Energy-saving control method for precise start of heating equipment and related device

Abstract

This application provides an energy-saving control method and related equipment for precise start-up of heating equipment, belonging to the field of equipment automation control technology. The method includes collecting current equipment operating data and desired parameter values; the current equipment operating data includes the current equipment temperature value, and the desired parameter values ​​include the desired temperature value; predicting the heating time based on the current equipment operating data and desired parameter values ​​to obtain the equipment heating duration, then calculating the equipment start-up time based on the heating duration, and then executing a branch logic method based on the waiting time from the current time to the equipment start-up time. Specifically, if the waiting time is less than the desired time, prepare to start the heating equipment according to the equipment start-up time; if the waiting time is greater than or equal to the desired time, repeat the above steps. This application can improve the accuracy of preheating start-up time prediction, ensuring that the temperature preheating completion time is earlier than and closer to the workpiece entering the furnace, balancing heating effect and energy consumption.

Description

Technical Field

[0001] This application relates to the field of equipment automation control technology, and in particular to an energy-saving control method and related equipment for precise start-up of heating equipment. Background Technology

[0002] In the painting process of large manufacturing industries such as automobiles, the curing and forming of the coating on the surface of the workpiece depends on heating equipment such as coating drying ovens, which consume energy such as electricity and gas to generate high-temperature hot air to bake the workpiece and make it meet the process quality requirements.

[0003] In typical production processes, heating equipment such as coating drying ovens needs to be preheated in advance to ensure that the oven temperature has stabilized and reached the process set value before the workpieces are placed inside. If the start-up timing is delayed, baking will begin before the oven temperature reaches the process requirements, leading to poor coating curing and directly scrapping the workpieces. If the start-up timing is too early, the equipment will run at high temperatures for an extended period without any workpieces inside, resulting in idling. This not only significantly increases energy consumption but also accelerates equipment aging and increases maintenance costs. Therefore, under the premise of ensuring stable production rhythm and achieving product coating quality standards, accurately controlling the start-up time of the drying oven, shortening idling time, and reducing energy consumption are the core requirements for energy saving and efficiency improvement in the coating process. The core objective is to preheat at an appropriate start-up time, so that the oven temperature is preheated earlier than the time the workpieces are placed inside, and the two are as close as possible, minimizing idling time while meeting process requirements.

[0004] In existing technologies, energy-saving control schemes for precise start-up of drying ovens mainly fall into the following two categories: (1) Fixed threshold control: The maximum time spent in the heating process of the drying oven in the past production is used as the fixed preheating reserve time. Preheating is started based on the preset unified start time. After the heating is completed, the workpiece is waited to enter the oven.

[0005] (2) Linear predictive control: Based on the historical production data of the drying furnace, including the initial temperature and heating time before the drying furnace starts, the average heating rate is calculated. Then, based on the linear model of the current initial temperature and average heating rate, the heating time can be calculated, thereby reverse-engineering the preheating start time.

[0006] While the above solutions can shorten the idling time of the drying oven to some extent, none of them take into account the impact of the real-time operating conditions of the equipment on the heating time, resulting in inaccurate prediction of the preheating start time and making it difficult to meet the high-precision and highly adaptable requirements for accurate preheating. Summary of the Invention

[0007] The main objective of this application is to propose an energy-saving control method and related equipment for precise start-up of heating equipment, aiming to improve the accuracy of preheating start-up timing prediction, so that the temperature completes preheating earlier than and close to the workpiece entering the furnace, thus balancing workpiece heating effect and energy consumption.

[0008] To achieve the above objectives, one aspect of this application proposes an energy-saving control method for precise start-up of a heating device, comprising the following steps: Collect current equipment operating condition data and desired parameter values; the current equipment operating condition data includes the current equipment temperature value, and the desired parameter values ​​include the desired temperature value; Based on the current equipment operating data and the expected parameter values, the heating time is predicted to obtain the equipment heating duration, and then the equipment start-up time is calculated based on the equipment heating duration. The branch logic method is executed based on the waiting time from the current time to the device's power-on time. The branch logic method is as follows: If the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; If the waiting time is greater than or equal to the expected time, repeat the step of collecting the current equipment operating data and the expected parameter value to execute the branch logic method according to the waiting time.

[0009] In some embodiments, the step of predicting the heating time based on the current equipment operating condition data and the expected parameter value to obtain the equipment heating duration includes the following steps: The current equipment operating condition data and the expected parameter values ​​are input into the heating time prediction model obtained based on machine learning training to obtain the equipment heating time.

[0010] In some embodiments, the heating time prediction model is trained and updated through the following steps: A training dataset is constructed based on the historical data of the heating equipment. The training dataset includes multiple training samples, each of which includes an initial equipment temperature, a desired parameter value, and a heating time label. Each training sample also carries the corresponding actual start-up time. The training samples are weighted according to the actual power-on time to determine the training weight of each training sample; The heating time prediction model based on the extreme gradient boosting algorithm is trained according to the training dataset and the training weights of the training samples to update the parameters of the heating time prediction model.

[0011] In some embodiments, the step of assigning weights to the training samples based on the actual power-on time to determine the training weights of each training sample includes the following steps: Calculate the first time interval between the actual power-on time and the model training time; The training samples are weighted according to the first time interval to determine the training weight of each training sample; wherein the first time interval is inversely proportional to the training weight.

[0012] In some embodiments, the step of repeatedly executing the method of collecting current device operating data and expected parameter values ​​until the branch logic method is executed according to the waiting time when the waiting time is greater than or equal to the expected time includes the following steps: If the waiting time is greater than or equal to the expected time, the future refresh time is determined based on the waiting time. When the future refresh time is reached, the step of collecting the current device operating data and expected parameter values ​​is executed to execute the branch logic method according to the waiting time.

[0013] In some embodiments, determining the future refresh time based on the waiting time includes the following steps: A corresponding second time interval is determined based on the numerical range of the waiting time; wherein, the larger the numerical range, the longer the second time interval. The future refresh time is determined based on the second time interval and the current time.

[0014] To achieve the above objectives, another aspect of this application proposes an energy-saving control system for precise start-up of heating equipment, comprising: The first module is used to collect current equipment operating condition data and expected parameter values; the current equipment operating condition data includes the current equipment temperature value, and the expected parameter values ​​include the expected temperature value. The second module is used to predict the heating time based on the current equipment operating data and the expected parameter value, obtain the equipment heating time, and then calculate the equipment start-up time based on the equipment heating time. The third module is used to execute a branch logic method based on the waiting time from the current time to the device's power-on time. The branch logic method is as follows: If the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; If the waiting time is greater than or equal to the expected time, the first module to the third module are run repeatedly.

[0015] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0016] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0017] The embodiments of this application include at least the following beneficial effects: This application provides an energy-saving control method, system, electronic device, storage medium, and program product for precise start-up of heating equipment. This solution collects current equipment operating condition data and expected parameter values. The current equipment operating condition data includes the current equipment temperature value, and the expected parameter values ​​include the expected temperature value. Based on the current equipment operating condition data and the expected parameter values, the heating time is predicted to obtain the equipment heating duration. Then, the equipment start-up time is calculated based on the equipment heating duration. Then, a branch logic method is executed based on the waiting time from the current time to the equipment start-up time. Specifically, if the waiting time is less than the expected time, the heating equipment is prepared to start up based on the equipment start-up time. If the waiting time is greater than or equal to the expected time, the above steps are repeated to continuously refresh the equipment start-up time based on the latest equipment operating condition data. Through a simple algorithm combined with a rolling refresh mechanism, a heating time prediction value that considers the real-time operating condition of the equipment can be obtained, thereby improving the accuracy of the preheating start-up time prediction. This ensures that the temperature preheating completion time is earlier than and close to the workpiece entering the furnace, taking into account both the workpiece heating effect and energy consumption. Attached Figure Description

[0018] Figure 1 This is a flowchart of the energy-saving control method for precise start-up of heating equipment provided in the embodiments of this application; Figure 2 The hardware structure diagram of the electronic device provided in the embodiments of this application is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] While related technologies can shorten the idle running time of drying ovens to some extent, they all suffer from common technical defects that prevent them from achieving the core goal of "precise start-up of drying ovens" and make it difficult to meet the dual requirements of high efficiency, energy saving, and stable production in the coating process. Specifically: 1. Insufficient accuracy in startup prediction; only a rough startup prediction can be achieved: The heating process of a drying oven is influenced by a combination of factors, including the oven structure, ambient temperature and humidity, production scheduling, heat transfer efficiency, burner heating power, and airflow distribution within the oven, exhibiting complex nonlinear dynamic characteristics. Currently, all existing energy-saving control methods employ a predictive approach based on "static presets" or "simplified assumptions," prioritizing that "the heating completion time must be earlier than the workpiece entry time," and secondarily satisfying that "the heating completion time is as close as possible to the workpiece entry time." Furthermore, to avoid potential process quality issues such as poor coating curing due to prediction deviations, operators often allow for a long buffer period to compensate for prediction errors, resulting in the heating completion time being even earlier than the workpiece entry time.

[0022] Table 1

[0023] Therefore, as shown in Table 1, although the current energy-saving control methods for heating equipment can reduce the idle running time of drying furnaces to varying degrees, they are limited by the fact that their core prediction methods are generally "rough and conservative estimates", and cannot achieve truly precise start-up. It is difficult to achieve the core control objective of "the time of temperature rise completion is earlier than and as close as possible to the time of workpiece entry into the furnace", and there is still a significant energy waste problem.

[0024] 2. High reliance on human intervention and poor adaptability of prediction algorithms: The relevant control schemes are essentially "generalizing from a few examples," that is, inferring all operating conditions from a few typical operating conditions and setting linear models and parameters. Their control parameters are all preset based on manual analysis of historical temperature rise data, ignoring the impact of real-time dynamic fluctuations in the operating conditions of the heating equipment on the prediction of start-up time.

[0025] In summary, the prediction of the preheating start-up time in the relevant technologies is inaccurate, making it difficult to simultaneously meet the dual requirements of high efficiency and energy saving in the coating process and stable production.

[0026] In view of this, this application provides an energy-saving control method and related equipment for precise start-up of heating equipment. This solution, through a simple algorithm and a rolling refresh mechanism for the start-up time of the equipment, can obtain a predicted value of the heating time that takes into account the real-time working conditions of the equipment, thereby improving the accuracy of the prediction of the preheating start-up time. This ensures that the temperature completes preheating earlier than and close to the time when the workpiece enters the furnace, taking into account both the workpiece heating effect and energy consumption.

[0027] The energy-saving control method for precise start-up of heating equipment provided in this application relates to the field of equipment automation control technology. This energy-saving control method for precise start-up of heating equipment can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the energy-saving control method for precise start-up of heating equipment, but is not limited to the above forms.

[0028] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0029] Figure 1 This is an optional flowchart of the energy-saving control method for precise start-up of heating equipment provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S103.

[0030] S101, collect current equipment operating condition data and expected parameter values; current equipment operating condition data includes current equipment temperature value, and expected parameter values ​​include expected temperature value; S102, predict the heating time based on the current equipment operating data and expected parameter values, obtain the equipment heating time, and then calculate the equipment start-up time based on the equipment heating time. S103, Execute the branch logic method based on the waiting time from the current moment to the device power-on time. The branch logic method is as follows: S103a, if the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; S103b, if the waiting time is greater than or equal to the expected time, repeat steps S101 to S103.

[0031] Steps S101 to S103 as shown in the embodiments of this application, through the above-mentioned simple startup analysis algorithm and combined with the rolling refresh mechanism, can obtain a predicted value of the heating time considering the real-time working conditions of the equipment, thereby improving the accuracy of the preheating start-up time prediction, so that the temperature completion time is earlier than and close to the workpiece entering the furnace, taking into account both the workpiece heating effect and energy consumption.

[0032] In step S101 of some embodiments, current equipment operating condition data is collected at a fixed sampling period (e.g., once / second). The current equipment operating condition data includes at least the current equipment temperature value (e.g., the furnace temperature of a coating drying oven), and may further include the current ambient temperature, furnace wind speed, etc. Expected parameter values ​​can be set in real time according to actual production conditions. Expected parameter values ​​include at least the expected temperature value when heating is complete (i.e., the workpiece enters the equipment) (i.e., the furnace temperature value set according to production process requirements), and may further include the expected time of heating completion (i.e., the time when the workpiece enters the furnace).

[0033] In step S102 of some embodiments, the heating time is predicted based on the current equipment operating data and the expected parameter values ​​to obtain the equipment heating time Δt (i.e., the equipment heating time). The heating time prediction method in this embodiment can be based on machine learning or deep learning, or it can be determined based on the calibrated heating characteristics of the equipment. This application embodiment does not impose specific limitations. The equipment start-up time is calculated based on the equipment heating time. Specifically, based on the time conservation relationship of the heating process, the expected heating completion time is subtracted from the equipment heating time to obtain the equipment start-up time.

[0034] In step S103 of some embodiments, a branch logic method is executed based on the waiting time from the current time to the device power-on time. The branch logic method is as follows: S103a, if the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; S103b, if the waiting time is greater than or equal to the expected time, repeat steps S101 to S103.

[0035] In this embodiment, the waiting time is determined by subtracting the current time from the equipment startup time. Then, the waiting time is compared with the expected time. If the waiting time is greater than or equal to the expected time, it means that the startup time is still far away, and the equipment condition may change significantly later, resulting in an inaccurate predicted startup time. In this case, steps S101 to S103 are re-executed. When re-executing steps S101 to S103, the latest obtained current equipment condition data and expected parameter values ​​are used to achieve dynamic updates of the equipment startup time. If the waiting time is less than the expected time, the startup critical range has been entered. At this time, the current equipment startup time is locked, rolling prediction is no longer performed, and the execution phase begins. That is, the startup control of the heating equipment is prepared according to the equipment startup time, so that the drying oven equipment starts up in time according to the equipment startup time and enters the heating process. It is understood that the expected duration in the embodiments of this application refers to the predicted locking window duration preset by the system. This value can be set based on comprehensive considerations such as natural cooling rate and start-up execution. For example, under normal circumstances, the natural cooling rate of a drying oven is <1℃ / 5 minutes, and 5 minutes is sufficient to execute the start-up, so it can be set to 5 minutes.

[0036] Traditional drying oven start-up control generally employs a one-time static prediction method, which results in a significant time misalignment between the prediction and actual execution. That is, the system performs a prediction only once at a specific point in time, using the oven temperature data at the prediction execution time (e.g., 5 hours in advance) as the prediction input to calculate a fixed start-up time. However, there is a time interval of several hours or even tens of hours between the prediction execution and the actual start-up. During this period, the actual state of the drying oven will inevitably undergo dynamic changes, including but not limited to: Natural furnace temperature decay: Affected by factors such as ambient temperature and humidity, seasonal changes, etc., the furnace temperature will slowly decrease over time. Therefore, the actual furnace temperature at startup is significantly lower than the predicted input value, resulting in the actual heating time being much longer than the predicted time.

[0037] Temporary furnace temperature fluctuations: Due to special equipment debugging requirements, temporary ignition debugging may occur before startup, which may lead to a short-term increase in furnace temperature. These subsequent changes cannot be detected by a one-time prediction.

[0038] Production plan fine-tuning: The workpiece launch time may be adjusted by ±10-30 minutes due to fluctuations in the previous process, and a one-time forecast cannot be updated synchronously.

[0039] Because the time-consuming prediction process considers past state data, rather than the actual state data at startup (or close to startup), even the most accurate prediction algorithm will have systematic biases in its prediction results. To avoid production disruptions due to temperature lag, many related technologies adopt a conservative strategy of starting up the equipment earlier than the estimated startup time, resulting in significant energy waste.

[0040] The embodiments of this application employ a two-layer control mechanism of rolling refresh re-prediction and prediction locking, ensuring that the prediction results are always based on the latest actual operating conditions. Specifically: Rolling refresh re-prediction refers to the system continuously collecting the latest current equipment operating condition data and expected parameter values ​​representing the production plan at a fixed sampling period (e.g., once / second), and predicting the lock window duration. When the time remaining until the currently calculated equipment startup time (i.e., the waiting time) is still greater than the preset prediction lock window duration, the previous prediction result is automatically discarded, and the latest status data at the current moment is used to re-execute the time consumption prediction and equipment startup time calculation, thereby enabling the prediction of the future heating process using the state at the most recent moment before future startup.

[0041] The predictive locking mechanism refers to the system determining that it has entered the critical start-up range when the start-up waiting time is less than the predictive locking window duration. At this point, the changes in key state parameters such as furnace temperature and ambient temperature are no longer sufficient to affect the prediction accuracy. The system locks the current optimal equipment start-up time and stops iterative updates to avoid control oscillations caused by minor data fluctuations.

[0042] In some embodiments, step S102 may include, but is not limited to, the following steps: S201, input the current equipment operating condition data and expected parameter values ​​into the heating time prediction model obtained based on machine learning training to obtain the equipment heating time.

[0043] In this embodiment, a machine learning-trained model is used to predict the heating time. This model incorporates practical experience from historically manually verified pre-start-up processes, improving the accuracy of the predicted heating time. Specifically, the real-time measured current equipment temperature is considered the initial heating value and input along with the desired parameter value into the pre-trained heating time prediction model, outputting the predicted heating time (i.e., the equipment heating duration). It is understood that the desired parameter value in this embodiment can be the desired temperature value, or it can be the desired temperature value and the desired heating completion time.

[0044] Furthermore, after the power-on process concludes, the manually verified heating data (including initial heating value, expected temperature value, and actual heating time) can be added to the training dataset as new training samples. Subsequently, the training weights of the training samples based on the time decay mechanism are recalculated, and the heating time prediction model is retrained to complete the model's self-learning and adaptive optimization. The time decay mechanism in this embodiment will be described in detail in subsequent embodiments.

[0045] In some embodiments, the heating time prediction model in step S201 can be obtained by training and updating through, but not limited to, the following steps: S301, a training dataset is constructed based on historical data of the heating equipment; the training dataset includes multiple training samples, each training sample includes the initial equipment temperature, expected parameter value and heating time label, and each training sample carries the corresponding actual start-up time; S302, assign weights to the training samples based on the actual power-on time, and determine the training weights of each training sample; S303, The heating time prediction model based on the extreme gradient boosting algorithm is trained according to the training dataset and the training weights of the training samples in order to update the parameters of the heating time prediction model.

[0046] In this embodiment, the recorded historical temperature rise data of the equipment is organized to construct a training dataset. The training dataset includes multiple training samples. Each training sample includes the initial equipment temperature, expected parameter value, and temperature rise duration label during the actual temperature rise process. The temperature rise duration label represents the actual temperature rise time of the equipment during the actual temperature rise process. Each training sample also carries the corresponding actual power-on time. Weights are assigned to each training sample based on the actual power-on time to determine the training weight of each training sample. By using the actual power-on time of the samples, the contribution of different samples to the training effect is distinguished. Furthermore, the temperature rise time prediction model is trained based on the training weights of the training samples, which improves the model training efficiency and allows the module to reach the desired accuracy as quickly as possible. The temperature rise time prediction model can be any type of machine learning model.

[0047] In one example, this embodiment can construct a heating time prediction model based on the XGBoost algorithm (Extreme Gradient Boosting Algorithm). The coating drying oven start-up control method based on the heating time prediction model in this embodiment has the following characteristics: By constructing a dedicated heating time prediction model based on the Extreme Gradient Boosting (XGBoost) algorithm, and using massive heating performance data accumulated in historical production processes as a basis, the complex nonlinear mapping relationship of the heating process of the drying oven is learned.

[0048] The model input features are the current real-time furnace temperature (i.e., the initial furnace temperature for heating) and the target furnace temperature required by the process; the model output is the predicted heating time required to heat from the initial furnace temperature to the target furnace temperature.

[0049] XGBoost integrates the prediction results of multiple decision trees, which can effectively handle high-dimensional nonlinear data, resist noise interference and avoid overfitting. It is suitable for complex and ever-changing working conditions in industrial sites, thereby realizing the prediction of the time consumption of nonlinear heating processes.

[0050] In some embodiments, step S302 may include, but is not limited to, the following steps: S401, calculate the first time interval between the actual power-on time and the model training time; S402, assign weights to the training samples according to the first time interval to determine the training weight of each training sample; wherein, the first time interval is inversely proportional to the training weight.

[0051] In this embodiment, based on the first time interval between the actual power-on time and the current model training time corresponding to each group of training samples, differentiated training weights are assigned to the samples. More recent training samples with shorter first time intervals are assigned higher training weights; conversely, more recent training samples with longer first time intervals are assigned lower training weights. In subsequent training processes, more attention is paid to training samples with higher weights to update the model parameters. Specifically, an exponential decay function can be used to calculate the training weights.

[0052] This application's embodiments take into account that the hardware characteristics of heating equipment such as drying ovens will slowly change over time, including: Equipment aging: With long-term use, the burner, insulation layer, etc. will inevitably age, and the heating capacity will slowly decrease.

[0053] Parameter adjustment: Due to changes in process, environmental protection and other requirements, the control parameters of the dryer burner may be adjusted, which may lead to changes in the heating temperature control process.

[0054] Equipment upgrades: Due to reasons such as equipment aging and technological upgrades, updating the equipment will result in significant changes in heating capacity.

[0055] The above factors can cause the hardware characteristics of the device to deviate from the hardware characteristics on which the prediction model is built, resulting in a decreasing accuracy of the model. Therefore, this application's embodiments assign training weights representing time decay to the samples before training the model, and simultaneously perform online incremental training based on the current temperature rise data, achieving self-learning and adaptive optimization of the model, thus rapidly improving the model's accuracy.

[0056] According to some embodiments of this application, through a closed-loop process of prediction, execution, feedback, and updating, the model can continuously learn the latest equipment thermal characteristics and automatically offset the effects of equipment aging, parameter adjustment, and equipment updates.

[0057] In some embodiments, step S103b may include, but is not limited to, the following steps: S501, if the waiting time is greater than or equal to the expected time, determine the future refresh time based on the waiting time; S502, when the future refresh time is reached, execute steps S101 to S103.

[0058] In this embodiment, in the branch logic method, when the waiting time is greater than or equal to the expected time, the future refresh time can be determined based on the current time and a preset fixed time interval, or the future refresh time can be adaptively calculated based on the currently calculated waiting time. This results in a higher refresh frequency for the device power-on time when the waiting time is longer and the future refresh time is closer to the current time. Conversely, a lower refresh frequency for the device power-on time when the waiting time is shorter and the future refresh time is farther from the current time. A higher refresh frequency can improve the accuracy of the final predicted device power-on time, while a lower refresh frequency can reduce computational resource expenditure. This solution can simultaneously balance the accuracy of device power-on time prediction and computational burden.

[0059] In some embodiments, determining the future refresh time based on the waiting time in step S501 may include, but is not limited to, the following steps: S601, determine the corresponding second time interval based on the numerical range of the waiting time; wherein, the larger the numerical range, the longer the second time interval; S602, determine the future refresh time based on the second time interval and the current time.

[0060] In this embodiment, a second time interval is determined based on the numerical range of the waiting time. The larger the numerical range (i.e., the longer the waiting time), the longer the corresponding second time interval. Then, the future refresh time is determined based on the second time interval and the current time. This achieves a balance between the accuracy of device power-on time prediction and computational burden. At the same time, a fuzzy granularity approach is adopted to assign the waiting time to a certain numerical range before determining the corresponding second time interval. This allows the future refresh time to be divided into different fine granularities. Compared with the method of directly mapping the waiting time to the corresponding second time interval through a continuous function formula, this can avoid the problem of low system stability caused by excessively high refresh frequency due to too short a waiting time. This embodiment can improve the rationality of the future refresh time setting and improve the system's operational stability.

[0061] This application embodiment also provides an energy-saving control system for precise start-up of heating equipment, including: The first module is used to collect current equipment operating condition data and expected parameter values; the current equipment operating condition data includes the current equipment temperature value, and the expected parameter values ​​include the expected temperature value. The second module is used to predict the heating time based on the current equipment operating data and expected parameter values, obtain the equipment heating time, and then calculate the equipment start-up time based on the equipment heating time. The third module is used to execute branch logic methods based on the waiting time from the current moment to the device power-on time. The branch logic methods are as follows: If the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; If the waiting time is greater than or equal to the expected time, repeat the first to third modules.

[0062] It is understood that the methods described in the above method embodiments are applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0063] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers and mobile phones.

[0064] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0065] Please see Figure 2 , Figure 2 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0066] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0067] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0068] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0069] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0070] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0071] The energy-saving control method and related equipment for precise start-up of heating equipment provided in this application have at least one of the following beneficial effects: (1) A dedicated heating time prediction model is constructed using the XGBoost ensemble learning algorithm, which can automatically learn the complex nonlinear mapping relationships hidden in massive historical data and improve prediction accuracy. This model does not rely on the experience of senior engineers and can automatically adapt to heating equipment of different models and volumes, which greatly reduces the threshold for system deployment and use.

[0072] (2) Through the rolling refresh and re-prediction mechanism, the latest operating condition data is continuously collected at a fixed sampling period. As long as the critical start-up range is not entered, the prediction results are continuously updated with the latest state data at the current moment. This realizes the prediction of the future heating process using the real state at the most recent moment before start-up, thus eliminating the systematic error caused by time misalignment in principle. At the same time, the supporting prediction locking mechanism balances prediction accuracy and system stability, ensuring dynamic correction capability while avoiding control oscillations caused by small data fluctuations.

[0073] (3) Through a retraining mechanism based on time decay weights, the actual data of each heating process is automatically added to the sample library after each heating process, and differentiated weights are assigned according to the time distance of the samples, so as to focus on learning the latest equipment characteristics reflected by recent data, while retaining the long-term patterns of historical data. This mechanism does not require manual intervention and can automatically offset the impact of equipment aging and environmental changes, so that the model prediction accuracy remains stable in the long term.

[0074] (4) Based on accurate prediction of heating time, the ineffective dry burning time of the drying oven can be reduced to near zero. By avoiding unnecessary long dry burning, the service life of core components such as burners can be effectively extended, reducing equipment maintenance costs. In addition, the system operates automatically throughout the entire process without the need for manual operation or intervention, which greatly reduces the workload of production schedulers.

[0075] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0076] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0077] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0079] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0080] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0081] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0082] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0084] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. An energy-saving control method for precise start-up of a heating device, characterized by, Includes the following steps: Collect current equipment operating condition data and desired parameter values; the current equipment operating condition data includes the current equipment temperature value, and the desired parameter values ​​include the desired temperature value; Based on the current equipment operating data and the expected parameter values, the heating time is predicted to obtain the equipment heating duration, and then the equipment start-up time is calculated based on the equipment heating duration. The branch logic method is executed based on the waiting time from the current time to the device's power-on time. The branch logic method is as follows: If the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; If the waiting time is greater than or equal to the expected time, repeat the step of collecting the current equipment operating data and the expected parameter value to execute the branch logic method according to the waiting time.

2. The energy-saving control method for precise start-up of a heating device according to claim 1, characterized in that, The step of predicting the heating time based on the current equipment operating data and the expected parameter values ​​to obtain the equipment heating duration includes the following steps: The current equipment operating condition data and the expected parameter values ​​are input into the heating time prediction model obtained based on machine learning training to obtain the equipment heating time.

3. The energy-saving control method for precise start-up of a heating device according to claim 2, characterized in that, The heating time prediction model is trained and updated through the following steps: A training dataset is constructed based on the historical data of the heating equipment. The training dataset includes multiple training samples, each of which includes an initial equipment temperature, a desired parameter value, and a heating time label. Each training sample also carries the corresponding actual start-up time. The training samples are weighted according to the actual power-on time to determine the training weight of each training sample; The heating time prediction model based on the extreme gradient boosting algorithm is trained according to the training dataset and the training weights of the training samples to update the parameters of the heating time prediction model.

4. The energy-saving control method for precise start-up of a heating device according to claim 3, characterized in that, The step of assigning weights to the training samples based on the actual power-on time, and determining the training weights for each training sample, includes the following steps: Calculate the first time interval between the actual power-on time and the model training time; The training samples are weighted according to the first time interval to determine the training weight of each training sample; wherein the first time interval is inversely proportional to the training weight.

5. The energy-saving control method for precise start-up of a heating device according to claim 1, characterized in that, When the waiting time is greater than or equal to the expected time, the step of repeatedly executing the method of collecting the current equipment operating condition data and the expected parameter value until the branch logic method is executed according to the waiting time includes the following steps: If the waiting time is greater than or equal to the expected time, the future refresh time is determined based on the waiting time. When the future refresh time is reached, the step of collecting the current device operating data and expected parameter values ​​is executed to execute the branch logic method according to the waiting time.

6. The energy-saving control method for precise start-up of a heating device according to claim 5, characterized in that, Determining the future refresh time based on the waiting time includes the following steps: A corresponding second time interval is determined based on the numerical range of the waiting time; wherein, the larger the numerical range, the longer the second time interval. The future refresh time is determined based on the second time interval and the current time.

7. An energy-saving control system for precise start-up of a heating device, characterized in that, include: The first module is used to collect current equipment operating condition data and expected parameter values; the current equipment operating condition data includes the current equipment temperature value, and the expected parameter values ​​include the expected temperature value. The second module is used to predict the heating time based on the current equipment operating data and the expected parameter value, obtain the equipment heating time, and then calculate the equipment start-up time based on the equipment heating time. The third module is used to execute a branch logic method based on the waiting time from the current time to the device's power-on time. The branch logic method is as follows: If the waiting time is less than the expected time, prepare to start the heating equipment according to the equipment start-up time; If the waiting time is greater than or equal to the expected time, the first module to the third module are run repeatedly.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images