CN116628576B

CN116628576B - Intelligent production yield monitoring method for heat carrier lime kiln

Info

Publication number: CN116628576B
Application number: CN202310919044.3A
Authority: CN
Inventors: 郭华; 邓胜祥
Original assignee: Central South University
Current assignee: Central South University
Priority date: 2023-07-26
Filing date: 2023-07-26
Publication date: 2023-10-13
Anticipated expiration: 2043-07-26
Also published as: CN116628576A

Abstract

The embodiment of the specification discloses an intelligent production yield monitoring method for a heat carrier lime kiln, and relates to the technical field of neural networks. The method comprises the following steps: determining corresponding data points at each moment based on the temperature data and the CO2 content data; determining category similarity between two adjacent CO2 content data according to two adjacent data points; classifying the CO2 content data according to the category similarity, wherein each classification corresponds to a production stage, and the production stage comprises a first stage, a second stage and a third stage; determining the CO2 content and the lime yield generated by limestone decomposition in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage; and training the CNN and MLP mixed neural network by taking the lime yield and the current production operation parameters as training data to obtain a trained yield prediction model.

Description

Intelligent production yield monitoring method for heat carrier lime kiln

Technical Field

The invention relates to the technical field of neural networks, in particular to an intelligent production yield monitoring method for a heat carrier lime kiln.

Background

Lime, calcium oxide, is widely used in the iron and steel industry, calcium carbide industry, alumina industry, etc., and is one of the production raw materials necessary for the production in these large-scale industrial fields. The existing lime preparation technology is to put limestone and solid fuel (coal dust and the like) into a heat carrier lime kiln, calcine the limestone by the heat released by fuel combustion, heat the limestone to a certain temperature, start to decompose, and form a lime finished product under the conditions of higher temperature and continuous heating; and cooling the generated lime, discharging the cooled lime out of the kiln, and thus completing the production of the quicklime product.

When the production yield of the heat carrier lime kiln is monitored, the chemical reaction of lime produced by limestone is CaCO 3(s) -CaO(s) +CO2 (g), so that the yield of lime can be obtained by monitoring the content of CO2 produced after limestone decomposition (impurities exist in the limestone, and the direct measurement of CaO content is not accurate enough). However, when monitoring the content of CO2 in the lime kiln, since CO2 is also generated by burning fuel, impurities in the limestone may react at high temperature to generate CO2 with a certain content, therefore, the direct use of the content of CO2 to perform characterization monitoring on the yield of lime may have a problem of inaccurate measurement, and if the direct use of the content of CO2 as final yield data is used for training the CNN and MLP hybrid neural network, the prediction classification precision of the yield is reduced, and further, the control and adjustment of parameters by an operator are affected.

Based on the above, it is necessary to research a more accurate and reasonable intelligent production yield monitoring method for a heat carrier lime kiln so as to accurately monitor the yield of lime.

Disclosure of Invention

Embodiments of the present disclosure provide an intelligent production yield monitoring method for a heat carrier lime kiln, the method comprising:

acquiring temperature data and CO2 content data in the production process of the heat carrier lime kiln;

determining corresponding data points at each moment based on the temperature data and the CO2 content data, wherein each data point comprises one temperature data and one CO2 content data;

determining category similarity between two adjacent CO2 content data according to two adjacent data points;

classifying the CO2 content data according to the category similarity, wherein each classification corresponds to a production stage, and the production stages comprise a first stage, a second stage and a third stage which are arranged in sequence;

determining the content of CO2 generated by limestone decomposition in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage;

determining a lime yield based on the CO2 content produced by limestone decomposition in the third stage;

Training a CNN and MLP mixed neural network by taking the lime yield and the current production operation parameters as training data to obtain a trained yield prediction model, and monitoring a real-time lime yield classification result predicted by the trained yield prediction model; the current production operation parameters comprise an upper arch bridge temperature, a circulating gas temperature, a lower combustion chamber temperature, a heat exchanger exhaust outlet temperature, a heat exchanger exhaust inlet temperature, a cooling air loop temperature, a furnace top waste gas temperature, an upper combustion chamber gas flow, a lower combustion chamber gas flow, an upper cooling flow, a driving fan flow and a feeding weight.

In some embodiments, the determining the category similarity between the two adjacent CO2 content data from the two adjacent data points comprises:

determining the CO2 content change rate corresponding to the current data point based on the CO2 content difference value and the time difference value corresponding to the current data point and the previous data point;

determining a rate of increase corresponding to the current data point based on a difference in the rate of change of the CO2 content corresponding to the current data point and the previous data point and a maximum value of the rate of change of the CO2 content corresponding to the current data point and the previous data point;

And obtaining the category similarity between the current data point and the previous data point according to the difference value of the rate increase rate corresponding to the current data point and the previous data point and the temperature difference value.

In some embodiments, the rate of change of the CO2 content corresponding to the current data point is:

wherein ,for the rate of change of the CO2 content corresponding to the current data point,the CO2 content data corresponding to the current data point,for the CO2 content data corresponding to the previous data point,for the acquisition time corresponding to the current data point,the acquisition time corresponding to the previous data point;

the rate of increase corresponding to the current data point is:

wherein ,for the rate of increase corresponding to the current data point,the rate of change of the CO2 content corresponding to the previous data point,representation selectionMaximum value of (2);

the class similarity between the current data point and the previous data point is:

wherein ,for class similarity between a current data point and the previous data point,andthe rate of increase corresponding to the current data point and the previous data point respectively,andtemperature data corresponding to the current data point and the previous data point respectively.

In some embodiments, the classifying the CO2 content data according to the category similarity includes:

when the category similarity between n continuous data points and a reference data point is smaller than a preset similarity judging threshold, taking the reference data point as the last data point corresponding to the previous production stage, and obtaining the category corresponding to each production stage; wherein the reference data point is an adjacent data point positioned before the forefront data point in the continuous n data points, and n is a preset positive integer.

In some embodiments, the determining the category similarity between the two adjacent CO2 content data from the two adjacent data points further comprises:

determining an optimization coefficient corresponding to a current data point according to the time difference value, the CO2 content change rate difference value and the rate increase rate difference value between the current data point and all data points positioned in front of the current data point in the current category;

and obtaining the optimized category similarity based on the category similarity and the optimization coefficient.

In some embodiments, the optimization factor corresponding to the current data point is:

wherein A is the optimization coefficient corresponding to the current data point, Andthe rate of increase and the rate of change of the CO2 content corresponding to the current data point,for the acquisition time corresponding to the current data point,for the acquisition time corresponding to the i-th data point in the current class that is located before the current data point,andthe rate of increase and the rate of change of the CO2 content corresponding to the i data point in the current class preceding the current data point,for the number of data points in the current class that precede the current data point,is a fixed parameter for preventing denominator from being 0;

the optimized category similarity is as follows:

wherein ,for the optimized category similarity, Y is the category similarity before optimization.

In some embodiments, the classifying the CO2 content data according to the category similarity includes: and classifying the CO2 content data based on the optimized category similarity.

In some embodiments, the determining the CO2 content generated by limestone decomposition in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage includes:

determining a first generation rate corresponding to CO2 generated by fuel combustion based on the CO2 content data corresponding to the first stage;

Determining a second generation rate corresponding to CO2 generated by the impurity based on the CO2 content data corresponding to the second stage and the first generation rate;

obtaining the total amount of CO2 generated by fuel combustion based on the CO2 content generated in the first stage, the time difference value corresponding to the current CO2 content data and the last data point of the first stage, and the first generation rate;

obtaining the total amount of CO2 generated by impurities based on the CO2 content generated by the second stage, the CO2 content generated by the combustion of the fuel in the second stage, the time difference value corresponding to the current CO2 content data and the last data point of the second stage, and the second generation rate;

the CO2 content produced by limestone decomposition in the third stage is determined based on the current CO2 content data in the third stage, the total amount of CO2 produced by fuel combustion, and the total amount of CO2 produced by impurities.

In some embodiments, the determining a second rate of production for CO2 produced by the impurity based on the CO2 content data corresponding to the second stage and the first rate of production comprises:

and determining a second generation rate corresponding to CO2 generated by impurities according to the CO2 content data corresponding to the last m data points in the second stage and the first generation rate.

In some embodiments, the deriving the total amount of CO2 produced by the impurity based on the CO2 content produced by the second stage, the CO2 content produced by the combustion of the fuel in the second stage, the time difference between the current CO2 content data and the last data point of the second stage, and the second rate of formation comprises:

judging whether the CO2 content change rate corresponding to CO2 generated by the impurity reaches a stable state before entering the third stage based on the second generation rate;

if the stable state is not reached, determining a mutation point in the third stage based on the CO2 content data in the third stage, and determining the time and the CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching the stable state based on the mutation point;

determining the total amount of CO2 generated after the CO2 content change rate generated by the impurity reaches a steady state based on the difference value of the current CO2 content data and the time corresponding to the CO2 content change rate generated by the impurity reaching a steady state and the CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching a steady state;

Determining the total amount of CO2 generated before the CO2 content change rate generated by the impurities reaches a steady state through integral operation;

and obtaining the total amount of CO2 generated by the impurities based on the total amount of CO2 generated by the CO2 content change rate after reaching the steady state and the total amount of CO2 generated before reaching the steady state.

The intelligent production yield monitoring method for the heat carrier lime kiln provided by the embodiment of the specification has the following beneficial effects: (1) The method comprises the steps of adaptively analyzing the production process of lime production by decomposing limestone, adaptively classifying generated CO2 based on temperature data and CO2 content data in the production process, dividing the CO2 into different production processes, adaptively decomposing CO2 content data acquired by a sensor based on the change characteristics of the CO2 content in the different production processes, dividing the CO2 content data into CO2 content generated by fuel combustion, and generating impuritiesThe content of CO2 generated by the chemical reaction and the content of CO2 generated by the pyrolysis of the limestone can accurately calculate the yield of the lime based on the content of CO2 generated by the pyrolysis of the limestone, and the interference of CO2 generated by fuel combustion and impurity reaction on the calculation of the yield of the lime is eliminated; (2) By using in calculating class similarity Constraint is carried out, so that the calculation accuracy of category similarity can be improved, and inaccurate data classification caused by the influence of temperature on the change of the content of CO2 is avoided; (3) The category similarity of the local data points is optimized through the overall change trend of the data points in the categories, so that the category judgment precision of the data points can be improved, and the precision and the efficiency of the follow-up yield monitoring are improved; (4) The mixed neural network of CNN and MLP is trained by using the lime yield and the current production operation parameters as training data to obtain a trained yield prediction model, then the production operation parameters are calculated by using the trained yield prediction model, the corresponding yield classification is obtained by prediction, an operator can timely know the yield classification under the current production operation parameters, and then corresponding operation is carried out on each parameter according to the corresponding regulation and control strategies of different categories, so that the purpose of improving the yield is achieved.

Additional features will be set forth in part in the description which follows. As will become apparent to those skilled in the art upon review of the following and drawings, or may be learned by the production or operation of the examples. The features of the present specification can be implemented and obtained by practicing or using the various aspects of the methods, tools, and combinations set forth in the detailed examples below.

Drawings

The present specification will be further described by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a schematic illustration of an exemplary application scenario for an intelligent production yield monitoring system for a heat carrier lime kiln, shown in accordance with some embodiments of the present description;

FIG. 2 is an exemplary block diagram of an intelligent production yield monitoring system for a heat carrier lime kiln, shown in accordance with some embodiments of the present description;

fig. 3 is an exemplary flow chart of an intelligent production yield monitoring method for a heat carrier lime kiln according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It should be appreciated that as used in this specification, a "system," "apparatus," "unit" and/or "module" is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

The following describes in detail the method and system for monitoring the intelligent production yield of a heat carrier lime kiln provided in the embodiments of the present specification with reference to the accompanying drawings.

Fig. 1 is a schematic illustration of an exemplary application scenario of an intelligent production yield monitoring system for a heat carrier lime kiln according to some embodiments of the present description.

Referring to fig. 1, in some embodiments, an application scenario 100 of an intelligent production yield monitoring system for a heat carrier lime kiln may include a data acquisition device 110, a storage device 120, a processing device 130, a terminal device 140, and a network 150. The various components in the application scenario 100 may be connected in a variety of ways. For example, the data acquisition device 110 may be connected to the storage device 120 and/or the processing device 130 through the network 150, or may be directly connected to the storage device 120 and/or the processing device 130. As another example, the storage device 120 may be directly connected to the processing device 130 or connected via the network 150. For another example, the terminal device 140 may be connected to the storage device 120 and/or the processing device 130 through the network 150, or may be directly connected to the storage device 120 and/or the processing device 130.

The data acquisition device 110 can be used for acquiring temperature data and CO2 content data in the production process of the heat carrier lime kiln. As shown in fig. 1, the data acquisition device 110 may include a temperature sensor 111 and a CO2 sensor 112, where the temperature sensor 111 may be used to acquire a temperature inside the heat carrier lime kiln, and the CO2 sensor 112 may be used to acquire a CO2 content inside the heat carrier lime kiln (i.e., a concentration that may reflect a change in an amount of a substance corresponding to CO2 inside the heat carrier lime kiln). In some embodiments, the temperature sensor 111 and the CO2 sensor 112 may synchronously collect temperature data and CO2 content data (e.g., every 5 seconds, 10 seconds, or other time period) inside the heat carrier lime kiln at a set data collection frequency. In some embodiments, the temperature sensor 111 and the CO2 sensor 112 may have independent power sources that may send the collected temperature data and CO2 content data to other components (e.g., the storage device 120, the processing device 130, the terminal device 140) in the application scenario 100 by wired or wireless (e.g., bluetooth, wiFi, etc.). In some embodiments, the application scenario 100 may include a plurality of (e.g., two or more) temperature sensors 111 and a plurality of CO2 sensors 112, where the plurality of temperature sensors 111 and the plurality of CO2 sensors 112 may respectively collect temperature data and CO2 content data for the inside of the heat carrier lime kiln, and compare and verify the collected data, so as to ensure accuracy and reliability of the data.

In some embodiments, the data acquisition device 110 may send the temperature data and the CO2 content data it acquires to the storage device 120, the processing device 130, the terminal device 140, etc. through the network 150. In some embodiments, the temperature data and the CO2 content data acquired by the data acquisition device 110 may be processed by the processing apparatus 130. For example, the processing plant 130 may determine the CO2 content generated by limestone decomposition based on the temperature data and the CO2 content data and determine the lime production based on the CO2 content. In some embodiments, the CO2 content resulting from limestone decomposition and/or the lime production determined based on the CO2 content may be sent to a storage device 120 for recording or to a terminal device 140 for feedback to a user (e.g., an associated worker of the lime production line).

Network 150 may facilitate the exchange of information and/or data. The network 150 may include any suitable network capable of facilitating the exchange of information and/or data of the application scenario 100. In some embodiments, at least one component of the application scenario 100 (e.g., the data acquisition device 110, the storage device 120, the processing device 130, the terminal device 140) may exchange information and/or data with at least one other component in the application scenario 100 via the network 150. For example, the processing device 130 may obtain temperature data and CO2 content data collected for the interior of the heat carrier lime kiln from the data collection apparatus 110 and/or the storage device 120 via the network 150. For another example, the processing device 130 may obtain user operating instructions from the terminal device 140 over the network 150, and exemplary operating instructions may include, but are not limited to, retrieving temperature data and CO2 content data, reading CO2 content resulting from limestone decomposition determined based on the temperature data and the CO2 content data, and/or lime production determined based on the CO2 content, etc.

In some embodiments, network 150 may be any form of wired or wireless network, or any combination thereof. By way of example only, the network 150 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, and the like, or any combination thereof. In some embodiments, the network 150 may include at least one network access point through which at least one component of the application scenario 100 may connect to the network 150 to exchange data and/or information.

Storage 120 may store data, instructions, and/or any other information. In some embodiments, the storage device 120 may store data obtained from the data acquisition apparatus 110, the processing device 130, and/or the terminal device 140. For example, the storage device 120 may store temperature data and CO2 content data acquired by the data acquisition apparatus 110; for another example, the storage device 120 may store the CO2 content resulting from the limestone decomposition calculated by the processing device 130 and/or the lime yield determined based on the CO2 content. In some embodiments, the storage device 120 may store data and/or instructions that the processing device 130 uses to perform or use to implement the exemplary methods described in this specification. In some embodiments, the storage device 120 may include mass memory, removable memory, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, storage device 120 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

In some embodiments, the storage device 120 may be connected to the network 150 to communicate with at least one other component (e.g., the data acquisition apparatus 110, the processing device 130, the terminal device 140) in the application scenario 100. At least one component in the application scenario 100 may access data, instructions, or other information stored in the storage device 120 through the network 150. In some embodiments, the storage device 120 may be directly connected or in communication with one or more components (e.g., the data acquisition apparatus 110, the terminal device 140) in the application scenario 100. In some embodiments, the storage device 120 may be part of the data acquisition apparatus 110 and/or the processing device 130.

The processing device 130 may process data and/or information obtained from the data acquisition apparatus 110, the storage device 120, the terminal device 140, and/or other components of the application scenario 100. In some embodiments, the processing device 130 may obtain temperature data and CO2 content data from any one or more of the data acquisition apparatus 110, the storage device 120, or the terminal device 140, determine the CO2 content resulting from limestone decomposition by processing the temperature data and the CO2 content data, and determine the lime production based on the CO2 content. In some embodiments, the processing device 130 may retrieve pre-stored computer instructions from the storage device 120 and execute the computer instructions to implement the intelligent production yield monitoring method for a heat carrier lime kiln described herein.

In some embodiments, the processing device 130 may be a single server or a group of servers. The server farm may be centralized or distributed. In some embodiments, the processing device 130 may be local or remote. For example, the processing device 130 may access information and/or data from the data acquisition device 110, the storage device 120, and/or the terminal device 140 via the network 150. As another example, the processing device 130 may be directly connected to the data acquisition apparatus 110, the storage device 120, and/or the terminal device 140 to access information and/or data. In some embodiments, the processing device 130 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

Terminal device 140 may receive, transmit, and/or display data. The received data may include data collected by the data collection device 110, data stored by the storage device 120, CO2 content generated by limestone decomposition and/or lime yield determined based on the CO2 content, etc., processed by the processing device 130. The transmitted data may include input data and instructions from a user, such as a worker associated with a lime production line, etc. For example, the terminal device 140 may send an operation instruction input by the user to the data acquisition device 110 through the network 150, so as to control the data acquisition device 110 to perform corresponding data acquisition. For another example, the terminal device 140 may transmit the data processing instruction input by the user to the processing device 130 through the network 150.

In some embodiments, terminal device 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, or the like, or any combination thereof. For example, mobile device 141 may include a mobile telephone, a Personal Digital Assistant (PDA), a dedicated mobile terminal, or the like, or any combination thereof. In some embodiments, terminal device 140 may include input devices (e.g., keyboard, touch screen), output devices (e.g., display, speaker), etc. In some embodiments, the processing device 130 may be part of the terminal device 140.

It should be noted that the above description about the application scenario 100 is only for illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the application scenario 100 may be made by those skilled in the art under the guidance of the present specification. However, such modifications and variations are still within the scope of the present description. For example, the data acquisition device 110 may include more or fewer functional components.

Fig. 2 is a block diagram of an intelligent production yield monitoring system for a heat carrier lime kiln according to some embodiments of the present disclosure. In some embodiments, the intelligent production yield monitoring system 200 for a heat carrier lime kiln shown in fig. 2 may be applied to the application scenario 100 shown in fig. 1 in software and/or hardware, for example, may be configured in software and/or hardware to the processing device 130 and/or the terminal device 140 for processing the temperature data and CO2 content data collected by the data collection device 110, and determining the CO2 content generated by limestone decomposition based on the temperature data and the CO2 content data, and determining the lime yield based on the CO2 content.

Referring to fig. 2, in some embodiments, an intelligent production yield monitoring system 200 for a heat carrier lime kiln may include an acquisition module 210, a data point determination module 220, a category similarity determination module 230, a classification module 240, a CO2 content determination module 250, a lime yield determination module 260, and a training module 270.

The acquisition module 210 may be used to acquire temperature data and CO2 content data during the production of the heat carrier lime kiln.

The data point determination module 220 may be configured to determine a corresponding data point for each time based on the temperature data and the CO2 content data.

The category similarity determination module 230 may be configured to determine a category similarity between two adjacent CO2 content data based on two of the data points.

The classification module 240 may be configured to classify the CO2 content data according to the category similarities, wherein each classification corresponds to a production phase including a first phase, a second phase, and a third phase in a sequential order.

The CO2 content determination module 250 may be configured to determine the CO2 content generated by limestone decomposition in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage.

The lime yield determination module 260 may be configured to determine lime yield based on the CO2 content produced by limestone decomposition in the third stage.

The training module 270 may be configured to train the mixed neural network of CNN and MLP with the lime output and the current production operation parameters as training data to obtain a trained output prediction model, where the current production operation parameters include an upper arch bridge temperature, a circulating gas temperature, a lower combustion chamber temperature, a heat exchanger exhaust outlet temperature, a heat exchanger exhaust inlet temperature, a cooling air loop temperature, a top exhaust gas temperature, an upper combustion chamber gas flow, a lower combustion chamber gas flow, an upper cooling flow, a driving fan flow, and a loading weight.

For more details on the above-mentioned respective modules, reference may be made to other locations in the present specification (for example, the related description of fig. 3), and a detailed description thereof will be omitted.

It should be appreciated that the intelligent production yield monitoring system 200 for a heat carrier lime kiln shown in fig. 2 and its modules may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system of the present specification and its modules may be implemented not only with hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software executed by various types of processors, for example, and with a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the intelligent production yield monitoring system 200 for a heat carrier lime kiln is provided for illustrative purposes only and is not intended to limit the scope of the present description. It will be appreciated by those skilled in the art from this disclosure that various modules may be combined arbitrarily or constituting a subsystem in connection with other modules without departing from this concept. For example, the acquisition module 210, the data point determination module 220, the category similarity determination module 230, the classification module 240, the CO2 content determination module 250, the lime yield determination module 260, and the training module 270 described in fig. 2 may be different modules in one system, or may be one module to implement the functions of two or more modules. As another example, the intelligent production yield monitoring system 200 for a heat carrier lime kiln may also include a data screening module (not shown in fig. 2) that may be used to screen the temperature data and CO2 content data collected by the aforementioned plurality of temperature sensors 111 and plurality of CO2 sensors 112 to determine target data for subsequent calculations. Such variations are within the scope of the present description. In some embodiments, the foregoing modules may be part of the processing device 130 and/or the terminal device 140.

Fig. 3 is an exemplary flow chart of an intelligent production yield monitoring method for a heat carrier lime kiln according to some embodiments of the present description. In some embodiments, method 300 may be performed by processing logic that may comprise hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (instructions run on a processing device to perform hardware simulation), or the like, or any combination thereof. In some embodiments, one or more operations in the flow chart of the intelligent production yield monitoring method 300 for a heat carrier lime kiln shown in fig. 3 may be implemented by the processing device 130 and/or the terminal device 140 shown in fig. 1. For example, method 300 may be stored in storage device 120 in the form of instructions and invoked and/or executed by processing device 130 and/or terminal device 140. The execution of method 300 is described below using processing device 130 as an example.

Referring to fig. 3, in some embodiments, an intelligent production yield monitoring method 300 for a heat carrier lime kiln may include:

and 310, acquiring temperature data and CO2 content data in the production process of the heat carrier lime kiln. In some embodiments, step 310 may be performed by the acquisition module 210.

In some embodiments, temperature data (denoted wd) during the production of the heat carrier lime kiln may be collected by a temperature sensor 111 and CO2 content data (denoted R) in the heat carrier lime kiln may be collected by a CO2 sensor 112. In some embodiments, the acquisition module 210 may acquire the temperature data directly from the temperature sensor 111 and the CO2 content data directly from the CO2 sensor 112. In some embodiments, the temperature data and the CO2 content data may also be stored to the storage device 120, and the acquisition module 210 may acquire the temperature data and the CO2 content data from the storage device 120.

Step 320, determining a data point corresponding to each time based on the temperature data and the CO2 content data. In some embodiments, step 320 may be performed by data point determination module 220.

In the embodiment of the present disclosure, the temperature data collected by the temperature sensor 111 and the CO2 content data collected by the CO2 sensor 112 may be time series data, which may be collected synchronously from the time of lime kiln heating production, and each sensor may obtain one time series data. Specifically, each data acquisition time may correspond to a data point, each data point including one temperature data acquired by the temperature sensor 111 and one CO2 content data acquired by the CO2 sensor 112.

Step 330, determining the category similarity between the adjacent two CO2 content data according to the adjacent two data points. In some embodiments, step 330 may be performed by category similarity determination module 230.

The above steps 310 and 320 can complete the collection of relevant data in lime production process in the lime kiln, but the CO2 content data collected by the CO2 sensor 112 includes CO2 generated by lime decomposition in lime production, CO2 generated by fuel combustion, and CO2 generated by reaction of impurities in the lime at high temperature. Therefore, after acquiring the CO2 content data acquired by the CO2 sensor 112, further analysis of the CO2 content data R is required.

From a priori knowledge, the CO2 content data collected by the CO2 sensor 112, wherein Represents the CO2 content data generated when lime is decomposed in limestone production,data representing the CO2 content produced by the combustion of the fuel,data representing the CO2 content of limestone impurities reacted at high temperatures. Based on this, in the examples of the present specification, the CO2 content data R is adaptively decomposed based on the characteristics of the limestone decomposition chemical reaction and the variation of the CO2 content during the production process, and decomposed into 、、. And useTo complete the monitoring of lime yield in the lime kiln.

For the whole lime production process, in the initial stage of the production process, as limestone and fuel are just put in, the fuel burns to release heat, the temperature in the lime kiln is increased, the temperature in the lime kiln is lower, the limestone and impurities in the lime kiln cannot chemically react, and only the CO2 content generated by the fuel burning at the moment can be adaptively constructed based on the CO2 content change in the initial stage of the production process. In the middle of the production process, as the temperature in the lime kiln reaches a certain height, partial impurities in the limestone can react at a high temperature to generate CO2, and meanwhile, CO2 generated by fuel combustion can also exist. For the later stage of the production process, limestone starts to decompose to form lime, and CO2 is generated simultaneously, and simultaneouslyThere is also CO2 generated by the impurity reaction and CO2 generated by the combustion of fuel. Based on this, in some embodiments of the present disclosure, the adaptive classification of the production process may be completed according to the temperature data and the variation characteristics of the CO2 content data in the production process, and the production process is divided into three stages, wherein the first stage is the initial stage of production, and the CO2 content data is mainly affected by CO2 generated by the combustion of the fuel; the second stage is the middle production stage, and the CO2 content data is mainly influenced by CO2 generated by chemical reaction of partial impurities at high temperature and CO2 generated by fuel combustion; in the third stage of production, CO2 content data is influenced by CO2 generated by fuel combustion, CO2 generated by chemical reaction of impurities and CO2 generated by limestone decomposition.

In the description, the terms early, middle and late production are used only for convenience of distinction and are not actual production periods.

In some embodiments, temperature data and CO2 content data collected during the production process may be analyzed in time sequence, and by classifying in time sequence, the CO2 content data is classified into three types, which correspond to the initial stage of production (i.e., the first stage), the middle stage of production (i.e., the second stage), and the later stage of production (i.e., the third stage).

In some embodiments, to classify the CO2 content data acquired by the CO2 sensor 112, a class similarity between two adjacent CO2 content data may be determined from two adjacent data points. Specifically, in some embodiments, the category similarity determination module 230 may determine the rate of change of the CO2 content corresponding to the current data point based on the difference in CO2 content and the time difference corresponding to the current data point and the previous data point; then, determining the rate of increase corresponding to the current data point based on the difference value of the rate of change of the CO2 content corresponding to the current data point and the previous data point and the maximum value of the rate of change of the CO2 content corresponding to the current data point and the previous data point; and finally, obtaining the category similarity between the current data point and the previous data point according to the difference value of the rate of increase corresponding to the current data point and the previous data point and the temperature difference value.

In some embodiments, the rate of change of the CO2 content corresponding to the current data point may be expressed as:

wherein ,for the rate of change of the CO2 content corresponding to the current data point,the CO2 content data corresponding to the current data point,for the CO2 content data corresponding to the previous data point,for the acquisition time corresponding to the current data point,the acquisition time corresponding to the previous data point.

The rate of increase corresponding to the current data point can be expressed as:

wherein ,for the rate of increase corresponding to the current data point,the rate of change of the CO2 content corresponding to the previous data point,representation selectionIs the maximum value of (a).

The class similarity between the current data point and the previous data point can be expressed as:

In the embodiment of the present specification, the foregoingCan be mutually constrained. Specifically, when the difference between the two is larger, the category similarity is larger, the purpose of the method is to make the temperature change larger, and the category similarity of the data points with larger rate of increase change is larger, so that the calculation accuracy of the category similarity is improved, and the inaccuracy of data classification caused by the influence of the temperature on the change of the content of CO2 is avoided.

Step 340, classifying the CO2 content data according to the category similarity, wherein each classification corresponds to a production phase, and the production phase comprises a first phase, a second phase and a third phase in sequence. In some embodiments, step 340 may be performed by classification module 240.

It will be appreciated that the greater the class similarity Y, the greater the likelihood that the current data point will be of the same production time period as the previous data point. In some embodiments, the class similarity determination threshold may be set to 0.8, where when the class similarity is greater than or equal to the set class similarity determination threshold, the current data point and the previous data point may be regarded as the same class of data points, and otherwise, the current data point and the previous data point are regarded as different class of data points, corresponding to different production stages.

In some embodiments, when the category similarity between n consecutive data points and the reference data point is smaller than the preset similarity determination threshold, the reference data point may be taken as the last data point corresponding to the previous production stage, where the reference data point refers to an adjacent data point located before the forefront data point in the n consecutive data points.

Specifically, after the classification similarity between the q point (current data point) and the a point (previous data point, that is, the reference data point) is judged according to the above steps, if the q point and the a point are not similar data points, the b point of the adjacent data point at the next moment of the q point is obtained, the above judgment is performed on the b point and the a point, if the b point and the a point are also not similar data points, the above steps are repeated, the adjacent data point at the next moment of the b point is judged with the a point, and when 3 (i.e., the n may be equal to 3) data points and the a point are not similar data points continuously appear, the a point can be the last data point of the previous classification, and the judgment acquisition of the initial data point or the mid-production data point is completed. It should be noted that 3 data points herein are empirically set values, which can be adjusted according to actual requirements.

In contrast, if the q point and the a point are similar data points, the adjacent data point b point of the next moment is acquired for the q point, and the steps are repeated for the b point and the q point to judge whether the adjacent data point b is similar data point. If the data points are similar data points, repeating the steps for the point b until the continuous 3 data points and the current judging data point (such as the point b) are not similar data points, and completing judging and acquiring the initial production data point or the middle production data point.

When the data points in the initial stage of production are determined based on the category similarity in the above steps, the determination accuracy in the initial stage is relatively high, but the determination accuracy at the boundary between the category in the initial stage of production and the category in the middle stage of production is relatively poor.

In some embodiments, the category similarity of the data points can be optimized through the CO2 content change trend of the data points in the current category, so that the optimized category similarity is obtained. Specifically, as CO2 is generated during the combustion of the fuel, the content of CO2 in the lime kiln is continuously increased, and the combustion of the fuel is possibly incomplete due to lower early temperature during the combustion, so that gases such as CO and the like can be generated, the quantity of generated CO2 is small, the combustion of the fuel is more complete along with the increase of the temperature, and the quantity of generated CO2 gradually increases and then tends to be stable, and is the trend of changing the content of CO2 in the initial stage of production.

Based on this, in some embodiments, the step of determining the category similarity between two adjacent CO2 content data from two adjacent data points may further comprise: determining an optimization coefficient corresponding to a current data point according to the time difference value, the CO2 content change rate difference value and the rate increase rate difference value between the current data point and all data points positioned in front of the current data point in the current category; and then, obtaining the optimized category similarity based on the optimization coefficient and the category similarity obtained through calculation in the previous steps.

Taking a certain data point c as an example, the class similarity of the c point is optimized, and then the optimization coefficient corresponding to the current data point c may be expressed as:

wherein A is the optimization coefficient corresponding to the current data point,andthe rate of increase and the rate of change of the CO2 content corresponding to the current data point,for the acquisition time corresponding to the current data point,for the acquisition time corresponding to the i-th data point in the current class that is located before the current data point,andthe rate of increase and the rate of change of the CO2 content corresponding to the i data point in the current class preceding the current data point,for the number of data points in the current class that precede the current data point,a fixed parameter (0.001 may be set in this specification) for preventing the denominator from being 0.

The optimized class similarity can be expressed as:

It can be understood that in the embodiment of the present disclosure, the optimization coefficient a optimizes the category similarity of the local data points through the overall variation trend of the data points in the category, so that the category judgment precision of the data points can be improved, and further, the precision and the efficiency of the subsequent yield monitoring can be improved.

It should be further noted that, in some embodiments of the present disclosure, when the optimization coefficient is sampled to calculate the optimized class similarity, the step 340 may include: and classifying the CO2 content data based on the optimized category similarity.

Step 350, determining the content of CO2 generated by decomposing limestone in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage. In some embodiments, step 350 may be performed by the CO2 content determination module 250.

In classifying the CO2 content data according to the above steps, for the initial (i.e., first stage) data points of production, the later the time the data points correspond to the more stable, nearly constant rate of change of CO2 content, because the only fuel that produces CO2 in the initial stage of production burns, and when the temperature is higher, the more complete the fuel burns and then tends to stabilize. I.e. the rate of change of the CO2 content tends to be stable. Based on this, in some embodiments, a first rate of production of CO2 generated by combustion of the fuel may be determined based on the CO2 content data corresponding to the first stage. Specifically, the last m data points (m may be 20) at the end of the initial period of production and located in the initial period of production can be obtained, and then the CO2 content change rate with the highest occurrence frequency is taken as the first CO2 generation rate when the fuel is completely combusted according to the CO2 content change rate of the m data points, and is recorded as 。

Further, assuming that the starting point of the mid-production (i.e., second stage) data point is the f point (which is the data point next to the last data point G in the early stage of production), and that some impurities in the limestone begin to react chemically to produce CO2, the above-described data point class determination step (wherein the rate of change of the CO2 concentration of the corresponding data point, such as for the u point,the rate of change of the CO2 content calculated for the above formula is used in making the category judgment as follows=-U2) until the discrimination stop requirement is reached, a mid-production correspondence data point may be determined. Assuming that the last data point corresponding to mid-production is point F, the data points following data point F may be recorded as mid-production data points. In some embodiments, the CO2 content data corresponding to the last m data points in the second stage (i.e. mid-production stage) and the first production rate can be usedA second rate of formation corresponding to CO2 produced by the impurity is determined.

After the production process is divided into three stages by the steps, the data point with the rate of change of CO2 content of 0 and the highest CO2 content in the production data can be recorded as the z point (the corresponding CO2 content is recorded as ) It can be considered that at the z-point the lime kiln has stopped production.

It will be appreciated that since chemical reactions that occur at high temperatures tend to occur at higher temperatures at faster rates, when the temperature reaches a certain level, the rate of reaction is not increased again, approximating the characteristics of fuel combustion changes. There are two cases for the middle of production.

The first case is that the rate of CO2 generated by chemical reaction of impurities is stabilized before entering the third stage, when limestone (CaCO 3) is not decomposed to generate CO2, the second rate of CO2 generated by impurities can be obtained according to the initial change characteristic of the production, and is recorded as。

The second case is that the rate of CO2 production by the chemical reaction of the impurity does not reach a steady state before entering the third stage, at this time, a mutation point in the third stage (the mutation point may be regarded as a turning point at which the rate of CO2 production by the chemical reaction of the impurity is unstable to a temperature) needs to be determined based on the CO2 content data in the third stage, and a time and a CO2 content change rate corresponding to the time when the CO2 content change rate corresponding to the CO2 produced by the impurity reaches a steady state are determined based on the mutation point; then, determining the total amount of CO2 generated after the CO2 content change rate generated by the impurity reaches a steady state based on the difference between the current CO2 content data and the time corresponding to the CO2 content change rate generated by the impurity reaching a steady state and the CO2 content change rate corresponding to the CO2 generated by the impurity reaching a steady state; finally, the total amount of CO2 generated by the impurity before the CO2 content change rate reaches the steady state is determined by an integral operation, and the total amount of CO2 generated by the impurity is obtained based on the total amount of CO2 generated by the CO2 content change rate after the steady state is reached and the total amount of CO2 generated before the steady state is reached.

Specifically, in some embodiments, the CO2 content determination module 250 may determine whether the rate of change of the CO2 content corresponding to CO2 generated by the impurity reaches a steady state before entering the third stage according to the CO2 content data corresponding to the last m data points in the second stage.

For the first case, if the rate of change of the CO2 content corresponding to the CO2 produced by the impurity reaches the steady state before entering the third stage, the CO2 content produced by limestone decomposition in the third stage is calculated based on the following steps S3501 to S3505:

s3501, determining a first generation rate corresponding to CO2 generated by fuel combustion based on the CO2 content data corresponding to the first stage.

And S3502, determining a second generation rate corresponding to CO2 generated by the impurities based on the CO2 content data corresponding to the second stage and the first generation rate.

S3503, obtaining the total amount of CO2 generated by fuel combustion based on the CO2 content generated by the first stage, the time difference value corresponding to the current CO2 content data and the last data point of the first stage and the first generation rate.

S3504, obtaining the total amount of CO2 generated from the impurity based on the CO2 content generated in the second stage, the CO2 content generated in the second stage by the combustion of the fuel, the time difference between the current CO2 content data and the last data point of the second stage, and the second rate of generation.

S3505 determining the CO2 content resulting from limestone decomposition in the third stage based on the current CO2 content data in the third stage, the total amount of CO2 resulting from fuel combustion, and the total amount of CO2 resulting from impurities.

It should be noted that, in the steps S3501 to S3505, the current CO2 content data may refer to the CO2 content corresponding to any one data point in the third stage. The above calculation process can be expressed as follows:

wherein ,to produce the CO2 content corresponding to the last data point G in the early stage,indicating the CO2 content in the lime kiln when production is not started,indicating the rate of CO2 production after complete combustion stabilization of the fuel (i.e. the aforementioned first production rate),represents the acquisition time corresponding to the z point of the monitoring point,representing the acquisition time corresponding to the last data point G in the initial stage of production,to produce the CO2 content corresponding to the last data point F in the mid-term,to obtain the corresponding acquisition time of the last data point F in the middle of production,indicating the rate of CO2 production after combustion stabilization of the impurity (i.e. the aforementioned second production rate),for the CO2 content produced by the decomposition of limestone,the CO2 content produced for the combustion of the fuel,for the content of CO2 produced by the impurity reaction, And (3) acquiring CO2 content data for a CO2 sensor in the third stage.

For the second case, if the rate of change of the CO2 content corresponding to the CO2 produced by the impurity does not reach the steady state before entering the third stage, the CO2 content produced by limestone decomposition in the third stage is calculated based on the following steps S3506 to S3509:

s3506: determining a mutation point in the third stage based on the CO2 content data in the third stage, and determining a time and a CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching a steady state based on the mutation point.

S3507: and determining the total amount of CO2 generated after the CO2 content change rate generated by the impurity reaches the steady state based on the difference value of the current CO2 content data and the time corresponding to the CO2 content change rate generated by the impurity reaching the steady state and the CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching the steady state.

S3508: the total amount of CO2 produced before the steady state is reached is determined by integrating the rate of change of the CO2 content produced by the impurity.

S3509: and obtaining the total amount of CO2 generated by the impurities based on the total amount of CO2 generated by the CO2 content change rate after reaching the steady state and the total amount of CO2 generated before reaching the steady state.

Specifically, in some embodiments, the foregoing mutation points may be determined by:

acquiring a CO2 content change rate V corresponding to a data point in the later production period, taking the data point H and the data point at the next time of the H as P points, taking the data point at the last time of the H as M points as an example, and acquiring a rate increase rateEach data point has a corresponding rate of increase, and the corresponding mutation degree of the data point is obtained based on the difference of the rate of increaseAnd setting a mutation rate judgment threshold value to be 0.2 according to an empirical value, when the mutation degree is larger than the set mutation rate judgment threshold value, marking the mutation degree as a mutation point, if a plurality of mutation points exist, selecting a data point with the largest corresponding mutation degree as the mutation point, and if no mutation point exists, indicating that the condition that the impurity is subjected to chemical reaction during the limestone production belongs to the first type. Assuming that the rate of CO2 content by impurities before the K point increases continuously in the post-production period, the rate of CO2 content after the K point becomes steady state. Obtaining the CO2 content change rate (subtracted from the production periodPost rate), a section of V-t curve can be obtained, a polynomial function is obtained by polynomial fitting of the curve, and the content change rate of the data point between the f point and the K point can be obtained based on the polynomial function 。

Further, the CO2 content resulting from limestone decomposition can be calculated as follows:

wherein ,represents the rate of change of the CO2 content corresponding to the point of mutation K (the rate of change of the CO2 content resulting from the combustion of the fuel has been subtracted),the acquisition time corresponding to the mutation point K is represented,represents the rate of change of the CO2 content (the rate of change of the CO2 content generated by the combustion of the fuel is subtracted) corresponding to the data points in the process of generating CO2 by the chemical reaction of the impurities,for the CO2 content produced by the decomposition of limestone,the CO2 content produced for the combustion of the fuel,for the content of CO2 produced by the impurity reaction,and (3) acquiring CO2 content data for a CO2 sensor in the third stage.

At step 360, lime production is determined based on the CO2 content produced by limestone decomposition in the third stage. In some embodiments, step 360 may be performed by lime yield determination module 260.

The ratio of CO2 yield to lime CaO yield in the chemical reaction formula due to the pyrolysis of limestone is 1:1, therefore, after the CO2 content generated by the decomposition of limestone in the third stage is calculated through the foregoing steps, the lime yield determination module 260 can directly calculate the yield of lime CaO from the ratio and the CO2 content generated by the decomposition of limestone. The calculation method is a known technology, and will not be described in detail in this specification.

And step 370, training the CNN and MLP mixed neural network by taking the lime yield and the current production operation parameters as training data to obtain a trained yield prediction model. In some embodiments, step 370 may be performed by training module 270.

In the production process, current production operation parameters such as upper arch bridge temperature, circulating gas temperature, lower combustion chamber temperature, heat exchanger exhaust outlet temperature, heat exchanger exhaust inlet temperature, cooling air loop temperature, furnace top exhaust gas temperature, upper combustion chamber gas flow, lower combustion chamber gas flow, upper cooling flow, driving fan flow, loading weight and the like can be detected by a system sensor. In some embodiments, the lime yield and the current production operating parameters obtained by the foregoing process may be used as training data to train a hybrid neural network of CNN (Convolutional Neural Network) and MLP (Multi-Layer Perceptron) to obtain a trained yield prediction model.

After the trained yield prediction model is obtained, the yield classification can be predicted by calculating the production operation parameters acquired in the production process by using the trained yield prediction model. Further, an operator can timely learn the yield classification under the current production operation parameters, and then perform corresponding operations according to different categories.

In some embodiments, the gray correlation analysis GRA (Grey Relation Analysis) algorithm may be used to obtain the correlation between the various production operating parameters and the yield YI under the same yield YI (obtained according to the above steps), then compare the correlation between each production operating parameter with a threshold of 0.75, select parameters greater than 0.75, and combine the screened parameters into a correlation sequence. By way of example only, the yields may be divided into five categories in some embodiments of the present description, depending on lime yield classification criteria, with category labels given to different yields YI: a (YI. Gtoreq.95% YIMx), B (95% YIMx > YI. Gtoreq.85% YIMx), C (85% YIMx > YI. Gtoreq.75% YIMx), D (75% YIMx > YI. Gtoreq.65% YIMx), E (65% YIMx > YI). Where YImax is the yield corresponding to complete decomposition of limestone.

A data matrix composed of the threshold-filtered parameter sequences and the correlation sequences can be obtained and used as input of a yield prediction model. In some embodiments, the yield prediction model may be a hybrid neural network of CNN and MLP, the optimization algorithm may be an adam algorithm, and the loss function may be a mean square error loss function. And obtaining a lime yield prediction result under the current production operation parameter after the input data passes through CNN in the yield prediction model, and further, taking the obtained lime yield prediction result as the input of MLP to obtain a lime yield classification result under the current production operation parameter. Because neural network training is a well-known technique, the specific training process for the yield prediction model is not described in detail in this specification.

Further, after training is completed, the data matrix corresponding to the production operation parameters in the real-time production process obtained by collection can be input into a trained yield prediction model, so that a classification result of the real-time lime yield corresponding to the production operation parameters in the real-time production process is obtained, and the classification result is sent to an operator. The operator can obtain the yield classification under the set of production operation parameters in time and then perform corresponding operations according to different categories.

It can be understood that in actual production, the difference of product yield is obvious due to the difference of parameters such as raw material consumption, fuel consumption, reaction temperature and the like. Lime calcination is a relatively slow production process, and the yield is data which can be obtained according to the ash discharge condition after the calcination is finished, when the calcination process is finished, only when faults occur, a worker can timely adjust parameters or operate an executing mechanism, if the monitored parameters are not abnormal or the system is not faulty, the worker cannot timely judge the final yield of the limestone being calcined, and the production parameters cannot be regulated and controlled in real time, so that the yield is improved. In some embodiments of the present disclosure, by calculating production operation parameters using a trained yield prediction model, a yield classification corresponding to the production operation parameters is obtained by prediction, so that an operator can timely learn the yield classification under the current production operation parameters, and then perform corresponding operations on each parameter according to corresponding regulation and control strategies of different categories, thereby achieving the purpose of improving yield.

In some embodiments, the production may be categorized into 5 production operation categories YO1, YO2, YO3, YO4, YO5, corresponding production prediction categories, production characteristics, production run parameter characteristics, and corresponding control schemes are shown in table 1.

TABLE 1 characteristics of yield operation classification and control scheme

In some embodiments, operating parameters that differ significantly from the optimal average may be found by comparing operating parameters corresponding to different production operation classifications to the optimal parameters.

In some embodiments, when a yield operation is classified as YO1, which indicates that this is the optimal operating parameter, the corresponding yield is also the optimal yield, so no regulation is required.

When the yield operation is classified as YO2, the optimum yield is approached. The average value for some conditions is not much different from the average value for YO 1. Such as: the maximum difference in the exhaust temperature TEGKT of the exhaust gas from the furnace roof was calculated to be 7.367%, followed by a cooling air loop temperature TCAL of 6.052% and a driving fan flow FDF of 5.235%. In this class, the control rank is ¢ ô. Because this value reflects the difference from the optimal operating mode, the operating mode parameters can be locally adjusted when the predicted yield operating mode level is YO 2. The regulation sequence may be ordered according to the relative error magnitude of the average value of the running parameters and the average value of YO1, for example: the top off-gas exhaust temperature TEGKT-cooling air loop temperature TCAL-drive fan flow FDF-upper combustor gas flow FUCCG-upper arch bridge temperature TUAB.

When the yield operation grade is YO3, a certain difference exists from the optimal yield, and the average value of part of operation parameters is significantly different from YO 1. Such as: the difference in lower combustor gas flow FLCCG is greatest (34.435%), followed by upper combustor gas flow FUCCG (27.819%) and upper cold flow FCU (12.120%). At this time, the control level is ¢ to rank the regulation order according to the relative error magnitude of the average value of the running parameters and the average value of YO1, for example: lower combustor gas flow FLCCG-upper combustor gas flow FUCCG-upper cold flow FCU-lower combustor temperature TLCC-drive fan flow FDF.

When the yield operation level is YO4, the difference from the optimum parameters is large. Such as: the maximum difference in drive fan flow FDF among the operating parameters was 96.827%, followed by 91.338% upper combustor gas flow FUCCG and 77.696% lower combustor gas flow FLCCG. At this time, the control level was ¢ Torr. The regulation sequence is ordered according to the relative error magnitude of the average value of the running parameters and the average value of YO1, for example: the fan flow FDF-the upper combustor gas flow FUCCG-the lower combustor gas flow FLCCG-the lower combustor temperature TLCC-the cooling air can temperature TCAL.

When the production operation level is YO2, YO3 or YO4, the parameter of YO1 is taken as the expected value of each controlled quantity, and the corresponding actuator is adjusted. For example, the flow FLCCG of the lower combustion chamber is regulated, the average value of the FLCCG corresponding to YO1 is taken as an expected value, and the flow is controlled by regulating the opening of the inlet valve, so that the running condition is debugged more quickly, and the waste is reduced.

When the yield operation is classified as YO5, there is no product output. In this case, the control priority is ¢ ñ, and the operation parameters are adjusted according to the control system according to the occurrence of the fault.

In summary, the possible benefits of the embodiments of the present disclosure include, but are not limited to: (1) In the intelligent production yield monitoring method for the heat carrier lime kiln provided by some embodiments of the present disclosure, by adaptively analyzing a production process of lime produced by limestone decomposition, adaptively classifying produced CO2 based on temperature data and CO2 content data in the production process, dividing the production process into different production processes, adaptively decomposing CO2 content data acquired by a sensor based on variation characteristics of the CO2 content in the different production processes, dividing the production process into CO2 content generated by fuel combustion, CO2 content generated by chemical reaction of impurities, and CO2 content generated by limestone pyrolysis, lime yield can be accurately calculated based on the CO2 content generated by limestone pyrolysis, and interference of CO2 generated by fuel combustion and impurity reaction on lime yield calculation can be eliminated; (2) In the intelligent production yield monitoring method for the heat carrier lime kiln provided in some embodiments of the present specification, the method is used in the process of calculating the category similarity Constraint is carried out, so that the calculation accuracy of category similarity can be improved, and inaccurate data classification caused by the influence of temperature on the change of the content of CO2 is avoided; (3) In the intelligent production yield monitoring method for the heat carrier lime kiln provided by some embodiments of the present disclosure, the category similarity of the local data points is optimized through the overall variation trend of the data points in the category, so that the category judgment precision of the data points can be improved, and the precision and the efficiency of the subsequent yield monitoring can be further improved; (4) In the intelligent production yield monitoring method for a heat carrier lime kiln provided in some embodiments of the present specification, CNN and MLP are mixed by using the aforementioned lime yield and current production operation parameters as training dataThe neural network is trained to obtain a trained yield prediction model, then the trained yield prediction model is utilized to calculate production operation parameters, the corresponding yield classification is obtained through prediction, an operator can timely know the yield classification under the current production operation parameters, and then corresponding operation is carried out on each parameter according to the corresponding regulation and control strategies of different categories, so that the purpose of improving yield is achieved.

It should be noted that, the benefits that may be generated by different embodiments may be different, and in different embodiments, the benefits that may be generated may be any one or a combination of several of the above, or any other benefits that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the specification can be illustrated and described in terms of several patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the specification may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.

The computer program code necessary for operation of portions of the present description may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python and the like, a conventional programming language such as C language, visual Basic, fortran2003, perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, ruby and Groovy, or other programming languages and the like. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or processing device. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing processing device or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. The intelligent production yield monitoring method for the heat carrier lime kiln is characterized by comprising the following steps of:

training a CNN and MLP mixed neural network by taking the lime yield and the current production operation parameters as training data to obtain a trained yield prediction model, and monitoring a classification result corresponding to the real-time lime yield predicted by the trained yield prediction model; the current production operation parameters comprise upper arch bridge temperature, circulating gas temperature, lower combustion chamber temperature, heat exchanger exhaust outlet temperature, heat exchanger exhaust inlet temperature, cooling air ring pipe temperature, furnace top waste gas temperature, upper combustion chamber gas flow, lower combustion chamber gas flow, upper cooling flow, driving fan flow and feeding weight;

the step of monitoring the classification result corresponding to the real-time lime yield predicted by the trained yield prediction model is as follows:

regulating and controlling the current production operation parameters according to a regulation and control strategy corresponding to a classification result corresponding to the real-time lime yield;

the specific method for determining the content of CO2 generated by decomposing limestone in the third stage based on the change characteristics of the CO2 content data corresponding to the first stage and the second stage is as follows:

If the rate of change of the CO2 content corresponding to the CO2 produced by the impurity reaches a steady state before entering the third stage, the CO2 content produced by limestone decomposition in the third stage is calculated based on the following steps S3501 to S3505:

s3501, determining a first generation rate corresponding to CO2 generated by fuel combustion based on CO2 content data corresponding to the first stage;

s3502, determining a second generation rate corresponding to CO2 generated by the impurity based on the CO2 content data corresponding to the second stage and the first generation rate;

s3503, obtaining the total amount of CO2 generated by fuel combustion based on the CO2 content generated in the first stage, the time difference value corresponding to the current CO2 content data in the third stage and the last data point of the first stage, and the first generation rate;

s3504 obtaining a total amount of CO2 produced from the impurity based on the CO2 content produced in the second stage, the CO2 content produced in the second stage from the combustion of the fuel, a time difference value corresponding to a current CO2 content data in the third stage and a last data point of the second stage, and the second rate of generation;

s3505 determining the CO2 content resulting from limestone decomposition in the third stage based on the current CO2 content data in the third stage, the total amount of CO2 resulting from fuel combustion, and the total amount of CO2 resulting from impurities;

The calculation process of step S3501 to step S3505 is expressed as follows:

wherein ,for the CO2 content corresponding to the last data point G point of the first phase, +.>Indicating the CO2 content in the lime kiln when production is not started,/->Indicating the rate of CO2 production after complete combustion stabilization of the fuel is the aforementioned first production rate,/>representing the acquisition time corresponding to the monitoring point z point, < ->Representing the acquisition time corresponding to the last data point G of the first phase,CO2 content corresponding to the last data point F of the second stage, +.>For the acquisition time corresponding to the last data point F point of the second phase, +.>Indicating the rate of CO2 production after combustion stabilization of the impurity, the aforementioned second production rate, +.>CO2 content generated for limestone decomposition, < >>CO2 content generated for fuel combustion, +.>CO2 content generated for impurity reaction, +.>The data of the content of CO2 acquired by the CO2 sensor in the third stage;

if the rate of change of the CO2 content corresponding to the CO2 produced by the impurity does not reach the steady state before entering the third stage, the CO2 content produced by limestone decomposition in the third stage is calculated based on the following steps S3506 to S3509:

s3506: determining a mutation point in the third stage based on the CO2 content data in the third stage, and determining a time and a CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching a steady state based on the mutation point;

S3507: determining the total amount of CO2 generated after the CO2 content change rate generated by the impurity reaches a steady state based on the difference value of the current CO2 content data and the time corresponding to the CO2 content change rate generated by the impurity reaching a steady state and the CO2 content change rate corresponding to the CO2 content change rate generated by the impurity reaching a steady state;

s3508: determining the total amount of CO2 generated before the CO2 content change rate generated by the impurities reaches a steady state through integral operation;

s3509: obtaining the total amount of CO2 generated by impurities based on the total amount of CO2 generated after reaching a steady state and the total amount of CO2 generated before reaching the steady state;

the CO2 content resulting from the limestone decomposition is calculated as follows:

wherein ,represents the CO2 content change rate corresponding to the mutation point K point,>the acquisition time corresponding to the mutation point K is represented,indicating the rate of change of CO2 content corresponding to the data points in the process of generating CO2 by chemical reaction of impurities,/->CO2 content generated for limestone decomposition, < >>CO2 content generated for fuel combustion, +.>CO2 content generated for impurity reaction, +. >And (3) acquiring CO2 content data for a CO2 sensor in the third stage.

2. The intelligent production yield monitoring method for a heat carrier lime kiln of claim 1, wherein said determining a category similarity between two adjacent CO2 content data from two adjacent data points comprises:

3. The intelligent production yield monitoring method for a heat carrier lime kiln according to claim 2, wherein the rate of change of the CO2 content corresponding to the current data point is:

wherein ,for the rate of change of the CO2 content corresponding to the current data point, and (2)>For the CO2 content data corresponding to the current data point, < >>For the CO2 content data corresponding to the previous data point, and (2)>For the acquisition time corresponding to the current data point, +.>The acquisition time corresponding to the previous data point;

the rate of increase corresponding to the current data point is:

wherein ,for the rate of increase corresponding to the current data point, +.>CO2 content change rate corresponding to the previous data point,/->Representation of the selection->Maximum value of (2);

wherein ,for class similarity between the current data point and the previous data point, +.> and />The rate of increase corresponding to the current data point and the previous data point, respectively, +.> and />Temperature data corresponding to the current data point and the previous data point respectively.

4. The intelligent production yield monitoring method for a heat carrier lime kiln according to any one of claims 1 to 3, wherein the classifying the CO2 content data according to the category similarity comprises:

5. The intelligent production yield monitoring method for a heat carrier lime kiln of claim 4, wherein said determining category similarity between two adjacent CO2 content data from two adjacent data points further comprises:

6. The intelligent production yield monitoring method for a heat carrier lime kiln according to claim 5, wherein the optimization coefficient corresponding to the current data point is:

wherein A is the optimization coefficient corresponding to the current data point, and />The rate of increase and the rate of change of the CO2 content corresponding to the current data point are respectively +.>For the acquisition time corresponding to the current data point, +.>For the acquisition time corresponding to the ith data point in the current class before the current data point, +.> and />The rate of increase and the rate of change of the CO2 content corresponding to the ith data point in the current class before the current data point are respectively +. >For the number of data points in the current class that are located before the current data point, +.>Is a fixed parameter for preventing denominator from being 0;

the optimized category similarity is as follows:

7. The intelligent production yield monitoring method for a heat carrier lime kiln of claim 5, wherein the classifying the CO2 content data according to the category similarity comprises: and classifying the CO2 content data based on the optimized category similarity.

8. The intelligent production yield monitoring method for a heat carrier lime kiln according to claim 1, wherein the determining a second production rate corresponding to CO2 generated by impurities based on the CO2 content data corresponding to the second stage and the first production rate in step S3502 comprises: