Cement kiln thermal diagnostic analysis method and system based on heat balance calculation

Abstract

The invention discloses a cement kiln thermotechnical diagnosis analysis method and system based on heat balance calculation, and relates to the field of cement kiln thermotechnical diagnos.The analysis method comprises the steps that a corresponding heat balance state is calculated by obtaining cement kiln thermotechnical parameters and material component data, the material balance relation between the material input quantity and the material output quantity of the cement kiln is analyzed; evaluating the energy utilization efficiency of the cement kiln firing system by taking the ratio of the cement kiln clinker formation heat to the input total heat as a thermal efficiency index, and generating a diagnostic index by combining a thermal balance state and a material balance relationship; and comparing the diagnosis index with a historical operation optimal value to determine a deviation condition, evaluating heat loss abnormity and an operation state of the cement kiln thermotechnical engineering according to the deviation condition, constructing a causal atlas to predict a development trend of the cement kiln thermotechnical engineering, and obtaining a cement kiln combustion control result. The method can help to understand how each factor affects the overall performance of the thermal system, and facilitates the optimization and adjustment of different parameters according to the causal relationship in the later stage.

Description

Technical Field

[0001] The present invention relates to the field of cement kiln thermal diagnosis, and in particular to a cement kiln thermal diagnosis and analysis method and system based on heat balance calculation. Background Art

[0002] Cement kiln thermal engineering refers to the application of thermal technologies such as heat energy utilization, heat exchange and heat loss in the cement production process. As one of the core equipment in cement production, the operating status of the thermal system of the cement kiln directly affects energy consumption, production efficiency, environmental emissions and product quality. The thermal system of the cement kiln mainly includes the combustion system, heat recovery system, kiln body and cooling system.

[0003] Traditional cement kiln thermal calibration is primarily manual, a process that takes up to 72 hours and requires frequent manual data collection. Data aggregation and analysis rely on manual operations, resulting in poor timeliness and prone to errors. Furthermore, this historical data-based calculation method cannot provide real-time feedback on the system's true status, making it difficult to meet the demands of modern cement production for efficient and precise control.

[0004] However, in the existing technology, during the thermal diagnosis process, it is impossible to predict the thermal development trend of the cement kiln in the future based on the thermal diagnosis results, making it impossible to adjust the thermal status of the cement kiln before the problem actually occurs, thereby reducing the production efficiency, product quality and environmental protection level of the cement kiln.

[0005] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0006] In response to the problems in the related art, the present invention proposes a cement kiln thermal diagnosis and analysis method and system based on heat balance calculation to overcome the above technical problems existing in the existing related art.

[0007] To this end, the specific technical solutions adopted in the present invention are as follows:

[0008] In a first aspect, the present invention proposes a cement kiln thermal diagnostic analysis method based on heat balance calculation, the analysis method comprising:

[0009] Obtain the thermal equilibrium state corresponding to the calculation of cement kiln thermal parameters and material composition data, and analyze the material balance relationship between the cement kiln material input and material output based on the law of conservation of mass;

[0010] The ratio of the heat of cement kiln clinker formation to the total heat input is used as a thermal efficiency indicator to evaluate the energy utilization efficiency of the cement kiln firing system. The diagnostic index is generated by combining the thermal balance state with the material balance relationship.

[0011] Compare diagnostic indicators with historical optimal operating values ​​to determine deviations, evaluate heat loss anomalies and operating status of the cement kiln thermal system based on the deviations, and construct a cause-and-effect diagram of the cement kiln thermal system operation;

[0012] The development trend of cement kiln thermal engineering is predicted based on the operation cause-effect diagram and target constraints. A dynamic tuning model is constructed in combination with model predictive control technology to obtain the adaptive combustion control results of the cement kiln.

[0013] Preferably, the diagnostic indicators are compared with the historical optimal operating values ​​to determine the deviation, and the heat loss anomaly and operating status of the cement kiln thermal system are evaluated based on the deviation, and a cause-effect diagram of the cement kiln thermal system operation is constructed, including:

[0014] Determine the historical operation optimal value and optimal operation state based on historical operation data, calculate the deviation between the diagnostic indicator and the historical operation optimal value, select the diagnostic indicator with a deviation value greater than the deviation threshold, and obtain the corresponding abnormal evaluation variable candidate set;

[0015] Correlation analysis and support vector description technology are used to detect anomaly in the candidate set of abnormal evaluation variables, and the heat loss anomaly of the cement kiln thermal system is evaluated based on the detection results and enhanced local linear embedding technology;

[0016] Based on the candidate set of abnormal evaluation variables, reference samples are selected to establish the original evaluation matrix, and the distance between the samples and the optimal operating state is determined. The operating state of the cement kiln thermal system is evaluated based on the distance results.

[0017] Based on the candidate set of abnormal evaluation variables, heat loss anomalies and operating status of the cement kiln thermal system, the key variables affecting the thermal state are determined, and a causal diagram of the cement kiln thermal operation is constructed according to the causal relationship between the key variables.

[0018] Preferably, the development trend of cement kiln thermal engineering is predicted based on the operation cause-effect diagram and target constraints, and a dynamic tuning model is constructed in combination with model predictive control technology to obtain the cement kiln adaptive combustion control results including:

[0019] According to the objective function and constraint conditions of cement kiln thermal control, target constraint conditions are set, and the trend factors affecting the development of cement kiln thermal control are extracted from the operation cause-effect diagram to construct the development characteristic vector;

[0020] The semantic decision tree is used to perform association cluster analysis on the development feature vectors to generate trend targets. The movement trend of the trend targets is predicted based on the target constraints and used as the development trend of cement kiln thermal engineering.

[0021] A mathematical model for cement kiln adaptive combustion control is established, and feedback compensation is performed on the cement kiln combustion control in combination with the optimal operating state to output the optimal combustion control result of the cement kiln.

[0022] In a second aspect, the present invention further proposes a cement kiln thermal diagnostic analysis system based on heat balance calculation, the analysis system comprising:

[0023] The balance relationship acquisition module is used to obtain the thermal balance state corresponding to the calculation of the thermal parameters of the cement kiln and the material composition data, and analyze the material balance relationship between the material input and material output of the cement kiln according to the law of conservation of mass;

[0024] A diagnostic indicator generation module is used to evaluate the energy efficiency of the cement kiln firing system by using the ratio of the heat of cement kiln clinker formation to the total heat input as a thermal efficiency indicator. This module also generates diagnostic indicators by combining the thermal balance state with the material balance relationship.

[0025] A cause-and-effect diagram construction module is used to compare diagnostic indicators with historical operating optimal values ​​to determine deviations, evaluate heat loss anomalies and operating status of the cement kiln thermal system based on the deviations, and construct a cause-and-effect diagram of the cement kiln thermal system operation;

[0026] The dynamic tuning control module is used to predict the development trend of cement kiln thermal engineering based on the operation cause-effect diagram and target constraints, and to build a dynamic tuning model in combination with model predictive control technology to obtain the adaptive combustion control results of the cement kiln.

[0027] The beneficial effects of the present invention are:

[0028] 1. The present invention realizes adaptive optimization of the thermal system of cement kiln through heat balance calculation and material balance analysis, combined with model predictive control technology, to improve the overall energy efficiency, production stability and environmental performance. By processing real-time operation data, a series of diagnostic indicators (such as heat loss rate, combustion efficiency, material balance, etc.) are generated, and these indicators are compared with historical optimal values ​​to analyze the deviation. At the same time, by constructing a thermal operation cause-and-effect diagram, the cause-and-effect relationship between different operating parameters is clearly presented, which helps to understand how various factors affect the overall performance of the thermal system, and facilitates the optimization and adjustment of different parameters according to the cause-and-effect relationship in the later stage to achieve the best operating state adjustment.

[0029] 2. The present invention can predict the thermal development trend of cement kilns in a certain period of time in the future through target constraints (such as emission standards, production costs, equipment loads, etc.) and operation cause-and-effect diagrams, and can make adjustments before problems actually occur, avoiding large-scale energy waste or production stagnation caused by uncontrollable factors. Ultimately, through model predictive control technology, combined with thermal status and target constraints, dynamic optimization can be automatically performed to achieve the purpose of real-time adjustment of combustion parameters, air-coal ratio, kiln body temperature, etc., thereby improving the production efficiency, product quality, and environmental protection level of cement kilns. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 This is a flow chart of a cement kiln thermal diagnostic analysis method based on heat balance calculation according to an embodiment of the present invention;

[0032] Figure 2 This is a principle block diagram of a cement kiln thermal diagnostic analysis system based on heat balance calculation according to an embodiment of the present invention;

[0033] Figure 3 1 is a schematic diagram of online thermal diagnosis of a firing system in a thermal diagnosis and analysis method of a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0034] Figure 4 This is a software network architecture diagram of a cement kiln thermal diagnostic analysis method based on heat balance calculation according to an embodiment of the present invention;

[0035] Figure 5 This is an overview diagram of online thermal diagnosis in a cement kiln thermal diagnosis and analysis method based on heat balance calculation according to an embodiment of the present invention;

[0036] Figure 6 This is a clinker production trend analysis diagram in a cement kiln thermal diagnostic analysis method based on heat balance calculation according to an embodiment of the present invention;

[0037] Figure 7 This is a comparative analysis diagram of rotary kiln system design indicators in a cement kiln thermal diagnostic analysis method based on heat balance calculation according to an embodiment of the present invention;

[0038] Figure 8 This is a daily year-on-year analysis chart of a rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0039] Figure 9 This is one of the core index analysis diagrams of air usage of a rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0040] Figure 10 This is the second analysis diagram of the core index of air usage of a rotary kiln system in a thermal diagnostic analysis method of a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0041] Figure 11This is one of the core index analysis diagrams of heat balance of a rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0042] Figure 12 This is the second analysis diagram of the thermal balance core index of the rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on thermal balance calculation according to an embodiment of the present invention;

[0043] Figure 13 This is one of the material balance analysis diagrams of a rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0044] Figure 14 This is the second material balance analysis diagram of a rotary kiln system in a thermal diagnostic analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention;

[0045] Figure 15 This is an online thermal diagnosis report diagram in a thermal diagnosis and analysis method for a cement kiln based on heat balance calculation according to an embodiment of the present invention.

[0046] In the picture:

[0047] 1. Balance relationship acquisition module; 2. Diagnostic indicator generation module; 3. Cause-effect graph construction module; 4. Dynamic tuning control module. DETAILED DESCRIPTION

[0048] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and the advantages of the present invention.

[0049] According to an embodiment of the present invention, a cement kiln thermal diagnostic analysis method and system based on heat balance calculation are provided.

[0050] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to an embodiment of the present invention, a cement kiln thermal diagnostic analysis method based on heat balance calculation includes:

[0051] Step S1: obtaining thermal parameters of the cement kiln and calculating the corresponding thermal equilibrium state of the material composition data, and analyzing the material balance relationship between the material input and material output of the cement kiln according to the law of conservation of mass.

[0052] It should be explained that in the process of achieving the thermal equilibrium state and obtaining the material balance relationship, based on the OPC protocol, a communication connection is established with the DCS system of the cement kiln firing system through the data acquisition device to obtain 39 types of thermal parameters and material composition data in real time, including temperature parameters (gas temperature at each level of the preheater outlet, decomposition furnace temperature, temperature at different positions in the kiln, gas temperature in each room of the cooler, clinker outlet temperature); pressure parameters (inlet and outlet pressures of each level of the preheater, decomposition furnace pressure, which is related to the combustion and airflow conditions in the decomposition furnace; kiln head hood pressure, kiln tail pressure, cooler inlet and outlet pressure); air volume parameters Data (primary air volume, secondary air volume, tertiary air volume, blast volume of each cooler chamber, total exhaust volume of the system); material composition data (chemical composition of raw materials entering the kiln, including calcium oxide, silicon dioxide, aluminum oxide, and iron oxide content), etc. At the same time, the collected raw data are preprocessed and heat balance calculation is performed on the preprocessed data. The heat balance calculation of the preprocessed data is based on the heat balance, material balance and thermal efficiency calculation model of the GB / T26281-2010 standard. The preprocessed data is calculated to obtain various thermal indicators. Specifically, the online thermal calibration measurement points of the kiln system are shown in Table 1:

[0053] Table 1: Online thermal calibration measurement points of kiln system

[0054]

[0055]

[0056]

[0057] The specific process of heat balance management is as follows:

[0058] (1) Pulverized coal combustion heat: The calculation formula is Qrr = mr × Qnet,ar = unit pulverized coal combustion heat * received base heat. The data required include the total exhaust gas volume at the preheater C1 outlet and the dust concentration at the C1 outlet;

[0059] (2) Pulverized coal sensible heat: The calculation formula is Q r =(Myr×cyr×ty r =Msh = (kiln head coal feed amount * specific heat of pulverized coal entering the kiln * temperature of pulverized coal entering the kiln + coal feed amount to the calciner * specific heat of pulverized coal entering the calciner * temperature of pulverized coal entering the calciner) / clinker output; Required data: total exhaust gas volume at the outlet of preheater C1, dust concentration at the outlet of C1 (measured data);

[0060] (3) Sensible heat of raw meal entering preheater: the calculation formula is Qs = ms × cs × ts = sensible heat of raw meal entering preheater per unit = raw meal consumption * specific heat of raw meal entering preheater * raw meal temperature entering preheater;

[0061] (4) Sensible heat of primary air:

[0062] The calculation formula is Qlk = (Vylk × cylk × tylk + Vysm × cysm × tysm + Vfsm × cfsm × tfsm) / Msh = (kiln head primary air volume * kiln head primary net air specific heat * kiln head primary net air temperature + kiln head coal supply air volume * kiln head coal supply air specific heat * kiln head coal supply air temperature + decomposition furnace coal supply air volume * decomposition furnace coal supply air specific heat * decomposition furnace coal supply air temperature) / clinker output;

[0063] (5) Sensible heat of air blown into the cooler: the calculation formula is QLk = VLk × cLk × tLk / Msh = cooler blown air volume * average specific heat of cold air entering the cooler * average temperature of cold air entering the cooler / clinker output; data required to be obtained: total exhaust gas volume at the outlet of preheater C1, dust concentration at the outlet of C1;

[0064] (6) Sensible heat of air leaking into the system: The calculation formula is Qlok = Vlok × ck × tk / Msh = (volume of air leaking into the system * specific heat of ambient air * ambient temperature) / clinker output; data required: total exhaust gas volume at the outlet of preheater C1, dust concentration at the outlet of C1;

[0065] (7) Total heat income of the firing system:

[0066] The calculation formula is Qzr = Qrr + Qr + Qs + Q1k + QLk + Qlok = pulverized coal combustion heat + pulverized coal sensible heat + raw meal sensible heat + primary air sensible heat + cooler blown air sensible heat + system leakage air sensible heat;

[0067] (8) Heat expenditure of firing system:

[0068] The calculation formula is Qsh = 17.19Al2O3sh + 27.10MgOsh + 32.01CaOsh - 2.47Fe2O3sh - 21.40SiO2sh = 17.19*Al2O3 content + 27.10*MgO content + 32.01*CaO content - 2.47*Fe2O3 content - 21.40*SiO2 content; the data required are: Al2O3 content, MgO content, CaO content, Fe2O3 content, and SiO2 content;

[0069] (9) Heat consumption for evaporating moisture in raw meal: The formula is Qss = ms × Ws / 100 × qqh = actual raw meal consumption coefficient * moisture content of raw meal entering the kiln / 100 * heat of vaporization of moisture; data to be obtained: total exhaust gas volume at the outlet of preheater C1, dust concentration at the outlet of C1, and temperature of raw meal entering the preheater;

[0070] (10) Sensible heat of clinker leaving the cooler: The calculation formula is QLsh = mLsh × cLsh × tLsh = amount of clinker leaving the cooler * specific heat of clinker leaving the cooler * temperature of clinker leaving the cooler; the data to be obtained are: static pressure of exhaust volume (square tube) of cooler to sedimentation chamber, static pressure of exhaust air from cooler, static pressure of exhaust air from cooler to sedimentation chamber (circular tube);

[0071] (11) Sensible heat of exhaust gas at preheater outlet: calculated as Qf = Vf × cf × tf / Msh = exhaust gas volume at preheater C1 outlet main pipe * exhaust gas specific heat at preheater outlet * exhaust gas temperature at preheater outlet / clinker output;

[0072] (12) Sensible heat of fly ash at preheater outlet: The calculation formula is Qfh = mfh × cfh × tfh = fly ash quantity at preheater outlet * specific heat of fly ash in exhaust gas at preheater outlet * temperature of fly ash in exhaust gas at preheater outlet;

[0073] (13) Heat consumption for fly ash dehydration and carbonate decomposition: The calculation formula is: H2OS = Al2O3s × 36 / 102; CO2S = (CaOS / 100 × 44 / 56 + MgOS / 100 × 44 / 40.3) * 100;

[0074] Qtf=mfh×(100-Lfh) / (100-Ls)×H2Os / 100×6690+〔mfh×(100-Lfh) / (100-Ls)×CO2S / 100-mfh×Lfh / 100〕×100 / 44×1660, i.e., heat consumption for fly ash dehydration and carbonate decomposition = fly ash amount at preheater outlet*(100-fly ash loss on ignition) / (100-raw meal loss on ignition)*combined water content in raw meal / 100*6690+(fly ash amount at preheater outlet*(100-fly ash loss on ignition) / (100-raw meal loss on ignition)*CO2 content in raw meal / 100)*100 / 44*1660;

[0075] (14) Sensible heat of the exhaust air from the cooler to the settling chamber: the calculation formula is Qyp = Vyp × cyp × typ / Msh = volume of the exhaust air from the cooler to the settling chamber (square tube) * specific heat of the exhaust air from the cooler to the settling chamber * temperature of the exhaust air from the cooler to the settling chamber / clinker output;

[0076] (15) Sensible heat of fly ash from cooler to settling chamber (square tube): The calculation formula is Qyph = myph × cyph × typ = amount of fly ash from cooler to settling chamber (square tube) * specific heat of fly ash from cooler to settling chamber * temperature of fly ash from cooler to settling chamber;

[0077] (16) Sensible heat of the exhaust air from the cooler to the settling chamber (circular pipe): The calculation formula is Qmp = Vmp × cmp × tmp / Msh = volume of the exhaust air from the cooler to the settling chamber (circular pipe) * specific heat of the exhaust air from the cooler to the settling chamber * temperature of the exhaust air from the cooler to the settling chamber / clinker output;

[0078] (17) Sensible heat of fly ash from cooler exhaust to settling chamber (circular pipe): The calculation formula is Qmph = mmph × cmph × tmph = amount of fly ash from cooler exhaust to settling chamber (circular pipe) * specific heat of fly ash from cooler exhaust to settling chamber * temperature of fly ash from cooler exhaust to settling chamber;

[0079] (18) Cooler exhaust gas sensible heat: the calculation formula is Qfp = Vfp × cfp × tfp / Msh = cooler exhaust gas exhaust volume * cooler exhaust gas specific heat * cooler exhaust gas temperature / clinker output;

[0080] (19) Sensible heat of cooler exhaust gas fly ash: the calculation formula is Qfph = mfph × cfph × tfph = cooler exhaust gas volume * cooler exhaust gas fly ash specific heat * cooler exhaust gas fly ash temperature;

[0081] (20) Heat of incomplete chemical combustion:

[0082] The calculation formula is Qhb = Vf × (1-H2Of / 100) × COf / 1000000 × 12630 / Msh = exhaust volume of the main pipe at the outlet of preheater C1 * (1-water vapor volume percentage of preheater outlet gas / 100) * CO dry gas volume content of preheater outlet gas / 1000000 * 12630 / clinker output;

[0083] (21) Mechanical incomplete combustion heat: The calculation formula is Qjb = Lsh / 100×33874 = clinker ignition loss / 100*33847;

[0084] (22) Surface heat dissipation of the firing system: the calculation formula is Qbs = Qbsh / Msh = surface heat dissipation of the firing system per hour / clinker output;

[0085] (23) Other thermal expenditures of the system:

[0086] The calculation formula is:

[0087] Qqt = Qzr - (Qsh + Qss + QLsh + Qf + Qfh + Qtf + Qyp + Qyph + Qfp + Qfph + Qhb + Qjb + Qbs) = total system heat income - (all heat losses);

[0088] (24) Rotary kiln thermal efficiency = clinker formation heat / (coal powder combustion heat + combustible material combustion heat in raw meal) * 100;

[0089] (25) System surface heat dissipation test results: preheater total = C1 + C2 + C3 + C4 + C5 + C6 (heat dissipation per hour); firing system surface heat dissipation = grate cooler + kiln head hood + smoke chamber + tertiary air duct + kiln body surface + decomposition furnace.

[0090] Material balance calculation of firing system (income materials):

[0091] (1) Pulverized coal consumption: The calculation formula is mr = (Myr + Mfr) / Msh (pulverized coal consumption = (kiln head coal feed amount + calciner coal feed amount) / clinker output);

[0092] (2) Raw meal consumption: The calculation formula is ms = Ms / Msh (raw meal consumption = raw meal feed amount / clinker output);

[0093] (3) Primary air volume: The calculation formula is mlk = (Vy1k + Vysm + Vfsm) / Msh × ρK (primary air volume = (kiln head primary air volume + kiln head coal supply air volume + calciner coal supply air volume) / clinker output * air density);

[0094] (4) Cooler air volume: The calculation formula is mLK = VLK / Msh × ρk (Cooler air volume = Cooler air volume / Clinker output * Air density);

[0095] (5) Total material income of the firing system: The calculation formula is mzr = mr + ms + mlk + mLk + mlok (total material income = coal powder consumption + raw meal consumption + primary air volume + cooler air volume + system leakage air volume).

[0096] Material balance calculation of firing system (expenditure materials):

[0097] (1) Clinker output from cooler: The calculation formula is mLsh = 1-(Vyp×δyp+Vfp×δfp+VMp×δMp) / 1000 / Msh (clinker output from cooler = 1-(cooler exhaust volume to sedimentation chamber (square tube) * cooler exhaust dust concentration to sedimentation chamber (square tube) + cooler exhaust volume * cooler exhaust dust concentration + cooler exhaust volume to sedimentation chamber (round tube) * cooler exhaust dust concentration to sedimentation chamber (round tube)) / 1000 / clinker output);

[0098] (2) Preheater outlet exhaust gas volume: The calculation formula is mf = Vf × ρf / Msh (preheater outlet exhaust gas volume = preheater C1 outlet main exhaust gas volume * preheater outlet exhaust gas density / clinker output);

[0099] (3) Fly ash volume at the preheater outlet: The calculation formula is mfh = Vf × δf / 1000 / Msh (fly ash volume at the preheater outlet = volume of exhaust gas from the preheater C1 outlet main pipe * dust concentration of exhaust gas from the preheater C1 outlet main pipe / 1000 / clinker output);

[0100] (4) Cooler exhaust volume to the settling chamber (square tube): The calculation formula is myp = Vyp × ρk / Msh (cooler exhaust volume to the settling chamber (square tube) = cooler exhaust volume to the settling chamber (square tube) * air density / clinker output);

[0101] (5) Fly ash volume from the exhaust of the cooler to the settling chamber (square tube): The calculation formula is myph = Vyp × δyp / 1000 / Msh (fly ash volume from the exhaust of the cooler to the settling chamber (square tube) = exhaust volume of the cooler to the settling chamber (square tube) * dust concentration of exhaust of the cooler to the settling chamber (square tube) / 1000 / clinker output);

[0102] (6) Cooler exhaust volume to the settling chamber (circular pipe): The calculation formula is mmph = Vmp × δmp / 1000 / Msh (Cooler exhaust volume to the settling chamber (circular pipe) = Cooler exhaust volume to the settling chamber (circular pipe) * air density / clinker output)

[0103] (7) Cooler exhaust gas volume: The calculation formula is mfp = Vfp × ρk / Msh (cooler exhaust gas volume = cooler exhaust gas exhaust volume * air density / clinker output);

[0104] (8) Cooler exhaust fly ash volume: The calculation formula is mfp = Vfp × ρk / Msh (cooler exhaust volume = cooler exhaust volume * air density / clinker output);

[0105] (9) Cooler exhaust gas fly ash quantity: The calculation formula is mfph = Vfp × δfp / 1000 / Msh (Cooler exhaust gas fly ash quantity = Cooler exhaust gas exhaust volume * Cooler exhaust gas dust concentration / 1000 / Clinker output).

[0106] When performing material balance calculations, based on the law of conservation of mass, the balance relationship between the input of raw materials such as raw meal, pulverized coal, and air into the kiln and the output of materials such as clinker, waste gas, and fly ash out of the kiln is analyzed. By accurately calculating the changes in the mass and composition of each material, the conversion and distribution of materials in the system are determined (mainly involving: the relationship between C1 dust content and feed rate and clinker output. Clinker material consumption = theoretical material consumption / (1-production loss rate). Theoretical material consumption is determined based on the amount of ash added and the loss on ignition of raw meal. Production loss mainly refers to the amount of raw meal that escapes. The CO content in the flue gas and the CO content in the smoke chamber evaluate the combustion conditions in the furnace and kiln), providing a basis for subsequent process adjustments.

[0107] Step S2: The ratio of the heat of cement kiln clinker formation to the total heat input is used as a thermal efficiency index to evaluate the energy utilization efficiency of the cement kiln firing system, and a diagnostic index is generated by combining the thermal balance state and the material balance relationship.

[0108] It should be explained that the calculation of thermal efficiency is to use the ratio of clinker formation heat to total heat input as the thermal efficiency index to evaluate the energy utilization efficiency of the cement kiln firing system. Through the calculation of thermal efficiency, we can intuitively understand the energy-saving effect of the system and provide key data support for optimizing the production process.

[0109] Conduct in-depth analysis of the calculated results of heat balance, material balance, and thermal efficiency, comparing the actual values ​​of each indicator with historical optimal values ​​and design values ​​to determine indicator deviations. By establishing a scientific comparative analysis model (establishing the comparative model requires determining key comparative indicators such as thermal efficiency, heat consumption, and waste gas volume per unit of clinker), it is possible to accurately identify existing problems in the system operation and potential optimization opportunities. Quantify the causes of indicator deviations and comprehensively consider the impact of various factors on indicator deviations.

[0110] For example, if the sensible heat of the cooler exhaust gas increases, the system's data analysis and logical reasoning functions are used (for example, to set the normal air volume range of the cooler and the corresponding clinker temperature range; analyze the abnormal conditions of related parameters: secondary air temperature, tertiary air temperature, waste heat extraction power generation air temperature, coal mill exhaust gas temperature, clinker temperature, and evaluate the cooling effect of each zone of the cooler; establish a data-based evaluation model) to analyze whether the cause is excessive cooler air volume, poor clinker cooling effect, or other reasons, and determine the contribution of each factor to the deviation through precise calculation. A diagnostic report is generated that includes a comparison of core indicators, a quantitative analysis of the causes of deviations, and process adjustment suggestions for the deviations. Core indicators include clinker output, heat consumption, and cooler heat recovery efficiency. These indicators are key parameters for measuring the performance of cement kiln firing systems. Process adjustment suggestions are formulated based on the specific deviations. For example, if the heat consumption is too high, it is recommended to adjust the air volume, optimize the combustion parameters, or check the sealing of the equipment. If the clinker output is insufficient, it may be considered to adjust the raw material batching or increase the kiln operating speed.

[0111] It should be explained that the thermal diagnosis system of the firing system is deployed in the production management network of the cement enterprise, which runs through the DCS production control network and the production management office network. It is connected to the DCS production network through the OPC communication protocol for field data collection. The data entry module can be set to enter the data. Through the digital technology of data collection, data storage, data calculation and other links, continuous online thermal diagnosis of the firing system is realized. It supports PC and mobile terminal access and meets network security specifications. It can be deployed independently or as a sub-module of the production control digital MES platform. The software network architecture is as follows Figure 4shown.

[0112] like Figure 3 As shown, the thermal performance is measured in accordance with GB / T26282-2010 "Method for Determination of Heat Balance of Cement Rotary Kiln", and the measurement data is processed in accordance with GB / T26281-2010 "Calculation Method for Heat Balance, Thermal Efficiency and Comprehensive Energy Consumption of Cement Rotary Kiln". By measuring the operating conditions, data and index analysis of the measurement system, the automatic measurement and comprehensive evaluation of the thermal performance of the kiln system are completed regularly. The online thermal diagnosis system overview screen of the firing system enables the online evaluation of key evaluation indicators every day, automatically completes the summary of production, quality and energy data, and automatically generates summary reports to achieve visual analysis of the heat balance and material balance of the kiln system and grate cooler system. At the same time, a thermal diagnosis report is automatically generated to achieve the integration of automatic diagnosis report and expert diagnosis, and the diagnosis report function is automatically pushed to assist decision-making.

[0113] like Figure 5 The online thermal diagnosis overview is shown in the figure, and its specific functions are described as follows:

[0114] Overall operating indicators of the cement kiln on the previous day, including output, process power consumption, heat consumption, kiln thermal efficiency, and cooler thermal efficiency; comparative analysis of the historical optimal indicators of the cement kiln production and operation process with yesterday's indicators; comparative analysis of cement kiln design indicators with yesterday's indicators; day-on-day comparative analysis of clinker output, heat consumption, and cooler heat recovery efficiency; coal industry analysis, kiln clinker composition, and production line optimal indicators; analysis of core indicators such as cooler air volume, sensible heat of clinker discharged from the kiln, and sensible heat of cooler exhaust gas; and thermal calibration analysis report.

[0115] like Figure 6 The clinker production trend analysis chart shown has the following specific functions:

[0116] Click on the "Home" clinker output title to penetrate and query the change trend of historical output. The baseline is the optimal output, and a comparative analysis with the historical optimal output can be achieved. This function can be realized for process power consumption, heat consumption, kiln thermal efficiency, and cooler thermal efficiency. It can be used to query and trace historical data trends and compare and analyze with historical optimal indicators.

[0117] like Figure 7 The comparative analysis diagram of rotary kiln system design indicators is shown in the figure, and its specific functions are described as follows:

[0118] Because the factory's raw coal replacement cycle is 7 days, the indicator analysis cycle here is displayed on a rolling 7-day basis. Analysis of the core indicators of the clinker process, including power consumption, heat consumption, and cooler heat recovery efficiency, provides feedback on the power consumption, coal consumption, and cooler heat recovery effects of the entire kiln system, enabling trend comparison and analysis with design indicators. Its coordinates adaptively display the trend of data changes to the greatest extent possible, providing intuitive feedback on the current operating status of the kiln system.

[0119] like Figure 8 The daily year-on-year analysis chart of the rotary kiln system is shown below. Its specific functions are described as follows:

[0120] The core indicators of "clinker output, heat consumption, and cooler heat recovery efficiency" are analyzed on a daily basis. The bar chart is used to reflect the trend of daily changes, and the comparative analysis can intuitively understand the operating status of the kiln system.

[0121] like Figure 9 and Figure 10 The core index analysis diagram of the rotary kiln system air consumption is shown in the figure, and its specific functions are described as follows:

[0122] The daily comparison method is used to analyze the air consumption of the cooler and the kiln system; the daily comparison analysis status feedback the trend change of air consumption, and the qualitative and quantitative analysis helps to assist decision-making.

[0123] like Figure 11 and Figure 12 The core indicator analysis diagram of the heat balance of the rotary kiln system is shown in the figure, and its specific functions are described as follows:

[0124] The heat of pulverized coal combustion and the heat of clinker formation in the kiln system's heat balance are analyzed on a daily basis; the sensible heat of the clinker out of the kiln and the sensible heat of the cooler exhaust gas are analyzed in the cooler's heat balance; the daily year-on-year analysis status feedback shows trend changes compared to yesterday, and qualitative and quantitative analysis helps assist decision-making.

[0125] like Figure 13 The heat balance analysis diagram of the rotary kiln system is shown in the figure, and its specific functions are described as follows:

[0126] It mainly realizes the heat balance analysis of kiln system and cooler; the heat balance of kiln system and cooler realizes the calculation of all heat received and all heat spent; graphically displays the proportion of each sensible heat; the kiln heat balance and cooler heat balance trends support 7-day and 30-day inquiries; during long-term use, it is conducive to analyzing the trend changes of heat input and expenditure of rotary kiln and cooler.

[0127] like Figure 14 The material balance analysis diagram of the rotary kiln system is shown in the figure, and its specific functions are described as follows:

[0128] It mainly realizes the analysis of kiln system material balance and cooler material balance; the kiln system material balance and cooler material balance analysis realize the calculation of all received materials and all spent materials; graphically displays the proportion of each material; the kiln system material balance and cooler material balance trends support 7-day and 30-day inquiries; during long-term use, it is beneficial to analyze the trend changes of rotary kiln and cooler material income and expenditure.

[0129] like Figure 15The online thermal diagnostic report shown has the following specific functions:

[0130] Core indicators of kiln system production and operation: output, comprehensive clinker power consumption, clinker burning heat consumption, kiln thermal efficiency, cooler heat recovery efficiency, clinker temperature; qualitative analysis of the kiln system is conducted from three aspects of core indicators of kiln system production and operation: heat consumption, cooler heat recovery efficiency, and cooler cooling efficiency; the factory coal replacement cycle is 7 days, and a comparative analysis of the usage of two piles of coal in the past two weeks with today's indicator data is more instructive; in the quantitative analysis, the main factors affecting the indicators are ranked and quantified; through qualitative and quantitative analysis, data support is provided for production auxiliary decision-making management; thermal engineering reports are pushed to the production management WeChat group at 14:00 every day for user viewing.

[0131] In the specific implementation, the data sources of online thermal diagnosis are shown in Tables 2 to 4:

[0132] Table 2: Chemical analysis of raw materials

[0133]

[0134] Table 3: Chemical analysis of clinker

[0135]

[0136] Table 4: Industrial analysis of pulverized coal

[0137]

[0138] Finally, diagnostic reports are automatically generated at preset time intervals (such as daily) and stored in the system database in the form of electronic documents (such as PDF, Excel, etc.). At the same time, reports can be pushed to the terminal devices (such as PCs, mobile phones, etc.) of relevant production managers so that they can grasp the system operation status in a timely manner and make scientific decisions.

[0139] This enables real-time, continuous monitoring and diagnosis of the thermal parameters of the cement kiln firing system, greatly shortening the diagnosis cycle from the traditional 72-hour manual calibration to real-time updates, improving the timeliness and scientific nature of production decisions, and through precise heat balance, material balance and thermal efficiency calculations, accurately identifying problems and potential optimization space during system operation, providing a strong basis for process adjustments, effectively reducing heat consumption, improving the heat recovery efficiency of the cooler, and reducing production costs.

[0140] At the same time, a detailed diagnostic report is automatically generated every day and pushed to relevant management personnel in a timely manner, so that they can grasp the system operation status at any time and take timely measures to solve problems, thereby improving the efficiency and level of production management. It is applicable to various types of cement kiln firing systems, including different process types, kiln sizes and fuel types. It has broad application prospects and promotion value, helps cement companies achieve energy conservation and emission reduction goals, reduces CO2 emissions, complies with the country's requirements for the green development of the building materials industry, and has good social and environmental benefits.

[0141] Step S3: compare the diagnostic indicators with the historical optimal operating values ​​to determine the deviation, evaluate the heat loss anomaly and operating status of the cement kiln thermal system based on the deviation, and construct a cause-effect diagram of the cement kiln thermal system operation.

[0142] In one embodiment, the diagnostic indicators are compared with the historical optimal operating values ​​to determine the deviation, and the heat loss anomaly and operating status of the cement kiln thermal system are evaluated based on the deviation. A cause-effect diagram of the cement kiln thermal system operation is constructed, including:

[0143] Based on historical operating data, the historical operating optimal value and optimal operating state are determined, and the deviation value between the diagnostic indicator and the historical operating optimal value is calculated. The diagnostic indicator with a deviation value greater than the deviation threshold is selected to obtain the corresponding abnormal evaluation variable candidate set; the abnormal evaluation variable candidate set is used to detect anomalies, and the heat loss anomaly of the cement kiln thermal engineering is evaluated based on the detection results and the enhanced local linear embedding technology; according to the abnormal evaluation variable candidate set, reference samples are selected to establish the evaluation original matrix, and the distance between the reference sample and the optimal operating state is determined, and the operating state of the cement kiln thermal engineering is evaluated based on the distance result; based on the abnormal evaluation variable candidate set, the heat loss anomaly of the cement kiln thermal engineering and the operating state, the key variables affecting the thermal engineering state are determined, and a causal graph of the cement kiln thermal engineering operation is constructed based on the causal relationship between the key variables.

[0144] Among them, when using correlation analysis and support vector description technology to detect anomalies on the abnormal evaluation variable candidate set, and evaluating the heat loss anomaly of the cement kiln thermal system based on the detection results and the enhanced local linear embedding technology, two groups of random vectors can be randomly generated based on the abnormal evaluation variable candidate set, and the eigendecomposition results of the abnormal evaluation variable candidate set are obtained with the goal of maximizing the correlation coefficient between the two groups of random vectors; the eigenvectors corresponding to the eigendecomposition values ​​that meet the preset requirements of the eigendecomposition results are selected as projection vectors, and the optimal typical variable set is screened from the abnormal evaluation variable candidate set based on the projection vectors; the minimum hypersphere is constructed based on the optimal typical variable set, and the distance between the abnormal evaluation variable candidate set and the center of the minimum hypersphere is obtained, and the preliminary heat loss anomaly set corresponding to the abnormal evaluation variable candidate set is obtained based on the distance result and the minimum hypersphere radius; the preliminary heat loss anomaly set is combined with the enhanced local linear embedding technology to generate a projection matrix, and the projection matrix is ​​used to obtain the direction vector representing the heat loss state to evaluate the heat loss anomaly of the cement kiln thermal system.

[0145] Specifically, the calculation formula for the minimum hypersphere radius is:

[0146]

[0147] Where R represents the minimum hypersphere radius, a b represents the projection vector, a c represents the cth optimal typical variable set, D AB represents the candidate set of abnormal evaluation variables; d c represents the optimal typical variable set a c The corresponding Lagrange multiplier, a e represents the e-th optimal typical variable set, d e represents the optimal typical variable set a e The corresponding Lagrange multiplier.

[0148] Specifically, in the process of obtaining the preliminary heat loss anomaly set, the candidate set of abnormal evaluation variables is first standardized to eliminate the dimension effect. Assuming that the candidate set contains m variables and n groups of observation data, an n×m-dimensional data matrix X is formed. Two sets of projection vectors A and B (both with dimensions of m×1) are randomly initialized. The vector direction is adjusted through an optimization algorithm (such as gradient ascent) to make the correlation coefficient ρ(A T X, B T X) reaches its maximum. When the correlation coefficient converges, the covariance matrix X T Perform eigendecomposition on X and select eigenvectors whose eigenvalues ​​are greater than a preset threshold (such as 0.7) as the projection basis.

[0149] In the process of constructing the optimal typical variable set, the selected k eigenvectors are combined into a projection matrix W (m×k dimensions), and a low-dimensional representation is obtained through linear transformation Z=XW. The contribution of each variable is calculated for the transformed data, and the top p variables (p≤k) whose total contribution exceeds 85% are retained to form the optimal typical variable set V. typical For example, in a cement kiln case, three key variables were retained after screening of the initial seven variables: flue gas temperature, secondary air volume, and coal powder fineness.

[0150] The process of modeling the minimum hypersphere in V typical The minimum hypersphere containing all normal samples is constructed in space by solving the optimization problem: minR 2 +C∑ξis.t.||Φ(vi)-a||2≤R 2 +ξi,ξi≥0, where a is the center of the sphere, R is the radius, Φ is the kernel function (usually Gaussian kernel), ξi is the "relaxation" amount between hyperspheres, assuming R = 1.5, the coordinates of the center of the sphere a = (0.32, 0.51, 0.42).

[0151] To determine heat loss anomaly, we need to calculate the distance between the sample v and the center of the sphere, set the anomaly threshold λR (e.g., λ = 1.2), and determine it as abnormal when d>1.8. The samples outside the hypersphere are combined into a preliminary heat loss anomaly set D abnormal , and record the degree of deviation δ = (dR) / R. For example, if d = 2.1 for an abnormal sample, then δ = 0.4, indicating that the operating condition deviates from the normal range by 40%.

[0152] Specifically, when combining the preliminary heat loss anomaly set with the enhanced local linear embedding technology to generate a projection matrix, and using the projection matrix to obtain the direction vector representing the heat loss state, when evaluating the heat loss anomaly of the cement kiln thermal engineering, a number of test samples can be randomly generated based on the preliminary heat loss anomaly set, and the adjacent point set of each test sample can be obtained, and the connection weight between the test sample and the adjacent point set can be judged to obtain a weight matrix; projection analysis is performed on the weight matrix to obtain a projection matrix represented in two-dimensional space, and the topological structure of the projection matrix is ​​judged. According to the topological structure, the direction vector formed by the projection matrix and the center point of the preliminary heat loss anomaly set is obtained to generate a test direction vector representing the heat loss state; the optimal operating state is used as the standard direction vector representing the ideal state, and the angle between the test direction vector and the standard direction vector is judged as the heat loss anomaly value for evaluating the cement kiln thermal engineering.

[0153] Among them, when selecting reference samples according to the abnormal evaluation variable candidate set to establish an evaluation original matrix and judging the distance between the candidate set and the optimal operating state, and evaluating the operating state of the cement kiln thermal system based on the distance results, key point reference samples and regional reference samples can be selected from the abnormal evaluation variable candidate set according to the key point selection requirements and partitioning requirements, and a key point evaluation matrix and a regional evaluation matrix can be constructed to obtain the evaluation original matrix; fuzzy processing is performed on the reference samples in the key point evaluation matrix and the regional evaluation matrix, and a key point evaluation membership matrix and a regional evaluation membership matrix are obtained according to the processing results; two groups of evaluation sequences whose lengths meet preset requirements are defined from the key point evaluation membership matrix and the regional evaluation membership matrix, and two groups of standard sequences corresponding to the optimal operating state are selected according to the key point selection requirements and partitioning requirements; distance matrices are constructed based on the evaluation sequences and the standard sequences, and the distance between the abnormal evaluation variable candidate set and the optimal operating state is judged; if the distance between the evaluation sequence and the standard sequence is less than a preset threshold, it indicates that the current operating state is ideal; if the distance between the evaluation sequence and the standard sequence is greater than or equal to the threshold, it indicates that the current operating state is abnormal.

[0154] Specifically, it is necessary to determine the variables that have a greater impact on the thermal state based on the operating characteristics of the cement kiln. Candidate abnormal evaluation variables (such as flue gas temperature, coal powder fineness, secondary air volume, etc.) are screened according to the following two criteria: Key point selection requirements include selecting variables that have the most significant impact on the thermal state, such as variables that are highly correlated with thermal efficiency and fuel consumption; Partitioning requirements include dividing variables into different areas according to process flow or physical areas, such as kiln head, kiln middle, and kiln tail areas; Based on these requirements, select from the candidate abnormal evaluation variables: Key point reference samples: For example, select variables that are closely related to thermal efficiency, such as kiln head temperature and coal powder fineness. Regional reference samples: For example, select variables related to flue gas emissions, such as flue gas composition and flue gas temperature at the kiln tail.

[0155] Assuming that the candidate set contains multiple variables, key points and regional reference samples are selected according to the above standards and used to construct evaluation matrices respectively. Two evaluation matrices are constructed using the selected reference samples. Among them, the key point evaluation matrix is ​​to form a matrix with the observation data of all key point reference samples, such as extracting the data of kiln head temperature and coal powder fineness from the data of 5 time periods; regional evaluation matrix: similarly, the observation data of regional reference samples are formed into a matrix to record the observation values ​​of kiln tail flue gas composition and flue gas temperature. These two matrices contain data of different dimensions and can reflect the operating status of key points and regions.

[0156] The key point evaluation matrix and the regional evaluation matrix are combined to form a comprehensive raw evaluation matrix that covers all selected reference sample data. The values ​​in the evaluation matrix are then fuzzified. The purpose of fuzzification is to convert each variable value into a membership degree, indicating the degree to which the sample belongs to a certain state. In this way, a fuzzy membership matrix of the variables is obtained, reflecting the proximity between the sample and the ideal state. For each reference sample, a membership value is assigned to it, indicating its similarity to the ideal state. The larger the value, the closer it is to the ideal state.

[0157] Evaluation sequences are extracted from the fuzzy membership matrix. Each evaluation sequence contains the membership value for each reference sample. The length of the evaluation sequence is pre-set, and each sequence represents the state of the sample in a certain time period. For example, evaluation sequences of key points and regions are extracted from the key point evaluation membership matrix and the region evaluation membership matrix respectively. These sequences can show the state of the system at different time points. The standard sequence is a reference sequence constructed based on the historical optimal operating state, which is used to represent the performance of the cement kiln under ideal or optimal conditions. The standard sequence can be set based on the average value or optimal value of historical data to represent the standard performance of the system under ideal conditions.

[0158] By calculating the distance between the evaluation sequence and the standard sequence, the deviation between the current state and the ideal state can be quantified. The distance here is usually calculated based on the Euclidean distance (or other appropriate metric). The distance value between each evaluation sequence and the standard sequence represents the difference between the current operating state and the ideal state. The smaller the distance, the closer the current state is to the ideal state. The operating state of the cement kiln can be judged based on the distance matrix:

[0159] If the distance between the evaluation sequence and the standard sequence is less than a preset threshold, it means that the current operating status is ideal; if the distance between the evaluation sequence and the standard sequence is greater than or equal to the threshold, it means that the current operating status is abnormal. The operating status of the cement kiln can be evaluated based on the distance, and corresponding adjustment measures can be taken according to the abnormal situation.

[0160] Step S4: predict the development trend of cement kiln thermal engineering based on the operation cause-effect graph and target constraints, and build a dynamic tuning model in combination with model predictive control technology to obtain the cement kiln adaptive combustion control results.

[0161] In one embodiment, the development trend of cement kiln thermal engineering is predicted based on the operation cause-effect graph and target constraints, and a dynamic tuning model is constructed in combination with model predictive control technology to obtain the cement kiln adaptive combustion control results, including:

[0162] Target constraints are set according to the objective function and constraints of cement kiln thermal control, and the trend factors affecting the development of cement kiln thermal engineering are extracted from the operation causal map to construct a development feature vector; the development feature vector is subjected to association clustering analysis using a semantic decision tree to generate a trend target, and the movement trend of the trend target is predicted in combination with the target constraints as the development trend of cement kiln thermal engineering; a mathematical model for cement kiln adaptive combustion control is established, and feedback compensation is performed on the cement kiln combustion control in combination with the optimal operating state, outputting the optimal combustion control result of the cement kiln.

[0163] Specifically, when using the semantic decision tree to perform association clustering analysis on the development feature vector, generate the trend target, and combine the target constraint conditions to predict the movement trend of the trend target as the development trend of cement kiln thermal engineering, the category to which the semantic decision tree node belongs can be determined according to the information to which the development feature vector belongs, and the development feature vector is placed in a two-dimensional data table based on the classification result to describe the relationship view of the development feature vector; based on the relationship view result, the development feature vector is divided into dynamic sets, the node concept in the relationship view is associated, and the root node of the semantic decision tree is selected from the node concept as the trend target; according to the trend target, the implicit state of the development feature vector is determined, and the movement trend of the trend target is converted into the movement state prediction of the trend target using the implicit state, and the observation object is represented based on the real spatial position corresponding to the trend target; the trend probability distribution of the observation object analysis is analyzed with the target constraint conditions as the boundary, and the association area is constructed in the form of a fan wave gate according to the analysis results to predict the movement trend of the trend target as the development trend of cement kiln thermal engineering.

[0164] It's important to note that in the process of identifying cement kiln thermal engineering development trends, each development feature vector is mapped to a corresponding classification node through the construction of a semantic decision tree. A semantic decision tree is a tree-like structure constructed by analyzing the inherent connections and features in the data. Each node represents a feature or attribute, and its child nodes represent different values ​​or classifications of that feature.

[0165] Assume the following feature vectors: coal fineness, fuel input, kiln temperature, etc. Based on the data distribution and feature relationships, these vectors are classified into different nodes when constructing a semantic decision tree. For example, node 1 is coal fineness (high / low); node 2 is fuel input (normal / excessive / insufficient); and node 3 is kiln temperature (normal / high / low). Based on the classification results of the semantic decision tree, each development feature vector is placed into a two-dimensional data table according to its category. This data table is used to describe the relationship view between development feature vectors, as shown in Table 5:

[0166] Table 5: Relationship between development feature vectors

[0167] feature Category 1 (high / low) Category 2 (normal / excessive / insufficient) Category 3 (normal / high / low) Coal powder fineness high Fuel input normal Kiln temperature normal

[0168] Based on the above two-dimensional data table, the development feature vector is divided into multiple dynamic sets according to the relational view. The dynamic set reflects the changing trend of the feature vector under different classification conditions. Specifically, according to the relationship between the classification results and the features, the feature vector is divided into multiple sets. For example, set 1 is that the coal powder fineness is high and the fuel input is normal, and the temperature in the kiln is normal; set 2 is that the coal powder fineness is low and the fuel input is excessive, and the temperature in the kiln is relatively high; set 3 is that the coal powder fineness is high and the fuel input is insufficient, and the temperature in the kiln is relatively low; according to the node concept in the dynamic set and the relational view, a semantic decision tree root node is selected as the trend target. The trend target is a key node that describes the change of the target state and represents the starting point for future trend prediction. For example, if coal powder fineness and fuel input are the key factors affecting the development trend of cement kiln thermal engineering, the corresponding decision tree root node (such as "coal powder fineness") can be selected as the trend target.

[0169] The implicit state reflects the changing trend or state of the development characteristic vector in the system. For example, implicit state 1 is high coal powder fineness, normal fuel input, and stable temperature in the kiln; implicit state 2 is low coal powder fineness, excessive fuel input, and high temperature in the kiln; the implicit state is determined by analyzing historical data, current data and their changing trends, which can help predict future movement trends. Once the movement target and implicit state are determined, the historical trend and current implicit state are used to convert the changing trend of the movement target into an actual movement state prediction, which can be achieved through time series analysis, regression model or machine learning algorithm. Assuming that the movement target is "coal powder fineness", the trend analysis of historical data can predict the future changes in coal powder fineness and convert it into a specific numerical value to represent the expected state of coal powder fineness in the next few hours.

[0170] Target constraints define the boundaries of changes in the moving target. For example, certain operations limit the upper and lower limits of coal powder fineness, or the temperature in the kiln has a certain safety range. These constraints need to be analyzed to ensure that the predicted trend is within an acceptable range. Combined with the target constraints, the probability distribution of the movement trend of the moving target is analyzed. Through models (such as Monte Carlo simulation, Bayesian network, etc.), the probability distribution of the target's possible changes in the future can be obtained. Based on the analyzed trend probability distribution, an associated region is constructed. The associated region is defined by a specific geometric form (such as a fan-shaped wave gate form) to represent the area where the moving target may move within a specific time. For example, assuming that the coal powder fineness has a 60% probability of falling within a specific range in the next few hours, then an expected range of change can be constructed based on this probability information.

[0171] Then, the development trend forecast of the thermal system of the cement kiln is obtained. These trend forecasts include the future change trends of key variables such as coal powder fineness and fuel input; whether the predicted change state meets the target constraints (such as temperature, coal powder fineness limit, etc.). Finally, based on the results of the trend target and spatial position prediction, decision support can be provided for the operation optimization of the cement kiln, thereby improving the thermal efficiency and production stability of the kiln.

[0172] Among them, when establishing a mathematical model for the adaptive combustion control of the cement kiln, performing feedback compensation on the cement kiln combustion control in combination with the optimal operating state, and outputting the optimal combustion control result of the cement kiln, the component structure of the combustion control can be determined based on the control process of the cement kiln, and the structure of the cement kiln combustion control system can be determined according to the working principle corresponding to the component structure, and the performance loss of each component structure during the control process is analyzed; the performance loss is used as a constraint condition to establish a mathematical model for the adaptive combustion control of the cement kiln, and converted into a state-space equation, and the state-space equation is processed in combination with the development trend and model predictive control technology; the optimal controller of the adaptive combustion control of the cement kiln is obtained according to the processing results, and the cement kiln combustion control is feedback compensated based on the optimal controller and the optimal operating state, and the optimal combustion control result of the cement kiln is output.

[0173] It needs to be explained that when outputting the optimal combustion control results, it is first necessary to understand the specific control process of the cement kiln combustion system. The combustion control system includes but is not limited to: fuel input subsystem (such as coal powder, oil and gas), air supply subsystem (such as primary air, secondary air), temperature detection and feedback subsystem, control actuator (such as valve adjustment, motor drive), etc. These subsystems together constitute the entire combustion control system. The data interaction and physical effects between them directly affect thermal efficiency and stability. For each subsystem, it is necessary to sort out its working principles and interactions: the fuel supply system adjusts the heat supply, the air system adjusts the combustion efficiency, the feedback system monitors the temperature, flue gas composition and other parameters in real time, and the execution system dynamically adjusts the ratio of fuel to air accordingly to achieve combustion balance.

[0174] In actual control, each subsystem has problems such as response lag, transmission delay, and energy loss. Performance losses need to be identified and quantified one by one: for example, valve adjustment lags of 1 to 2 seconds, the fan has reduced energy transmission efficiency, and the fuel combustion process is incomplete. These performance losses will serve as constraints for subsequent mathematical models to ensure that the model is closer to the actual working conditions. A mathematical model is then established to describe cement kiln combustion control. The core elements include control variables such as system input fuel flow and air volume; observation variables such as system output temperature and flue gas oxygen content; internal state temperature distribution, pressure fluctuations, and changes in air-fuel ratio; and constraints are restrictions determined by performance losses, such as maximum air volume and minimum fuel channel response time.

[0175] In order to achieve system control, the mathematical model in the previous step needs to be converted into a state space form. The state space model takes the system's "state variables" as its core, and can dynamically describe the evolution of the system under different inputs. It uses time as a sequence and continuously or discretely describes the mapping relationship between state and output. It is combined with model predictive control (MPC) technology to make optimized decisions.

[0176] Historical operating data is introduced to perform trend modeling on system variables (such as temperature and fuel consumption) to predict future operating status. The trend model can help predict potential deviations in advance. MPC is a control strategy that predicts future behavior based on a model and performs rolling optimization. Its core is to predict the state evolution path in the future period at each control moment; perform calculations based on optimization objectives (such as minimum fuel consumption and maximum temperature stability); consider system constraints and performance losses to solve the optimal control quantity sequence; only execute the control output at the current moment, and continue to predict and correct it later to generate a control strategy that can respond to dynamic changes in real time.

[0177] Based on the above optimization, combined with development trends and constraints, a controller that can adapt to the dynamic changes of the system is designed: the controller has learning and self-adjusting capabilities, and can adjust strategies according to feedback; it can continuously output effective control signals under different operating conditions (such as raw material changes, temperature fluctuations); realize the "control-feedback-optimization-update" closed-loop control process, and finally realize feedback compensation based on the deviation between the optimal controller and the optimal operating state of the cement kiln: compare the current operating state with the optimal state to evaluate the gap; use the controller to perform intelligent compensation adjustments, such as fine-tuning the fuel ratio and air volume intensity; adjust the control instructions in real time and output the current optimal combustion control parameters; the controller automatically iterates and updates to ensure that the operation continues to be close to the optimal state.

[0178] like Figure 2 As shown, according to another embodiment of the present invention, a cement kiln thermal diagnostic analysis system based on heat balance calculation is also proposed, and the analysis system includes:

[0179] The equilibrium relationship acquisition module 1 is used to obtain the thermal equilibrium state corresponding to the calculation of the thermal parameters of the cement kiln and the material composition data, and analyze the material balance relationship between the material input and material output of the cement kiln according to the law of conservation of mass;

[0180] Diagnostic indicator generation module 2 is used to evaluate the energy utilization efficiency of the cement kiln firing system by using the ratio of the heat of cement kiln clinker formation to the total heat input as a thermal efficiency indicator, and to generate diagnostic indicators by combining the thermal balance state with the material balance relationship;

[0181] Cause-and-effect diagram construction module 3 is used to compare the diagnostic indicators with the historical optimal operating values ​​to determine the deviation, evaluate the heat loss anomaly and operating status of the cement kiln thermal system based on the deviation, and construct a cause-and-effect diagram of the cement kiln thermal system operation;

[0182] The dynamic tuning control module 4 is used to predict the development trend of cement kiln thermal engineering based on the operation cause-effect diagram and target constraints, and to build a dynamic tuning model in combination with model predictive control technology to obtain the cement kiln adaptive combustion control results.

[0183] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A cement kiln thermal diagnostic analysis method based on heat balance calculation, characterized in that: The analytical method includes: Obtain the thermal equilibrium state corresponding to the calculation of cement kiln thermal parameters and material composition data, and analyze the material balance relationship between the cement kiln material input and material output based on the law of conservation of mass; The ratio of the heat of cement kiln clinker formation to the total heat input is used as a thermal efficiency indicator to evaluate the energy utilization efficiency of the cement kiln firing system. The diagnostic index is generated by combining the thermal balance state with the material balance relationship. Compare diagnostic indicators with historical optimal operating values ​​to determine deviations, evaluate heat loss anomalies and operating status of the cement kiln thermal system based on the deviations, and construct a cause-and-effect diagram of the cement kiln thermal system operation; The development trend of cement kiln thermal engineering is predicted based on the operation cause-effect diagram and target constraints. A dynamic tuning model is constructed in combination with model predictive control technology to obtain the adaptive combustion control results of the cement kiln.

2. The cement kiln thermal diagnostic analysis method based on heat balance calculation according to claim 1, characterized in that: The diagnostic indicators are compared with the historical optimal operating values ​​to determine the deviation, the heat loss anomaly and operating status of the cement kiln thermal system are evaluated based on the deviation, and a cause-effect diagram of the cement kiln thermal system operation is constructed, including: Determine the historical operation optimal value and optimal operation state based on historical operation data, calculate the deviation between the diagnostic indicator and the historical operation optimal value, select the diagnostic indicator with a deviation value greater than the deviation threshold, and obtain the corresponding abnormal evaluation variable candidate set; Correlation analysis and support vector description technology are used to detect anomaly in the candidate set of abnormal evaluation variables, and the heat loss anomaly of the cement kiln thermal system is evaluated based on the detection results and enhanced local linear embedding technology; Based on the candidate set of abnormal evaluation variables, reference samples are selected to establish the original evaluation matrix, and the distance between the samples and the optimal operating state is determined. The operating state of the cement kiln thermal system is evaluated based on the distance results. Based on the candidate set of abnormal evaluation variables, heat loss anomalies and operating status of the cement kiln thermal system, the key variables affecting the thermal state are determined, and a causal diagram of the cement kiln thermal operation is constructed according to the causal relationship between the key variables.

3. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 2, characterized in that: The method of using correlation analysis and support vector description technology to detect anomaly on the candidate set of abnormal evaluation variables and using the enhanced local linear embedding technology to evaluate the heat loss anomaly of the cement kiln thermal process includes: Based on the abnormality assessment variable candidate set, two sets of random vectors are randomly generated, and the characteristic decomposition results of the abnormality assessment variable candidate set are obtained with the maximum correlation coefficient between the two sets of random vectors as the goal; The eigenvector corresponding to the eigendecomposition value whose eigendecomposition result meets the preset requirements is selected as the projection vector, and the optimal typical variable set is screened from the abnormal assessment variable candidate set based on the projection vector; The minimum hypersphere is constructed based on the optimal typical variable set, the distance between the candidate set of abnormal evaluation variables and the center of the minimum hypersphere is obtained, and the preliminary heat loss anomaly set corresponding to the candidate set of abnormal evaluation variables is obtained based on the distance result and the radius of the minimum hypersphere; The preliminary heat loss anomaly set is combined with the enhanced local linear embedding technique to generate a projection matrix, which is then used to obtain the direction vector representing the heat loss state to evaluate the heat loss anomaly of cement kiln thermal engineering.

4. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 3, characterized in that: The calculation formula of the minimum hypersphere radius is: Where R represents the minimum hypersphere radius, a b represents the projection vector, a c represents the cth optimal typical variable set, D AB represents the candidate set of abnormal evaluation variables; d c represents the optimal typical variable set a c The corresponding Lagrange multiplier, a e represents the e-th optimal typical variable set, d e represents the optimal typical variable set a e The corresponding Lagrange multiplier.

5. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 4, characterized in that: The preliminary heat loss anomaly set is combined with the enhanced local linear embedding technology to generate a projection matrix, and the projection matrix is ​​used to obtain the direction vector representing the heat loss state. The heat loss anomaly assessment of the cement kiln thermal system includes: Based on the preliminary heat loss anomaly set, several test samples are randomly generated, and the adjacent point set of each test sample is obtained. The connection weight between the test sample and the adjacent point set is determined to obtain the weight matrix; Projection analysis is performed on the weight matrix to obtain a projection matrix represented in two-dimensional space, and the topological structure of the projection matrix is ​​determined. Based on the topological structure, the direction vector formed by the projection matrix and the center point of the preliminary heat loss anomaly set is obtained to generate a test direction vector representing the heat loss state. The optimal operating state is used as the standard direction vector to represent the ideal state, and the angle between the test direction vector and the standard direction vector is determined as the abnormal value of heat loss in evaluating the thermal engineering of cement kiln.

6. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 5, characterized in that: The method of selecting reference samples based on the abnormal evaluation variable candidate set to establish an original evaluation matrix and determining the distance from the optimal operating state, and evaluating the operating state of the cement kiln thermal system based on the distance result includes: According to the key point selection requirements and partitioning requirements, key point reference samples and regional reference samples are selected from the abnormal evaluation variable candidate set, and the key point evaluation matrix and regional evaluation matrix are constructed to obtain the original evaluation matrix; Fuzzy processing is performed on the reference samples in the key point evaluation matrix and the regional evaluation matrix respectively, and the key point evaluation membership matrix and the regional evaluation membership matrix are obtained according to the processing results; Two groups of evaluation sequences with lengths that meet preset requirements are defined from the key point evaluation membership matrix and the regional evaluation membership matrix respectively. At the same time, two groups of standard sequences corresponding to the optimal operating state are selected according to the key point selection requirements and the partitioning requirements. Construct distance matrices based on the evaluation sequence and the standard sequence to determine the distance between the candidate set of abnormal evaluation variables and the optimal operating state; If the distance between the evaluation sequence and the standard sequence is less than the preset threshold, it indicates that the current operating state is ideal. If the distance between the evaluation sequence and the standard sequence is greater than or equal to the threshold, it indicates that the current operating state is abnormal.

7. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 1, characterized in that: The method of predicting the development trend of cement kiln thermal engineering based on the operation cause-effect diagram and target constraints, and building a dynamic tuning model in combination with model predictive control technology to obtain the cement kiln adaptive combustion control results includes: According to the objective function and constraint conditions of cement kiln thermal control, target constraint conditions are set, and the trend factors affecting the development of cement kiln thermal control are extracted from the operation cause-effect diagram to construct the development characteristic vector; The semantic decision tree is used to perform association cluster analysis on the development feature vectors to generate trend targets. The movement trend of the trend targets is predicted based on the target constraints and used as the development trend of cement kiln thermal engineering. A mathematical model for cement kiln adaptive combustion control is established, and feedback compensation is performed on the cement kiln combustion control in combination with the optimal operating state to output the optimal combustion control result of the cement kiln.

8. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 7, characterized in that: The semantic decision tree is used to perform association cluster analysis on the development feature vector to generate a trend target, and the movement trend of the trend target is predicted in combination with the target constraint conditions. The development trend of cement kiln thermal engineering includes: Determine the category to which the semantic decision tree node belongs according to the information of the development feature vector, and place the development feature vector into a two-dimensional data table based on the classification result to describe the relationship view of the development feature vector; Based on the relationship view results, the development feature vectors are divided into dynamic sets, the node concepts in the relationship view are associated, and the root node of the semantic decision tree is selected from the node concepts as the movement target; Determine the implicit state of the development feature vector according to the moving target, use the implicit state to convert the moving target's motion trend into the moving state prediction of the moving target, and represent the observed object based on the real spatial position corresponding to the moving target; The trend probability distribution of the observed object analysis is analyzed with the target constraint conditions as the boundary, and the associated area is constructed in the form of a fan-shaped wave gate according to the analysis results to predict the movement trend of the moving target as the development trend of cement kiln thermal engineering.

9. The method for thermal diagnosis and analysis of cement kilns based on heat balance calculation according to claim 8, characterized in that: The mathematical model for cement kiln adaptive combustion control is established, and feedback compensation is performed on the cement kiln combustion control in combination with the optimal operating state to output the optimal combustion control result of the cement kiln, including: Determine the combustion control component structure based on the cement kiln control process, and determine the cement kiln combustion control system structure according to the corresponding working principle of the component structure, and analyze the performance loss of each component structure during the control process; A mathematical model for cement kiln adaptive combustion control is established using performance loss as a constraint, and converted into a state-space equation. The state-space equation is processed by combining development trend-based and model predictive control technology. According to the processing results, the optimal controller of the cement kiln adaptive combustion control is obtained, and the cement kiln combustion control is feedback compensated based on the optimal controller and the optimal operating state, and the optimal combustion control result of the cement kiln is output.

10. A cement kiln thermal diagnostic analysis system based on heat balance calculation, used to implement the cement kiln thermal diagnostic analysis method based on heat balance calculation according to any one of claims 1 to 9, characterized in that: The analysis system includes: The balance relationship acquisition module is used to obtain the thermal balance state corresponding to the calculation of the thermal parameters of the cement kiln and the material composition data, and analyze the material balance relationship between the material input and material output of the cement kiln according to the law of conservation of mass; A diagnostic indicator generation module is used to evaluate the energy efficiency of the cement kiln firing system by using the ratio of the heat of cement kiln clinker formation to the total heat input as a thermal efficiency indicator. This module also generates diagnostic indicators by combining the thermal balance state with the material balance relationship. A cause-and-effect diagram construction module is used to compare diagnostic indicators with historical operating optimal values ​​to determine deviations, evaluate heat loss anomalies and operating status of the cement kiln thermal system based on the deviations, and construct a cause-and-effect diagram of the cement kiln thermal system operation; The dynamic tuning control module is used to predict the development trend of cement kiln thermal engineering based on the operation cause-effect diagram and target constraints, and to build a dynamic tuning model in combination with model predictive control technology to obtain the adaptive combustion control results of the cement kiln.

Images