Fan frequency control method and device, electronic equipment and computer storage medium
By acquiring historical parameters and real-time values of the automatic combustion control system, and using a time-series prediction model and a proportional-integral-derivative controller to calculate the fan frequency, the problems of response lag and overshoot in the existing technology are solved, achieving more efficient fan frequency control and improving system stability and combustion efficiency.
Patent Information
- Application Number
- CN202511721860.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-21
- Publication Date
- 2025-12-26
- Estimated Expiration
- 2045-11-21
AI Technical Summary
In existing automatic combustion control systems, due to the large variations in waste composition, control methods based on thermodynamic models are not applicable to actual production, leading to response lag and overshoot problems, and large system fluctuations.
By acquiring historical parameter sequence values and current real-time values of the automatic combustion control system, and using a time-series prediction model and a proportional-integral-derivative controller, the fan frequency is calculated and dynamically corrected to improve response speed and control accuracy.
It effectively improves the response speed of the automatic combustion control system, reduces overshoot, and makes the fan frequency control closer to actual production needs, thereby improving the system's stability and combustion efficiency.
Smart Images

Figure CN121206497A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure belongs to the technical field of automatic incineration, and in particular relates to a fan frequency control method and device, an electronic device, and a computer readable storage medium. BACKGROUND
[0002] ACC (Automatic Combustion Control) is the core technology of the incinerator operation, which is mainly used to realize the automatic and intelligent control of the waste incineration process, ensure the stable combustion, environmental protection and economic operation. The core principle is to monitor and adjust the grate speed, air volume, feeding speed and other parameters in real time to optimize the combustion efficiency.
[0003] The conventional ACC control method establishes a combustion chamber thermodynamic model according to the mass conservation equation and the energy conservation equation, but due to the large variation of garbage components, the mechanism model based on the thermodynamic model is not suitable for actual production conditions. SUMMARY
[0004] To solve the problems in the prior art, the present disclosure provides a fan frequency control method and device, an electronic device and a computer readable storage medium.
[0005] To achieve the above-mentioned purpose, the present disclosure realizes the following technical solutions: The first aspect of the present disclosure provides a fan frequency control method applied to an automatic combustion control system, which comprises: obtaining a parameter sequence value of a control parameter related to a main steam flow in a historical period of the automatic combustion control system, a current flow value of the main steam flow, a flow set value of the main steam flow, a real-time value of a steam drum pressure, a furnace bed layer pressure difference value, and a control variable sequence value related to a furnace bed layer pressure difference height in the historical period; calculating a flow prediction value of the main steam flow based on the parameter sequence value and the current flow value; calculating a flow deviation based on the flow set value and the flow prediction value; calculating an intermediate fan frequency based on the furnace bed layer pressure difference value and the control variable sequence value; calculating a steam drum fan frequency based on the real-time value of the steam drum pressure; obtaining a flow fan frequency based on the flow prediction value; calculating a primary frequency given value based on the intermediate fan frequency, the flow fan frequency and the steam drum fan frequency; dynamically correcting the primary frequency given value based on the flow deviation to obtain a target primary fan frequency of a primary fan and control the primary fan.
[0006] The method further comprises: obtaining a furnace average temperature set value, a temperature parameter related to the furnace temperature in the automatic combustion control system, a current temperature of the furnace, a coal gas parameter related to the oxygen content of the flue gas at the outlet of the economizer in the automatic combustion control system; calculating a furnace average temperature prediction value based on the current temperature and the temperature parameter; calculating a temperature deviation based on the furnace average temperature set value and the furnace average temperature prediction value; calculating a secondary frequency given value based on the gas parameter, the target primary air blower frequency and the furnace average temperature prediction value; dynamically correcting the secondary frequency given value based on the temperature deviation to obtain and adopt a target secondary air blower frequency of the secondary air blower to control the secondary air blower.
[0007] obtaining the flow blower frequency based on the flow prediction value includes: obtaining a flow broken line function representing a corresponding relationship between the main steam flow and the primary air blower frequency; obtaining the flow blower frequency based on the flow prediction value and the flow broken line function.
[0008] calculating the intermediate air blower frequency based on the furnace bed pressure difference value and the control variable sequence value includes: extracting a bed thickness characteristic value based on the control variable sequence value and the furnace bed pressure difference value; obtaining the intermediate air blower frequency based on the bed thickness characteristic value.
[0009] calculating the flow prediction value of the main steam flow based on the parameter sequence value and the flow value includes: constructing a characteristic parameter value based on the parameter sequence value and the flow value; inputting the characteristic parameter value into a pre-trained time series prediction model to obtain the flow prediction value of the main steam flow.
[0010] calculating the primary frequency given value based on the intermediate air blower frequency, the flow blower frequency and the steam drum blower frequency includes: performing weighted summation on the intermediate air blower frequency, the flow blower frequency and the steam drum blower frequency to obtain the primary frequency given value.
[0011] dynamically correcting the primary frequency given value based on the flow deviation to obtain and adopt a target primary air blower frequency of the primary air blower to control the primary air blower includes: inputting the flow deviation and the primary frequency given value into a proportional-integral-derivative controller to obtain a target primary air blower frequency of the primary air blower from an output of the proportional-integral-derivative controller; adopting the target primary air blower frequency to control the primary air blower.
[0012] The second aspect of the present disclosure provides a fan frequency control device applied to an automatic combustion control system, the device comprising: a parameter acquisition unit configured to acquire a parameter sequence value of a control parameter related to a main steam flow in a historical period of the automatic combustion control system, a current flow value of the main steam flow, a flow set value of the main steam flow, a real-time value of a steam drum pressure, a bed pressure difference value, and a control variable sequence value related to a bed pressure difference height in the historical period; a prediction calculation unit configured to calculate a flow prediction value of the main steam flow based on the parameter sequence value and the current flow value; a deviation calculation unit configured to calculate a flow deviation based on the flow set value and the flow prediction value; an intermediate frequency calculation unit configured to calculate an intermediate fan frequency based on the bed pressure difference value and the control variable sequence value; a steam drum frequency calculation unit configured to calculate a steam drum fan frequency based on the real-time value of the steam drum pressure; an obtaining unit configured to obtain a flow fan frequency based on the flow prediction value and a flow broken line function; a given value calculation unit configured to calculate a primary frequency given value based on the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency; and a control unit configured to dynamically correct the primary frequency given value based on the flow deviation to obtain a target primary fan frequency of a primary fan and control the primary fan.
[0013] The third aspect of the present disclosure provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any implementation manner of the first aspect.
[0014] The fourth aspect of the present disclosure provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method described in any implementation manner of the first aspect.
[0015] Compared with the prior art, the present disclosure has the beneficial effects that: based on the parameter sequence value and the current flow value, the flow prediction value of the main steam flow is calculated and input into the control loop of the fan frequency, which can effectively improve the response speed of the automatic combustion control system, and the unnecessary swing output by the automatic combustion control system can be compensated in advance by calculating the flow deviation based on the flow prediction value, thereby solving the overshoot problem caused by the response lag, so that the control of the fan frequency can be more close to the actual production situation. BRIEF DESCRIPTION OF DRAWINGS
[0016] Figure 1 is a flow chart according to an embodiment of the fan frequency control method of the present disclosure; Figure 2 is a structural schematic diagram of the fan frequency control of the present disclosure; Figure 3 is another structural schematic diagram of the extension frequency control of the present disclosure; Figure 4 is a schematic diagram of the flow broken line function in the present disclosure; Figure 5 is a structural schematic diagram of an embodiment of the fan frequency control device of the present disclosure; Figure 6 is a block diagram of an electronic device for implementing the fan frequency control method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0017] The present application will be further described below in connection with specific embodiments. It should be understood that these embodiments are only used to illustrate the present application and not used to limit the scope of the present application. Furthermore, it should be understood that after reading the content taught by the present application, those skilled in the art can make various modifications or changes to the present application, and these equivalent forms also fall within the scope defined by the present application.
[0018] The automatic combustion control system comprises a feeding device, a grate system, a fan system, a slagging machine system, a monitoring device, and a control system comprising a plurality of control modules. The feeding device comprises a material pusher for uniformly and stably feeding the material into the incinerator, and the speed of the material pusher can be adjusted according to the combustion condition. The control system comprises an evaporation amount control module, a garbage layer control module, an in-furnace temperature control module, a slag heat loss rate control module, and an oxygen amount control module. The evaporation amount control module adjusts the combustion process to ensure the stable steam production and meet the process requirements. The grate system comprises dry grates, combustion grates, and afterburning grates located at different sections of different hearths. The running speed and air supply amount of each section are controlled to realize the sectional combustion of the garbage. The fan system comprises a primary fan and a secondary fan. The primary fan supplies air for combustion under the grate, and the secondary fan supplies air for the secondary combustion chamber, and both of them are controlled by frequency conversion.
[0019] In the automatic combustion control system, the garbage truck transports the garbage to the incineration plant, and unloads it into the garbage pool. The garbage in the garbage pool enters the drying chamber through the conveying assembly. The heating pipe in the drying chamber pre-dries the garbage. The garbage layer control module calculates the thickness of the garbage layer by measuring the pressure difference between the garbage on the combustion grate and the air below the combustion grate, and then adjusts the speed of the garbage pusher, the drying grate and the combustion grate to stabilize the thickness of the garbage layer. The garbage in the drying grate is dried by high-temperature combustion air in the furnace, radiation heat from the side wall of the furnace and the top of the furnace, etc. The residence time is about 30 minutes. The dried garbage enters the combustion section for vigorous combustion, and the residence time is about 30 minutes. 60%-80% of the total combustion air is supplied in this section. The fixed carbon and unburned part of the garbage in the burnout section are completely burned, and the residence time is about one hour, which ensures that the ignition loss rate of the slag is reduced to 1%-2%. The primary air fan extracts the air above the garbage pool, heats it through the steam-air preheater, and then sends it to the drying section, the combustion section and the burnout section. The frequency is adjusted and controlled. The secondary air fan extracts the air above the garbage pool, heats it through the steam-air preheater, and then supplies it to the secondary combustion chamber. The frequency is adjusted and controlled. During the garbage combustion process, the temperature in the furnace is controlled within a suitable range by adjusting parameters such as the amount of primary air, the amount of secondary air and the amount of garbage feeding to determine stable garbage combustion. According to the oxygen content in the flue gas measured by the oxygen sensor, PID or fuzzy control is used to adjust the speed of the primary air fan and the secondary air fan, change the amount of primary air and secondary air, and keep the oxygen content in the flue gas at a reasonable level.
[0020] The current automatic combustion control system establishes a combustion chamber thermodynamic model based on the mass conservation equation and the energy conservation equation, uses real-time detection values such as furnace temperature, flue gas oxygen content and steam flow as input variables, and outputs grate movement speed, primary / secondary air fan frequency and other execution instructions through a PID controller. However, the composition of garbage changes greatly, the mechanism model based on thermodynamics is not suitable for actual production conditions, and there is a long lag period from sensor detection to actuator response, resulting in severe control overshoot and large system fluctuation amplitude.
[0021] To overcome the defects in the prior art, the present disclosure provides a fan frequency control method. Figure 1 An embodiment of the fan frequency control method according to the present disclosure is shown in flowchart 100, which comprises the following steps: Step 101, obtaining the parameter sequence value of the control parameter related to the main steam flow, the current flow value of the main steam flow, the flow set value of the main steam flow, the real-time value of the steam drum pressure, the furnace layer pressure difference value and the control variable sequence value related to the height of the furnace layer pressure difference in the historical period of the automatic combustion control system.
[0022] In the embodiment, the historical period is a historical time period of the automatic combustion control system, and a length of the historical period can be set according to development requirements, for example, the historical period is three months; the control parameter is a parameter in the automatic combustion control system that affects the main steam flow, and the control parameter can be a parameter obtained by analyzing through a correlation algorithm such as a Pearson algorithm and a Spearman algorithm, for example, a main steam pressure, a furnace average temperature, an outlet flue gas temperature of a smoke window, and the like, and a parameter sequence value includes at least one value of the control parameter, and the value of the control parameter can be obtained by a sensor, and the parameter sequence value is a serialized representation of the value of the control parameter in the historical period.
[0023] In the embodiment, the parameter sequence value is obtained through the following steps: obtaining a historical parameter set of the automatic combustion control system; calculating a correlation coefficient of the historical parameter set and the main steam flow under different time delays; and determining the parameter sequence value based on the correlation coefficient.
[0024] The calculation of the correlation coefficient of the historical parameter set and the main steam flow under different time delays includes: determining a plurality of time delay times; specifically, the plurality of time delay times are different time delay times, for example, specific times 0S, 5S, 10S, and the like, or can be identified by a number of sampling periods, and one sampling period can be 5S or 10S, and the like. When the time delay times are determined, the interval and the number of time delays are determined, and the plurality of time delay times are a continuous time, for example, every 5S is a time delay time, and when the number of time delays is 20, the entire time delay process is 100S. The time delay time can represent the time at which the change of the parameter of the automatic combustion control system causes a significant change in the to-be-predicted parameter (for example, a flow prediction value of the main steam flow) of the automatic combustion control system. At each time delay time, the correlation coefficient of each historical parameter in the historical parameter set and the main steam flow is calculated, and specifically, the Pearson algorithm or the Spearman algorithm can be used to calculate the correlation coefficient.
[0025] The determination of the parameter sequence value based on the correlation coefficient includes: selecting at least one parameter with the largest correlation coefficient in the automatic combustion control system as the control parameter, and extracting the parameter value of the control parameter in the historical period to obtain the parameter sequence value. In actual calculation, the control parameters related to the main steam flow include: a drum pressure, a temperature before an evaporation pipe left, a main feed water pressure, a temperature before an evaporation pipe right, a main feed water flow, a main steam pressure, a primary desuperheating water flow, a furnace average temperature, a secondary desuperheating water flow, an outlet flue gas temperature of a smoke window right, a coal economizer inlet oxygen concentration, a furnace flue gas temperature left, a furnace flue gas temperature middle, a furnace flue gas temperature right, a furnace outlet flue gas temperature right, a coal economizer outlet flue gas pressure left, a coal economizer outlet flue gas pressure right, a NOx concentration, a furnace outlet flue gas temperature left, a coal economizer outlet oxygen concentration right, a primary frequency given value, and the main steam flow, and the parameter sequence value of these control parameters can be a value obtained by a field sensor.
[0026] In this embodiment, in the optional implementation, the target delay (or prediction step ) is defined as the delay corresponding to the maximum correlation between the control parameter (active change parameter) and the controlled parameter (follow-up parameter). Specifically, it is the response time required for the controlled parameter to reach a steady state after a step change in the control parameter.
[0027] The target delay can be obtained by the step response method or the correlation delay algorithm (cross-correlation method), where the step response method is a mature algorithm and will not be described here. The core of the correlation delay algorithm is as follows: first, determine the multi-step delay time range of the control parameter x and the controlled parameter y, which is the range of the delay step k (k is a non-negative integer, and the multi-step delay time range is usually limited between 0 and 2000, and this non-negative limit is because online prediction can only be based on historical data and cannot use future data). For each delay step k in the multi-step delay time range (each delay step corresponds to a fixed time interval, for example, 5 seconds), the time-aligned control parameter sequence x(t) and the controlled parameter sequence y(t+k) (or equivalent form) need to be constructed. The construction of the sequence is essentially a sliding window process: a new sequence at each delay is obtained by removing the last value of the control parameter and the first value of the controlled parameter in the previous sequence and re-aligning the time points. For example, when k=0, x(t) is aligned with y(t) (no delay), when k=1, x(t) is aligned with y(t+1) (representing a 1-sample interval, i.e. 5 seconds, lag of y value relative to x value), when k=2, x(t) is aligned with y(t+2) (lag of 10 seconds), and so on. Then, calculate the Pearson correlation coefficient ρ(k) of each delay k sequence x(t) and y(t+k), find the maximum value in all |ρ(k)|, and determine the delay k corresponding to the maximum value as the target delay , whose mathematical expression is shown in equation (1): (1); The target delay obtained by this method comprehensively reflects the physical process transmission delay and the response time of the measuring instrument.
[0028] The present embodiment provides a reliable method for obtaining control parameter sequence values (or prediction steps) by calculating correlation coefficients under different time delays and determining the time delay corresponding to the maximum value. In the present embodiment, the current flow value of the main steam flow is directly collected by a sensor, and the flow set value of the main steam flow is a target value set by the user based on historical experience. The flow set value is set according to the actual situation of the combustion process and the furnace. This flow set value is the optimal flow value that the main steam flow is expected to maintain, which can ensure the combustion efficiency and stability.
[0029] In the present embodiment, in the automatic waste combustion system, the real-time value of the drum pressure is usually measured by a pressure sensor or a pressure transmitter installed on the drum of the automatic combustion control system. These sensors convert the pressure signal in the drum into an electrical signal and transmit it to the DCS (Distributed Control System) or other monitoring systems for real-time monitoring and control.
[0030] The measurement position of the real-time value of the drum pressure is generally located on the body of the drum, and the specific position may vary depending on the design of the system, but it is usually selected to accurately reflect the internal pressure of the drum. The measured real-time value of the drum pressure is crucial for the stable operation of the system, as it helps the control system adjust the combustion process to ensure that the main steam pressure remains within the rated operating conditions.
[0031] In the present embodiment, the furnace bed pressure difference value refers to the pressure difference generated on both sides of the bed when the airflow passes through the waste bed in the furnace. It is an important indicator of the resistance of the waste bed to airflow. In a waste incinerator, the size of the bed pressure difference can reflect the accumulation of the waste bed. When the thickness of the waste bed increases, the resistance of the airflow through the bed increases, resulting in an increase in the furnace bed pressure difference. By monitoring the change in the furnace bed pressure difference, the trend of the bed thickness can be determined. For example, if the furnace bed pressure difference increases from the initial 1000 Pa to 1500 Pa, it may mean that the bed thickness is increasing.
[0032] In the present embodiment, the control variable related to the height of the furnace bed pressure difference is a parameter in the automatic waste combustion control system that affects the height of the furnace bed pressure difference. This control variable can be obtained through correlation analysis algorithms such as Pearson's algorithm and Spearman's algorithm, such as primary air fan frequency, secondary air fan frequency, furnace negative pressure, drying furnace primary air damper opening, combustion furnace primary air damper opening, and combustion furnace primary air damper opening. The control variable sequence value includes at least one control variable value, which can be collected by a sensor. The control variable sequence value is a serialized representation of the control variable value at a historical time.
[0033] At step 102, a flow prediction value of the main steam flow is calculated based on the parameter sequence value and the current flow value.
[0034] In this embodiment, the parameter sequence value is a serialized representation of values of control parameters in a historical period, and the control parameters include the main steam flow because the main steam flow has the highest degree of correlation with itself. Arranging the parameter sequence value and the current flow value together and inputting them into the pre-trained time series prediction model can enable the time series prediction model to refer to the control parameters other than the main steam flow in the parameter sequence value to predict a future value of the main steam flow, thereby obtaining the flow prediction value.
[0035] Optionally, the step 102 includes extracting the parameter values of the main steam flow and the control parameters other than the main steam flow from the parameter sequence value, fitting a main steam flow curve based on the parameter value of the main steam flow, fitting a development trend curve based on the parameter values of the control parameters other than the main steam flow, adjusting the main steam flow curve based on the development trend curve to obtain an adjusted curve, and obtaining the flow prediction value of the main steam flow based on the adjusted curve.
[0036] At step 103, a flow deviation is calculated based on the flow set value and the flow prediction value.
[0037] In this embodiment, the flow prediction value and the flow set value can be directly subtracted to obtain the flow deviation, as shown in FIG. 4. Figure 2 The flow prediction value and the flow set value are subtracted to obtain the flow deviation.
[0038] Optionally, the step 103 includes obtaining the parameter value of the main steam flow from the parameter sequence value, determining an upper limit value and a lower limit value of the parameter value of the main steam flow, subtracting the lower limit value from the upper limit value to obtain a limit value difference, multiplying the limit value difference by a preset coefficient to obtain a deviation limit value, subtracting the flow set value from the flow prediction value to obtain a first difference value, detecting whether the first difference value is within the deviation limit value, and taking the first difference value as the flow deviation if the first difference value is within the deviation limit value.
[0039] At step 104, an intermediate fan frequency is calculated based on the hearth bed pressure difference value and a control variable sequence value.
[0040] In this embodiment, the intermediate fan frequency is a frequency value of a frequency of the primary fan reflected by a hearth bed thickness characteristic value. The hearth bed thickness characteristic value can be determined through the hearth bed pressure difference value and the control variable sequence value, and the intermediate fan frequency can be obtained through the hearth bed thickness.
[0041] In this embodiment, the furnace layer pressure difference value and the control variable sequence value are input into the first fan frequency prediction model trained, to obtain the intermediate fan frequency output by the first fan frequency prediction model. The first fan frequency prediction model is a model trained by using samples generated by the automatic combustion control system including the primary fan frequency and the frequency control variable value related to the primary fan frequency. As shown in Figure 2 , the frequency control variable value is calculated by a function F1(x) to obtain the intermediate fan frequency (f1) in Figure 2 , which is not shown in the figure).
[0042] Step 105, based on the real-time value of the steam drum pressure, the steam drum fan frequency is calculated.
[0043] In this embodiment, the steam drum fan frequency is the frequency value of the steam drum pressure reflected on the frequency of the primary fan. Through the real-time value of the steam drum pressure, the steam drum fan frequency can be obtained.
[0044] In this embodiment, the real-time value of the steam drum pressure is input into the second fan frequency prediction model trained, to obtain the steam drum fan frequency output by the second fan frequency prediction model. The second fan frequency prediction model is a model trained by using samples generated by the automatic combustion control system including the primary fan frequency and the steam drum pressure value. As shown in Figure 2 , the real-time value of the steam drum pressure is calculated by a function F2(x) to obtain the steam drum fan frequency (f2) in Figure 2 , which is not marked in the figure).
[0045] Step 106, based on the flow prediction value, the flow fan frequency is obtained.
[0046] In this embodiment, the flow fan frequency is the frequency value of the main steam flow reflected on the frequency of the primary fan. Through the flow prediction value, the flow fan frequency can be obtained.
[0047] In this embodiment, the flow prediction value is input into the third fan frequency prediction model trained, to obtain the flow fan frequency output by the third fan frequency prediction model. The third fan frequency prediction model is a model trained by using samples generated by the automatic combustion control system including the primary fan frequency and the flow value of the main steam flow. As shown in Figure 2 , the flow prediction value of the main steam flow is calculated by a function F3(x) to obtain the flow fan frequency (f3) in Figure 2 , which is not marked in the figure).
[0048] Step 107, based on the intermediate fan frequency, the flow fan frequency and the steam drum fan frequency, the primary frequency given value is calculated.
[0049] In this embodiment, the intermediate fan frequency, the flow fan frequency and the steam drum fan frequency are directly added to obtain the primary frequency given value.
[0050] Step 108, based on the flow deviation, dynamically correct the given value of the primary frequency, obtain and adopt the target primary fan frequency of the primary fan to control the primary fan.
[0051] In this embodiment, the fuzzy logic controller (FLC) can be used to obtain the target speed value of the pusher. The fuzzy logic controller is a control method based on fuzzy logic, which is suitable for processes with strong uncertainty and fuzziness. The following are the specific implementation steps of using the fuzzy logic controller to obtain the target speed value of the pusher: The input variables of the fuzzy logic controller are: flow deviation ΔF; flow deviation rate ΔF', which is the rate of change of flow deviation, i.e. the derivative of ΔF. The output variable: the frequency correction value Δf of the primary fan: the frequency correction value of the primary fan calculated according to the flow deviation and the flow deviation rate.
[0052] The fuzzy logic controller divides the input variables and output variables into fuzzy sets. For example, the flow deviation ΔF can be divided into fuzzy sets such as "negative large" (NB), "negative small" (NS), "zero" (Z), "positive small" (PS), "positive large" (PB), etc. According to experience and expert knowledge, define fuzzy rules. For example: if ΔF is "negative large" and ΔF' is "negative large", then ΔV is "positive large"; if ΔF is "zero" and ΔF' is "zero", then ΔV is "zero"; if ΔF is "positive large" and ΔF' is "positive large", then ΔV is "negative large".
[0053] The fuzzy logic controller calculates the membership degree of the fuzzy set. According to the actual value of the input variable, calculate its membership degree in each fuzzy set. For example, if ΔF = 10 tons / hour, calculate its membership degree in the fuzzy sets "negative large", "negative small", "zero", "positive small", "positive large", etc.
[0054] The fuzzy logic controller determines the fuzzy set of the output variable according to the fuzzy rules and membership degrees. For example, according to the above fuzzy rules, if the membership degree of ΔF is high in "positive large", and the membership degree of ΔF' is high in "positive large", then the membership degree of ΔV is high in "negative large".
[0055] The fuzzy logic controller converts the fuzzy output into a concrete value. Common defuzzification methods include the maximum membership degree method, the barycenter method, etc. For example, the barycenter method is used to calculate the concrete value of ΔV; Δf after defuzzification is added to the primary frequency given value Vinitial to obtain the target primary fan frequency Vtarget, i.e., Vtarget=Vinitial+Δf; the calculated target primary fan frequency Vtarget is taken as a control signal and sent to the driving system of the primary fan, and the driving system of the primary fan adjusts the actual operating frequency of the primary fan according to the received target primary fan frequency.
[0056] The method for controlling the frequency of the fan provided by the embodiments of the present disclosure obtains the parameter sequence value of the control parameter related to the main steam flow in the historical period of the automatic combustion control system, the current flow value of the main steam flow, the flow set value of the main steam flow, the real-time value of the steam drum pressure, the bed pressure difference value, and the control variable sequence value related to the bed pressure difference height in the historical period; based on the parameter sequence value and the current flow value, the flow prediction value of the main steam flow is calculated; based on the flow set value and the flow prediction value, the flow deviation is calculated; based on the bed pressure difference value and the control variable sequence value, the intermediate fan frequency is calculated; based on the real-time value of the steam drum pressure, the steam drum fan frequency is calculated; based on the flow prediction value, the flow fan frequency is obtained; based on the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency, the primary frequency given value is calculated; based on the flow deviation, the primary frequency given value is dynamically corrected to obtain the target primary fan frequency of the primary fan, and the target primary fan frequency of the primary fan is used to control the primary fan; thereby, the flow prediction value of the main steam flow is obtained based on the parameter sequence value and the current flow value, and the flow prediction value is input into the control loop of the fan frequency, which can effectively improve the response speed of the automatic combustion control system, and the flow deviation calculated based on the flow prediction value can compensate for unnecessary swings of the output of the automatic combustion control system in advance, thereby solving the overshoot problem caused by the response lag, so that the control of the fan frequency can be more close to the actual production situation.
[0057] Optionally, the above-mentioned fan frequency control method further comprises: obtaining the material layer image of the combustion grate by using a camera (such as an infrared thermal imager), pre-processing, hole filling processing and edge detection on the collected material layer image, extracting the edge contour of the garbage pile area, then using the size of the furnace pushing platform, the resolution and the field of view angle of the camera to convert the actual size of a single pixel, and finally processing the obtained garbage pile edge contour image according to the pixel size to obtain the actual thickness of the material layer of the combustion grate; calculating the additional fan frequency based on the actual thickness of the material layer; and the calculation of the primary frequency given value based on the intermediate fan frequency, the flow fan frequency and the steam drum fan frequency comprises: weighting and summing the intermediate fan frequency, the flow fan frequency, the steam drum fan frequency and the additional fan frequency to obtain the primary frequency given value. In this embodiment, the computer vision algorithm is used to extract the actual thickness of the material layer of the combustion grate as a participating factor of the primary frequency given value, so that the target primary fan frequency can be adjusted specifically, and the accuracy of the target primary fan frequency of the primary fan is improved.
[0058] In some optional implementations of the present disclosure, the above-mentioned fan frequency control method further comprises: obtaining a furnace average temperature set value, a temperature parameter related to the furnace temperature which is predetermined in the automatic combustion control system, a current temperature of the furnace, a coal gas parameter related to the oxygen content of the flue gas at the outlet of the economizer which is predetermined in the automatic combustion control system; calculating a furnace average temperature prediction value based on the current temperature and the temperature parameter; calculating a temperature deviation based on the furnace average temperature set value and the furnace average temperature prediction value; calculating a secondary frequency given value based on the coal gas parameter, the target primary fan frequency and the furnace average temperature prediction value; and dynamically correcting the secondary frequency given value based on the temperature deviation to obtain and use the target secondary fan frequency of the secondary fan to control the secondary fan.
[0059] In this embodiment, the temperature parameter is collected by a related sensor, and the temperature parameter comprises: left furnace flue gas temperature, right outlet smoke window flue gas temperature, right furnace outlet flue gas temperature, right furnace flue gas temperature, middle furnace flue gas temperature, left furnace outlet flue gas temperature, middle furnace outlet flue gas temperature, right economizer outlet oxygen concentration, steam drum pressure, superheated steam flow, economizer inlet oxygen concentration, primary fan current, primary air pressure, secondary air frequency, secondary air flow, left economizer outlet oxygen concentration, left outlet smoke window flue gas temperature, primary fan frequency, right pre-evaporation tube temperature, left pre-evaporation tube temperature, primary air flow, secondary air pressure, combustion grate II primary air volume B, material layer pressure difference B, material layer pressure difference A, and furnace average temperature.
[0060] In this embodiment, the prediction step of calculating the furnace average temperature prediction value based on the current temperature and the temperature parameter is as follows: the above-mentioned temperature parameter and current temperature are collected every 5 seconds, and 200 (1000 seconds) need to be collected to form a 200 26, the input variables are collected every 5 seconds to fill the last row of the input matrix and delete the first row (the oldest row) at the same time, so that the input matrix always maintains the size of 26x200 26, and the next cycle of inference is performed, and the cycle is repeated.
[0061] In this embodiment, the gas parameters are collected by related sensors, and the gas parameters include: right outlet economizer oxygen concentration, left outlet economizer oxygen concentration, right outlet flue gas temperature, right furnace flue gas temperature, middle furnace flue gas temperature, drum pressure, left outlet flue gas temperature, average furnace temperature, left outlet flue gas temperature, superheated steam flow, outlet economizer water temperature, left outlet flue gas temperature, low-temperature superheater outlet steam temperature, right outlet flue gas temperature, medium-temperature superheater outlet steam temperature, main steam pressure, and inlet economizer oxygen concentration.
[0062] In this embodiment, the outlet economizer flue gas oxygen content prediction value can be obtained based on the gas parameters related to the outlet economizer flue gas oxygen content. Figure 3 The outlet economizer flue gas oxygen content prediction value is shown in the figure, and the prediction process of the outlet economizer flue gas oxygen content prediction value is similar to the prediction steps of the average furnace temperature prediction value, which will not be described here.
[0063] In this embodiment, the calculation of the secondary frequency given value based on the gas parameters, the target primary air fan frequency, and the average furnace temperature prediction value includes: obtaining the outlet economizer flue gas oxygen content prediction value based on the gas parameters; obtaining the first secondary air fan frequency through the outlet economizer flue gas oxygen content prediction value and the first fold line function F1'(x) representing the corresponding relationship between the secondary air fan frequency and the outlet economizer flue gas oxygen content; obtaining the second secondary air fan frequency based on the target primary air fan frequency and the second fold line function F2'(x) representing the corresponding relationship between the primary air fan frequency and the secondary air fan frequency; obtaining the third secondary air fan frequency based on the average furnace temperature prediction value and the third fold line function F3'(x) representing the corresponding relationship between the secondary air fan frequency and the average temperature; and obtaining the secondary frequency given value by weighted sum of the first secondary air fan frequency, the second secondary air fan frequency, and the third secondary air fan frequency.
[0064] In the embodiment, the secondary fan frequency is dynamically corrected based on the temperature deviation and the secondary fan frequency set value to obtain the target secondary fan frequency, and the target secondary fan frequency is used to control the secondary fan.
[0065] In the optional implementation, the PID controller adopts a PID closed-loop control architecture, as shown in the figure, and the temperature deviation between the furnace average temperature set value and the furnace average temperature prediction value is used as the control input, and the secondary fan frequency set value is dynamically corrected and limited by the adjustment mechanism of the PID controller to obtain the target secondary fan frequency. Figure 3
[0066] The fan frequency control method provided in the embodiment is based on the target primary fan frequency obtained by controlling the primary fan, and the target secondary fan frequency is calculated based on the obtained furnace average temperature set value, the temperature parameter related to the furnace temperature in the automatic combustion control system, the current temperature of the furnace, and the coal gas parameter related to the oxygen content of the flue gas at the outlet of the economizer in the automatic combustion control system. The target secondary fan frequency is used to control the secondary fan, thereby providing a reliable implementation for the control of the secondary fan.
[0067] In some optional implementations of the present disclosure, the flow fan frequency is obtained based on the flow prediction value, including: obtaining a flow broken line function representing the corresponding relationship between the main steam flow and the primary fan frequency; and obtaining the flow fan frequency based on the flow prediction value and the flow broken line function.
[0068] The method for obtaining the flow fan frequency provided in the optional implementation includes: obtaining a flow broken line function representing the corresponding relationship between the main steam flow and the primary fan frequency; and obtaining the flow fan frequency based on the flow prediction value and the flow broken line function, thereby providing a reliable implementation for obtaining the flow fan frequency.
[0069] In some optional implementations of the present disclosure, the intermediate fan frequency is calculated based on the furnace bed pressure difference value and the control variable sequence value, including: extracting a bed thickness characteristic value based on the control variable sequence value and the furnace bed pressure difference value; and obtaining the intermediate fan frequency based on the bed thickness characteristic value.
[0070] In the optional implementation, the extracting the bed thickness feature value based on the control variable sequence value and the hearth bed pressure difference value comprises: clustering the control variable sequence value by using a clustering algorithm to obtain clustering data; extracting a sub-variable value belonging to the moderate bed type from the clustering data; inputting the sub-variable value into a pre-trained long short-term memory neural network to obtain a predicted bed pressure difference value output by the long short-term memory neural network; and obtaining the bed thickness feature value by subtracting the predicted bed pressure difference value from the hearth bed pressure difference value.
[0071] In the optional implementation, in the garbage automatic combustion control system, the thickness of the garbage in the hearth needs to be controlled in a proper range: if the thickness of the garbage is too thick, the primary air cannot blow through the garbage bed, which affects the garbage drying effect and causes the garbage in the hearth to be difficult to ignite; if the thickness of the garbage is too thin, the fuel in the hearth is insufficient, and a small amount of garbage is quickly burned out, which is difficult to maintain a proper furnace temperature for a long time. Since there is no sensor for directly measuring the thickness of the garbage bed in the hearth, only the hearth bed pressure difference can be measured, and there is one pressure measuring point on the upper part of the garbage bed and the lower air chamber of the garbage bed in the hearth, respectively. The bed thickness is indirectly reflected by calculating the hearth bed pressure difference value of the upper and lower sides of the garbage bed.
[0072] In the optional implementation, the bed pressure difference is simultaneously affected by two key factors, i.e., the bed thickness and the real-time flow value of the primary air. The greater the real-time flow value of the primary air, the greater the hearth bed pressure difference value, and the thicker the hearth bed, the greater the bed pressure difference value. Therefore, the bed thickness cannot be directly reflected by the hearth bed pressure difference value, and the bed thickness feature extraction model needs to exclude the influence of the real-time flow value of the primary air from the bed pressure difference, and adjust the pusher speed and the furnace grate cycle of each section based on the extracted bed thickness feature.
[0073] In the optional implementation, the clustering the control variable sequence value by using a clustering algorithm to obtain clustering data comprises: dividing the control variable sequence value into three categories by using a K-means clustering algorithm. Specifically, the corresponding relationship between the primary air fan frequency and the hearth bed pressure difference value is observed by drawing a scatter plot, and the control variable sequence value is divided into three categories, i.e., a too thick bed, a too thin bed, and a moderate bed.
[0074] In the optional implementation, the extracting a sub-variable value belonging to the moderate bed type from the clustering data comprises: picking out the data of the moderate bed, performing data preprocessing (data cleaning and missing value filling) to obtain the sub-variable value.
[0075] In the optional implementation, the pre-trained long short-term memory neural network is a model for predicting the furnace bed pressure difference value (i.e., predicting the bed pressure difference value), and the bed thickness characteristic value can be obtained through the predicted bed pressure difference value. Specifically, the input variables of the long short-term memory neural network are: primary air fan frequency, secondary air frequency, left furnace negative pressure, right furnace negative pressure, drying grate I primary air door A opening degree, drying grate I primary air door B opening degree, drying grate I primary air door C opening degree, combustion grate I primary air door A opening degree, combustion grate I primary air door B opening degree, combustion grate I primary air door C opening degree, combustion grate II primary air door A opening degree, combustion grate II primary air door B opening degree, combustion grate II primary air door C opening degree, combustion grate III primary air door A opening degree, combustion grate III primary air door B opening degree, combustion grate III primary air door C opening degree, burnout grate I primary air door A opening degree, burnout grate I primary air door B opening degree, burnout grate I primary air door C opening degree, burnout grate II primary air door A opening degree, burnout grate II primary air door B opening degree, and burnout grate II primary air door C opening degree. The output variable of the long short-term memory neural network is: the predicted bed pressure difference value, and the output of the long short-term memory neural network is considered to be the predicted bed pressure difference value corresponding to the current air volume under the condition that the bed thickness is moderate from the process principle.
[0076] In the optional implementation, the furnace bed pressure difference value is the actual bed pressure difference value, and the bed thickness characteristic value = furnace bed pressure difference value - long short-term memory neural network output variable (furnace bed pressure difference value corresponding to the current air volume under the condition that the bed thickness is moderate); when the actual bed pressure difference is inconsistent with the bed pressure difference under the condition that the bed thickness is moderate output by the long short-term memory neural network, it can be considered that the bed thickness is thick or thin, and the difference between the two reflects the degree of thick or thin bed.
[0077] In the optional implementation, based on the bed thickness characteristic value, the intermediate air fan frequency is obtained by: obtaining a thickness broken line function representing the corresponding relationship between the bed thickness characteristic value and the garbage pusher speed; and obtaining the intermediate air fan frequency based on the bed thickness characteristic value and the thickness broken line function.
[0078] In the optional implementation, the thickness broken line function is a broken line function of the linear relationship between the input variable and the output variable established through big data technology, such as Figure 2The process of obtaining the thickness piecewise linear function is as follows: Collect the characteristic values of the material layer thickness and the frequency of the primary blower during historical periods. Set the material layer thickness characteristic values and the primary blower frequency as a correspondence with a target delay. Under this correspondence, mark the points corresponding to the material layer thickness characteristic values and the primary blower frequency (each point represents a correspondence between a material layer thickness characteristic value and the primary blower frequency). Based on the distribution of all points, select a suitable function form for fitting. For example, a linear function, a polynomial function, an exponential function, etc., can be selected to obtain the thickness piecewise linear function. The calculation method of the target delay is the same as that described in the above embodiment, only the dataset (this dataset is a dataset formed by the material layer thickness characteristic values and the primary blower frequency) is different, which will not be repeated here. The calculation method of the material layer thickness characteristic values has been explained in the above embodiment and will not be repeated here.
[0079] In this optional implementation, obtaining the second pusher speed value based on the material layer thickness characteristic value and the thickness polygonal function includes: plotting the thickness polygonal function on a two-dimensional coordinate system, wherein the horizontal axis and vertical axis of the two-dimensional coordinate system represent the material layer thickness characteristic value and the primary fan frequency, respectively; finding the material layer thickness characteristic value on the horizontal axis; and finding the primary fan frequency that corresponds to both the thickness polygonal function and the material layer thickness characteristic value on the vertical axis, thereby obtaining the intermediate fan frequency.
[0080] Optionally, obtaining the second pusher speed value based on the material layer thickness characteristic value and the thickness polygonal function includes: obtaining the polygonal function expression based on the thickness polygonal function; and substituting the flow prediction value into the polygonal function expression to obtain the intermediate fan frequency.
[0081] The optional implementation provides a method for obtaining the intermediate fan frequency by extracting the material layer thickness feature value based on the control variable sequence value and the furnace material layer pressure difference value; and obtaining the intermediate fan frequency based on the material layer thickness feature value, thus providing a reliable implementation method for obtaining the intermediate fan frequency.
[0082] In some optional implementations of this disclosure, the above-mentioned calculation of the main steam flow rate prediction value based on parameter sequence values and flow rate values includes: constructing feature parameter values based on parameter sequence values and flow rate values; and inputting the feature parameter values into a pre-trained time series prediction model to obtain the main steam flow rate prediction value.
[0083] Optionally, the step 102 comprises: constructing a feature parameter value based on the parameter sequence value and the current flow value; inputting the feature parameter value into the pre-trained main steam flow prediction model to obtain a flow prediction value output by the main steam flow prediction model. The constructing of the feature parameter value based on the parameter sequence value and the current flow value comprises: extracting parameter values other than the main steam flow in the parameter sequence value as input features; extracting the parameter value of the main steam flow in the parameter sequence value and the current flow value as target variables or output features; and combining the input features and the target variables or output features into an input feature matrix. Assuming that there are three control parameters (pusher speed, secondary air volume, and garbage feeding rate) and the time step is 10, the shape of the input feature matrix of each sample is (10, 4), where 4 represents three control parameters and one flow value.
[0084] For each control parameter in the parameter sequence value, the control parameter is collected every 5 seconds, and 200 (1000 seconds) are collected to form a 200 22-dimensional input feature matrix, which is input into the main steam flow prediction model. The main steam flow prediction model outputs a one-dimensional array with a length of 33, and the first element of the array is the prediction value after 5 seconds, and the 33rd element is the flow prediction value after 165 seconds. Then, the input variables are collected every 5 seconds and filled into the last row of the input matrix, and the first row (the oldest row) is deleted at the same time, so that the input matrix always maintains a size of 200 22, and the next cycle of reasoning is performed, and the cycle is repeated.
[0085] In this embodiment, the main steam flow prediction model can use a long short-term memory network (LSTM). LSTM is a special recurrent neural network that can learn long-term dependencies. It controls the flow of information through a gating mechanism, avoiding the gradient disappearance problem of traditional recurrent neural networks. The LSTM model includes an input layer, an LSTM layer, a fully connected layer, and an output layer. The LSTM layer includes an input gate, a forget gate, and an output gate, each of which controls the inflow and outflow of information. LSTM is suitable for time series data that needs to learn long-term dependencies.
[0086] The method for calculating the flow prediction value of the main steam flow provided by the optional implementation manner predicts the feature parameter value formed by the control parameter sequence and the current flow value through the main steam flow prediction model, to obtain the flow prediction value, thereby improving the reliability and accuracy of the flow prediction value.
[0087] In some optional implementations of the present disclosure, the calculation of the primary frequency set value based on the intermediate fan frequency, the flow fan frequency and the drum fan frequency comprises: weighted sum of the intermediate fan frequency, the flow fan frequency and the drum fan frequency to obtain the primary frequency set value.
[0088] In the optional implementation, the weight values of the intermediate fan frequency, the flow fan frequency and the drum fan frequency in the weighted sum can be set according to the development requirements.
[0089] In the optional implementation, the weighted sum of the intermediate fan frequency, the flow fan frequency and the drum fan frequency to obtain the primary frequency set value provides a reliable implementation for obtaining the frequency set value of the primary fan.
[0090] In some optional implementations of the present disclosure, the dynamic correction of the primary frequency set value based on the flow deviation to obtain and adopt the target primary fan frequency of the primary fan comprises: inputting the flow deviation and the primary frequency set value into a proportional-integral-derivative controller to obtain the primary fan frequency of the primary fan output by the proportional-integral-derivative controller; and adopting the target primary fan frequency to control the primary fan.
[0091] In the optional implementation, the proportional-integral-derivative controller adopts a PID closed-loop control architecture, as shown in FIG. 2, wherein the flow deviation between the main steam flow set value and the flow prediction value is taken as the control input, and the primary frequency set value is dynamically corrected by the adjustment mechanism of the proportional-integral-derivative controller to obtain the target primary fan frequency of the primary fan. Figure 2
[0092] In the optional implementation, the control principle of the proportional-integral-derivative controller is as formula (2) to obtain the target pusher speed value Y(s).
[0093] (2); In formula (2), FF(s) is the frequency reference value, that is, the primary frequency set value, E(s) is the flow deviation, K p is the proportional coefficient, which is used to determine the amplification multiple of the error signal by the controller; T i is the integral time constant, which is used to integrate the error signal to eliminate the steady-state error of the system; T d is the derivative time constant, S is the complex frequency operator in Laplace domain, which represents the mathematical symbol of “derivative / complex frequency”; K d is the derivative gain, which is used to adjust the strength of the derivative control.
[0094] The method for obtaining the target speed value of the pusher provided by the optional implementation mode inputs the flow deviation and the given value of the primary frequency into the proportional-integral-derivative controller to obtain the target primary fan frequency output by the proportional-integral-derivative controller, which is simple and convenient.
[0095] Optionally, before the speed of the pusher is controlled by using the target speed value of the pusher, the fan frequency control method further includes limiting the amplitude and speed of the target primary fan frequency.
[0096] Further referring to Figure 5 , as an implementation of the method shown in the above figures, the disclosure provides an embodiment of a fan frequency control device, which corresponds to the method embodiment shown in Figure 1 , and the device can be specifically applied to various electronic devices.
[0097] As shown in Figure 5 , the fan frequency control device 500 provided by the embodiment includes a parameter acquisition unit 501, a prediction value calculation unit 502, a deviation calculation unit 503, an intermediate frequency calculation unit 504, a drum frequency calculation unit 505, an obtaining unit 506, a given value calculation unit 507, and a control unit 508. The parameter acquisition unit 501 can be configured to acquire the parameter sequence value of the control parameter related to the main steam flow in the historical period of the automatic combustion control system, the current flow value of the main steam flow, the flow set value of the main steam flow, the real-time value of the drum pressure, the bed pressure difference value, and the control variable sequence value related to the bed pressure difference height in the historical period. The prediction calculation unit 502 can be configured to calculate the flow prediction value of the main steam flow based on the parameter sequence value and the current flow value. The deviation calculation unit 503 can be configured to calculate the flow deviation based on the flow set value and the flow prediction value. The intermediate frequency calculation unit 504 can be configured to calculate the intermediate fan frequency based on the bed pressure difference value and the control variable sequence value. The drum frequency calculation unit 505 can be configured to calculate the drum fan frequency based on the real-time value of the drum pressure. The obtaining unit 506 can be configured to obtain the flow fan frequency based on the flow prediction value and the flow broken line function. The given value calculation unit 507 can be configured to calculate the primary frequency given value based on the intermediate fan frequency, the flow fan frequency, and the drum fan frequency. The control unit 508 can be configured to dynamically correct the primary frequency given value based on the flow deviation to obtain and use the target primary fan frequency of the primary fan to control the primary fan.
[0098] In this embodiment, the wind turbine frequency control device 500 includes: parameter acquisition unit 501, predicted value calculation unit 502, deviation calculation unit 503, intermediate frequency calculation unit 504, steam drum frequency calculation unit 505, obtaining unit 506, setpoint calculation unit 507, and control unit 508. The specific processing and technical effects of these components can be found in the following references: Figure 1 The relevant descriptions of steps 101, 102, 103, 104, 105, 106, 107, and 108 in the corresponding embodiments will not be repeated here.
[0099] In some embodiments of this disclosure, the aforementioned fan frequency control device 500 further includes a secondary fan control unit (not shown in the figure), which is configured to: acquire a furnace average temperature setpoint, temperature parameters related to the furnace temperature predetermined in the automatic combustion control system, the current furnace temperature, and gas parameters related to the oxygen content of the economizer outlet flue gas predetermined in the automatic combustion control system; calculate a predicted furnace average temperature based on the current temperature and temperature parameters; calculate a temperature deviation based on the furnace average temperature setpoint and the predicted furnace average temperature; calculate a secondary frequency setpoint based on the gas parameters, the target primary fan frequency, and the predicted furnace average temperature; and dynamically correct the secondary frequency setpoint based on the temperature deviation to obtain and use the target secondary fan frequency to control the secondary fan.
[0100] In some embodiments of this disclosure, the obtaining unit 506 is configured to: acquire a flow rate piecewise linear function characterizing the relationship between the main steam flow rate and the primary blower frequency; and obtain the flow rate blower frequency based on the predicted flow rate and the flow rate piecewise linear function.
[0101] In some embodiments of this disclosure, the aforementioned intermediate frequency calculation unit 504 is configured to: extract material layer thickness feature values based on the control variable sequence values and the furnace material layer pressure difference values; and obtain the intermediate fan frequency based on the material layer thickness feature values.
[0102] In some embodiments of this disclosure, the prediction calculation unit 502 is configured to: construct feature parameter values based on parameter sequence values and flow rate values; input the feature parameter values into a pre-trained time series prediction model to obtain the flow rate prediction value of the main steam flow.
[0103] In some embodiments of this disclosure, the given value calculation unit 507 is configured to: perform a weighted summation of the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency to obtain a primary frequency given value.
[0104] In some embodiments of the present disclosure, the control unit 508 is configured to input the flow deviation and the primary frequency given value into a proportional-integral-derivative controller to obtain a target primary fan frequency of the primary fan from an output of the proportional-integral-derivative controller, and control the primary fan by using the target primary fan frequency.
[0105] The fan frequency control device provided by the embodiments of the present disclosure, the parameter acquisition unit 501 can be configured to acquire a parameter sequence value of a control parameter related to the main steam flow in a historical period of the automatic combustion control system, a current flow value of the main steam flow, a flow set value of the main steam flow, a real-time value of the drum pressure, a bed pressure difference value, and a control variable sequence value related to a bed pressure difference height in the historical period. The prediction calculation unit 502 can be configured to calculate a flow prediction value of the main steam flow based on the parameter sequence value and the current flow value. The deviation calculation unit 503 can be configured to calculate a flow deviation based on the flow set value and the flow prediction value. The intermediate frequency calculation unit 504 can be configured to calculate an intermediate fan frequency based on the bed pressure difference value and the control variable sequence value. The drum frequency calculation unit 505 can be configured to calculate a drum fan frequency based on the real-time value of the drum pressure. The obtaining unit 506 can be configured to obtain a flow fan frequency based on the flow prediction value and a flow broken line function. The given value calculation unit 507 can be configured to calculate a primary frequency given value based on the intermediate fan frequency, the flow fan frequency, and the drum fan frequency. The control unit 508 can be configured to dynamically correct the primary frequency given value based on the flow deviation to obtain a target primary fan frequency of the primary fan and control the primary fan by using the target primary fan frequency. Thus, the flow of the main steam flow is predicted based on the parameter sequence value and the current flow value, and the obtained flow prediction value is input into a control loop of the fan frequency, which can effectively improve the response speed of the automatic combustion control system. The flow deviation is calculated based on the flow prediction value, which can compensate for unnecessary swings output by the automatic combustion control system in advance, thereby solving the overshoot problem caused by response lag, and making the control of the fan frequency more close to the actual production situation.
[0106] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.
[0107] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their patterns are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0108] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0109] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0110] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the fan frequency control method. For example, in some embodiments, the fan frequency control method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the computing unit 601, one or more steps of the fan frequency control method described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the fan frequency control method by any other suitable means, such as by means of firmware.
[0111] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
[0112] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable computing apparatus to produce a machine, such that the program code, when executed by the processor or controller, implements the methods / operations specified in the flow charts and / or block diagrams. The program code can execute entirely on a machine, partly on a machine, as a stand-alone software package, partly on a machine and partly on a remote machine or entirely on a remote machine or server.
[0113] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a lined- up electrical connection, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0114] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
[0115] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.
[0116] It should be understood that various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the spirit of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without departing from the desired results of the technology disclosed in the present disclosure, which are not limited herein.
[0117] The foregoing description of specific exemplary embodiments of the disclosure has been presented for the purposes of illustration and explanation. It is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. It is intended that the embodiments be chosen and / or described such that the disclosure is practical and sufficient for one skilled in the art to practice and utilize the disclosure, as well as to customize the disclosure for various uses and conditions. The scope of the disclosure is intended to be limited only by the claims and their equivalents.
Claims
1. A method of fan frequency control for use in an automatic combustion control system, comprising: The method includes: The automatic combustion control system acquires the parameter sequence values of control parameters related to the main steam flow rate during historical periods, the current flow rate value of the main steam flow rate, the flow rate setpoint value of the main steam flow rate, the real-time value of the steam drum pressure, the furnace material layer pressure difference value, and the sequence values of control variables highly related to the furnace material layer pressure difference during historical periods. Based on the parameter sequence values and the current flow rate value, calculate the predicted flow rate of the main steam flow rate; Calculate the flow deviation based on the process setpoint and the flow prediction value; The intermediate fan frequency is calculated based on the furnace charge pressure difference value and the control variable sequence value. Calculate the frequency of the steam drum fan based on the real-time value of the steam drum pressure; Based on the predicted flow rate, the flow rate fan frequency is obtained; Calculate a frequency setpoint based on the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency; Based on the flow deviation, the primary frequency setpoint is dynamically corrected to obtain and use the target primary fan frequency to control the primary fan.
2. The method of claim 1, wherein, The method further includes: The system acquires the average furnace temperature setpoint, temperature parameters related to the furnace temperature that are predetermined in the automatic combustion control system, the current furnace temperature, and gas parameters related to the oxygen content of the economizer outlet flue gas that are predetermined in the automatic combustion control system. Based on the current temperature and the temperature parameters, calculate the predicted average furnace temperature; The temperature deviation is calculated based on the furnace average temperature setpoint and the furnace average temperature predicted value. Based on the gas parameters, the target primary air fan frequency, and the predicted average furnace temperature, the secondary frequency setpoint is calculated. Based on the temperature deviation, the secondary frequency setpoint is dynamically corrected to obtain and use the target secondary fan frequency to control the secondary fan.
3. The method according to claim 1 or 2, characterized in that, The process of obtaining the flow rate fan frequency based on the predicted flow rate includes: Obtain a piecewise linear function representing the relationship between main steam flow rate and primary air fan frequency; Based on the predicted flow rate and the flow rate piecewise linear function, the flow rate fan frequency is obtained.
4. The method according to claim 1 or 2, characterized in that, The calculation of the intermediate blower frequency based on the furnace charge pressure difference value and the control variable sequence value includes: Based on the control variable sequence values and the furnace material layer pressure difference values, the material layer thickness characteristic value is extracted; The intermediate fan frequency is obtained based on the material layer thickness characteristic value.
5. The method according to claim 1 or 2, characterized in that, The step of calculating the predicted flow rate of the main steam flow rate based on the parameter sequence value and the flow rate value includes: Based on the parameter sequence values and the flow rate values, feature parameter values are constructed; The feature parameter values are input into a pre-trained time series prediction model to obtain the predicted flow rate of the main steam flow.
6. The method of claim 1 or 2, wherein, The calculation of the frequency setpoint based on the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency includes: The intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency are weighted and summed to obtain a primary frequency setpoint.
7. The method according to claim 1 or 2, characterized in that, The step of dynamically correcting the primary frequency setpoint based on the flow deviation to obtain and use the target primary fan frequency to control the primary fan includes: inputting the flow deviation and the primary frequency given value into a proportional-integral-derivative controller to obtain a target primary fan frequency of the primary fan from an output of the proportional-integral-derivative controller; controlling the primary fan by using the target primary fan frequency. 8.A fan frequency control device applied to an automatic combustion control system, the device comprising: a parameter acquisition unit configured to acquire a parameter sequence value of a control parameter related to a main steam flow in a historical period of the automatic combustion control system, a current flow value of the main steam flow, a flow set value of the main steam flow, a real-time value of a steam drum pressure, a bed pressure difference value, and a control variable sequence value related to a bed pressure difference height in the historical period; a prediction calculation unit configured to calculate a flow prediction value of the main steam flow based on the parameter sequence value and the current flow value; a deviation calculation unit configured to calculate a flow deviation based on the flow set value and the flow prediction value; an intermediate frequency calculation unit configured to calculate an intermediate fan frequency based on the bed pressure difference value and the control variable sequence value; a steam drum frequency calculation unit configured to calculate a steam drum fan frequency based on the real-time value of the steam drum pressure; an obtaining unit configured to obtain a flow fan frequency based on the flow prediction value and a flow broken line function; a given value calculation unit configured to calculate a primary frequency given value based on the intermediate fan frequency, the flow fan frequency, and the steam drum fan frequency; a control unit configured to dynamically correct the primary frequency given value based on the flow deviation to obtain a target primary fan frequency of a primary fan and control the primary fan by using the target primary fan frequency.
9. An electronic device, comprising: comprise: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-7.
Citation Information
Patent Citations
Method for controlling combustion process of circulating fluidized bed boiler on basis of multivariable generalized predictive control optimization
CN105240846A
Grate furnace feeding control method based on material layer thickness big data prediction
CN114659121A
Method and system for automatically controlling primary air volume of circulating fluidized bed boiler
CN118729317A
Method and system for controlling combustion-supporting air of garbage incinerator based on ACC + AI
CN118836453A
Power plant gas-fired boiler control method based on machine learning model prediction
CN118980087A
Cited By
Fire grate period control method and device, electronic equipment and computer storage medium
CN121900252A
Air volume self-adaptive adjustment control method for smoke exhaust system
CN122041598A
