Energy-saving control method, device and equipment for sintering main exhaust fan and storage medium

Abstract

According to the energy-saving control method, device and equipment for the sintering main exhaust fan and the storage medium, the problem that online optimization cannot be achieved due to the fact that the power consumption of each ton of mine is seriously lagged is solved through a fusion method that the short-term energy efficiency proxy index is created to serve as a real-time feedback signal and is subjected to space-time alignment with lagged real power consumption of each ton of mine, and the energy-saving control efficiency of the sintering main exhaust fan is improved. Minute-level real-time energy-saving optimization under the condition of lack of real-time feedback is realized; a fuzzy rule base based on self-adaptive weights is constructed, reward and punishment updating is carried out on the weights based on lagging data alignment, a complete intelligent closed loop from perception to decision-making to action to effect evaluation to self-correction is achieved, and the method can adapt to long-term slow change of working conditions such as raw materials and equipment in a self-adaptive mode; by means of the self-learning closed loop, operation of the main exhaust fan can be continuously optimized, and therefore electricity consumption per ton of mine is effectively reduced. The system does not depend on an accurate mathematical model, is insensitive to field interference, and has extremely high engineering application value.

Description

Technical Field

[0001] This invention relates to the field of sintering technology, and in particular to an energy-saving control method, device, equipment and storage medium for a sintering main exhaust fan. Background Technology

[0002] The main exhaust fan in sintering is the "energy hog" of the sintering process, and its energy-saving control is an industry challenge. Existing advanced control methods attempt to achieve energy savings by adjusting the fan frequency to track process status (such as the sintering endpoint), but all face a critical engineering bottleneck: the core energy efficiency indicator of power consumption per ton of ore cannot be obtained in real time. There is a lag of 1.5 to 2.5 hours between the fan's power consumption and the corresponding sintered ore output and metering.

[0003] This results in the following: any optimization algorithm targeting power consumption per ton of ore is difficult to run online and cannot be optimized in real time because it cannot obtain immediate feedback; data lag makes it impossible for the control system to judge the long-term energy efficiency effect of its adjustment actions (such as changing the frequency), thus making it impossible to carry out effective self-learning and strategy updates; the system can only run preset, fixed control strategies and cannot adapt to the long-term slow changes in operating conditions such as raw materials and equipment status, and the energy-saving effect gradually degrades.

[0004] Therefore, there is an urgent need in this field for an innovative solution that can overcome the data lag barrier and achieve truly online, adaptive, and self-learning energy-saving control.

[0005] In view of this, it is necessary to propose an energy-saving control method, device, equipment and storage medium for the sintering main exhaust fan to solve or at least alleviate the above-mentioned defects. Summary of the Invention

[0006] The main objective of this invention is to provide an energy-saving control method, device, equipment, and storage medium for sintering main exhaust fans, in order to solve the problem that in the energy-saving control of sintering main exhaust fans, the real-time optimization closed loop cannot be constructed due to the lag in power consumption per ton of ore, thereby causing the control strategy to be unable to learn online and adapt to slow changes in operating conditions.

[0007] To achieve the above objectives, the present invention provides an energy-saving control method for a sintering main exhaust fan, comprising the following steps: S1, collect real-time process parameter data of the sintering process, wherein the real-time process parameters include at least the sintering endpoint and the temperature difference of the exhaust gas. S2, based on the sintering endpoint and the temperature difference of the exhaust gas, the fan frequency adjustment amount is output by querying the fuzzy rule base and performing fuzzy inference; wherein, each rule in the fuzzy rule base is associated with an adaptive weight for fuzzy inference. S3, Based on the fan frequency adjustment amount, correct the current operating frequency of the main exhaust fan; S4. When the lagging real power consumption per ton of ore data is available, the real power consumption per ton of ore is spatiotemporally aligned with the process parameters recorded at historical time nodes and the fuzzy rules triggered at the historical time nodes. S5, determine the change of the actual power consumption per ton of ore after alignment relative to the benchmark value of power consumption per ton of ore, and dynamically update the adaptive weight of the triggering rule; wherein, when the actual power consumption per ton of ore decreases, the adaptive weight is increased, and when the actual power consumption per ton of ore increases, the adaptive weight is decreased. S6, normalize the adaptive weights of all rules in the fuzzy rule base according to a preset time interval so that the total weight remains constant.

[0008] Preferably, the rule form of the fuzzy rule base is: IF sintering endpoint state AND exhaust gas temperature difference state THEN fan frequency adjustment amount; wherein, the sintering endpoint state is fuzzified into multiple fuzzy sets representing the position state of the sintering endpoint, the exhaust gas temperature difference state is fuzzified into multiple fuzzy sets representing the magnitude of the exhaust gas temperature difference in the wind box, and the fan frequency adjustment amount is fuzzified into multiple fuzzy sets representing the direction and / or amplitude of the fan frequency adjustment; each rule in the fuzzy rule base is associated with an adaptive weight, and the adaptive weight of each rule is initialized to the same value at the beginning.

[0009] Preferably, step S2 specifically includes the following steps: S21, for each rule in the fuzzy rule base, calculate the first membership degree of the sintering endpoint belonging to the fuzzy set of sintering endpoints defined in the premise of the rule, and calculate the second membership degree of the exhaust gas temperature difference belonging to the fuzzy set of exhaust gas temperature difference defined in the premise of the rule. S22, the minimum value between the first membership degree and the second membership degree is calculated by taking the smaller operator, and the minimum value is used as the premise membership degree of this rule; S23, Multiply the membership degree of the precondition and the adaptive weight corresponding to the rule to obtain the triggering strength of the rule; S24 uses the centroid method to calculate the trigger strength of each rule and the corresponding preset output value of the conclusion, and outputs the fan frequency adjustment amount.

[0010] Preferably, step S3 specifically includes the following steps: Using formula The current operating frequency of the main exhaust fan is corrected; among which, The corrected operating frequency of the main exhaust fan. The current operating frequency of the main exhaust fan. This represents the frequency adjustment of the fan, where K is the gain coefficient, and 0 represents the frequency adjustment of the fan. <K≤1。

[0011] Preferably, the process parameters are short-term energy efficiency surrogate indicators, using the formula... Obtain; among them, The aforementioned short-term energy efficiency proxy index The average input active power of the main exhaust fan within a preset cycle. The average speed of the sintering machine trolley within the preset period; the short-term energy efficiency proxy index is an index that is negatively correlated with the power consumption per ton of ore and can reflect the instantaneous energy efficiency status of the main exhaust fan.

[0012] Preferably, step S4 specifically includes the following steps: S41, receive the delayed actual power consumption per ton of ore, and obtain the sinter production time period and power consumption per ton of ore corresponding to the actual power consumption per ton of ore. S42, based on the sinter production time period, retrieve from the historical database all short-term energy efficiency proxy indicators recorded during the sinter production time period and the timestamp corresponding to each short-term energy efficiency proxy indicator; as well as the rule unique identifier of all triggered fuzzy rules and the timestamp corresponding to the rule unique identifier; S43, bind the actual power consumption per ton of ore, the short-term energy efficiency proxy index data sequence, and the rule-unique identifier sequence to perform spatiotemporal alignment.

[0013] Preferably, a reward and punishment mechanism is adopted for the dynamic update of adaptive weights: the weight is increased as a reward when the actual power consumption per ton of ore decreases, and the weight is decreased as a punishment when the actual power consumption per ton of ore increases.

[0014] The present invention also provides an energy-saving control device for a sintering main exhaust fan, used to execute the energy-saving control method for the sintering main exhaust fan as described above, comprising: The data acquisition module is used to collect real-time process parameter data of the sintering process; wherein, the real-time process parameters include the sintering endpoint and the temperature difference of the exhaust gas. The result output module is used to output the fan frequency adjustment amount based on the sintering endpoint and the temperature difference of the exhaust gas by querying the fuzzy rule base and performing fuzzy inference; wherein, each rule in the fuzzy rule base is associated with an adaptive weight for fuzzy inference. The frequency correction module is used to correct the current operating frequency of the main exhaust fan according to the fan frequency adjustment amount. The spatiotemporal alignment module is used to spatiotemporally align the real electricity consumption per ton of ore with the process parameters recorded at historical time nodes and the fuzzy rules triggered at the historical time nodes when the lagging real electricity consumption per ton of ore data is available. The weight update module is used to determine the change of the actual power consumption per ton of ore after alignment relative to the benchmark value of power consumption per ton of ore, and to dynamically update the adaptive weight of the triggering rule; wherein, when the actual power consumption per ton of ore decreases, the adaptive weight is increased, and when the actual power consumption per ton of ore increases, the adaptive weight is decreased. The periodic update module is used to normalize the adaptive weights of all rules in the fuzzy rule base at preset time intervals so that the total weight remains constant.

[0015] The present invention also provides an energy-saving control device for a sintering main exhaust fan, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the energy-saving control method for the sintering main exhaust fan as described above.

[0016] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described energy-saving control method for a sintering main exhaust fan.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This invention provides an energy-saving control method, device, equipment, and storage medium for sintering main exhaust fans. By creating a short-term energy efficiency proxy index as a real-time feedback signal and merging it with the lagging real-time power consumption per ton of ore, this invention successfully overcomes the global challenge of severely lagging power consumption per ton of ore, which prevents online optimization. It achieves minute-level real-time energy-saving optimization even in the absence of immediate real-time feedback. This application constructs a fuzzy rule base based on adaptive weights and updates the weights based on lagging data alignment with rewards and penalties, realizing a complete intelligent closed loop from perception to decision-making to action, effect evaluation, and self-correction. This allows the control system to continuously tap into energy-saving potential, and its energy-saving effect does not degrade over time, adapting to the long-term slow changes in raw materials and equipment operating conditions. This application ensures the stability of the learning process through weight normalization and gain coefficients, preventing system oscillation or divergence. Data alignment and periodic correction mechanisms ensure the long-term correctness of the optimization direction. This application can significantly reduce the power consumption per ton of ore for sintering main exhaust fans. The system does not rely on precise mathematical models, is insensitive to on-site interference, and has extremely high engineering application value. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0019] Figure 1 This is a flow chart of the sintering process in one embodiment of the present invention; Figure 2 This is a schematic diagram of a process in one embodiment of the present invention; Figure 3 This is a flowchart illustrating the specific steps involved in step S2 of one embodiment of the present invention.

[0020] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0023] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0024] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination should be considered non-existent and not within the scope of protection claimed by this invention.

[0025] Please see the appendix Figures 1 to 3 An energy-saving control method for a sintering main exhaust fan, provided in one embodiment of the present invention, includes the following steps: S1, Collect real-time process parameter data of the sintering process; wherein, the real-time process parameters include the sintering endpoint and the temperature difference of the exhaust gas; It is worth noting that the end position of the sintering process, usually indicated by the bellows number, is a core parameter for judging whether the sintering process is normal. An early sintering endpoint indicates premature termination of the sintering process, resulting in wasted airflow from the bellows between the endpoint and the tail end, leading to high power consumption. An late sintering endpoint indicates that the sintering process has not finished before reaching the tail end, resulting in insufficient cooling and crystallization time, easily generating return ore, which also leads to high power consumption and quality problems. A normal sintering endpoint indicates that the blower's airflow is being utilized most efficiently, resulting in high energy efficiency. Therefore, the sintering endpoint position can effectively reflect the golden standard of blower work efficiency; controlling the sintering endpoint at a normal position is a prerequisite for energy saving. The temperature difference of the exhaust gas between the penultimate and penultimate bellows is a barometer reflecting the "smoothness" of the sintering process and the "energy consumption cost" of blower operation. Under the premise of ensuring a normal sintering endpoint, a smaller exhaust gas temperature difference can reduce the blower's operating resistance, thereby achieving deep energy savings.

[0026] Preferably, the exhaust gas temperature difference is the temperature difference (in °C) between the exhaust gas from the penultimate and penultimate wind boxes after the sintering endpoint. This difference serves as an auxiliary criterion, reflecting the stability and thickness of the sintering "combustion zone." A small temperature difference indicates a narrow and concentrated combustion zone with good permeability, but incomplete combustion may occur. A large temperature difference indicates a wide and dispersed combustion zone, potentially poor permeability, and high fan operating resistance.

[0027] This application selects the sintering endpoint and the temperature difference of the exhaust gas as key process parameters that can comprehensively reflect the thermal state of the sintering process and uses them as the premise input of the fuzzy rule base. Furthermore, these parameters have a strong correlation with the final power consumption per ton of ore. Thus, even if only these two parameters are obtained and the scheme of this application is executed, this application can converge towards reducing the power consumption per ton of ore.

[0028] S2, based on the temperature difference between the sintering endpoint and the exhaust gas, the fan frequency adjustment amount is output by querying the fuzzy rule base and performing fuzzy inference. Each rule in the fuzzy rule base is associated with an adaptive weight used for fuzzy inference. By constructing a fuzzy rule base that takes the sintering endpoint and exhaust gas temperature difference as input and the fan frequency adjustment amount as output, real-time automatic optimization is achieved, avoiding reliance on manual experience for control. The fuzzy inference process includes three steps: fuzzification, inference, and defuzzification, ultimately outputting a clear fan frequency adjustment amount.

[0029] As a preferred embodiment, the rule form of the fuzzy rule base is: IF sintering end state AND waste gas temperature difference state THEN fan frequency adjustment amount; wherein, the sintering end state is fuzzified into multiple fuzzy sets representing the sintering end position state, the waste gas temperature difference state is fuzzified into multiple fuzzy sets representing the magnitude of the waste gas temperature difference in the wind box, and the fan frequency adjustment amount is fuzzified into multiple fuzzy sets representing the fan frequency adjustment direction and / or amplitude; each rule in the fuzzy rule base is associated with an adaptive weight, and at the start time, the adaptive weight of each rule is initialized to the same value.

[0030] As a better example, the sintering end state is fuzzified into any one of too early, normal, and too late, the waste gas temperature difference state is fuzzified into any one of small temperature difference and large temperature difference, and the fan frequency adjustment amount is fuzzified into any one of large negative, small negative, zero, small positive, and large positive; each rule in the fuzzy rule base is associated with an adaptive weight, and at the start time, the adaptive weight of each rule is initialized to the same value. For example, they are all initialized to 1.0. Among them, IF sintering end state AND waste gas temperature difference state is the premise of the rule, and THEN fan frequency adjustment amount is the conclusion of the rule. Preferably, the initial weight of each rule is set to 1.0. For example, when first put into operation, the initial weight of each rule is set to 1.0.

[0031] S3. According to the fan frequency adjustment amount, correct the current operating frequency of the main exhaust fan; Further, the step S3 specifically includes the following steps: Use the formula to correct the current operating frequency of the main exhaust fan; wherein, is the operating frequency of the main exhaust fan after correction, is the current operating frequency of the main exhaust fan, is the fan frequency adjustment amount, K is the gain coefficient, 0 < K ≤ 1, and the adjustment of K can be set according to the requirements of system stability and optimization speed. In the initial stage of system operation or when the working conditions fluctuate greatly, a smaller K value (such as 0.2 - 0.5) is selected to preferentially ensure system stability. As the system self-learning process progresses and the control strategy tends to be stable, the K value can be gradually increased up to 1 at most to improve the response speed of the optimization process. K = 1 is the limit case of "fully execute the adjustment amount", but in actual applications, it may never be necessary to reach 1.

[0032] S4. When the data of the lagging actual power consumption per ton of ore is available, align the actual power consumption per ton of ore with the process parameters recorded at the historical time node and the fuzzy rules triggered at the historical time node in space and time; Furthermore, the process parameters are short-term energy efficiency proxy indicators, using the formula... Obtain; among them, The aforementioned short-term energy efficiency proxy index is expressed in kW / (m / min). The average input active power of the main exhaust fan within a preset cycle, in kW. The average speed of the sintering machine trolley within the preset period is expressed in m / min. Preferably, the system operates on a minute-level cycle, where the preset period is 1 minute. The short-term energy efficiency proxy index is an index negatively correlated with the power consumption per ton of ore and reflecting the instantaneous energy efficiency status of the main exhaust fan. Its construction methods include, but are not limited to, the ratio of the main exhaust fan power to the sintering machine trolley speed.

[0033] This application constructs a short-term energy efficiency surrogate index by dividing two instantaneous parameters (fan active power, representing energy consumption, sintering machine trolley speed, representing sinter production speed) that have different physical meanings and dimensions. This short-term energy efficiency surrogate index can characterize the trend of energy utilization efficiency changes during the sintering process, and its direction of change is highly consistent and strongly correlated with the lagged change in actual power consumption per ton of ore. A strong negative correlation exists between the short-term energy efficiency surrogate index and the lagged actual power consumption per ton of ore; a larger short-term energy efficiency surrogate index indicates a higher final actual power consumption per ton of ore (worse energy efficiency), and a smaller short-term energy efficiency surrogate index indicates a lower final actual power consumption per ton of ore (better energy efficiency). By using this instantaneous process-oriented index as an intermediate bridge for real-time optimization, working in conjunction with the lagged actual power consumption per ton of ore in a self-learning loop, this effectively solves the problem of the lagged actual power consumption per ton of ore preventing online optimization.

[0034] S5, determine the change in the actual electricity consumption per ton of ore after alignment relative to the benchmark value of electricity consumption per ton of ore, and dynamically update the adaptive weight of the triggering rule; wherein, when the actual electricity consumption per ton of ore decreases, the adaptive weight is increased, and when the actual electricity consumption per ton of ore increases, the adaptive weight is decreased; wherein, the benchmark value of electricity consumption per ton of ore is preferably the average of all available actual electricity consumption per ton of ore data within the most recent predetermined time window before the alignment time period. Alternatively, the electricity consumption per ton of ore calculated after the previous alignment can be directly taken.

[0035] Preferably, the dynamic update of the adaptive weights in step S5 adopts a reward and punishment mechanism: the weights are increased as a reward when the actual power consumption per ton of ore decreases, and the weights are decreased as a punishment when the actual power consumption per ton of ore increases.

[0036] As a preferred example, when the actual power consumption per ton of ore decreases, the adaptive weight is increased by 0.1 to obtain the adjusted adaptive weight; when the actual power consumption per ton of ore increases, the adaptive weight is decreased by 0.1 to obtain the adjusted adaptive weight; when the actual power consumption per ton of ore remains unchanged, the adaptive weight is maintained unchanged. Specifically, the weight update in this embodiment adopts a reward and punishment mechanism. When the actual power consumption per ton of ore decreases, the rule is deemed valid, and a reward is given, for example, the formula... When the actual electricity consumption per ton of ore increases, the rule is deemed invalid and penalties are imposed, for example, the formula. ;in, Let be the learning rate; for example, we'll use 0.1. The penalty coefficient is set to 0.1 for example. This implements a data-driven evolution of the control strategy, guiding the control behavior of the entire system to continuously optimize towards energy saving.

[0037] S6. Normalize the adaptive weights of all rules in the fuzzy rule base according to a preset time interval to keep the total weight constant. To prevent some rule weights from growing or decaying indefinitely, normalization is performed periodically. The preset time interval can be set according to actual needs, such as one day or one week. Preferably, the sum of all weights can be kept at 1, thereby transforming the weight system into a distribution of relative importance.

[0038] This application's solution overcomes the global challenge of severely lagging power consumption per ton of ore, which prevents online optimization, by creating a short-term energy efficiency proxy indicator as a real-time feedback signal and merging it with the lagging real power consumption per ton of ore in a spatiotemporal alignment. This achieves minute-level real-time energy-saving optimization even in the absence of immediate real feedback. Furthermore, by constructing a fuzzy rule base based on adaptive weights and updating the weights based on lagging data alignment with rewards and penalties, this application realizes a complete intelligent closed loop from perception to decision-making to action, effect evaluation, and self-correction. This allows the control system to continuously tap into energy-saving potential, with energy-saving effects that do not degrade over time and can adapt to long-term slow changes in raw material and equipment operating conditions. The application ensures the stability of the learning process through weight normalization and gain coefficients, preventing system oscillations or divergence. Data alignment and periodic correction mechanisms ensure the long-term correctness of the optimization direction. This application can significantly reduce the power consumption per ton of ore for the sintering main exhaust fan. The system does not rely on precise mathematical models, is insensitive to on-site interference, and possesses extremely high engineering application value.

[0039] In a preferred embodiment, step S2 specifically includes the following steps: S21, for each rule in the fuzzy rule base, calculate the first membership degree of the sintering endpoint belonging to the fuzzy set of sintering endpoints defined in the premise of the rule, and calculate the second membership degree of the exhaust gas temperature difference belonging to the fuzzy set of exhaust gas temperature difference defined in the premise of the rule. Specifically, the system takes the currently detected actual value of the sintering endpoint, for example (in this embodiment, the total number of sintering wind boxes is 24, and the normal sintering endpoint target position is 23.0), and then queries the rule for the requirements of the sintering endpoint. The fuzzy set of the sintering endpoint is preset with wind box intervals corresponding to too early, too late, and normal. For example, if it is too late, the system calculates the degree to which the actual value of the endpoint 23.5 meets the requirement of being too late using a preset membership function, for example, the matching degree is 0.7. Similarly, the exhaust gas temperature difference is calculated in the same way to calculate the degree to which the current exhaust gas temperature difference meets the rule requirements, for example, the matching degree is 0.4. For each rule in the fuzzy rule base, this step is repeated to obtain the first membership degree and the second membership degree corresponding to all rules.

[0040] S22, by taking the smallest operator, the minimum value between the first membership degree and the second membership degree is calculated, and the minimum value is used as the premise membership degree of the rule; for example, taking the minimum value between 0.7 and 0.4, we get 0.4.

[0041] S23, multiply the membership degree of the precondition and the adaptive weight corresponding to the rule to obtain the trigger strength of the rule; for example, if the adaptive weight corresponding to the rule is 0.2, multiply the overall matching degree of 0.4 by the weight of 0.2 to get 0.08, which is the trigger strength of the rule; S24 uses the centroid method to calculate the trigger strength of each rule and the corresponding preset output value of the conclusion, and outputs the fan frequency adjustment amount.

[0042] For example, Rule 1: Trigger strength = 0.08, the default output value corresponding to the conclusion "positively small" is +1 Hz; Rule 2: Trigger strength = 0.04, the corresponding preset output value for "Zhengda" is +2 Hz; Rule 3: Trigger strength = 0.05, the default output value corresponding to the conclusion "zero" is 0 Hz.

[0043] The center-of-gravity method is a mature technical approach, and will not be elaborated upon here.

[0044] This embodiment calculates the trigger strength by multiplying the matching degree of the rule premise by the historical weight, and combines the democratic decision-making mechanism of the center of gravity method to output reasonable control commands after comprehensively considering various operating parameters, thus realizing rule-based intelligent control.

[0045] In a preferred embodiment, step S4 specifically includes the following steps: S41, receive the delayed actual power consumption per ton of ore, and obtain the sinter production time period and power consumption value corresponding to the actual power consumption per ton of ore; by continuously receiving the metering message queue from the sintering system, the processing flow is triggered immediately upon receiving a new power consumption data packet per ton of ore. The power consumption data per ton of ore includes the corresponding sinter production time period and power consumption value per ton of ore. For example, if this batch of sintered ore was produced from 14:00 to 15:30 today, its power consumption per ton of ore is 28.5 kWh / t. Three key pieces of information are obtained: start time 14:00, end time 15:30, and power consumption value 28.5, and a timestamp is added.

[0046] S42, based on the sinter production time period, retrieve from the historical database all short-term energy efficiency proxy indicators recorded within the sinter production time period and the timestamp corresponding to each short-term energy efficiency proxy indicator; as well as the rule unique identifier and the timestamp corresponding to the rule unique identifier for all triggered fuzzy rules; the rule unique identifier can be the rule number or hash value. For example, for the obtained time period of 14:00-15:30, retrieve from the historical database the short-term energy efficiency proxy indicators for each minute (single control cycle) within this 1.5-hour period and their corresponding timestamps (accurate timestamps). A complete record of each triggered fuzzy rule includes the rule unique identifier and the trigger time, such as rule number R01. The historical database uses a unified timeline to record real-time process parameters and short-term energy efficiency proxy indicators with timestamps in parallel.

[0047] S43, bind the actual power consumption per ton of ore, the short-term energy efficiency proxy indicator data sequence, and the rule-unique identifier sequence to perform spatiotemporal alignment. Through accurate spatiotemporal alignment, a complete chain is established: what control was used during what time period, what was the energy efficiency at that time, and what was the final result.

[0048] This embodiment establishes an accurate causal mapping between macro-production results (electricity consumption per ton of ore) lasting 1.5-2.5 hours and control decisions (triggered rules) and process parameters (short-term energy efficiency proxy indicators) every minute by aligning with timestamps accurate to the minute level. This enables the system to accurately identify the long-term value of each control action from complex production data.

[0049] The present invention also provides an energy-saving control device for a sintering main exhaust fan, used to execute the energy-saving control method for the sintering main exhaust fan as described above, comprising: The data acquisition module is used to collect real-time process parameters during the sintering process; these real-time process parameters include the sintering endpoint and the temperature difference of the exhaust gas. The result output module is used to output the fan frequency adjustment amount based on the sintering endpoint and the temperature difference of the exhaust gas by querying the fuzzy rule base and performing fuzzy inference; wherein, each rule in the fuzzy rule base is associated with an adaptive weight for fuzzy inference. The frequency correction module is used to correct the current operating frequency of the main exhaust fan according to the fan frequency adjustment amount. The spatiotemporal alignment module is used to spatiotemporally align the real electricity consumption per ton of ore with the process parameters recorded at historical time nodes and the fuzzy rules triggered at the historical time nodes when the lagging real electricity consumption per ton of ore data is available. The weight update module is used to determine the change of the actual power consumption per ton of ore after alignment relative to the benchmark value of power consumption per ton of ore, and to dynamically update the adaptive weight of the triggering rule; wherein, when the actual power consumption per ton of ore decreases, the adaptive weight is increased, and when the actual power consumption per ton of ore increases, the adaptive weight is decreased. The periodic update module is used to normalize the adaptive weights of all rules in the fuzzy rule base at preset time intervals so that the total weight remains constant.

[0050] The present invention also provides an energy-saving control device for a sintering main exhaust fan, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the energy-saving control method for the sintering main exhaust fan as described above.

[0051] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described energy-saving control method for a sintering main exhaust fan.

[0052] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0053] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. An energy-saving control method for a sintering main exhaust fan, characterized in that, Includes the following steps: S1, collect real-time process parameter data of the sintering process; wherein, the real-time process parameters include at least the sintering endpoint and the temperature difference of the exhaust gas; S2, based on the sintering endpoint and the temperature difference of the exhaust gas, the fan frequency adjustment amount is output by querying the fuzzy rule base and performing fuzzy inference; wherein, each rule in the fuzzy rule base is associated with an adaptive weight for fuzzy inference. S3, Based on the fan frequency adjustment amount, correct the current operating frequency of the main exhaust fan; S4. When the lagging real power consumption per ton of ore data is available, the real power consumption per ton of ore is spatiotemporally aligned with the process parameters recorded at historical time nodes and the fuzzy rules triggered at the historical time nodes. S5, determine the change of the actual power consumption per ton of ore after alignment relative to the benchmark value of power consumption per ton of ore, and dynamically update the adaptive weight of the triggering rule; wherein, when the actual power consumption per ton of ore decreases, the adaptive weight is increased, and when the actual power consumption per ton of ore increases, the adaptive weight is decreased. S6, normalize the adaptive weights of all rules in the fuzzy rule base according to a preset time interval so that the total weight remains constant.

2. The energy-saving control method for the sintering main exhaust fan according to claim 1, characterized in that, The rule form of the fuzzy rule base is: IF sintering endpoint state AND exhaust gas temperature difference state THEN fan frequency adjustment amount; wherein, the sintering endpoint state is fuzzified into multiple fuzzy sets representing the position state of the sintering endpoint, the exhaust gas temperature difference state is fuzzified into multiple fuzzy sets representing the magnitude of the exhaust gas temperature difference in the wind box, and the fan frequency adjustment amount is fuzzified into multiple fuzzy sets representing the direction and / or amplitude of the fan frequency adjustment; each rule in the fuzzy rule base is associated with an adaptive weight, and the adaptive weight of each rule is initialized to the same value at the beginning.

3. The energy-saving control method for the sintering main exhaust fan according to claim 2, characterized in that, Step S2 specifically includes the following steps: S21, for each rule in the fuzzy rule base, calculate the first membership degree of the sintering endpoint belonging to the fuzzy set of sintering endpoints defined in the premise of the rule, and calculate the second membership degree of the exhaust gas temperature difference belonging to the fuzzy set of exhaust gas temperature difference defined in the premise of the rule. S22, the minimum value between the first membership degree and the second membership degree is calculated by taking the smaller operator, and the minimum value is used as the premise membership degree of this rule; S23, Multiply the membership degree of the precondition and the adaptive weight corresponding to the rule to obtain the triggering strength of the rule; S24 uses the centroid method to calculate the trigger strength of each rule and the corresponding preset output value of the conclusion, and outputs the fan frequency adjustment amount.

4. The energy-saving control method for the sintering main exhaust fan according to claim 1, characterized in that, Step S3 specifically includes the following steps: Using formula The current operating frequency of the main exhaust fan is corrected; among which, The corrected operating frequency of the main exhaust fan. The current operating frequency of the main exhaust fan. This represents the frequency adjustment of the fan, where K is the gain coefficient, and 0 represents the frequency adjustment of the fan. <K≤1。 5. The energy-saving control method for the sintering main exhaust fan according to claim 1, characterized in that, The process parameters are short-term energy efficiency proxy indicators, using the formula... Obtain; among them, As a short-term energy efficiency proxy indicator, The average input active power of the main exhaust fan within a preset cycle. The average speed of the sintering machine trolley within the preset period; the short-term energy efficiency proxy index is an index that is negatively correlated with the power consumption per ton of ore and can reflect the instantaneous energy efficiency status of the main exhaust fan.

6. The energy-saving control method for the sintering main exhaust fan according to claim 5, characterized in that, Step S4 specifically includes the following steps: S41, receive the delayed actual power consumption per ton of ore, and obtain the sinter production time period and power consumption per ton of ore corresponding to the actual power consumption per ton of ore. S42, based on the sinter production time period, retrieve from the historical database all short-term energy efficiency proxy indicators recorded during the sinter production time period and the timestamp corresponding to each short-term energy efficiency proxy indicator; as well as the rule unique identifier of all triggered fuzzy rules and the timestamp corresponding to the rule unique identifier; S43, bind the actual power consumption per ton of ore, the short-term energy efficiency proxy index data sequence, and the rule-unique identifier sequence to perform spatiotemporal alignment.

7. The energy-saving control method for the sintering main exhaust fan according to claim 1, characterized in that, In step S5, the dynamic update of the adaptive weights adopts a reward and punishment mechanism: the weights are increased as a reward when the actual power consumption per ton of ore decreases, and the weights are decreased as a punishment when the actual power consumption per ton of ore increases.

8. An energy-saving control device for a sintering main exhaust fan, used to execute the energy-saving control method for a sintering main exhaust fan as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to collect real-time process parameter data of the sintering process; wherein, the real-time process parameters include the sintering endpoint and the temperature difference of the exhaust gas. The result output module is used to output the fan frequency adjustment amount based on the sintering endpoint and the temperature difference of the exhaust gas by querying the fuzzy rule base and performing fuzzy inference; wherein, each rule in the fuzzy rule base is associated with an adaptive weight for fuzzy inference. The frequency correction module is used to correct the current operating frequency of the main exhaust fan according to the fan frequency adjustment amount. The spatiotemporal alignment module is used to spatiotemporally align the real electricity consumption per ton of ore with the process parameters recorded at historical time nodes and the fuzzy rules triggered at the historical time nodes when the lagging real electricity consumption per ton of ore data is available. The weight update module is used to determine the change of the actual power consumption per ton of ore after alignment relative to the benchmark value of power consumption per ton of ore, and to dynamically update the adaptive weight of the triggering rule; wherein, when the actual power consumption per ton of ore decreases, the adaptive weight is increased, and when the actual power consumption per ton of ore increases, the adaptive weight is decreased. The periodic update module is used to normalize the adaptive weights of all rules in the fuzzy rule base at preset time intervals so that the total weight remains constant.

9. An energy-saving control device for a sintering main exhaust fan, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the energy-saving control method for the sintering main exhaust fan as described in any one of claims 1 to 7.

10. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the energy-saving control method for a sintering main exhaust fan as described in any one of claims 1 to 7.

Images