of each orthogonal modal component. The thermal field region is divided into grid cells, and the difference between the maximum and minimum values of each orthogonal modal component in each grid is calculated, and then divided by the mean of the orthogonal modal component to obtain the spatial variation index. Finally, the energy ranking of each mode and the results of the spatial heterogeneity analysis are output.

[0174] 702. Construct a multi-dimensional decomposition model of the historical energy consumption data, extract the eigenvectors dynamically associated with the temperature field during different operation cycles of the heating device, and calculate the stability index of the eigenvectors;

[0175] In step 702, the multi-dimensional decomposition model is a mathematical model that decomposes the historical energy consumption data according to dimensions such as time, load, and ambient temperature. The eigenvectors are the key parameter combinations that reflect the relationship between the operating state of the heating device and the temperature field, such as the heating power fluctuation frequency, the fan speed gradient, etc. The stability index refers to the fluctuation amplitude of the eigenvector during consecutive operation cycles, and is comprehensively calculated through variance and autocorrelation coefficient.

[0176] In the embodiments of the present application, time-frequency analysis technology is used for the historical energy consumption data, and the eigenvectors dynamically associated with the temperature field during different operation cycles of the heating device are decomposed multi-dimensionally to construct a 16-dimensional eigenvector set. The variance and autocorrelation coefficient of each eigenvector are calculated, and a stability index score is generated through weighted fusion. Principal component analysis is used to screen the core eigenvectors that are highly sensitive to the changes in the temperature field, and an energy consumption-thermal field correlation model is established.

[0177] 703. Establish an asymmetric mapping relationship between the energy proportion coefficient and the stability index, and determine the sensitivity coefficient of the uniform hot air distribution to the energy consumption efficiency;

[0178] In step 703, the energy proportion coefficient refers to the proportion of the energy contained in each orthogonal modal component in the total energy of the thermal field, reflecting the contribution weight of this component to the overall thermal field distribution. The asymmetric mapping relationship is the correlation characteristic with directional differences between the change in thermal field uniformity and the change in energy consumption efficiency. The sensitivity coefficient is the degree coefficient reflecting the change in energy consumption efficiency caused by a unit change in the thermal field uniformity.

[0179] In the embodiments of this application, the grey relational analysis method is used to calculate the asymmetric mapping relationship between the energy proportion coefficients of each mode and the eigenvector stability index. By piecewise regression fitting of the curve of energy proportion and stability index, the sensitivity coefficients in different intervals are calculated. High-sensitivity modes (such as the second mode corresponding to the upper air supply area) are identified, and their regulation priorities for energy consumption efficiency are determined.

[0180] 704. Construct a collaborative optimization function based on the spatial variation index and the sensitivity coefficient, and use the dynamic change range of the eigenvector as a constraint condition to generate a two-objective optimization boundary;

[0181] In step 704, the spatial variation index describes the degree of fluctuation of the modal component in the spatial dimension, and is calculated by the ratio of the difference (range) between the local maximum value and the minimum value to the mean value of this mode. The collaborative optimization function is a mathematical expression with the dual objectives of reducing the spatial variation index and increasing the sensitivity coefficient. The two-objective optimization boundary refers to the feasible solution region defined by the allowable fluctuation range of the eigenvector.

[0182] In the embodiments of this application, constructing the collaborative optimization function is to minimize the sum of the spatial variation indices and maximize the sum of the sensitivity coefficients. Then, the constraint conditions are set that the variance of the eigenvector does not exceed a set proportion of the historical extreme value, and the autocorrelation coefficient is not lower than the critical value. Finally, a constraint optimization algorithm is used to generate a two-objective optimization boundary containing feasible solutions.

[0183] 705. By iteratively correcting the weight allocation of the orthogonal modal components, make the collaborative optimization function satisfy the Pareto optimal condition within the two-objective optimization boundary, and generate the collaborative optimization target parameters of uniform hot air distribution and energy consumption efficiency.

[0184] In step 705, iterative correction is an optimization process of gradually approaching the optimal solution by repeatedly adjusting the weight parameters in multiple cycles. The orthogonal modal component refers to decomposing the thermal field distribution parameters into multiple mutually independent spatial mode components through a mathematical decomposition method (such as proper orthogonal decomposition), and each component represents the thermal field distribution characteristics of a specific region or direction. The Pareto optimal condition refers to the set of optimal solutions within the two-objective optimization boundary where neither objective can be further optimized without harming the other objective.

[0185] In the embodiments of this application, a multi-objective evolutionary algorithm is applied to iteratively optimize the weight allocation of orthogonal modal components and dynamically adjust the search direction. A non-dominated solution set that simultaneously meets the improvement of hot air uniform distribution and energy consumption efficiency is screened within the double-objective optimization boundary. The optimal collaborative optimization target parameters are selected based on a comprehensive scoring model to balance the thermal field performance and energy efficiency requirements.

[0186] The following is a specific example:

[0187] In the optimization of the high-temperature sterilization chamber on a certain disinfection equipment production line: First, 6 orthogonal modes are decomposed. Among them, the energy proportion of the second mode (bottom hot air reflux) reaches 35%, but the spatial variation index is as high as 1.2, indicating that the distribution in this area is extremely unstable. The eigenvector extracted from the energy consumption data shows that the correlation coefficient between the fan frequency conversion period and the bottom temperature fluctuation is 0.91, and the variance exceeds the limit to trigger a constraint alarm. The sensitivity coefficient of the second mode is 0.65, indicating that improving the bottom uniformity has a significant impact on the energy consumption efficiency. The fluctuation of the fan speed is limited by the optimization boundary to be <±15%, and the heating power adjustment interval is >30 seconds. Finally, after 5 rounds of iterative optimization, the selected weight allocation scheme reduces the temperature standard deviation of the bottom area from 4.3 °C to 2.8 °C, and the energy consumption per batch of sterilization decreases during the same period.

[0188] In summary, steps 701 to 705 achieve precise collaborative control of the thermal field distribution and energy consumption efficiency through the deep integration of modal decomposition and multi-objective optimization. In the disinfection equipment production line, the system can automatically identify high-sensitivity areas and dynamically adjust the operating parameters, improving the temperature uniformity while reducing the energy consumption fluctuation. The use of an asymmetric mapping relationship and a Pareto optimal solution screening mechanism effectively avoids the local overshoot problem caused by traditional single-objective optimization. Through the dual guarantee of constraint conditions and stability indicators, the reliable operation of the equipment under complex working conditions is ensured, and the comprehensive energy efficiency ratio is improved, providing an innovative solution for high-precision thermal field control.

[0189] Figure 2 FIG. is a schematic structural diagram of a quality control system for the production and processing of disinfection equipment based on intelligent analysis provided by the embodiments of this application. As Figure 2 shown, the system includes:

[0190] An acquisition module 21, which acquires the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection equipment, synchronously collects the historical energy consumption data of the heating device, and constructs collaborative optimization target parameters for hot air uniform distribution and energy consumption efficiency based on the hot air distribution parameters and historical energy consumption data;

[0191] An analysis module 22, which obtains the dynamic distribution data of the temperature field during the heating operation of the disinfection equipment according to the collaborative optimization target parameters, and performs dynamic correlation analysis on the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection equipment to obtain the result of the dynamic correlation analysis;

[0192] The generation module 23 generates a heating power adjustment instruction based on the result of the dynamic association analysis, and converts it into a control signal for the power supply frequency by utilizing the synergistic effect of differential control and frequency conversion adjustment according to the heating power adjustment instruction.

[0193] Figure 2 The described quality control system for the production and processing of disinfection equipment based on intelligent analysis can execute Figure 1 The described quality control method for the production and processing of disinfection equipment based on intelligent analysis in the illustrated embodiment, its implementation principle and technical effects will not be elaborated further. For the quality control system for the production and processing of disinfection equipment based on intelligent analysis in the above-mentioned embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated in detail here.

[0194] In a possible design, Figure 2 The quality control system for the production and processing of disinfection equipment based on intelligent analysis in the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device can include a storage component 31 and a processing component 32;

[0195] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0196] The processing component 32 is used for the above Figure 1 The quality control method for the production and processing of disinfection equipment based on intelligent analysis in the illustrated embodiment.

[0197] Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0198] The storage component 31 is configured to store various types of data to support operations on the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0199] Of course, the computing device must also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0200] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device, an input device, etc.

[0201] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0202] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server, and the above-mentioned processing component, storage component, etc. can be basic server resources rented or purchased from a cloud computing platform.

[0203] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 A quality control method for the production and processing of disinfection equipment based on intelligent analysis shown in the above-mentioned embodiments.

[0204] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0205] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0206] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0207] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A quality control method for the production and processing of disinfection equipment based on intelligent analysis, characterized in that, Including: Obtain the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection equipment, and synchronously collect the historical energy consumption data of the heating device. Based on the hot air distribution parameters and the historical energy consumption data, construct the collaborative optimization target parameters of hot air uniform distribution and energy consumption efficiency; According to the collaborative optimization target parameters, obtain the dynamic distribution data of the temperature field during the heating operation of the disinfection equipment, and perform dynamic correlation analysis on the dynamic distribution data of the temperature field and the real-time energy consumption data of the heating device in the disinfection equipment to obtain the result of the dynamic correlation analysis; Generate a heating power adjustment instruction based on the result of the dynamic correlation analysis, and use the synergistic effect of differential control and frequency conversion adjustment to convert the heating power adjustment instruction into a control signal for the power supply frequency.

2. The method according to claim 1, wherein The using the synergistic effect of differential control and frequency conversion adjustment to convert the heating power adjustment instruction into a control signal for the power supply frequency includes: Perform differential control processing on the heating power adjustment instruction, and extract the attenuation coefficient of the high-frequency fluctuation component and the compensation amount of the cumulative deviation in the heating power to generate an intermediate adjustment signal; Calculate the reference offset of the power supply frequency based on the intermediate adjustment signal and the frequency-power response curve of the heating device; Input the reference offset into the dynamic weight distribution mechanism of frequency conversion adjustment, and combine the spatial propagation delay characteristics of the hot air distribution parameters to generate a frequency adjustment step size and a phase compensation threshold; Adjust the proportional relationship between the frequency adjustment step size and the phase compensation threshold to make the instantaneous change rate of the power supply frequency match the spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, and output the control signal for the power supply frequency.

3. The method according to claim 2, wherein The adjusting the proportional relationship between the frequency adjustment step size and the phase compensation threshold includes: Based on the propagation direction and spatio-temporal attenuation rate of the temperature gradient in the hot air distribution parameters, establish a dynamic mapping relationship between the instantaneous change rate of the power supply frequency and the spatio-temporal attenuation rate of the temperature gradient to extract the initial proportional coefficient of the frequency adjustment step size and the phase compensation threshold; Determine the dynamic adjustment factor of the initial proportional coefficient according to the real-time deviation amount between the instantaneous change rate and the spatio-temporal attenuation rate in the dynamic mapping relationship; Input the dynamic adjustment factor and the initial proportional coefficient into the dynamic weight distribution mechanism, and combine the propagation path length of the maximum temperature gradient in the hot air distribution parameters to perform multi-dimensional weighted fusion on the proportional relationship between the frequency adjustment step size and the phase compensation threshold to generate an updated proportional coefficient; Based on the updated proportional coefficient, perform iterative approximation on the instantaneous change rate. When the cumulative error between the instantaneous change rate and the spatio-temporal attenuation rate is lower than the preset threshold, obtain the adjusted proportional relationship.

4. The method according to claim 3, wherein The when the cumulative error between the instantaneous change rate and the spatio-temporal attenuation rate is lower than the preset threshold, obtaining the adjusted proportional relationship includes: Calculate the cumulative error amount of the instantaneous change rate based on the updated proportional coefficient and the real-time monitoring data of the spatio-temporal attenuation rate in the hot air distribution parameters; Dynamically adjust the adaptation range of the preset threshold according to the cumulative error amount and the propagation path length of the maximum temperature gradient in the hot air distribution parameters. When the cumulative error amount is lower than the adjusted preset threshold, based on the spatial propagation delay characteristic of the hot air distribution parameter and the decay trend of the cumulative error amount, perform multi-cycle fluctuation suppression verification on the instantaneous change rate; After the multi-cycle fluctuation suppression verification passes, combine the long-term convergence trend slope of the cumulative error amount and the critical propagation rate of the spatio-temporal decay rate to trigger a global locking instruction and output an adjusted proportional relationship.

5. The method according to claim 1, characterized in that, The dynamically associating and analyzing the temperature field dynamic distribution data with the real-time energy consumption data of the heating device includes: Based on the temperature deviation amount at each position point in the temperature field dynamic distribution data and the real-time energy consumption data of the heating device, extract the temperature deviation propagation direction and the energy consumption fluctuation coefficient; Perform coupling analysis on the temperature deviation propagation direction and the energy consumption fluctuation coefficient to generate a joint optimization index for the decay rate of hot air uniform distribution and energy consumption efficiency; Combine the mean offset of historical energy consumption data and the propagation delay characteristic of the temperature gradient to dynamically correct the weight ratio of the joint optimization index; Based on the spatio-temporal consistency of the temperature gradient propagation direction and the thermal inertia parameter, perform multi-cycle iterative verification on the corrected weight ratio, and output the dynamic association analysis result when the verification error is lower than the tolerance boundary of the joint optimization index.

6. The method according to claim 5, wherein The combining the mean offset of historical energy consumption data and the propagation delay characteristic of the temperature gradient to dynamically correct the weight ratio of the joint optimization index includes: Based on the fluctuation amplitude of the mean offset of the historical energy consumption data and the decay rate of the propagation delay characteristic of the temperature gradient, determine the dynamic correction factor for the decay rate of hot air uniform distribution and energy consumption efficiency; Input the dynamic correction factor into the weight allocation mechanism of the joint optimization index, and combine the real-time change rate of the temperature gradient propagation direction and the thermal inertia parameter of the heating device to perform multi-dimensional coupling correction on the weight ratio of the decay rate of hot air uniform distribution and energy consumption efficiency; Based on the corrected weight ratio, calculate the co-deviation amount between the maximum temperature gradient in the temperature field dynamic distribution data and the real-time energy consumption data of the heating device. When the decay trend of the co-deviation amount matches the stability boundary of the thermal inertia parameter, determine the optimal weight ratio; Feed back the optimal weight ratio to the dynamic mapping relationship mechanism of the joint optimization index, update the correlation logic of the thermal field energy consumption mapping in the heating device and output the dynamic correction result.

7. The method according to claim 1, characterized in that, The constructing the collaborative optimization target parameter for hot air uniform distribution and energy consumption efficiency based on the hot air distribution parameter and historical energy consumption data includes: Decompose the hot air distribution parameter into multiple orthogonal mode components in the spatial dimension, and calculate the energy occupancy ratio coefficient and the spatial variation index of the orthogonal mode components; Construct a multi-dimensional decomposition model of the historical energy consumption data, extract the eigenvectors dynamically associated with the temperature field during different operation cycles of the heating device, and calculate the stability index of the eigenvectors; Establish an asymmetric mapping relationship between the energy occupancy ratio coefficient and the stability index, and determine the sensitivity coefficient of hot air uniform distribution to energy consumption efficiency; Construct a collaborative optimization function based on the spatial variation index and the sensitivity coefficient, and use the dynamic change range of the eigenvector as a constraint condition to generate a two-objective optimization boundary; By iteratively correcting the weight allocation of the orthogonal mode components, the collaborative optimization function obtains the Pareto optimal conditions within the two-objective optimization boundary, and generates the collaborative optimization target parameters for the uniform distribution of hot air and the energy consumption efficiency.

8. A quality control method for the production and processing of disinfection equipment based on intelligent analysis, characterized in that, It includes: An acquisition module, which acquires the hot air distribution parameters corresponding to the drying technology in the production process of the disinfection equipment, synchronously collects the historical energy consumption data of the heating device, and constructs the collaborative optimization target parameters for the uniform distribution of hot air and the energy consumption efficiency based on the hot air distribution parameters and the historical energy consumption data; An analysis module, according to the collaborative optimization target parameters, obtains the dynamic distribution data of the temperature field during the heating operation of the disinfection equipment, and dynamically correlates and analyzes the dynamic distribution data of the temperature field with the real-time energy consumption data of the heating device in the disinfection equipment to obtain the result of the dynamic correlation analysis; A generation module, which generates a heating power adjustment instruction based on the result of the dynamic correlation analysis, and converts the heating power adjustment instruction into a regulation signal of the power supply frequency by using the synergistic effect of differential control and frequency conversion regulation.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for controlling the production and processing quality of a disinfection equipment based on intelligent analysis as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, There is a computer program stored, and when the computer program is executed by the computer, it implements a method for controlling the production and processing quality of a disinfection equipment based on intelligent analysis as described in any one of claims 1 to 7.

Images